Merge branch 'master' of ssh://github.com/tqchen/xgboost

fix (trivial) leak in xgboost_regrank, Thanks for the fix

.clang-tidy

@@ -1,21 +0,0 @@
-Checks: 'modernize-*,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
-CheckOptions:
-  - { key: readability-identifier-naming.ClassCase,           value: CamelCase  }
-  - { key: readability-identifier-naming.StructCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypeAliasCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypedefCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypeTemplateParameterCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.MemberCase,          value: lower_case  }
-  - { key: readability-identifier-naming.PrivateMemberSuffix,    value: '_'  }
-  - { key: readability-identifier-naming.ProtectedMemberSuffix,  value: '_'  }
-  - { key: readability-identifier-naming.EnumCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstant,          value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.GlobalConstantCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.GlobalConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.StaticConstantCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.StaticConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.ConstexprVariableCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.ConstexprVariablePrefix,          value: k  }
-  - { key: readability-identifier-naming.FunctionCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.NamespaceCase,       value: lower_case }

.editorconfig

@@ -1,11 +0,0 @@
-root = true
-
-[*]
-charset=utf-8
-indent_style = space
-indent_size = 2
-insert_final_newline = true
-
-[*.py]
-indent_style = space
-indent_size = 4

.github/ISSUE_TEMPLATE.md

@@ -1,7 +0,0 @@
-Thanks for participating in the XGBoost community! We use https://discuss.xgboost.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion, roadmaps, and bug tracking.  You are always welcomed to post on the forum first :)
-
-Issues that are inactive for a period of time may get closed. We adopt this policy so that we won't lose track of actionable issues that may fall at the bottom of the pile. Feel free to reopen a new one if you feel there is an additional problem that needs attention when an old one gets closed.
-
-For bug reports, to help the developer act on the issues, please include a description of your environment, preferably a minimum script to reproduce the problem.
-
-For feature proposals, list clear, small actionable items so we can track the progress of the change.

.github/lock.yml

@@ -1,32 +0,0 @@
-# Configuration for lock-threads - https://github.com/dessant/lock-threads
-
-# Number of days of inactivity before a closed issue or pull request is locked
-daysUntilLock: 90
-
-# Issues and pull requests with these labels will not be locked. Set to `[]` to disable
-exemptLabels:
-  - feature-request
-
-# Label to add before locking, such as `outdated`. Set to `false` to disable
-lockLabel: false
-
-# Comment to post before locking. Set to `false` to disable
-lockComment: false
-
-# Assign `resolved` as the reason for locking. Set to `false` to disable
-setLockReason: true
-
-# Limit to only `issues` or `pulls`
-# only: issues
-
-# Optionally, specify configuration settings just for `issues` or `pulls`
-# issues:
-#   exemptLabels:
-#     - help-wanted
-#   lockLabel: outdated
-
-# pulls:
-#   daysUntilLock: 30
-
-# Repository to extend settings from
-# _extends: repo

.gitignore

@@ -2,97 +2,25 @@
 *.slo
 *.lo
 *.o
-*.page
+
 # Compiled Dynamic libraries
 *.so
 *.dylib
-*.page
+
 # Compiled Static libraries
 *.lai
 *.la
 *.a
 *~
-*.Rcheck
-*.rds
-*.tar.gz
+*txt*
 *conf
 *buffer
 *model
+xgboost
 *pyc
-*.train
-*.test
-*.tar
+*train
+*test
 *group
 *rar
 *vali
-*sdf
-Release
-*exe*
-*exp
-ipch
-*.filters
-*.user
-*log
-Debug
-*suo
-.Rhistory
-*.dll
-*i386
-*x64
-*dump
-*save
-*csv
-.Rproj.user
-*.cpage.col
-*.cpage
-*.Rproj
-./xgboost.mpi
-./xgboost.mock
-#.Rbuildignore
-R-package.Rproj
-*.cache*
-# java
-java/xgboost4j/target
-java/xgboost4j/tmp
-java/xgboost4j-demo/target
-java/xgboost4j-demo/data/
-java/xgboost4j-demo/tmp/
-java/xgboost4j-demo/model/
-nb-configuration*
-# Eclipse
-.project
-.cproject
-.pydevproject
-.settings/
-build
-config.mk
-/xgboost
-*.data
-build_plugin
-.idea
-recommonmark/
-tags
-*.iml
-*.class
-target
-*.swp
-
-# cpp tests and gcov generated files
-*.gcov
-*.gcda
-*.gcno
-build_tests
-/tests/cpp/xgboost_test
-
-.DS_Store
-lib/
-
-# spark
-metastore_db
-
-plugin/updater_gpu/test/cpp/data
-/include/xgboost/build_config.h
-
-# files from R-package source install
-**/config.status
-R-package/src/Makevars
+*data

.gitmodules

@@ -1,9 +0,0 @@
-[submodule "dmlc-core"]
-	path = dmlc-core
-	url = https://github.com/dmlc/dmlc-core
-[submodule "rabit"]
-	path = rabit
-	url = https://github.com/dmlc/rabit
-[submodule "cub"]
-	path = cub
-	url = https://github.com/NVlabs/cub

.travis.yml

@@ -1,60 +0,0 @@
-# disable sudo for container build.
-sudo: required
-
-# Enabling test on Linux and OS X
-os:
-  - osx
-
-osx_image: xcode9.3
-
-# Use Build Matrix to do lint and build seperately
-env:
-  matrix:
-    # python package test
-    - TASK=python_test
-    # java package test
-    - TASK=java_test
-    # cmake test
-    # - TASK=cmake_test
-
-# dependent apt packages
-addons:
-  homebrew:
-    packages:
-      - gcc@7
-      - graphviz
-      - openssl
-      - libgit2
-      - r
-    update: true
-
-before_install:
-  - source dmlc-core/scripts/travis/travis_setup_env.sh
-  - export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package
-  - echo "MAVEN_OPTS='-Xmx2g -XX:MaxPermSize=1024m -XX:ReservedCodeCacheSize=512m -Dorg.slf4j.simpleLogger.defaultLogLevel=error'" > ~/.mavenrc
-
-install:
-  - source tests/travis/setup.sh
-
-script:
-  - tests/travis/run_test.sh
-
-cache:
-  directories:
-    - ${HOME}/.cache/usr
-    - ${HOME}/.cache/pip
-
-before_cache:
-  - dmlc-core/scripts/travis/travis_before_cache.sh
-
-after_failure:
-  - tests/travis/travis_after_failure.sh
-
-after_success:
-  - tree build
-  - bash <(curl -s https://codecov.io/bash) -a '-o src/ src/*.c'
-
-notifications:
-  email:
-    on_success: change
-    on_failure: always

CITATION

@@ -1,18 +0,0 @@
-@inproceedings{Chen:2016:XST:2939672.2939785,
- author = {Chen, Tianqi and Guestrin, Carlos},
- title = {{XGBoost}: A Scalable Tree Boosting System},
- booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
- series = {KDD '16},
- year = {2016},
- isbn = {978-1-4503-4232-2},
- location = {San Francisco, California, USA},
- pages = {785--794},
- numpages = {10},
- url = {http://doi.acm.org/10.1145/2939672.2939785},
- doi = {10.1145/2939672.2939785},
- acmid = {2939785},
- publisher = {ACM},
- address = {New York, NY, USA},
- keywords = {large-scale machine learning},
-}
-

CMakeLists.txt

@@ -1,229 +0,0 @@
-cmake_minimum_required(VERSION 3.3)
-project(xgboost LANGUAGES CXX C VERSION 0.90)
-include(cmake/Utils.cmake)
-list(APPEND CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/cmake/modules")
-cmake_policy(SET CMP0022 NEW)
-
-message(STATUS "CMake version ${CMAKE_VERSION}")
-if (MSVC)
-  cmake_minimum_required(VERSION 3.11)
-endif (MSVC)
-
-set_default_configuration_release()
-
-#-- Options
-option(BUILD_C_DOC "Build documentation for C APIs using Doxygen." OFF)
-option(USE_OPENMP "Build with OpenMP support." ON)
-## Bindings
-option(JVM_BINDINGS "Build JVM bindings" OFF)
-option(R_LIB "Build shared library for R package" OFF)
-## Dev
-option(GOOGLE_TEST "Build google tests" OFF)
-option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule (EXPERIMENTAL)" OFF)
-option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
-set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
-## CUDA
-option(USE_CUDA  "Build with GPU acceleration" OFF)
-option(USE_NCCL  "Build with NCCL to enable multi-GPU support." OFF)
-option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
-set(GPU_COMPUTE_VER "" CACHE STRING
-  "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
-if (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_NCCL=ON to enable BUILD_WITH_SHARED_NCCL.")
-endif (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-## Sanitizers
-option(USE_SANITIZER "Use santizer flags" OFF)
-option(SANITIZER_PATH "Path to sanitizes.")
-set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
-  "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
-address, leak and thread.")
-## Plugins
-option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
-option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
-
-## Deprecation warning
-if (USE_AVX)
-  message(WARNING "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from xgboost.")
-endif (USE_AVX)
-
-# Sanitizer
-if (USE_SANITIZER)
-  # Older CMake versions have had troubles with Sanitizer
-  cmake_minimum_required(VERSION 3.12)
-  include(cmake/Sanitizer.cmake)
-  enable_sanitizers("${ENABLED_SANITIZERS}")
-endif (USE_SANITIZER)
-
-if (USE_CUDA)
-  cmake_minimum_required(VERSION 3.12)
-  SET(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
-  # `export CXX=' is ignored by CMake CUDA.
-  set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
-  message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
-
-  enable_language(CUDA)
-  set(GEN_CODE "")
-  format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
-  message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
-endif (USE_CUDA)
-
-# dmlc-core
-msvc_use_static_runtime()
-add_subdirectory(${PROJECT_SOURCE_DIR}/dmlc-core)
-set_target_properties(dmlc PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-list(APPEND LINKED_LIBRARIES_PRIVATE dmlc)
-
-# rabit
-# full rabit doesn't build on windows, so we can't import it as subdirectory
-if(MINGW OR R_LIB)
-  set(RABIT_SOURCES
-    rabit/src/engine_empty.cc
-    rabit/src/c_api.cc)
-else ()
-  set(RABIT_SOURCES
-    rabit/src/allreduce_base.cc
-    rabit/src/allreduce_robust.cc
-    rabit/src/engine.cc
-    rabit/src/c_api.cc)
-endif (MINGW OR R_LIB)
-add_library(rabit STATIC ${RABIT_SOURCES})
-target_include_directories(rabit PRIVATE
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/dmlc-core/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/rabit/include/rabit>)
-set_target_properties(rabit
-  PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-list(APPEND LINKED_LIBRARIES_PRIVATE rabit)
-
-# Exports some R specific definitions and objects
-if (R_LIB)
-  add_subdirectory(${PROJECT_SOURCE_DIR}/R-package)
-endif (R_LIB)
-
-# core xgboost
-add_subdirectory(${PROJECT_SOURCE_DIR}/src)
-set(XGBOOST_OBJ_SOURCES "${XGBOOST_OBJ_SOURCES};$<TARGET_OBJECTS:objxgboost>")
-
-#-- Shared library
-add_library(xgboost SHARED ${XGBOOST_OBJ_SOURCES} ${PLUGINS_SOURCES})
-target_include_directories(xgboost
-  INTERFACE
-  $<INSTALL_INTERFACE:${CMAKE_INSTALL_PREFIX}/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
-target_link_libraries(xgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
-
-# This creates its own shared library `xgboost4j'.
-if (JVM_BINDINGS)
-  add_subdirectory(${PROJECT_SOURCE_DIR}/jvm-packages)
-endif (JVM_BINDINGS)
-#-- End shared library
-
-#-- CLI for xgboost
-add_executable(runxgboost ${PROJECT_SOURCE_DIR}/src/cli_main.cc ${XGBOOST_OBJ_SOURCES})
-# For cli_main.cc only
-if (USE_OPENMP)
-  find_package(OpenMP REQUIRED)
-  target_compile_options(runxgboost PRIVATE ${OpenMP_CXX_FLAGS})
-endif (USE_OPENMP)
-target_include_directories(runxgboost
-  PRIVATE
-  ${PROJECT_SOURCE_DIR}/include
-  ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include)
-target_link_libraries(runxgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
-set_target_properties(
-  runxgboost PROPERTIES
-  OUTPUT_NAME xgboost
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON)
-#-- End CLI for xgboost
-
-set_output_directory(runxgboost ${PROJECT_SOURCE_DIR})
-set_output_directory(xgboost ${PROJECT_SOURCE_DIR}/lib)
-# Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
-add_dependencies(xgboost runxgboost)
-
-#-- Installing XGBoost
-if (R_LIB)
-  set_target_properties(xgboost PROPERTIES PREFIX "")
-  if (APPLE)
-    set_target_properties(xgboost PROPERTIES SUFFIX ".so")
-  endif (APPLE)
-  setup_rpackage_install_target(xgboost ${CMAKE_CURRENT_BINARY_DIR})
-  set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
-endif (R_LIB)
-if (MINGW)
-  set_target_properties(xgboost PROPERTIES PREFIX "")
-endif (MINGW)
-
-if (BUILD_C_DOC)
-  include(cmake/Doc.cmake)
-  run_doxygen()
-endif (BUILD_C_DOC)
-
-include(GNUInstallDirs)
-# Exposing only C APIs.
-install(FILES
-  "${PROJECT_SOURCE_DIR}/include/xgboost/c_api.h"
-  DESTINATION
-  include/xgboost/)
-
-install(TARGETS xgboost runxgboost
-  EXPORT XGBoostTargets
-  ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
-  INCLUDES DESTINATION ${LIBLEGACY_INCLUDE_DIRS})
-install(EXPORT XGBoostTargets
-  FILE XGBoostTargets.cmake
-  NAMESPACE xgboost::
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-
-include(CMakePackageConfigHelpers)
-configure_package_config_file(
-  ${CMAKE_CURRENT_LIST_DIR}/cmake/xgboost-config.cmake.in
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
-  INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-write_basic_package_version_file(
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  VERSION ${XGBOOST_VERSION}
-  COMPATIBILITY AnyNewerVersion)
-install(
-  FILES
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-
-#-- Test
-if (GOOGLE_TEST)
-  enable_testing()
-  # Unittests.
-  add_subdirectory(${PROJECT_SOURCE_DIR}/tests/cpp)
-  add_test(
-    NAME TestXGBoostLib
-    COMMAND testxgboost
-    WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
-
-  # CLI tests
-  configure_file(
-    ${PROJECT_SOURCE_DIR}/tests/cli/machine.conf.in
-    ${PROJECT_BINARY_DIR}/tests/cli/machine.conf
-    @ONLY)
-  add_test(
-    NAME TestXGBoostCLI
-    COMMAND runxgboost ${PROJECT_BINARY_DIR}/tests/cli/machine.conf
-    WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
-  set_tests_properties(TestXGBoostCLI
-    PROPERTIES
-    PASS_REGULAR_EXPRESSION ".*test-rmse:0.087.*")
-endif (GOOGLE_TEST)
-
-# For MSVC: Call msvc_use_static_runtime() once again to completely
-# replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
-# for issues caused by mixing of /MD and /MT flags
-msvc_use_static_runtime()

CONTRIBUTORS.md

@@ -1,91 +0,0 @@
-Contributors of DMLC/XGBoost
-============================
-XGBoost has been developed and used by a group of active community. Everyone is more than welcomed to is a great way to make the project better and more accessible to more users.
-
-Committers
-----------
-Committers are people who have made substantial contribution to the project and granted write access to the project.
-* [Tianqi Chen](https://github.com/tqchen), University of Washington
-  - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
-* [Tong He](https://github.com/hetong007), Amazon AI
-  - Tong is an applied scientist in Amazon AI. He is the maintainer of XGBoost R package.
-* [Vadim Khotilovich](https://github.com/khotilov)
-  - Vadim contributes many improvements in R and core packages.
-* [Bing Xu](https://github.com/antinucleon)
-  - Bing is the original creator of XGBoost Python package and currently the maintainer of [XGBoost.jl](https://github.com/antinucleon/XGBoost.jl).
-* [Michael Benesty](https://github.com/pommedeterresautee)
-  - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Ant Financial
-  - Yuan is a software engineer in Ant Financial. He contributed mostly in R and Python packages.
-* [Nan Zhu](https://github.com/CodingCat), Uber
-  - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
-* [Sergei Lebedev](https://github.com/superbobry), Criteo
-  - Sergei is a software engineer in Criteo. He contributed mostly in JVM packages.
-* [Hongliang Liu](https://github.com/phunterlau)
-* [Scott Lundberg](http://scottlundberg.com/), University of Washington
-  - Scott is a Ph.D. student at University of Washington. He is the creator of SHAP, a unified approach to explain the output of machine learning models such as decision tree ensembles. He also helps maintain the XGBoost Julia package.
-* [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
-  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
-* [Hyunsu Cho](http://hyunsu-cho.io/), Amazon AI
-  - Hyunsu is an applied scientist in Amazon AI. He is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater. 
-* [Jiaming](https://github.com/trivialfis)
-  - Jiaming contributed to the GPU algorithms. He has also introduced new abstractions to improve the quality of the C++ codebase.
-
-Become a Committer
-------------------
-XGBoost is a opensource project and we are actively looking for new committers who are willing to help maintaining and lead the project.
-Committers comes from contributors who:
-* Made substantial contribution to the project.
-* Willing to spent time on maintaining and lead the project.
-
-New committers will be proposed by current committer members, with support from more than two of current committers.
-
-List of Contributors
---------------------
-* [Full List of Contributors](https://github.com/dmlc/xgboost/graphs/contributors)
-  - To contributors: please add your name to the list when you submit a patch to the project:)
-* [Kailong Chen](https://github.com/kalenhaha)
-  - Kailong is an early contributor of XGBoost, he is creator of ranking objectives in XGBoost.
-* [Skipper Seabold](https://github.com/jseabold)
-  - Skipper is the major contributor to the scikit-learn module of XGBoost.
-* [Zygmunt Zając](https://github.com/zygmuntz)
-  - Zygmunt is the master behind the early stopping feature frequently used by kagglers.
-* [Ajinkya Kale](https://github.com/ajkl)
-* [Boliang Chen](https://github.com/cblsjtu)
-* [Yangqing Men](https://github.com/yanqingmen)
-  - Yangqing is the creator of XGBoost java package.
-* [Engpeng Yao](https://github.com/yepyao)
-* [Giulio](https://github.com/giuliohome)
-  - Giulio is the creator of Windows project of XGBoost
-* [Jamie Hall](https://github.com/nerdcha)
-  - Jamie is the initial creator of XGBoost scikit-learn module.
-* [Yen-Ying Lee](https://github.com/white1033)
-* [Masaaki Horikoshi](https://github.com/sinhrks)
-  - Masaaki is the initial creator of XGBoost Python plotting module.
-* [daiyl0320](https://github.com/daiyl0320)
-  - daiyl0320 contributed patch to XGBoost distributed version more robust, and scales stably on TB scale datasets.
-* [Huayi Zhang](https://github.com/irachex)
-* [Johan Manders](https://github.com/johanmanders)
-* [yoori](https://github.com/yoori)
-* [Mathias Müller](https://github.com/far0n)
-* [Sam Thomson](https://github.com/sammthomson)
-* [ganesh-krishnan](https://github.com/ganesh-krishnan)
-* [Damien Carol](https://github.com/damiencarol)
-* [Alex Bain](https://github.com/convexquad)
-* [Baltazar Bieniek](https://github.com/bbieniek)
-* [Adam Pocock](https://github.com/Craigacp)
-* [Gideon Whitehead](https://github.com/gaw89)
-* [Yi-Lin Juang](https://github.com/frankyjuang)
-* [Andrew Hannigan](https://github.com/andrewhannigan)
-* [Andy Adinets](https://github.com/canonizer)
-* [Henry Gouk](https://github.com/henrygouk)
-* [Pierre de Sahb](https://github.com/pdesahb)
-* [liuliang01](https://github.com/liuliang01)
-  - liuliang01 added support for the qid column for LibSVM input format. This makes ranking task easier in distributed setting.
-* [Andrew Thia](https://github.com/BlueTea88)
-  - Andrew Thia implemented feature interaction constraints
-* [Wei Tian](https://github.com/weitian)
-* [Chen Qin](https://github.com/chenqin)
-* [Sam Wilkinson](https://samwilkinson.io)
-* [Matthew Jones](https://github.com/mt-jones)
-* [Jiaxiang Li](https://github.com/JiaxiangBU)

Jenkinsfile

@@ -1,345 +0,0 @@
-#!/usr/bin/groovy
-// -*- mode: groovy -*-
-// Jenkins pipeline
-// See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
-
-// Command to run command inside a docker container
-dockerRun = 'tests/ci_build/ci_build.sh'
-
-pipeline {
-  // Each stage specify its own agent
-  agent none
-
-  environment {
-    DOCKER_CACHE_REPO = '492475357299.dkr.ecr.us-west-2.amazonaws.com'
-  }
-
-  // Setup common job properties
-  options {
-    ansiColor('xterm')
-    timestamps()
-    timeout(time: 120, unit: 'MINUTES')
-    buildDiscarder(logRotator(numToKeepStr: '10'))
-    preserveStashes()
-  }
-
-  // Build stages
-  stages {
-    stage('Jenkins Linux: Get sources') {
-      agent { label 'linux && cpu' }
-      steps {
-        script {
-          checkoutSrcs()
-        }
-        stash name: 'srcs'
-        milestone ordinal: 1
-      }
-    }
-    stage('Jenkins Linux: Formatting Check') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'clang-tidy': { ClangTidy() },
-            'lint': { Lint() },
-            'sphinx-doc': { SphinxDoc() },
-            'doxygen': { Doxygen() }
-          ])
-        }
-        milestone ordinal: 2
-      }
-    }
-    stage('Jenkins Linux: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-cpu': { BuildCPU() },
-            'build-gpu-cuda8.0': { BuildCUDA(cuda_version: '8.0') },
-            'build-gpu-cuda9.0': { BuildCUDA(cuda_version: '9.0') },
-            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
-            'build-jvm-doc': { BuildJVMDoc() }
-          ])
-        }
-        milestone ordinal: 3
-      }
-    }
-    stage('Jenkins Linux: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-python-cpu': { TestPythonCPU() },
-            'test-python-gpu-cuda8.0': { TestPythonGPU(cuda_version: '8.0') },
-            'test-python-gpu-cuda9.0': { TestPythonGPU(cuda_version: '9.0') },
-            'test-python-gpu-cuda10.0': { TestPythonGPU(cuda_version: '10.0') },
-            'test-python-gpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1') },
-            'test-python-mgpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1', multi_gpu: true) },
-            'test-cpp-gpu': { TestCppGPU(cuda_version: '10.1') },
-            'test-cpp-mgpu': { TestCppGPU(cuda_version: '10.1', multi_gpu: true) },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '2.4.3') },
-            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
-            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
-            'test-r-3.4.4': { TestR(use_r35: false) },
-            'test-r-3.5.3': { TestR(use_r35: true) }
-          ])
-        }
-        milestone ordinal: 4
-      }
-    }
-  }
-}
-
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def ClangTidy() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running clang-tidy job..."
-    def container_type = "clang_tidy"
-    def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION=9.2"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} tests/ci_build/clang_tidy.sh
-    """
-    deleteDir()
-  }
-}
-
-def Lint() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running lint..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} make lint
-    """
-    deleteDir()
-  }
-}
-
-def SphinxDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running sphinx-doc..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
-    sh """#!/bin/bash
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} make -C doc html
-    """
-    deleteDir()
-  }
-}
-
-def Doxygen() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running doxygen..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
-    """
-    archiveArtifacts artifacts: "build/${BRANCH_NAME}.tar.bz2", allowEmptyArchive: true
-    echo 'Uploading doc...'
-    s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
-    deleteDir()
-  }
-}
-
-def BuildCPU() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh
-    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
-    """
-    // Sanitizer test
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 --cap-add SYS_PTRACE'"
-    def docker_args = "--build-arg CMAKE_VERSION=3.12"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address" \
-      -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
-    """
-    deleteDir()
-  }
-}
-
-def BuildCUDA(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build with CUDA ${args.cuda_version}"
-    def container_type = "gpu_build"
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    """
-    // Stash wheel for CUDA 8.0 / 9.0 target
-    if (args.cuda_version == '8.0') {
-      echo 'Stashing Python wheel...'
-      stash name: 'xgboost_whl_cuda8', includes: 'python-package/dist/*.whl'
-    } else if (args.cuda_version == '9.0') {
-      echo 'Stashing Python wheel...'
-      stash name: 'xgboost_whl_cuda9', includes: 'python-package/dist/*.whl'
-      archiveArtifacts artifacts: "python-package/dist/*.whl", allowEmptyArchive: true
-      echo 'Stashing C++ test executable (testxgboost)...'
-      stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost'
-    }
-    deleteDir()
-  }
-}
-
-def BuildJVMPackages(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}"
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    // Use only 4 CPU cores
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
-    """
-    echo 'Stashing XGBoost4J JAR...'
-    stash name: 'xgboost4j_jar', includes: 'jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar'
-    deleteDir()
-  }
-}
-
-def BuildJVMDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Building JVM doc..."
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
-    """
-    archiveArtifacts artifacts: "jvm-packages/${BRANCH_NAME}.tar.bz2", allowEmptyArchive: true
-    echo 'Uploading doc...'
-    s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
-    deleteDir()
-  }
-}
-
-def TestPythonCPU() {
-  node('linux && cpu') {
-    unstash name: 'xgboost_whl_cuda9'
-    unstash name: 'srcs'
-    echo "Test Python CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  node(nodeReq) {
-    if (args.cuda_version == '8.0') {
-      unstash name: 'xgboost_whl_cuda8'
-    } else {
-      unstash name: 'xgboost_whl_cuda9'
-    }
-    unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
-      """
-    } else {
-      echo "Using a single GPU"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
-      """
-    }
-    deleteDir()
-  }
-}
-
-def TestCppGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  node(nodeReq) {
-    unstash name: 'xgboost_cpp_tests'
-    unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=*.MGPU_*"
-    } else {
-      echo "Using a single GPU"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=-*.MGPU_*"
-    }
-    deleteDir()
-  }
-}
-
-def CrossTestJVMwithJDK(args) {
-  node('linux && cpu') {
-    unstash name: 'xgboost4j_jar'
-    unstash name: 'srcs'
-    if (args.spark_version != null) {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
-    } else {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
-    }
-    def container_type = "jvm_cross"
-    def docker_binary = "docker"
-    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
-    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
-    // Run integration tests only when spark_version is given
-    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
-    """
-    deleteDir()
-  }
-}
-
-def TestR(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Test R package"
-    def container_type = "rproject"
-    def docker_binary = "docker"
-    def use_r35_flag = (args.use_r35) ? "1" : "0"
-    def docker_args = "--build-arg USE_R35=${use_r35_flag}"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_test_rpkg.sh
-    """
-    deleteDir()
-  }
-}

Jenkinsfile-win64

@@ -1,134 +0,0 @@
-#!/usr/bin/groovy
-// -*- mode: groovy -*-
-
-/* Jenkins pipeline for Windows AMD64 target */
-
-pipeline {
-  agent none
-  // Build stages
-  stages {
-    stage('Jenkins Win64: Get sources') {
-      agent { label 'win64 && build' }
-      steps {
-        script {
-          checkoutSrcs()
-        }
-        stash name: 'srcs'
-        milestone ordinal: 1
-      }
-    }
-    stage('Jenkins Win64: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-win64-cuda9.0': { BuildWin64() }
-          ])
-        }
-        milestone ordinal: 2
-      }
-    }
-    stage('Jenkins Win64: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-win64-cpu': { TestWin64CPU() },
-            'test-win64-gpu-cuda9.0': { TestWin64GPU(cuda_target: 'cuda9') },
-            'test-win64-gpu-cuda10.0': { TestWin64GPU(cuda_target: 'cuda10_0') },
-            'test-win64-gpu-cuda10.1': { TestWin64GPU(cuda_target: 'cuda10_1') }
-          ])
-        }
-        milestone ordinal: 3
-      }
-    }
-  }
-}
-
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def BuildWin64() {
-  node('win64 && build') {
-    unstash name: 'srcs'
-    echo "Building XGBoost for Windows AMD64 target..."
-    bat "nvcc --version"
-    bat """
-    mkdir build
-    cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
-    """
-    bat """
-    cd build
-    "C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Community\\MSBuild\\15.0\\Bin\\MSBuild.exe" xgboost.sln /m /p:Configuration=Release /nodeReuse:false
-    """
-    bat """
-    cd python-package
-    conda activate && python setup.py bdist_wheel --universal
-    """
-    echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
-    bat """
-    cd python-package\\dist
-    COPY /B ..\\..\\tests\\ci_build\\insert_vcomp140.py
-    conda activate && python insert_vcomp140.py *.whl
-    """
-    echo 'Stashing Python wheel...'
-    stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    archiveArtifacts artifacts: "python-package/dist/*.whl", allowEmptyArchive: true
-    echo 'Stashing C++ test executable (testxgboost)...'
-    stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
-    deleteDir()
-  }
-}
-
-def TestWin64CPU() {
-  node('win64 && cpu') {
-    unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    echo "Test Win64 CPU"
-    echo "Installing Python wheel..."
-    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
-    bat """
-    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "Running Python tests..."
-    bat "conda activate && python -m pytest -v -s --fulltrace tests\\python"
-    bat "conda activate && python -m pip uninstall -y xgboost"
-    deleteDir()
-  }
-}
-
-def TestWin64GPU(args) {
-  node("win64 && gpu && ${args.cuda_target}") {
-    unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    unstash name: 'xgboost_cpp_tests'
-    echo "Test Win64 GPU (${args.cuda_target})"
-    bat "nvcc --version"
-    echo "Running C++ tests..."
-    bat "build\\testxgboost.exe"
-    echo "Installing Python wheel..."
-    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
-    bat """
-    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "Running Python tests..."
-    bat """
-    conda activate && python -m pytest -v -s --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
-    """
-    bat "conda activate && python -m pip uninstall -y xgboost"
-    deleteDir()
-  }
-}

LICENSE

@@ -1,201 +1,13 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
+Copyright (c) 2014 by Tianqi Chen and Contributors 
 
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+    
+   http://www.apache.org/licenses/LICENSE-2.0
 
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "{}"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright (c) 2018 by Contributors
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

Makefile

@@ -1,281 +1,26 @@
-ifndef config
-ifneq ("$(wildcard ./config.mk)","")
-	config = config.mk
-else
-	config = make/config.mk
-endif
-endif
-
-ifndef DMLC_CORE
-	DMLC_CORE = dmlc-core
-endif
-
-ifndef RABIT
-	RABIT = rabit
-endif
-
-ROOTDIR = $(CURDIR)
-
-# workarounds for some buggy old make & msys2 versions seen in windows
-ifeq (NA, $(shell test ! -d "$(ROOTDIR)" && echo NA ))
-        $(warning Attempting to fix non-existing ROOTDIR [$(ROOTDIR)])
-        ROOTDIR := $(shell pwd)
-        $(warning New ROOTDIR [$(ROOTDIR)] $(shell test -d "$(ROOTDIR)" && echo " is OK" ))
-endif
-MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
-ifndef MAKE_OK
-        $(warning Attempting to recover non-functional MAKE [$(MAKE)])
-        MAKE := $(shell which make 2> /dev/null)
-        MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
-endif
-$(warning MAKE [$(MAKE)] - $(if $(MAKE_OK),checked OK,PROBLEM))
-
-ifeq ($(OS), Windows_NT)
-	UNAME="Windows"
-else
-	UNAME=$(shell uname)
-endif
-
-include $(config)
-ifeq ($(USE_OPENMP), 0)
-	export NO_OPENMP = 1
-endif
-include $(DMLC_CORE)/make/dmlc.mk
-
-# include the plugins
-ifdef XGB_PLUGINS
-include $(XGB_PLUGINS)
-endif
-
-# set compiler defaults for OSX versus *nix
-# let people override either
-OS := $(shell uname)
-ifeq ($(OS), Darwin)
-ifndef CC
-export CC = $(if $(shell which clang), clang, gcc)
-endif
-ifndef CXX
-export CXX = $(if $(shell which clang++), clang++, g++)
-endif
-else
-# linux defaults
-ifndef CC
-export CC = gcc
-endif
-ifndef CXX
+export CC  = gcc
 export CXX = g++
-endif
-endif
-
-export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS) $(PLUGIN_LDFLAGS)
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS) $(PLUGIN_CFLAGS)
-CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
-#java include path
-export JAVAINCFLAGS = -I${JAVA_HOME}/include -I./java
-
-ifeq ($(TEST_COVER), 1)
-	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
-else
-	CFLAGS += -O3 -funroll-loops
-ifeq ($(USE_SSE), 1)
-	CFLAGS += -msse2
-endif
-endif
-
-ifndef LINT_LANG
-	LINT_LANG= "all"
-endif
-
-ifeq ($(UNAME), Windows)
-	XGBOOST_DYLIB = lib/xgboost.dll
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/win32
-else
-ifeq ($(UNAME), Darwin)
-	XGBOOST_DYLIB = lib/libxgboost.dylib
-	CFLAGS += -fPIC
-else
-	XGBOOST_DYLIB = lib/libxgboost.so
-	CFLAGS += -fPIC
-endif
-endif
-
-ifeq ($(UNAME), Linux)
-	LDFLAGS += -lrt
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/linux
-endif
-
-ifeq ($(UNAME), Darwin)
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/darwin
-endif
-
-OPENMP_FLAGS =
-ifeq ($(USE_OPENMP), 1)
-	OPENMP_FLAGS = -fopenmp
-else
-	OPENMP_FLAGS = -DDISABLE_OPENMP
-endif
-CFLAGS += $(OPENMP_FLAGS)
+export CFLAGS = -Wall -O3 -msse2  -Wno-unknown-pragmas -fopenmp 
 
 # specify tensor path
-.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck java pylint
+BIN = xgboost
+OBJ = 
+.PHONY: clean all
 
-all: lib/libxgboost.a $(XGBOOST_DYLIB) xgboost
+all: $(BIN) $(OBJ)
+export LDFLAGS= -pthread -lm 
 
-$(DMLC_CORE)/libdmlc.a: $(wildcard $(DMLC_CORE)/src/*.cc $(DMLC_CORE)/src/*/*.cc)
-	+ cd $(DMLC_CORE); "$(MAKE)" libdmlc.a config=$(ROOTDIR)/$(config); cd $(ROOTDIR)
-
-$(RABIT)/lib/$(LIB_RABIT): $(wildcard $(RABIT)/src/*.cc)
-	+ cd $(RABIT); "$(MAKE)" lib/$(LIB_RABIT) USE_SSE=$(USE_SSE); cd $(ROOTDIR)
-
-jvm: jvm-packages/lib/libxgboost4j.so
-
-SRC = $(wildcard src/*.cc src/*/*.cc)
-ALL_OBJ = $(patsubst src/%.cc, build/%.o, $(SRC)) $(PLUGIN_OBJS)
-AMALGA_OBJ = amalgamation/xgboost-all0.o
-LIB_DEP = $(DMLC_CORE)/libdmlc.a $(RABIT)/lib/$(LIB_RABIT)
-ALL_DEP = $(filter-out build/cli_main.o, $(ALL_OBJ)) $(LIB_DEP)
-CLI_OBJ = build/cli_main.o
-include tests/cpp/xgboost_test.mk
-
-build/%.o: src/%.cc
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.d
-	$(CXX) -c $(CFLAGS) $< -o $@
-
-build_plugin/%.o: plugin/%.cc
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -MM -MT build_plugin/$*.o $< >build_plugin/$*.d
-	$(CXX) -c $(CFLAGS) $< -o $@
-
-# The should be equivalent to $(ALL_OBJ)  except for build/cli_main.o
-amalgamation/xgboost-all0.o: amalgamation/xgboost-all0.cc
-	$(CXX) -c $(CFLAGS) $< -o $@
-
-# Equivalent to lib/libxgboost_all.so
-lib/libxgboost_all.so: $(AMALGA_OBJ) $(LIB_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %.a, $^) $(LDFLAGS)
-
-lib/libxgboost.a: $(ALL_DEP)
-	@mkdir -p $(@D)
-	ar crv $@ $(filter %.o, $?)
-
-lib/xgboost.dll lib/libxgboost.so lib/libxgboost.dylib: $(ALL_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %a,  $^) $(LDFLAGS)
-
-jvm-packages/lib/libxgboost4j.so: jvm-packages/xgboost4j/src/native/xgboost4j.cpp $(ALL_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) $(JAVAINCFLAGS) -shared -o $@ $(filter %.cpp %.o %.a, $^) $(LDFLAGS)
+xgboost: regrank/xgboost_regrank_main.cpp regrank/*.h regrank/*.hpp booster/*.h booster/*/*.hpp booster/*.hpp
 
 
-xgboost: $(CLI_OBJ) $(ALL_DEP)
-	$(CXX) $(CFLAGS) -o $@  $(filter %.o %.a, $^)  $(LDFLAGS)
+$(BIN) : 
+	$(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^)
 
-rcpplint:
-	python3 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
+$(OBJ) : 
+	$(CXX) -c $(CFLAGS) -o $@ $(firstword $(filter %.cpp %.c, $^) )
 
-lint: rcpplint
-	python3 dmlc-core/scripts/lint.py --exclude_path python-package/xgboost/dmlc-core \
-	  python-package/xgboost/include python-package/xgboost/lib \
-	  python-package/xgboost/make python-package/xgboost/rabit \
-	  python-package/xgboost/src --pylint-rc ${PWD}/python-package/.pylintrc xgboost \
-	  ${LINT_LANG} include src plugin python-package
-
-pylint:
-	flake8 --ignore E501 python-package
-	flake8 --ignore E501 tests/python
-
-test: $(ALL_TEST)
-	$(ALL_TEST)
-
-check: test
-	./tests/cpp/xgboost_test
-
-ifeq ($(TEST_COVER), 1)
-cover: check
-	@- $(foreach COV_OBJ, $(COVER_OBJ), \
-		gcov -pbcul -o $(shell dirname $(COV_OBJ)) $(COV_OBJ) > gcov.log || cat gcov.log; \
-	)
-endif
+install:
+	cp -f -r $(BIN)  $(INSTALL_PATH)
 
 clean:
-	$(RM) -rf build build_plugin lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
-	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
-	if [ -d "R-package/src" ]; then \
-		cd R-package/src; \
-		$(RM) -rf rabit src include dmlc-core amalgamation *.so *.dll; \
-		cd $(ROOTDIR); \
-	fi
-
-clean_all: clean
-	cd $(DMLC_CORE); "$(MAKE)" clean; cd $(ROOTDIR)
-	cd $(RABIT); "$(MAKE)" clean; cd $(ROOTDIR)
-
-doxygen:
-	doxygen doc/Doxyfile
-
-# create standalone python tar file.
-pypack: ${XGBOOST_DYLIB}
-	cp ${XGBOOST_DYLIB} python-package/xgboost
-	cd python-package; tar cf xgboost.tar xgboost; cd ..
-
-# create pip source dist (sdist) pack for PyPI
-pippack: clean_all
-	rm -rf xgboost-python
-# remove symlinked directories in python-package/xgboost
-	rm -rf python-package/xgboost/lib
-	rm -rf python-package/xgboost/dmlc-core
-	rm -rf python-package/xgboost/include
-	rm -rf python-package/xgboost/make
-	rm -rf python-package/xgboost/rabit
-	rm -rf python-package/xgboost/src
-	cp -r python-package xgboost-python
-	cp -r Makefile xgboost-python/xgboost/
-	cp -r make xgboost-python/xgboost/
-	cp -r src xgboost-python/xgboost/
-	cp -r tests xgboost-python/xgboost/
-	cp -r include xgboost-python/xgboost/
-	cp -r dmlc-core xgboost-python/xgboost/
-	cp -r rabit xgboost-python/xgboost/
-# Use setup_pip.py instead of setup.py
-	mv xgboost-python/setup_pip.py xgboost-python/setup.py
-# Build sdist tarball
-	cd xgboost-python; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
-
-# Script to make a clean installable R package.
-Rpack: clean_all
-	rm -rf xgboost xgboost*.tar.gz
-	cp -r R-package xgboost
-	rm -rf xgboost/src/*.o xgboost/src/*.so xgboost/src/*.dll
-	rm -rf xgboost/src/*/*.o
-	rm -rf xgboost/demo/*.model xgboost/demo/*.buffer xgboost/demo/*.txt
-	rm -rf xgboost/demo/runall.R
-	cp -r src xgboost/src/src
-	cp -r include xgboost/src/include
-	cp -r amalgamation xgboost/src/amalgamation
-	mkdir -p xgboost/src/rabit
-	cp -r rabit/include xgboost/src/rabit/include
-	cp -r rabit/src xgboost/src/rabit/src
-	rm -rf xgboost/src/rabit/src/*.o
-	mkdir -p xgboost/src/dmlc-core
-	cp -r dmlc-core/include xgboost/src/dmlc-core/include
-	cp -r dmlc-core/src xgboost/src/dmlc-core/src
-	cp ./LICENSE xgboost
-	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' | sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.in
-	cp xgboost/src/Makevars.in xgboost/src/Makevars.win
-	sed -i -e 's/@OPENMP_CXXFLAGS@/$$\(SHLIB_OPENMP_CXXFLAGS\)/g' xgboost/src/Makevars.win
-	sed -i -e 's/-pthread/$$\(SHLIB_PTHREAD_FLAGS\)/g' xgboost/src/Makevars.win
-	bash R-package/remove_warning_suppression_pragma.sh
-	rm xgboost/remove_warning_suppression_pragma.sh
-
-Rbuild: Rpack
-	R CMD build --no-build-vignettes xgboost
-	rm -rf xgboost
-
-Rcheck: Rbuild
-	R CMD check xgboost*.tar.gz
-
--include build/*.d
--include build/*/*.d
--include build_plugin/*/*.d
+	$(RM) $(OBJ) $(BIN) *~

NEWS.md

@@ -1,792 +0,0 @@
-XGBoost Change Log
-==================
-
-This file records the changes in xgboost library in reverse chronological order.
-
-## v0.90 (2019.05.18)
-
-### XGBoost Python package drops Python 2.x (#4379, #4381)
-Python 2.x is reaching its end-of-life at the end of this year. [Many scientific Python packages are now moving to drop Python 2.x](https://python3statement.org/).
-
-### XGBoost4J-Spark now requires Spark 2.4.x (#4377)
-* Spark 2.3 is reaching its end-of-life soon. See discussion at #4389.
-* **Consistent handling of missing values** (#4309, #4349, #4411): Many users had reported issue with inconsistent predictions between XGBoost4J-Spark and the Python XGBoost package. The issue was caused by Spark mis-handling non-zero missing values (NaN, -1, 999 etc). We now alert the user whenever Spark doesn't handle missing values correctly (#4309, #4349). See [the tutorial for dealing with missing values in XGBoost4J-Spark](https://xgboost.readthedocs.io/en/release_0.90/jvm/xgboost4j_spark_tutorial.html#dealing-with-missing-values). This fix also depends on the availability of Spark 2.4.x.
-
-### Roadmap: better performance scaling for multi-core CPUs (#4310)
-* Poor performance scaling of the `hist` algorithm for multi-core CPUs has been under investigation (#3810). #4310 optimizes quantile sketches and other pre-processing tasks. Special thanks to @SmirnovEgorRu.
-
-### Roadmap: Harden distributed training (#4250)
-* Make distributed training in XGBoost more robust by hardening [Rabit](https://github.com/dmlc/rabit), which implements [the AllReduce primitive](https://en.wikipedia.org/wiki/Reduce_%28parallel_pattern%29). In particular, improve test coverage on mechanisms for fault tolerance and recovery. Special thanks to @chenqin.
-
-### New feature: Multi-class metric functions for GPUs (#4368)
-* Metrics for multi-class classification have been ported to GPU: `merror`, `mlogloss`. Special thanks to @trivialfis.
-* With supported metrics, XGBoost will select the correct devices based on your system and `n_gpus` parameter.
-
-### New feature: Scikit-learn-like random forest API (#4148, #4255, #4258)
-* XGBoost Python package now offers `XGBRFClassifier` and `XGBRFRegressor` API to train random forests. See [the tutorial](https://xgboost.readthedocs.io/en/release_0.90/tutorials/rf.html). Special thanks to @canonizer
-
-### New feature: use external memory in GPU predictor (#4284, #4396, #4438, #4457)
-* It is now possible to make predictions on GPU when the input is read from external memory. This is useful when you want to make predictions with big dataset that does not fit into the GPU memory. Special thanks to @rongou, @canonizer, @sriramch.
-
-  ```python
-  dtest = xgboost.DMatrix('test_data.libsvm#dtest.cache')
-  bst.set_param('predictor', 'gpu_predictor')
-  bst.predict(dtest)
-  ```
-
-* Coming soon: GPU training (`gpu_hist`) with external memory
-
-### New feature: XGBoost can now handle comments in LIBSVM files (#4430)
-* Special thanks to @trivialfis and @hcho3
-
-### New feature: Embed XGBoost in your C/C++ applications using CMake (#4323, #4333, #4453)
-* It is now easier than ever to embed XGBoost in your C/C++ applications. In your CMakeLists.txt, add `xgboost::xgboost` as a linked library:
-
-  ```cmake
-  find_package(xgboost REQUIRED)
-  add_executable(api-demo c-api-demo.c)
-  target_link_libraries(api-demo xgboost::xgboost)
-  ```
-
-  [XGBoost C API documentation is available.](https://xgboost.readthedocs.io/en/release_0.90/dev) Special thanks to @trivialfis
-
-### Performance improvements
-* Use feature interaction constraints to narrow split search space (#4341, #4428)
-* Additional optimizations for `gpu_hist` (#4248, #4283)
-* Reduce OpenMP thread launches in `gpu_hist` (#4343)
-* Additional optimizations for multi-node multi-GPU random forests. (#4238)
-* Allocate unique prediction buffer for each input matrix, to avoid re-sizing GPU array (#4275)
-* Remove various synchronisations from CUDA API calls (#4205)
-* XGBoost4J-Spark
-  - Allow the user to control whether to cache partitioned training data, to potentially reduce execution time (#4268)
-
-### Bug-fixes
-* Fix node reuse in `hist` (#4404)
-* Fix GPU histogram allocation (#4347)
-* Fix matrix attributes not sliced (#4311)
-* Revise AUC and AUCPR metrics now work with weighted ranking task (#4216, #4436)
-* Fix timer invocation for InitDataOnce() in `gpu_hist` (#4206)
-* Fix R-devel errors (#4251)
-* Make gradient update in GPU linear updater thread-safe (#4259)
-* Prevent out-of-range access in column matrix (#4231)
-* Don't store DMatrix handle in Python object until it's initialized, to improve exception safety (#4317)
-* XGBoost4J-Spark
-  - Fix non-deterministic order within a zipped partition on prediction (#4388)
-  - Remove race condition on tracker shutdown (#4224)
-  - Allow set the parameter `maxLeaves`. (#4226)
-  - Allow partial evaluation of dataframe before prediction (#4407)
-  - Automatically set `maximize_evaluation_metrics` if not explicitly given (#4446)
-
-### API changes
-* Deprecate `reg:linear` in favor of `reg:squarederror`. (#4267, #4427)
-* Add attribute getter and setter to the Booster object in XGBoost4J (#4336)
-
-### Maintenance: Refactor C++ code for legibility and maintainability
-* Fix clang-tidy warnings. (#4149)
-* Remove deprecated C APIs. (#4266)
-* Use Monitor class to time functions in `hist`. (#4273)
-* Retire DVec class in favour of c++20 style span for device memory. (#4293)
-* Improve HostDeviceVector exception safety (#4301)
-
-### Maintenance: testing, continuous integration, build system
-* **Major refactor of CMakeLists.txt** (#4323, #4333, #4453): adopt modern CMake and export XGBoost as a target
-* **Major improvement in Jenkins CI pipeline** (#4234)
-  - Migrate all Linux tests to Jenkins (#4401)
-  - Builds and tests are now de-coupled, to test an artifact against multiple versions of CUDA, JDK, and other dependencies (#4401)
-  - Add Windows GPU to Jenkins CI pipeline (#4463, #4469)
-* Support CUDA 10.1 (#4223, #4232, #4265, #4468)
-* Python wheels are now built with CUDA 9.0, so that JIT is not required on Volta architecture (#4459)
-* Integrate with NVTX CUDA profiler (#4205)
-* Add a test for cpu predictor using external memory (#4308)
-* Refactor tests to get rid of duplication (#4358)
-* Remove test dependency on `craigcitro/r-travis`, since it's deprecated (#4353)
-* Add files from local R build to `.gitignore` (#4346)
-* Make XGBoost4J compatible with Java 9+ by revising NativeLibLoader (#4351)
-* Jenkins build for CUDA 10.0 (#4281)
-* Remove remaining `silent` and `debug_verbose` in Python tests (#4299)
-* Use all cores to build XGBoost4J lib on linux (#4304)
-* Upgrade Jenkins Linux build environment to GCC 5.3.1, CMake 3.6.0 (#4306)
-* Make CMakeLists.txt compatible with CMake 3.3 (#4420)
-* Add OpenMP option in CMakeLists.txt (#4339)
-* Get rid of a few trivial compiler warnings (#4312)
-* Add external Docker build cache, to speed up builds on Jenkins CI (#4331, #4334, #4458)
-* Fix Windows tests (#4403)
-* Fix a broken python test (#4395)
-* Use a fixed seed to split data in XGBoost4J-Spark tests, for reproducibility (#4417)
-* Add additional Python tests to test training under constraints (#4426)
-* Enable building with shared NCCL. (#4447)
-
-### Usability Improvements, Documentation
-* Document limitation of one-split-at-a-time Greedy tree learning heuristic (#4233)
-* Update build doc: PyPI wheel now support multi-GPU (#4219)
-* Fix docs for `num_parallel_tree` (#4221)
-* Fix document about `colsample_by*` parameter (#4340)
-* Make the train and test input with same colnames. (#4329)
-* Update R contribute link. (#4236)
-* Fix travis R tests (#4277)
-* Log version number in crash log in XGBoost4J-Spark (#4271, #4303)
-* Allow supression of Rabit output in Booster::train in XGBoost4J (#4262)
-* Add tutorial on handling missing values in XGBoost4J-Spark (#4425)
-* Fix typos (#4345, #4393, #4432, #4435)
-* Added language classifier in setup.py (#4327)
-* Added Travis CI badge (#4344)
-* Add BentoML to use case section (#4400)
-* Remove subtly sexist remark (#4418)
-* Add R vignette about parsing JSON dumps (#4439)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Andy Adinets (@canonizer), Jonas (@elcombato), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), James Lamb (@jameslamb), Jean-Francois Zinque (@jeffzi), Yang Yang (@jokerkeny), Mayank Suman (@mayanksuman), jess (@monkeywithacupcake), Hajime Morrita (@omo), Ravi Kalia (@project-delphi), @ras44, Rong Ou (@rongou), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Jiaming Yuan (@trivialfis), Christopher Suchanek (@wsuchy), Bozhao (@yubozhao)
-
-**Reviewers**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Laurae (@Laurae2), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), @alois-bissuel, Andy Adinets (@canonizer), Chen Qin (@chenqin), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), @jakirkham, James Lamb (@jameslamb), Julien Schueller (@jschueller), Mayank Suman (@mayanksuman), Hajime Morrita (@omo), Rong Ou (@rongou), Sara Robinson (@sararob), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Sean Owen (@srowen), Sergei Lebedev (@superbobry), Yuan (Terry) Tang (@terrytangyuan), Theodore Vasiloudis (@thvasilo), Matthew Tovbin (@tovbinm), Jiaming Yuan (@trivialfis), Xin Yin (@xydrolase)
-
-## v0.82 (2019.03.03)
-This release is packed with many new features and bug fixes.
-
-### Roadmap: better performance scaling for multi-core CPUs (#3957)
-* Poor performance scaling of the `hist` algorithm for multi-core CPUs has been under investigation (#3810). #3957 marks an important step toward better performance scaling, by using software pre-fetching and replacing STL vectors with C-style arrays. Special thanks to @Laurae2 and @SmirnovEgorRu.
-* See #3810 for latest progress on this roadmap.
-
-### New feature: Distributed Fast Histogram Algorithm (`hist`) (#4011, #4102, #4140, #4128)
-* It is now possible to run the `hist` algorithm in distributed setting. Special thanks to @CodingCat. The benefits include:
-  1. Faster local computation via feature binning
-  2. Support for monotonic constraints and feature interaction constraints
-  3. Simpler codebase than `approx`, allowing for future improvement
-* Depth-wise tree growing is now performed in a separate code path, so that cross-node syncronization is performed only once per level.
-
-### New feature: Multi-Node, Multi-GPU training (#4095)
-* Distributed training is now able to utilize clusters equipped with NVIDIA GPUs. In particular, the rabit AllReduce layer will communicate GPU device information. Special thanks to @mt-jones, @RAMitchell, @rongou, @trivialfis, @canonizer, and @jeffdk.
-* Resource management systems will be able to assign a rank for each GPU in the cluster.
-* In Dask, users will be able to construct a collection of XGBoost processes over an inhomogeneous device cluster (i.e. workers with different number and/or kinds of GPUs).
-
-### New feature: Multiple validation datasets in XGBoost4J-Spark (#3904, #3910)
-* You can now track the performance of the model during training with multiple evaluation datasets. By specifying `eval_sets` or call `setEvalSets` over a `XGBoostClassifier` or `XGBoostRegressor`, you can pass in multiple evaluation datasets typed as a `Map` from `String` to `DataFrame`. Special thanks to @CodingCat.
-* See the usage of multiple validation datasets [here](https://github.com/dmlc/xgboost/blob/0c1d5f1120c0a159f2567b267f0ec4ffadee00d0/jvm-packages/xgboost4j-example/src/main/scala/ml/dmlc/xgboost4j/scala/example/spark/SparkTraining.scala#L66-L78)
-
-### New feature: Additional metric functions for GPUs (#3952)
-* Element-wise metrics have been ported to GPU: `rmse`, `mae`, `logloss`, `poisson-nloglik`, `gamma-deviance`, `gamma-nloglik`, `error`, `tweedie-nloglik`. Special thanks to @trivialfis and @RAMitchell.
-* With supported metrics, XGBoost will select the correct devices based on your system and `n_gpus` parameter.
-
-### New feature: Column sampling at individual nodes (splits) (#3971)
-* Columns (features) can now be sampled at individual tree nodes, in addition to per-tree and per-level sampling. To enable per-node sampling, set `colsample_bynode` parameter, which represents the fraction of columns sampled at each node. This parameter is set to 1.0 by default (i.e. no sampling per node). Special thanks to @canonizer.
-* The `colsample_bynode` parameter works cumulatively with other `colsample_by*` parameters: for example, `{'colsample_bynode':0.5, 'colsample_bytree':0.5}` with 100 columns will give 25 features to choose from at each split.
-
-### Major API change: consistent logging level via `verbosity` (#3982, #4002, #4138)
-* XGBoost now allows fine-grained control over logging. You can set `verbosity` to 0 (silent), 1 (warning), 2 (info), and 3 (debug). This is useful for controlling the amount of logging outputs. Special thanks to @trivialfis.
-* Parameters `silent` and `debug_verbose` are now deprecated.
-* Note: Sometimes XGBoost tries to change configurations based on heuristics, which is displayed as warning message.  If there's unexpected behaviour, please try to increase value of verbosity.
-
-### Major bug fix: external memory (#4040, #4193)
-* Clarify object ownership in multi-threaded prefetcher, to avoid memory error.
-* Correctly merge two column batches (which uses [CSC layout](https://en.wikipedia.org/wiki/Sparse_matrix#Compressed_sparse_column_(CSC_or_CCS))).
-* Add unit tests for external memory.
-* Special thanks to @trivialfis and @hcho3.
-
-### Major bug fix: early stopping fixed in XGBoost4J and XGBoost4J-Spark (#3928, #4176)
-* Early stopping in XGBoost4J and XGBoost4J-Spark is now consistent with its counterpart in the Python package. Training stops if the current iteration is `earlyStoppingSteps` away from the best iteration. If there are multiple evaluation sets, only the last one is used to determinate early stop.
-* See the updated documentation [here](https://xgboost.readthedocs.io/en/release_0.82/jvm/xgboost4j_spark_tutorial.html#early-stopping)
-* Special thanks to @CodingCat, @yanboliang, and @mingyang.
-
-### Major bug fix: infrequent features should not crash distributed training (#4045)
-* For infrequently occuring features, some partitions may not get any instance. This scenario used to crash distributed training due to mal-formed ranges. The problem has now been fixed.
-* In practice, one-hot-encoded categorical variables tend to produce rare features, particularly when the cardinality is high.
-* Special thanks to @CodingCat.
-
-### Performance improvements
-* Faster, more space-efficient radix sorting in `gpu_hist` (#3895)
-* Subtraction trick in histogram calculation in `gpu_hist` (#3945)
-* More performant re-partition in XGBoost4J-Spark (#4049)
-
-### Bug-fixes
-* Fix semantics of `gpu_id` when running multiple XGBoost processes on a multi-GPU machine (#3851)
-* Fix page storage path for external memory on Windows (#3869)
-* Fix configuration setup so that DART utilizes GPU (#4024)
-* Eliminate NAN values from SHAP prediction (#3943)
-* Prevent empty quantile sketches in `hist` (#4155)
-* Enable running objectives with 0 GPU (#3878)
-* Parameters are no longer dependent on system locale (#3891, #3907)
-* Use consistent data type in the GPU coordinate descent code (#3917)
-* Remove undefined behavior in the CLI config parser on the ARM platform (#3976)
-* Initialize counters in GPU AllReduce (#3987)
-* Prevent deadlocks in GPU AllReduce (#4113)
-* Load correct values from sliced NumPy arrays (#4147, #4165)
-* Fix incorrect GPU device selection (#4161)
-* Make feature binning logic in `hist` aware of query groups when running a ranking task (#4115). For ranking task, query groups are weighted, not individual instances.
-* Generate correct C++ exception type for `LOG(FATAL)` macro (#4159)
-* Python package
-  - Python package should run on system without `PATH` environment variable (#3845)
-  - Fix `coef_` and `intercept_` signature to be compatible with `sklearn.RFECV` (#3873)
-  - Use UTF-8 encoding in Python package README, to support non-English locale (#3867)
-  - Add AUC-PR to list of metrics to maximize for early stopping (#3936)
-  - Allow loading pickles without `self.booster` attribute, for backward compatibility (#3938, #3944)
-  - White-list DART for feature importances (#4073)
-  - Update usage of [h2oai/datatable](https://github.com/h2oai/datatable) (#4123)
-* XGBoost4J-Spark
-  - Address scalability issue in prediction (#4033)
-  - Enforce the use of per-group weights for ranking task (#4118)
-  - Fix vector size of `rawPredictionCol` in `XGBoostClassificationModel` (#3932)
-  - More robust error handling in Spark tracker (#4046, #4108)
-  - Fix return type of `setEvalSets` (#4105)
-  - Return correct value of `getMaxLeaves` (#4114)
-
-### API changes
-* Add experimental parameter `single_precision_histogram` to use single-precision histograms for the `gpu_hist` algorithm (#3965)
-* Python package
-  - Add option to select type of feature importances in the scikit-learn inferface (#3876)
-  - Add `trees_to_df()` method to dump decision trees as Pandas data frame (#4153)
-  - Add options to control node shapes in the GraphViz plotting function (#3859)
-  - Add `xgb_model` option to `XGBClassifier`, to load previously saved model (#4092)
-  - Passing lists into `DMatrix` is now deprecated (#3970)
-* XGBoost4J
-  - Support multiple feature importance features (#3801)
-
-### Maintenance: Refactor C++ code for legibility and maintainability
-* Refactor `hist` algorithm code and add unit tests (#3836)
-* Minor refactoring of split evaluator in `gpu_hist` (#3889)
-* Removed unused leaf vector field in the tree model (#3989)
-* Simplify the tree representation by combining `TreeModel` and `RegTree` classes (#3995)
-* Simplify and harden tree expansion code (#4008, #4015)
-* De-duplicate parameter classes in the linear model algorithms (#4013)
-* Robust handling of ranges with C++20 span in `gpu_exact` and `gpu_coord_descent` (#4020, #4029)
-* Simplify tree training code (#3825). Also use Span class for robust handling of ranges.
-
-### Maintenance: testing, continuous integration, build system
-* Disallow `std::regex` since it's not supported by GCC 4.8.x (#3870)
-* Add multi-GPU tests for coordinate descent algorithm for linear models (#3893, #3974)
-* Enforce naming style in Python lint (#3896)
-* Refactor Python tests (#3897, #3901): Use pytest exclusively, display full trace upon failure
-* Address `DeprecationWarning` when using Python collections (#3909)
-* Use correct group for maven site plugin (#3937)
-* Jenkins CI is now using on-demand EC2 instances exclusively, due to unreliability of Spot instances (#3948)
-* Better GPU performance logging (#3945)
-* Fix GPU tests on machines with only 1 GPU (#4053)
-* Eliminate CRAN check warnings and notes (#3988)
-* Add unit tests for tree serialization (#3989)
-* Add unit tests for tree fitting functions in `hist` (#4155)
-* Add a unit test for `gpu_exact` algorithm (#4020)
-* Correct JVM CMake GPU flag (#4071)
-* Fix failing Travis CI on Mac (#4086)
-* Speed up Jenkins by not compiling CMake (#4099)
-* Analyze C++ and CUDA code using clang-tidy, as part of Jenkins CI pipeline (#4034)
-* Fix broken R test: Install Homebrew GCC (#4142)
-* Check for empty datasets in GPU unit tests (#4151)
-* Fix Windows compilation (#4139)
-* Comply with latest convention of cpplint (#4157)
-* Fix a unit test in `gpu_hist` (#4158)
-* Speed up data generation in Python tests (#4164)
-
-### Usability Improvements
-* Add link to [InfoWorld 2019 Technology of the Year Award](https://www.infoworld.com/article/3336072/application-development/infoworlds-2019-technology-of-the-year-award-winners.html) (#4116)
-* Remove outdated AWS YARN tutorial (#3885)
-* Document current limitation in number of features (#3886)
-* Remove unnecessary warning when `gblinear` is selected (#3888)
-* Document limitation of CSV parser: header not supported (#3934)
-* Log training parameters in XGBoost4J-Spark (#4091)
-* Clarify early stopping behavior in the scikit-learn interface (#3967)
-* Clarify behavior of `max_depth` parameter (#4078)
-* Revise Python docstrings for ranking task (#4121). In particular, weights must be per-group in learning-to-rank setting.
-* Document parameter `num_parallel_tree` (#4022)
-* Add Jenkins status badge (#4090)
-* Warn users against using internal functions of `Booster` object (#4066)
-* Reformat `benchmark_tree.py` to comply with Python style convention (#4126)
-* Clarify a comment in `objectiveTrait` (#4174)
-* Fix typos and broken links in documentation (#3890, #3872, #3902, #3919, #3975, #4027, #4156, #4167)
-
-### Acknowledgement
-**Contributors** (in no particular order): Jiaming Yuan (@trivialfis), Hyunsu Cho (@hcho3), Nan Zhu (@CodingCat), Rory Mitchell (@RAMitchell), Yanbo Liang (@yanboliang), Andy Adinets (@canonizer), Tong He (@hetong007), Yuan Tang (@terrytangyuan)
-
-**First-time Contributors** (in no particular order): Jelle Zijlstra (@JelleZijlstra), Jiacheng Xu (@jiachengxu), @ajing, Kashif Rasul (@kashif), @theycallhimavi, Joey Gao (@pjgao), Prabakaran Kumaresshan (@nixphix), Huafeng Wang (@huafengw), @lyxthe, Sam Wilkinson (@scwilkinson), Tatsuhito Kato (@stabacov), Shayak Banerjee (@shayakbanerjee), Kodi Arfer (@Kodiologist), @KyleLi1985, Egor Smirnov (@SmirnovEgorRu), @tmitanitky, Pasha Stetsenko (@st-pasha), Kenichi Nagahara (@keni-chi), Abhai Kollara Dilip (@abhaikollara), Patrick Ford (@pford221), @hshujuan, Matthew Jones (@mt-jones), Thejaswi Rao (@teju85), Adam November (@anovember)
-
-**First-time Reviewers** (in no particular order): Mingyang Hu (@mingyang), Theodore Vasiloudis (@thvasilo), Jakub Troszok (@troszok), Rong Ou (@rongou), @Denisevi4, Matthew Jones (@mt-jones), Jeff Kaplan (@jeffdk)
-
-## v0.81 (2018.11.04)
-### New feature: feature interaction constraints
-* Users are now able to control which features (independent variables) are allowed to interact by specifying feature interaction constraints (#3466).
-* [Tutorial](https://xgboost.readthedocs.io/en/release_0.81/tutorials/feature_interaction_constraint.html) is available, as well as [R](https://github.com/dmlc/xgboost/blob/9254c58e4dfff6a59dc0829a2ceb02e45ed17cd0/R-package/demo/interaction_constraints.R) and [Python](https://github.com/dmlc/xgboost/blob/9254c58e4dfff6a59dc0829a2ceb02e45ed17cd0/tests/python/test_interaction_constraints.py) examples.
-
-### New feature: learning to rank using scikit-learn interface
-* Learning to rank task is now available for the scikit-learn interface of the Python package (#3560, #3848). It is now possible to integrate the XGBoost ranking model into the scikit-learn learning pipeline.
-* Examples of using `XGBRanker` class is found at [demo/rank/rank_sklearn.py](https://github.com/dmlc/xgboost/blob/24a268a2e3cb17302db3d72da8f04016b7d352d9/demo/rank/rank_sklearn.py).
-
-### New feature: R interface for SHAP interactions
-* SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. Previously, this feature was only available from the Python package; now it is available from the R package as well (#3636).
-
-### New feature: GPU predictor now use multiple GPUs to predict
-* GPU predictor is now able to utilize multiple GPUs at once to accelerate prediction (#3738)
-
-### New feature: Scale distributed XGBoost to large-scale clusters
-* Fix OS file descriptor limit assertion error on large cluster (#3835, dmlc/rabit#73) by replacing `select()` based AllReduce/Broadcast with `poll()` based implementation.
-* Mitigate tracker "thundering herd" issue on large cluster. Add exponential backoff retry when workers connect to tracker.
-* With this change, we were able to scale to 1.5k executors on a 12 billion row dataset after some tweaks here and there.
-
-### New feature: Additional objective functions for GPUs
-* New objective functions ported to GPU: `hinge`, `multi:softmax`, `multi:softprob`, `count:poisson`, `reg:gamma`, `"reg:tweedie`.
-* With supported objectives, XGBoost will select the correct devices based on your system and `n_gpus` parameter.
-
-### Major bug fix: learning to rank with XGBoost4J-Spark
-* Previously, `repartitionForData` would shuffle data and lose ordering necessary for ranking task.
-* To fix this issue, data points within each RDD partition is explicitly group by their group (query session) IDs (#3654). Also handle empty RDD partition carefully (#3750).
-
-### Major bug fix: early stopping fixed in XGBoost4J-Spark
-* Earlier implementation of early stopping had incorrect semantics and didn't let users to specify direction for optimizing (maximize / minimize)
-* A parameter `maximize_evaluation_metrics` is defined so as to tell whether a metric should be maximized or minimized as part of early stopping criteria (#3808). Also early stopping now has correct semantics.
-
-### API changes
-* Column sampling by level (`colsample_bylevel`) is now functional for `hist` algorithm (#3635, #3862)
-* GPU tag `gpu:` for regression objectives are now deprecated. XGBoost will select the correct devices automatically (#3643)
-* Add `disable_default_eval_metric` parameter to disable default metric (#3606)
-* Experimental AVX support for gradient computation is removed (#3752)
-* XGBoost4J-Spark
-  - Add `rank:ndcg` and `rank:map` to supported objectives (#3697)
-* Python package
-  - Add `callbacks` argument to `fit()` function of sciki-learn API (#3682)
-  - Add `XGBRanker` to scikit-learn interface (#3560, #3848)
-  - Add `validate_features` argument to `predict()` function of scikit-learn API (#3653)
-  - Allow scikit-learn grid search over parameters specified as keyword arguments (#3791)
-  - Add `coef_` and `intercept_` as properties of scikit-learn wrapper (#3855). Some scikit-learn functions expect these properties.
-
-### Performance improvements
-* Address very high GPU memory usage for large data (#3635)
-* Fix performance regression within `EvaluateSplits()` of `gpu_hist` algorithm. (#3680)
-
-### Bug-fixes
-* Fix a problem in GPU quantile sketch with tiny instance weights. (#3628)
-* Fix copy constructor for `HostDeviceVectorImpl` to prevent dangling pointers (#3657)
-* Fix a bug in partitioned file loading (#3673)
-* Fixed an uninitialized pointer in `gpu_hist` (#3703)
-* Reshared data among GPUs when number of GPUs is changed (#3721)
-* Add back `max_delta_step` to split evaluation (#3668)
-* Do not round up integer thresholds for integer features in JSON dump (#3717)
-* Use `dmlc::TemporaryDirectory` to handle temporaries in cross-platform way (#3783)
-* Fix accuracy problem with `gpu_hist` when `min_child_weight` and `lambda` are set to 0 (#3793)
-* Make sure that `tree_method` parameter is recognized and not silently ignored (#3849)
-* XGBoost4J-Spark
-  - Make sure `thresholds` are considered when executing `predict()` method (#3577)
-  - Avoid losing precision when computing probabilities by converting to `Double` early (#3576)
-  - `getTreeLimit()` should return `Int` (#3602)
-  - Fix checkpoint serialization on HDFS (#3614)
-  - Throw `ControlThrowable` instead of `InterruptedException` so that it is properly re-thrown (#3632)
-  - Remove extraneous output to stdout (#3665)
-  - Allow specification of task type for custom objectives and evaluations (#3646)
-  - Fix distributed updater check (#3739)
-  - Fix issue when spark job execution thread cannot return before we execute `first()` (#3758)
-* Python package
-  - Fix accessing `DMatrix.handle` before it is set (#3599)
-  - `XGBClassifier.predict()` should return margin scores when `output_margin` is set to true (#3651)
-  - Early stopping callback should maximize metric of form `NDCG@n-` (#3685)
-  - Preserve feature names when slicing `DMatrix` (#3766)
-* R package
-  - Replace `nround` with `nrounds` to match actual parameter (#3592)
-  - Amend `xgb.createFolds` to handle classes of a single element (#3630)
-  - Fix buggy random generator and make `colsample_bytree` functional (#3781)
-
-### Maintenance: testing, continuous integration, build system
-* Add sanitizers tests to Travis CI (#3557)
-* Add NumPy, Matplotlib, Graphviz as requirements for doc build (#3669)
-* Comply with CRAN submission policy (#3660, #3728)
-* Remove copy-paste error in JVM test suite (#3692)
-* Disable flaky tests in `R-package/tests/testthat/test_update.R` (#3723)
-* Make Python tests compatible with scikit-learn 0.20 release (#3731)
-* Separate out restricted and unrestricted tasks, so that pull requests don't build downloadable artifacts (#3736)
-* Add multi-GPU unit test environment (#3741)
-* Allow plug-ins to be built by CMake (#3752)
-* Test wheel compatibility on CPU containers for pull requests (#3762)
-* Fix broken doc build due to Matplotlib 3.0 release (#3764)
-* Produce `xgboost.so` for XGBoost-R on Mac OSX, so that `make install` works (#3767)
-* Retry Jenkins CI tests up to 3 times to improve reliability (#3769, #3769, #3775, #3776, #3777)
-* Add basic unit tests for `gpu_hist` algorithm (#3785)
-* Fix Python environment for distributed unit tests (#3806)
-* Test wheels on CUDA 10.0 container for compatibility (#3838)
-* Fix JVM doc build (#3853)
-
-### Maintenance: Refactor C++ code for legibility and maintainability
-* Merge generic device helper functions into `GPUSet` class (#3626)
-* Re-factor column sampling logic into `ColumnSampler` class (#3635, #3637)
-* Replace `std::vector` with `HostDeviceVector` in `MetaInfo` and `SparsePage` (#3446)
-* Simplify `DMatrix` class (#3395)
-* De-duplicate CPU/GPU code using `Transform` class (#3643, #3751)
-* Remove obsoleted `QuantileHistMaker` class (#3761)
-* Remove obsoleted `NoConstraint` class (#3792)
-
-### Other Features
-* C++20-compliant Span class for safe pointer indexing (#3548, #3588)
-* Add helper functions to manipulate multiple GPU devices (#3693)
-* XGBoost4J-Spark
-  - Allow specifying host ip from the `xgboost-tracker.properties file` (#3833). This comes in handy when `hosts` files doesn't correctly define localhost.
-
-### Usability Improvements
-* Add reference to GitHub repository in `pom.xml` of JVM packages (#3589)
-* Add R demo of multi-class classification (#3695)
-* Document JSON dump functionality (#3600, #3603)
-* Document CUDA requirement and lack of external memory for GPU algorithms (#3624)
-* Document LambdaMART objectives, both pairwise and listwise (#3672)
-* Document `aucpr` evaluation metric (#3687)
-* Document gblinear parameters: `feature_selector` and `top_k` (#3780)
-* Add instructions for using MinGW-built XGBoost with Python. (#3774)
-* Removed nonexistent parameter `use_buffer` from documentation (#3610)
-* Update Python API doc to include all classes and members (#3619, #3682)
-* Fix typos and broken links in documentation (#3618, #3640, #3676, #3713, #3759, #3784, #3843, #3852)
-* Binary classification demo should produce LIBSVM with 0-based indexing (#3652)
-* Process data once for Python and CLI examples of learning to rank (#3666)
-* Include full text of Apache 2.0 license in the repository (#3698)
-* Save predictor parameters in model file (#3856)
-* JVM packages
-  - Let users specify feature names when calling `getModelDump` and `getFeatureScore` (#3733)
-  - Warn the user about the lack of over-the-wire encryption (#3667)
-  - Fix errors in examples (#3719)
-  - Document choice of trackers (#3831)
-  - Document that vanilla Apache Spark is required (#3854)
-* Python package
-  - Document that custom objective can't contain colon (:) (#3601)
-  - Show a better error message for failed library loading (#3690)
-  - Document that feature importance is unavailable for non-tree learners (#3765)
-  - Document behavior of `get_fscore()` for zero-importance features (#3763)
-  - Recommend pickling as the way to save `XGBClassifier` / `XGBRegressor` / `XGBRanker` (#3829)
-* R package
-  - Enlarge variable importance plot to make it more visible (#3820)
-
-### BREAKING CHANGES
-* External memory page files have changed, breaking backwards compatibility for temporary storage used during external memory training. This only affects external memory users upgrading their xgboost version - we recommend clearing all `*.page` files before resuming training. Model serialization is unaffected.
-
-### Known issues
-* Quantile sketcher fails to produce any quantile for some edge cases (#2943)
-* The `hist` algorithm leaks memory when used with learning rate decay callback (#3579)
-* Using custom evaluation funciton together with early stopping causes assertion failure in XGBoost4J-Spark (#3595)
-* Early stopping doesn't work with `gblinear` learner (#3789)
-* Label and weight vectors are not reshared upon the change in number of GPUs (#3794). To get around this issue, delete the `DMatrix` object and re-load.
-* The `DMatrix` Python objects are initialized with incorrect values when given array slices (#3841)
-* The `gpu_id` parameter is broken and not yet properly supported (#3850)
-
-### Acknowledgement
-**Contributors** (in no particular order): Hyunsu Cho (@hcho3), Jiaming Yuan (@trivialfis), Nan Zhu (@CodingCat), Rory Mitchell (@RAMitchell), Andy Adinets (@canonizer), Vadim Khotilovich (@khotilov), Sergei Lebedev (@superbobry)
-
-**First-time Contributors** (in no particular order): Matthew Tovbin (@tovbinm), Jakob Richter (@jakob-r), Grace Lam (@grace-lam), Grant W Schneider (@grantschneider), Andrew Thia (@BlueTea88), Sergei Chipiga (@schipiga), Joseph Bradley (@jkbradley), Chen Qin (@chenqin), Jerry Lin (@linjer), Dmitriy Rybalko (@rdtft), Michael Mui (@mmui), Takahiro Kojima (@515hikaru), Bruce Zhao (@BruceZhaoR), Wei Tian (@weitian), Saumya Bhatnagar (@Sam1301), Juzer Shakir (@JuzerShakir), Zhao Hang (@cleghom), Jonathan Friedman (@jontonsoup), Bruno Tremblay (@meztez), Boris Filippov (@frenzykryger), @Shiki-H, @mrgutkun, @gorogm, @htgeis, @jakehoare, @zengxy, @KOLANICH
-
-**First-time Reviewers** (in no particular order): Nikita Titov (@StrikerRUS), Xiangrui Meng (@mengxr), Nirmal Borah (@Nirmal-Neel)
-
-
-## v0.80 (2018.08.13)
-* **JVM packages received a major upgrade**: To consolidate the APIs and improve the user experience, we refactored the design of XGBoost4J-Spark in a significant manner. (#3387)
-  - Consolidated APIs: It is now much easier to integrate XGBoost models into a Spark ML pipeline. Users can control behaviors like output leaf prediction results by setting corresponding column names. Training is now more consistent with other Estimators in Spark MLLIB: there is now one single method `fit()` to train decision trees.
-  - Better user experience: we refactored the parameters relevant modules in XGBoost4J-Spark to provide both camel-case (Spark ML style) and underscore (XGBoost style) parameters
-  - A brand-new tutorial is [available](https://xgboost.readthedocs.io/en/release_0.80/jvm/xgboost4j_spark_tutorial.html) for XGBoost4J-Spark.
-  - Latest API documentation is now hosted at https://xgboost.readthedocs.io/.
-* XGBoost documentation now keeps track of multiple versions:
-  - Latest master: https://xgboost.readthedocs.io/en/latest
-  - 0.80 stable: https://xgboost.readthedocs.io/en/release_0.80
-  - 0.72 stable: https://xgboost.readthedocs.io/en/release_0.72
-* Support for per-group weights in ranking objective (#3379)
-* Fix inaccurate decimal parsing (#3546)
-* New functionality
-  - Query ID column support in LIBSVM data files (#2749). This is convenient for performing ranking task in distributed setting.
-  - Hinge loss for binary classification (`binary:hinge`) (#3477)
-  - Ability to specify delimiter and instance weight column for CSV files (#3546)
-  - Ability to use 1-based indexing instead of 0-based (#3546)
-* GPU support
-  - Quantile sketch, binning, and index compression are now performed on GPU, eliminating PCIe transfer for 'gpu_hist' algorithm (#3319, #3393)
-  - Upgrade to NCCL2 for multi-GPU training (#3404).
-  - Use shared memory atomics for faster training (#3384).
-  - Dynamically allocate GPU memory, to prevent large allocations for deep trees (#3519)
-  - Fix memory copy bug for large files (#3472)
-* Python package
-  - Importing data from Python datatable (#3272)
-  - Pre-built binary wheels available for 64-bit Linux and Windows (#3424, #3443)
-  - Add new importance measures 'total_gain', 'total_cover' (#3498)
-  - Sklearn API now supports saving and loading models (#3192)
-  - Arbitrary cross validation fold indices (#3353)
-  - `predict()` function in Sklearn API uses `best_ntree_limit` if available, to make early stopping easier to use (#3445)
-  - Informational messages are now directed to Python's `print()` rather than standard output (#3438). This way, messages appear inside Jupyter notebooks.
-* R package
-  - Oracle Solaris support, per CRAN policy (#3372)
-* JVM packages
-  - Single-instance prediction (#3464)
-  - Pre-built JARs are now available from Maven Central (#3401)
-  - Add NULL pointer check (#3021)
-  - Consider `spark.task.cpus` when controlling parallelism (#3530)
-  - Handle missing values in prediction (#3529)
-  - Eliminate outputs of `System.out` (#3572)
-* Refactored C++ DMatrix class for simplicity and de-duplication (#3301)
-* Refactored C++ histogram facilities (#3564)
-* Refactored constraints / regularization mechanism for split finding (#3335, #3429). Users may specify an elastic net (L2 + L1 regularization) on leaf weights as well as monotonic constraints on test nodes. The refactor will be useful for a future addition of feature interaction constraints.
-* Statically link `libstdc++` for MinGW32 (#3430)
-* Enable loading from `group`, `base_margin` and `weight` (see [here](http://xgboost.readthedocs.io/en/latest/tutorials/input_format.html#auxiliary-files-for-additional-information)) for Python, R, and JVM packages (#3431)
-* Fix model saving for `count:possion` so that `max_delta_step` doesn't get truncated (#3515)
-* Fix loading of sparse CSC matrix (#3553)
-* Fix incorrect handling of `base_score` parameter for Tweedie regression (#3295)
-
-## v0.72.1 (2018.07.08)
-This version is only applicable for the Python package. The content is identical to that of v0.72.
-
-## v0.72 (2018.06.01)
-* Starting with this release, we plan to make a new release every two months. See #3252 for more details.
-* Fix a pathological behavior (near-zero second-order gradients) in multiclass objective (#3304)
-* Tree dumps now use high precision in storing floating-point values (#3298)
-* Submodules `rabit` and `dmlc-core` have been brought up to date, bringing bug fixes (#3330, #3221).
-* GPU support
-  - Continuous integration tests for GPU code (#3294, #3309)
-  - GPU accelerated coordinate descent algorithm (#3178)
-  - Abstract 1D vector class now works with multiple GPUs (#3287)
-  - Generate PTX code for most recent architecture (#3316)
-  - Fix a memory bug on NVIDIA K80 cards (#3293)
-  - Address performance instability for single-GPU, multi-core machines (#3324)
-* Python package
-  - FreeBSD support (#3247)
-  - Validation of feature names in `Booster.predict()` is now optional (#3323)
-* Updated Sklearn API
-  - Validation sets now support instance weights (#2354)
-  - `XGBClassifier.predict_proba()` should not support `output_margin` option. (#3343) See BREAKING CHANGES below.
-* R package:
-  - Better handling of NULL in `print.xgb.Booster()` (#3338)
-  - Comply with CRAN policy by removing compiler warning suppression (#3329)
-  - Updated CRAN submission
-* JVM packages
-  - JVM packages will now use the same versioning scheme as other packages (#3253)
-  - Update Spark to 2.3 (#3254)
-  - Add scripts to cross-build and deploy artifacts (#3276, #3307)
-  - Fix a compilation error for Scala 2.10 (#3332)
-* BREAKING CHANGES
-  - `XGBClassifier.predict_proba()` no longer accepts paramter `output_margin`. The paramater makes no sense for `predict_proba()` because the method is to predict class probabilities, not raw margin scores.
-
-## v0.71 (2018.04.11)
-* This is a minor release, mainly motivated by issues concerning `pip install`, e.g. #2426, #3189, #3118, and #3194.
-  With this release, users of Linux and MacOS will be able to run `pip install` for the most part.
-* Refactored linear booster class (`gblinear`), so as to support multiple coordinate descent updaters (#3103, #3134). See BREAKING CHANGES below.
-* Fix slow training for multiclass classification with high number of classes (#3109)
-* Fix a corner case in approximate quantile sketch (#3167). Applicable for 'hist' and 'gpu_hist' algorithms
-* Fix memory leak in DMatrix (#3182)
-* New functionality
-  - Better linear booster class (#3103, #3134)
-  - Pairwise SHAP interaction effects (#3043)
-  - Cox loss (#3043)
-  - AUC-PR metric for ranking task (#3172)
-  - Monotonic constraints for 'hist' algorithm (#3085)
-* GPU support
-  - Create an abtract 1D vector class that moves data seamlessly between the main and GPU memory (#2935, #3116, #3068). This eliminates unnecessary PCIe data transfer during training time.
-  - Fix minor bugs (#3051, #3217)
-  - Fix compatibility error for CUDA 9.1 (#3218)
-* Python package:
-  - Correctly handle parameter `verbose_eval=0` (#3115)
-* R package:
-  - Eliminate segmentation fault on 32-bit Windows platform (#2994)
-* JVM packages
-  - Fix a memory bug involving double-freeing Booster objects (#3005, #3011)
-  - Handle empty partition in predict (#3014)
-  - Update docs and unify terminology (#3024)
-  - Delete cache files after job finishes (#3022)
-  - Compatibility fixes for latest Spark versions (#3062, #3093)
-* BREAKING CHANGES: Updated linear modelling algorithms. In particular L1/L2 regularisation penalties are now normalised to number of training examples. This makes the implementation consistent with sklearn/glmnet. L2 regularisation has also been removed from the intercept. To produce linear models with the old regularisation behaviour, the alpha/lambda regularisation parameters can be manually scaled by dividing them by the number of training examples.
-
-## v0.7 (2017.12.30)
-* **This version represents a major change from the last release (v0.6), which was released one year and half ago.**
-* Updated Sklearn API
-  - Add compatibility layer for scikit-learn v0.18: `sklearn.cross_validation` now deprecated
-  - Updated to allow use of all XGBoost parameters via `**kwargs`.
-  - Updated `nthread` to `n_jobs` and `seed` to `random_state` (as per Sklearn convention); `nthread` and `seed` are now marked as deprecated
-  - Updated to allow choice of Booster (`gbtree`, `gblinear`, or `dart`)
-  - `XGBRegressor` now supports instance weights (specify `sample_weight` parameter)
-  - Pass `n_jobs` parameter to the `DMatrix` constructor
-  - Add `xgb_model` parameter to `fit` method, to allow continuation of training
-* Refactored gbm to allow more friendly cache strategy
-  - Specialized some prediction routine
-* Robust `DMatrix` construction from a sparse matrix
-* Faster consturction of `DMatrix` from 2D NumPy matrices: elide copies, use of multiple threads
-* Automatically remove nan from input data when it is sparse.
-  - This can solve some of user reported problem of istart != hist.size
-* Fix the single-instance prediction function to obtain correct predictions
-* Minor fixes
-  - Thread local variable is upgraded so it is automatically freed at thread exit.
-  - Fix saving and loading `count::poisson` models
-  - Fix CalcDCG to use base-2 logarithm
-  - Messages are now written to stderr instead of stdout
-  - Keep built-in evaluations while using customized evaluation functions
-  - Use `bst_float` consistently to minimize type conversion
-  - Copy the base margin when slicing `DMatrix`
-  - Evaluation metrics are now saved to the model file
-  - Use `int32_t` explicitly when serializing version
-  - In distributed training, synchronize the number of features after loading a data matrix.
-* Migrate to C++11
-  - The current master version now requires C++11 enabled compiled(g++4.8 or higher)
-* Predictor interface was factored out (in a manner similar to the updater interface).
-* Makefile support for Solaris and ARM
-* Test code coverage using Codecov
-* Add CPP tests
-* Add `Dockerfile` and `Jenkinsfile` to support continuous integration for GPU code
-* New functionality
-  - Ability to adjust tree model's statistics to a new dataset without changing tree structures.
-  - Ability to extract feature contributions from individual predictions, as described in [here](http://blog.datadive.net/interpreting-random-forests/) and [here](https://arxiv.org/abs/1706.06060).
-  - Faster, histogram-based tree algorithm (`tree_method='hist'`) .
-  - GPU/CUDA accelerated tree algorithms (`tree_method='gpu_hist'` or `'gpu_exact'`), including the GPU-based predictor.
-  - Monotonic constraints: when other features are fixed, force the prediction to be monotonic increasing with respect to a certain specified feature.
-  - Faster gradient caculation using AVX SIMD
-  - Ability to export models in JSON format
-  - Support for Tweedie regression
-  - Additional dropout options for DART: binomial+1, epsilon
-  - Ability to update an existing model in-place: this is useful for many applications, such as determining feature importance
-* Python package:
-  - New parameters:
-    - `learning_rates` in `cv()`
-    - `shuffle` in `mknfold()`
-    - `max_features` and `show_values` in `plot_importance()`
-    - `sample_weight` in `XGBRegressor.fit()`
-  - Support binary wheel builds
-  - Fix `MultiIndex` detection to support Pandas 0.21.0 and higher
-  - Support metrics and evaluation sets whose names contain `-`
-  - Support feature maps when plotting trees
-  - Compatibility fix for Python 2.6
-  - Call `print_evaluation` callback at last iteration
-  - Use appropriate integer types when calling native code, to prevent truncation and memory error
-  - Fix shared library loading on Mac OS X
-* R package:
-  - New parameters:
-    - `silent` in `xgb.DMatrix()`
-    - `use_int_id` in `xgb.model.dt.tree()`
-    - `predcontrib` in `predict()`
-    - `monotone_constraints` in `xgb.train()`
-  - Default value of the `save_period` parameter in `xgboost()` changed to NULL (consistent with `xgb.train()`).
-  - It's possible to custom-build the R package with GPU acceleration support.
-  - Enable JVM build for Mac OS X and Windows
-  - Integration with AppVeyor CI
-  - Improved safety for garbage collection
-  - Store numeric attributes with higher precision
-  - Easier installation for devel version
-  - Improved `xgb.plot.tree()`
-  - Various minor fixes to improve user experience and robustness
-  - Register native code to pass CRAN check
-  - Updated CRAN submission
-* JVM packages
-  - Add Spark pipeline persistence API
-  - Fix data persistence: loss evaluation on test data had wrongly used caches for training data.
-  - Clean external cache after training
-  - Implement early stopping
-  - Enable training of multiple models by distinguishing stage IDs
-  - Better Spark integration: support RDD / dataframe / dataset, integrate with Spark ML package
-  - XGBoost4j now supports ranking task
-  - Support training with missing data
-  - Refactor JVM package to separate regression and classification models to be consistent with other machine learning libraries
-  - Support XGBoost4j compilation on Windows
-  - Parameter tuning tool
-  - Publish source code for XGBoost4j to maven local repo
-  - Scala implementation of the Rabit tracker (drop-in replacement for the Java implementation)
-  - Better exception handling for the Rabit tracker
-  - Persist `num_class`, number of classes (for classification task)
-  - `XGBoostModel` now holds `BoosterParams`
-  - libxgboost4j is now part of CMake build
-  - Release `DMatrix` when no longer needed, to conserve memory
-  - Expose `baseMargin`, to allow initialization of boosting with predictions from an external model
-  - Support instance weights
-  - Use `SparkParallelismTracker` to prevent jobs from hanging forever
-  - Expose train-time evaluation metrics via `XGBoostModel.summary`
-  - Option to specify `host-ip` explicitly in the Rabit tracker
-* Documentation
-  - Better math notation for gradient boosting
-  - Updated build instructions for Mac OS X
-  - Template for GitHub issues
-  - Add `CITATION` file for citing XGBoost in scientific writing
-  - Fix dropdown menu in xgboost.readthedocs.io
-  - Document `updater_seq` parameter
-  - Style fixes for Python documentation
-  - Links to additional examples and tutorials
-  - Clarify installation requirements
-* Changes that break backward compatibility
-  - [#1519](https://github.com/dmlc/xgboost/pull/1519) XGBoost-spark no longer contains APIs for DMatrix; use the public booster interface instead.
-  - [#2476](https://github.com/dmlc/xgboost/pull/2476) `XGBoostModel.predict()` now has a different signature
-
-
-## v0.6 (2016.07.29)
-* Version 0.5 is skipped due to major improvements in the core
-* Major refactor of core library.
-  - Goal: more flexible and modular code as a portable library.
-  - Switch to use of c++11 standard code.
-  - Random number generator defaults to ```std::mt19937```.
-  - Share the data loading pipeline and logging module from dmlc-core.
-  - Enable registry pattern to allow optionally plugin of objective, metric, tree constructor, data loader.
-    - Future plugin modules can be put into xgboost/plugin and register back to the library.
-  - Remove most of the raw pointers to smart ptrs, for RAII safety.
-* Add official option to approximate algorithm `tree_method` to parameter.
-  - Change default behavior to switch to prefer faster algorithm.
-  - User will get a message when approximate algorithm is chosen.
-* Change library name to libxgboost.so
-* Backward compatiblity
-  - The binary buffer file is not backward compatible with previous version.
-  - The model file is backward compatible on 64 bit platforms.
-* The model file is compatible between 64/32 bit platforms(not yet tested).
-* External memory version and other advanced features will be exposed to R library as well on linux.
-  - Previously some of the features are blocked due to C++11 and threading limits.
-  - The windows version is still blocked due to Rtools do not support ```std::thread```.
-* rabit and dmlc-core are maintained through git submodule
-  - Anyone can open PR to update these dependencies now.
-* Improvements
-  - Rabit and xgboost libs are not thread-safe and use thread local PRNGs
-  - This could fix some of the previous problem which runs xgboost on multiple threads.
-* JVM Package
-  - Enable xgboost4j for java and scala
-  - XGBoost distributed now runs on Flink and Spark.
-* Support model attributes listing for meta data.
-  - https://github.com/dmlc/xgboost/pull/1198
-  - https://github.com/dmlc/xgboost/pull/1166
-* Support callback API
-  - https://github.com/dmlc/xgboost/issues/892
-  - https://github.com/dmlc/xgboost/pull/1211
-  - https://github.com/dmlc/xgboost/pull/1264
-* Support new booster DART(dropout in tree boosting)
-  - https://github.com/dmlc/xgboost/pull/1220
-* Add CMake build system
-  - https://github.com/dmlc/xgboost/pull/1314
-
-## v0.47 (2016.01.14)
-
-* Changes in R library
-  - fixed possible problem of poisson regression.
-  - switched from 0 to NA for missing values.
-  - exposed access to additional model parameters.
-* Changes in Python library
-  - throws exception instead of crash terminal when a parameter error happens.
-  - has importance plot and tree plot functions.
-  - accepts different learning rates for each boosting round.
-  - allows model training continuation from previously saved model.
-  - allows early stopping in CV.
-  - allows feval to return a list of tuples.
-  - allows eval_metric to handle additional format.
-  - improved compatibility in sklearn module.
-  - additional parameters added for sklearn wrapper.
-  - added pip installation functionality.
-  - supports more Pandas DataFrame dtypes.
-  - added best_ntree_limit attribute, in addition to best_score and best_iteration.
-* Java api is ready for use
-* Added more test cases and continuous integration to make each build more robust.
-
-## v0.4 (2015.05.11)
-
-* Distributed version of xgboost that runs on YARN, scales to billions of examples
-* Direct save/load data and model from/to S3 and HDFS
-* Feature importance visualization in R module, by Michael Benesty
-* Predict leaf index
-* Poisson regression for counts data
-* Early stopping option in training
-* Native save load support in R and python
-  - xgboost models now can be saved using save/load in R
-  - xgboost python model is now pickable
-* sklearn wrapper is supported in python module
-* Experimental External memory version
-
-
-## v0.3 (2014.09.07)
-
-* Faster tree construction module
-  - Allows subsample columns during tree construction via ```bst:col_samplebytree=ratio```
-* Support for boosting from initial predictions
-* Experimental version of LambdaRank
-* Linear booster is now parallelized, using parallel coordinated descent.
-* Add [Code Guide](src/README.md) for customizing objective function and evaluation
-* Add R module
-
-
-## v0.2x (2014.05.20)
-
-* Python module
-* Weighted samples instances
-* Initial version of pairwise rank
-
-
-## v0.1 (2014.03.26)
-
-* Initial release

R-package/.Rbuildignore

@@ -1,6 +0,0 @@
-\.o$
-\.so$
-\.dll$
-^.*\.Rproj$
-^\.Rproj\.user$
-README.md

R-package/CMakeLists.txt

@@ -1,34 +0,0 @@
-find_package(LibR REQUIRED)
-message(STATUS "LIBR_CORE_LIBRARY " ${LIBR_CORE_LIBRARY})
-
-file(GLOB_RECURSE R_SOURCES
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.cc
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
-# Use object library to expose symbols
-add_library(xgboost-r OBJECT ${R_SOURCES})
-
-set(R_DEFINITIONS
-  -DXGBOOST_STRICT_R_MODE=1
-  -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
-  -DDMLC_LOG_BEFORE_THROW=0
-  -DDMLC_DISABLE_STDIN=1
-  -DDMLC_LOG_CUSTOMIZE=1
-  -DRABIT_CUSTOMIZE_MSG_
-  -DRABIT_STRICT_CXX98_)
-target_compile_definitions(xgboost-r
-  PRIVATE ${R_DEFINITIONS})
-target_include_directories(xgboost-r
-  PRIVATE
-  ${LIBR_INCLUDE_DIRS}
-  ${PROJECT_SOURCE_DIR}/include
-  ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include)
-set_target_properties(
-  xgboost-r PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-
-set(XGBOOST_DEFINITIONS ${R_DEFINITIONS} PARENT_SCOPE)
-set(XGBOOST_OBJ_SOURCES $<TARGET_OBJECTS:xgboost-r> PARENT_SCOPE)
-set(LINKED_LIBRARIES_PRIVATE ${LINKED_LIBRARIES_PRIVATE} ${LIBR_CORE_LIBRARY} PARENT_SCOPE)

R-package/DESCRIPTION

@@ -1,65 +0,0 @@
-Package: xgboost
-Type: Package
-Title: Extreme Gradient Boosting
-Version: 0.82.0.1
-Date: 2019-03-11
-Authors@R: c(
-  person("Tianqi", "Chen", role = c("aut"),
-         email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut", "cre"),
-         email = "hetong007@gmail.com"),
-  person("Michael", "Benesty", role = c("aut"),
-         email = "michael@benesty.fr"),
-  person("Vadim", "Khotilovich", role = c("aut"),
-         email = "khotilovich@gmail.com"),
-  person("Yuan", "Tang", role = c("aut"),
-         email = "terrytangyuan@gmail.com",
-         comment = c(ORCID = "0000-0001-5243-233X")),
-  person("Hyunsu", "Cho", role = c("aut"),
-         email = "chohyu01@cs.washington.edu"),
-  person("Kailong", "Chen", role = c("aut")),
-  person("Rory", "Mitchell", role = c("aut")),
-  person("Ignacio", "Cano", role = c("aut")),
-  person("Tianyi", "Zhou", role = c("aut")),
-  person("Mu", "Li", role = c("aut")),
-  person("Junyuan", "Xie", role = c("aut")),
-  person("Min", "Lin", role = c("aut")),
-  person("Yifeng", "Geng", role = c("aut")),
-  person("Yutian", "Li", role = c("aut")),
-  person("XGBoost contributors", role = c("cph"),
-         comment = "base XGBoost implementation")
-  )
-Description: Extreme Gradient Boosting, which is an efficient implementation
-    of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
-    This package is its R interface. The package includes efficient linear 
-    model solver and tree learning algorithms. The package can automatically 
-    do parallel computation on a single machine which could be more than 10 
-    times faster than existing gradient boosting packages. It supports
-    various objective functions, including regression, classification and ranking.
-    The package is made to be extensible, so that users are also allowed to define
-    their own objectives easily.
-License: Apache License (== 2.0) | file LICENSE
-URL: https://github.com/dmlc/xgboost
-BugReports: https://github.com/dmlc/xgboost/issues
-NeedsCompilation: yes
-VignetteBuilder: knitr
-Suggests:
-    knitr,
-    rmarkdown,
-    ggplot2 (>= 1.0.1),
-    DiagrammeR (>= 0.9.0),
-    Ckmeans.1d.dp (>= 3.3.1),
-    vcd (>= 1.3),
-    testthat,
-    lintr,
-    igraph (>= 1.0.1)
-Depends:
-    R (>= 3.3.0)
-Imports:
-    Matrix (>= 1.1-0),
-    methods,
-    data.table (>= 1.9.6),
-    magrittr (>= 1.5),
-    stringi (>= 0.5.2)
-RoxygenNote: 6.1.0
-SystemRequirements: GNU make, C++11

R-package/LICENSE

@@ -1,13 +0,0 @@
-Copyright (c) 2014 by Tianqi Chen and Contributors 
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-    
-   http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.

R-package/NAMESPACE

@@ -1,86 +0,0 @@
-# Generated by roxygen2: do not edit by hand
-
-S3method("[",xgb.DMatrix)
-S3method("dimnames<-",xgb.DMatrix)
-S3method(dim,xgb.DMatrix)
-S3method(dimnames,xgb.DMatrix)
-S3method(getinfo,xgb.DMatrix)
-S3method(predict,xgb.Booster)
-S3method(predict,xgb.Booster.handle)
-S3method(print,xgb.Booster)
-S3method(print,xgb.DMatrix)
-S3method(print,xgb.cv.synchronous)
-S3method(setinfo,xgb.DMatrix)
-S3method(slice,xgb.DMatrix)
-export("xgb.attr<-")
-export("xgb.attributes<-")
-export("xgb.parameters<-")
-export(cb.cv.predict)
-export(cb.early.stop)
-export(cb.evaluation.log)
-export(cb.gblinear.history)
-export(cb.print.evaluation)
-export(cb.reset.parameters)
-export(cb.save.model)
-export(getinfo)
-export(setinfo)
-export(slice)
-export(xgb.Booster.complete)
-export(xgb.DMatrix)
-export(xgb.DMatrix.save)
-export(xgb.attr)
-export(xgb.attributes)
-export(xgb.create.features)
-export(xgb.cv)
-export(xgb.dump)
-export(xgb.gblinear.history)
-export(xgb.ggplot.deepness)
-export(xgb.ggplot.importance)
-export(xgb.importance)
-export(xgb.load)
-export(xgb.model.dt.tree)
-export(xgb.plot.deepness)
-export(xgb.plot.importance)
-export(xgb.plot.multi.trees)
-export(xgb.plot.shap)
-export(xgb.plot.tree)
-export(xgb.save)
-export(xgb.save.raw)
-export(xgb.train)
-export(xgboost)
-import(methods)
-importClassesFrom(Matrix,dgCMatrix)
-importClassesFrom(Matrix,dgeMatrix)
-importFrom(Matrix,colSums)
-importFrom(Matrix,sparse.model.matrix)
-importFrom(Matrix,sparseMatrix)
-importFrom(Matrix,sparseVector)
-importFrom(Matrix,t)
-importFrom(data.table,":=")
-importFrom(data.table,as.data.table)
-importFrom(data.table,data.table)
-importFrom(data.table,is.data.table)
-importFrom(data.table,rbindlist)
-importFrom(data.table,setkey)
-importFrom(data.table,setkeyv)
-importFrom(data.table,setnames)
-importFrom(grDevices,rgb)
-importFrom(graphics,barplot)
-importFrom(graphics,grid)
-importFrom(graphics,lines)
-importFrom(graphics,par)
-importFrom(graphics,points)
-importFrom(graphics,title)
-importFrom(magrittr,"%>%")
-importFrom(stats,median)
-importFrom(stats,predict)
-importFrom(stringi,stri_detect_regex)
-importFrom(stringi,stri_match_first_regex)
-importFrom(stringi,stri_replace_all_regex)
-importFrom(stringi,stri_replace_first_regex)
-importFrom(stringi,stri_split_regex)
-importFrom(utils,head)
-importFrom(utils,object.size)
-importFrom(utils,str)
-importFrom(utils,tail)
-useDynLib(xgboost, .registration = TRUE)

R-package/R/callbacks.R

@@ -1,831 +0,0 @@
-#' Callback closures for booster training.
-#'
-#' These are used to perform various service tasks either during boosting iterations or at the end.
-#' This approach helps to modularize many of such tasks without bloating the main training methods,
-#' and it offers .
-#'
-#' @details
-#' By default, a callback function is run after each boosting iteration.
-#' An R-attribute \code{is_pre_iteration} could be set for a callback to define a pre-iteration function.
-#'
-#' When a callback function has \code{finalize} parameter, its finalizer part will also be run after
-#' the boosting is completed.
-#'
-#' WARNING: side-effects!!! Be aware that these callback functions access and modify things in
-#' the environment from which they are called from, which is a fairly uncommon thing to do in R.
-#'
-#' To write a custom callback closure, make sure you first understand the main concepts about R environments.
-#' Check either R documentation on \code{\link[base]{environment}} or the
-#' \href{http://adv-r.had.co.nz/Environments.html}{Environments chapter} from the "Advanced R"
-#' book by Hadley Wickham. Further, the best option is to read the code of some of the existing callbacks -
-#' choose ones that do something similar to what you want to achieve. Also, you would need to get familiar
-#' with the objects available inside of the \code{xgb.train} and \code{xgb.cv} internal environments.
-#'
-#' @seealso
-#' \code{\link{cb.print.evaluation}},
-#' \code{\link{cb.evaluation.log}},
-#' \code{\link{cb.reset.parameters}},
-#' \code{\link{cb.early.stop}},
-#' \code{\link{cb.save.model}},
-#' \code{\link{cb.cv.predict}},
-#' \code{\link{xgb.train}},
-#' \code{\link{xgb.cv}}
-#'
-#' @name callbacks
-NULL
-
-#
-# Callbacks -------------------------------------------------------------------
-#
-
-#' Callback closure for printing the result of evaluation
-#'
-#' @param period  results would be printed every number of periods
-#' @param showsd  whether standard deviations should be printed (when available)
-#'
-#' @details
-#' The callback function prints the result of evaluation at every \code{period} iterations.
-#' The initial and the last iteration's evaluations are always printed.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst_evaluation} (also \code{bst_evaluation_err} when available),
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.print.evaluation <- function(period = 1, showsd = TRUE) {
-
-  callback <- function(env = parent.frame()) {
-    if (length(env$bst_evaluation) == 0 ||
-        period == 0 ||
-        NVL(env$rank, 0) != 0 )
-      return()
-
-    i <- env$iteration
-    if ((i-1) %% period == 0 ||
-        i == env$begin_iteration ||
-        i == env$end_iteration) {
-      stdev <- if (showsd) env$bst_evaluation_err else NULL
-      msg <- format.eval.string(i, env$bst_evaluation, stdev)
-      cat(msg, '\n')
-    }
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.print.evaluation'
-  callback
-}
-
-
-#' Callback closure for logging the evaluation history
-#'
-#' @details
-#' This callback function appends the current iteration evaluation results \code{bst_evaluation}
-#' available in the calling parent frame to the \code{evaluation_log} list in a calling frame.
-#'
-#' The finalizer callback (called with \code{finalize = TURE} in the end) converts
-#' the \code{evaluation_log} list into a final data.table.
-#'
-#' The iteration evaluation result \code{bst_evaluation} must be a named numeric vector.
-#'
-#' Note: in the column names of the final data.table, the dash '-' character is replaced with
-#' the underscore '_' in order to make the column names more like regular R identifiers.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{evaluation_log},
-#' \code{bst_evaluation},
-#' \code{iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.evaluation.log <- function() {
-
-  mnames <- NULL
-
-  init <- function(env) {
-    if (!is.list(env$evaluation_log))
-      stop("'evaluation_log' has to be a list")
-    mnames <<- names(env$bst_evaluation)
-    if (is.null(mnames) || any(mnames == ""))
-      stop("bst_evaluation must have non-empty names")
-
-    mnames <<- gsub('-', '_', names(env$bst_evaluation))
-    if(!is.null(env$bst_evaluation_err))
-      mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
-  }
-
-  finalizer <- function(env) {
-    env$evaluation_log <- as.data.table(t(simplify2array(env$evaluation_log)))
-    setnames(env$evaluation_log, c('iter', mnames))
-
-    if(!is.null(env$bst_evaluation_err)) {
-      # rearrange col order from _mean,_mean,...,_std,_std,...
-      # to be _mean,_std,_mean,_std,...
-      len <- length(mnames)
-      means <- mnames[seq_len(len/2)]
-      stds <- mnames[(len/2 + 1):len]
-      cnames <- numeric(len)
-      cnames[c(TRUE, FALSE)] <- means
-      cnames[c(FALSE, TRUE)] <- stds
-      env$evaluation_log <- env$evaluation_log[, c('iter', cnames), with = FALSE]
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (is.null(mnames))
-      init(env)
-
-    if (finalize)
-      return(finalizer(env))
-
-    ev <- env$bst_evaluation
-    if(!is.null(env$bst_evaluation_err))
-      ev <- c(ev, env$bst_evaluation_err)
-    env$evaluation_log <- c(env$evaluation_log,
-                            list(c(iter = env$iteration, ev)))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.evaluation.log'
-  callback
-}
-
-#' Callback closure for resetting the booster's parameters at each iteration.
-#'
-#' @param new_params a list where each element corresponds to a parameter that needs to be reset.
-#'        Each element's value must be either a vector of values of length \code{nrounds}
-#'        to be set at each iteration,
-#'        or a function of two parameters \code{learning_rates(iteration, nrounds)}
-#'        which returns a new parameter value by using the current iteration number
-#'        and the total number of boosting rounds.
-#'
-#' @details
-#' This is a "pre-iteration" callback function used to reset booster's parameters
-#' at the beginning of each iteration.
-#'
-#' Note that when training is resumed from some previous model, and a function is used to
-#' reset a parameter value, the \code{nrounds} argument in this function would be the
-#' the number of boosting rounds in the current training.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst} or \code{bst_folds},
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.reset.parameters <- function(new_params) {
-
-  if (typeof(new_params) != "list")
-    stop("'new_params' must be a list")
-  pnames <- gsub("\\.", "_", names(new_params))
-  nrounds <- NULL
-
-  # run some checks in the begining
-  init <- function(env) {
-    nrounds <<- env$end_iteration - env$begin_iteration + 1
-
-    if (is.null(env$bst) && is.null(env$bst_folds))
-      stop("Parent frame has neither 'bst' nor 'bst_folds'")
-
-    # Some parameters are not allowed to be changed,
-    # since changing them would simply wreck some chaos
-    not_allowed <- pnames %in%
-      c('num_class', 'num_output_group', 'size_leaf_vector', 'updater_seq')
-    if (any(not_allowed))
-      stop('Parameters ', paste(pnames[not_allowed]), " cannot be changed during boosting.")
-
-    for (n in pnames) {
-      p <- new_params[[n]]
-      if (is.function(p)) {
-        if (length(formals(p)) != 2)
-          stop("Parameter '", n, "' is a function but not of two arguments")
-      } else if (is.numeric(p) || is.character(p)) {
-        if (length(p) != nrounds)
-          stop("Length of '", n, "' has to be equal to 'nrounds'")
-      } else {
-        stop("Parameter '", n, "' is not a function or a vector")
-      }
-    }
-  }
-
-  callback <- function(env = parent.frame()) {
-    if (is.null(nrounds))
-      init(env)
-
-    i <- env$iteration
-    pars <- lapply(new_params, function(p) {
-      if (is.function(p))
-        return(p(i, nrounds))
-      p[i]
-    })
-
-    if (!is.null(env$bst)) {
-      xgb.parameters(env$bst$handle) <- pars
-    } else {
-      for (fd in env$bst_folds)
-        xgb.parameters(fd$bst) <- pars
-    }
-  }
-  attr(callback, 'is_pre_iteration') <- TRUE
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.reset.parameters'
-  callback
-}
-
-
-#' Callback closure to activate the early stopping.
-#'
-#' @param stopping_rounds The number of rounds with no improvement in
-#'        the evaluation metric in order to stop the training.
-#' @param maximize whether to maximize the evaluation metric
-#' @param metric_name the name of an evaluation column to use as a criteria for early
-#'        stopping. If not set, the last column would be used.
-#'        Let's say the test data in \code{watchlist} was labelled as \code{dtest},
-#'        and one wants to use the AUC in test data for early stopping regardless of where
-#'        it is in the \code{watchlist}, then one of the following would need to be set:
-#'        \code{metric_name='dtest-auc'} or \code{metric_name='dtest_auc'}.
-#'        All dash '-' characters in metric names are considered equivalent to '_'.
-#' @param verbose whether to print the early stopping information.
-#'
-#' @details
-#' This callback function determines the condition for early stopping
-#' by setting the \code{stop_condition = TRUE} flag in its calling frame.
-#'
-#' The following additional fields are assigned to the model's R object:
-#' \itemize{
-#' \item \code{best_score} the evaluation score at the best iteration
-#' \item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
-#' \item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
-#'      It differs from \code{best_iteration} in multiclass or random forest settings.
-#' }
-#'
-#' The Same values are also stored as xgb-attributes:
-#' \itemize{
-#' \item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)
-#' \item \code{best_msg} message string is also stored.
-#' }
-#'
-#' At least one data element is required in the evaluation watchlist for early stopping to work.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{stop_condition},
-#' \code{bst_evaluation},
-#' \code{rank},
-#' \code{bst} (or \code{bst_folds} and \code{basket}),
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration},
-#' \code{num_parallel_tree}.
-#'
-#' @seealso
-#' \code{\link{callbacks}},
-#' \code{\link{xgb.attr}}
-#'
-#' @export
-cb.early.stop <- function(stopping_rounds, maximize = FALSE,
-                          metric_name = NULL, verbose = TRUE) {
-  # state variables
-  best_iteration <- -1
-  best_ntreelimit <- -1
-  best_score <- Inf
-  best_msg <- NULL
-  metric_idx <- 1
-
-  init <- function(env) {
-    if (length(env$bst_evaluation) == 0)
-      stop("For early stopping, watchlist must have at least one element")
-
-    eval_names <- gsub('-', '_', names(env$bst_evaluation))
-    if (!is.null(metric_name)) {
-      metric_idx <<- which(gsub('-', '_', metric_name) == eval_names)
-      if (length(metric_idx) == 0)
-        stop("'metric_name' for early stopping is not one of the following:\n",
-             paste(eval_names, collapse = ' '), '\n')
-    }
-    if (is.null(metric_name) &&
-        length(env$bst_evaluation) > 1) {
-      metric_idx <<- length(eval_names)
-      if (verbose)
-        cat('Multiple eval metrics are present. Will use ',
-            eval_names[metric_idx], ' for early stopping.\n', sep = '')
-    }
-
-    metric_name <<- eval_names[metric_idx]
-
-    # maximize is usually NULL when not set in xgb.train and built-in metrics
-    if (is.null(maximize))
-      maximize <<- grepl('(_auc|_map|_ndcg)', metric_name)
-
-    if (verbose && NVL(env$rank, 0) == 0)
-      cat("Will train until ", metric_name, " hasn't improved in ",
-          stopping_rounds, " rounds.\n\n", sep = '')
-
-    best_iteration <<- 1
-    if (maximize) best_score <<- -Inf
-
-    env$stop_condition <- FALSE
-
-    if (!is.null(env$bst)) {
-      if (!inherits(env$bst, 'xgb.Booster'))
-        stop("'bst' in the parent frame must be an 'xgb.Booster'")
-      if (!is.null(best_score <- xgb.attr(env$bst$handle, 'best_score'))) {
-        best_score <<- as.numeric(best_score)
-        best_iteration <<- as.numeric(xgb.attr(env$bst$handle, 'best_iteration')) + 1
-        best_msg <<- as.numeric(xgb.attr(env$bst$handle, 'best_msg'))
-      } else {
-        xgb.attributes(env$bst$handle) <- list(best_iteration = best_iteration - 1,
-                                               best_score = best_score)
-      }
-    } else if (is.null(env$bst_folds) || is.null(env$basket)) {
-      stop("Parent frame has neither 'bst' nor ('bst_folds' and 'basket')")
-    }
-  }
-
-  finalizer <- function(env) {
-    if (!is.null(env$bst)) {
-      attr_best_score = as.numeric(xgb.attr(env$bst$handle, 'best_score'))
-      if (best_score != attr_best_score)
-        stop("Inconsistent 'best_score' values between the closure state: ", best_score,
-             " and the xgb.attr: ", attr_best_score)
-      env$bst$best_iteration = best_iteration
-      env$bst$best_ntreelimit = best_ntreelimit
-      env$bst$best_score = best_score
-    } else {
-      env$basket$best_iteration <- best_iteration
-      env$basket$best_ntreelimit <- best_ntreelimit
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (best_iteration < 0)
-      init(env)
-
-    if (finalize)
-      return(finalizer(env))
-
-    i <- env$iteration
-    score = env$bst_evaluation[metric_idx]
-
-    if (( maximize && score > best_score) ||
-        (!maximize && score < best_score)) {
-
-      best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
-      best_score <<- score
-      best_iteration <<- i
-      best_ntreelimit <<- best_iteration * env$num_parallel_tree
-      # save the property to attributes, so they will occur in checkpoint
-      if (!is.null(env$bst)) {
-        xgb.attributes(env$bst) <- list(
-          best_iteration = best_iteration - 1, # convert to 0-based index
-          best_score = best_score,
-          best_msg = best_msg,
-          best_ntreelimit = best_ntreelimit)
-      }
-    } else if (i - best_iteration >= stopping_rounds) {
-      env$stop_condition <- TRUE
-      env$end_iteration <- i
-      if (verbose && NVL(env$rank, 0) == 0)
-        cat("Stopping. Best iteration:\n", best_msg, "\n\n", sep = '')
-    }
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.early.stop'
-  callback
-}
-
-
-#' Callback closure for saving a model file.
-#'
-#' @param save_period save the model to disk after every
-#'        \code{save_period} iterations; 0 means save the model at the end.
-#' @param save_name the name or path for the saved model file.
-#'        It can contain a \code{\link[base]{sprintf}} formatting specifier
-#'        to include the integer iteration number in the file name.
-#'        E.g., with \code{save_name} = 'xgboost_%04d.model',
-#'        the file saved at iteration 50 would be named "xgboost_0050.model".
-#'
-#' @details
-#' This callback function allows to save an xgb-model file, either periodically after each \code{save_period}'s or at the end.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst},
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.save.model <- function(save_period = 0, save_name = "xgboost.model") {
-
-  if (save_period < 0)
-    stop("'save_period' cannot be negative")
-
-  callback <- function(env = parent.frame()) {
-    if (is.null(env$bst))
-      stop("'save_model' callback requires the 'bst' booster object in its calling frame")
-
-    if ((save_period > 0 && (env$iteration - env$begin_iteration) %% save_period == 0) ||
-        (save_period == 0 && env$iteration == env$end_iteration))
-      xgb.save(env$bst, sprintf(save_name, env$iteration))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.save.model'
-  callback
-}
-
-
-#' Callback closure for returning cross-validation based predictions.
-#'
-#' @param save_models a flag for whether to save the folds' models.
-#'
-#' @details
-#' This callback function saves predictions for all of the test folds,
-#' and also allows to save the folds' models.
-#'
-#' It is a "finalizer" callback and it uses early stopping information whenever it is available,
-#' thus it must be run after the early stopping callback if the early stopping is used.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst_folds},
-#' \code{basket},
-#' \code{data},
-#' \code{end_iteration},
-#' \code{params},
-#' \code{num_parallel_tree},
-#' \code{num_class}.
-#'
-#' @return
-#' Predictions are returned inside of the \code{pred} element, which is either a vector or a matrix,
-#' depending on the number of prediction outputs per data row. The order of predictions corresponds
-#' to the order of rows in the original dataset. Note that when a custom \code{folds} list is
-#' provided in \code{xgb.cv}, the predictions would only be returned properly when this list is a
-#' non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be
-#' meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
-#' When some of the indices in the training dataset are not included into user-provided \code{folds},
-#' their prediction value would be \code{NA}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.cv.predict <- function(save_models = FALSE) {
-
-  finalizer <- function(env) {
-    if (is.null(env$basket) || is.null(env$bst_folds))
-      stop("'cb.cv.predict' callback requires 'basket' and 'bst_folds' lists in its calling frame")
-
-    N <- nrow(env$data)
-    pred <-
-      if (env$num_class > 1) {
-        matrix(NA_real_, N, env$num_class)
-      } else {
-        rep(NA_real_, N)
-      }
-
-    ntreelimit <- NVL(env$basket$best_ntreelimit,
-                      env$end_iteration * env$num_parallel_tree)
-    if (NVL(env$params[['booster']], '') == 'gblinear') {
-      ntreelimit <- 0 # must be 0 for gblinear
-    }
-    for (fd in env$bst_folds) {
-      pr <- predict(fd$bst, fd$watchlist[[2]], ntreelimit = ntreelimit, reshape = TRUE)
-      if (is.matrix(pred)) {
-        pred[fd$index,] <- pr
-      } else {
-        pred[fd$index] <- pr
-      }
-    }
-    env$basket$pred <- pred
-    if (save_models) {
-      env$basket$models <- lapply(env$bst_folds, function(fd) {
-        xgb.attr(fd$bst, 'niter') <- env$end_iteration - 1
-        xgb.Booster.complete(xgb.handleToBooster(fd$bst), saveraw = TRUE)
-      })
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (finalize)
-      return(finalizer(env))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.cv.predict'
-  callback
-}
-
-
-#' Callback closure for collecting the model coefficients history of a gblinear booster
-#' during its training.
-#'
-#' @param sparse when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
-#'       Sparse format is useful when one expects only a subset of coefficients to be non-zero,
-#'       when using the "thrifty" feature selector with fairly small number of top features
-#'       selected per iteration.
-#'
-#' @details
-#' To keep things fast and simple, gblinear booster does not internally store the history of linear
-#' model coefficients at each boosting iteration. This callback provides a workaround for storing
-#' the coefficients' path, by extracting them after each training iteration.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst} (or \code{bst_folds}).
-#'
-#' @return
-#' Results are stored in the \code{coefs} element of the closure.
-#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
-#' With \code{xgb.train}, it is either a dense of a sparse matrix.
-#' While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
-#'
-#' @seealso
-#' \code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
-#'
-#' @examples
-#' #### Binary classification:
-#' #
-#' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
-#' # without considering the 2nd order interactions:
-#' require(magrittr)
-#' x <- model.matrix(Species ~ .^2, iris)[,-1]
-#' colnames(x)
-#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
-#' param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
-#' # For 'shotgun', which is a default linear updater, using high eta values may result in
-#' # unstable behaviour in some datasets. With this simple dataset, however, the high learning
-#' # rate does not break the convergence, but allows us to illustrate the typical pattern of
-#' # "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
-#'                  callbacks = list(cb.gblinear.history()))
-#' # Extract the coefficients' path and plot them vs boosting iteration number:
-#' coef_path <- xgb.gblinear.history(bst)
-#' matplot(coef_path, type = 'l')
-#'
-#' # With the deterministic coordinate descent updater, it is safer to use higher learning rates.
-#' # Will try the classical componentwise boosting which selects a single best feature per round:
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
-#'                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
-#'                  callbacks = list(cb.gblinear.history()))
-#' xgb.gblinear.history(bst) %>% matplot(type = 'l')
-#' #  Componentwise boosting is known to have similar effect to Lasso regularization.
-#' # Try experimenting with various values of top_k, eta, nrounds,
-#' # as well as different feature_selectors.
-#'
-#' # For xgb.cv:
-#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-#'              callbacks = list(cb.gblinear.history()))
-#' # coefficients in the CV fold #3
-#' xgb.gblinear.history(bst)[[3]] %>% matplot(type = 'l')
-#'
-#'
-#' #### Multiclass classification:
-#' #
-#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
-#' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
-#' # For the default linear updater 'shotgun' it sometimes is helpful
-#' # to use smaller eta to reduce instability
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
-#'                  callbacks = list(cb.gblinear.history()))
-#' # Will plot the coefficient paths separately for each class:
-#' xgb.gblinear.history(bst, class_index = 0) %>% matplot(type = 'l')
-#' xgb.gblinear.history(bst, class_index = 1) %>% matplot(type = 'l')
-#' xgb.gblinear.history(bst, class_index = 2) %>% matplot(type = 'l')
-#'
-#' # CV:
-#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-#'               callbacks = list(cb.gblinear.history(FALSE)))
-#' # 1st forld of 1st class
-#' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l')
-#'
-#' @export
-cb.gblinear.history <- function(sparse=FALSE) {
-  coefs <- NULL
-
-  init <- function(env) {
-    if (!is.null(env$bst)) { # xgb.train:
-      coef_path <- list()
-    } else if (!is.null(env$bst_folds)) { # xgb.cv:
-      coef_path <- rep(list(), length(env$bst_folds))
-    } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
-  }
-
-  # convert from list to (sparse) matrix
-  list2mat <- function(coef_list) {
-    if (sparse) {
-      coef_mat <- sparseMatrix(x = unlist(lapply(coef_list, slot, "x")),
-                               i = unlist(lapply(coef_list, slot, "i")),
-                               p = c(0, cumsum(sapply(coef_list, function(x) length(x@x)))),
-                               dims = c(length(coef_list[[1]]), length(coef_list)))
-      return(t(coef_mat))
-    } else {
-      return(do.call(rbind, coef_list))
-    }
-  }
-
-  finalizer <- function(env) {
-    if (length(coefs) == 0)
-      return()
-    if (!is.null(env$bst)) { # # xgb.train:
-      coefs <<- list2mat(coefs)
-    } else { # xgb.cv:
-      # first lapply transposes the list
-      coefs <<- lapply(seq_along(coefs[[1]]), function(i) lapply(coefs, "[[", i)) %>%
-                lapply(function(x) list2mat(x))
-    }
-  }
-
-  extract.coef <- function(env) {
-    if (!is.null(env$bst)) { # # xgb.train:
-      cf <- as.numeric(grep('(booster|bias|weigh)', xgb.dump(env$bst), invert = TRUE, value = TRUE))
-      if (sparse) cf <- as(cf, "sparseVector")
-    } else { # xgb.cv:
-      cf <- vector("list", length(env$bst_folds))
-      for (i in seq_along(env$bst_folds)) {
-        dmp <- xgb.dump(xgb.handleToBooster(env$bst_folds[[i]]$bst))
-        cf[[i]] <- as.numeric(grep('(booster|bias|weigh)', dmp, invert = TRUE, value = TRUE))
-        if (sparse) cf[[i]] <- as(cf[[i]], "sparseVector")
-      }
-    }
-    cf
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (is.null(coefs)) init(env)
-    if (finalize) return(finalizer(env))
-    cf <- extract.coef(env)
-    coefs <<- c(coefs, list(cf))
-  }
-
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.gblinear.history'
-  callback
-}
-
-#' Extract gblinear coefficients history.
-#'
-#' A helper function to extract the matrix of linear coefficients' history
-#' from a gblinear model created while using the \code{cb.gblinear.history()}
-#' callback.
-#'
-#' @param model either an \code{xgb.Booster} or a result of \code{xgb.cv()}, trained
-#'        using the \code{cb.gblinear.history()} callback.
-#' @param class_index zero-based class index to extract the coefficients for only that
-#'        specific class in a multinomial multiclass model. When it is NULL, all the
-#'        coefficients are returned. Has no effect in non-multiclass models.
-#'
-#' @return
-#' For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns
-#' corresponding to iteration's coefficients (in the order as \code{xgb.dump()} would
-#' return) and the rows corresponding to boosting iterations.
-#'
-#' For an \code{xgb.cv} result, a list of such matrices is returned with the elements
-#' corresponding to CV folds.
-#'
-#' @export
-xgb.gblinear.history <- function(model, class_index = NULL) {
-
-  if (!(inherits(model, "xgb.Booster") ||
-        inherits(model, "xgb.cv.synchronous")))
-    stop("model must be an object of either xgb.Booster or xgb.cv.synchronous class")
-  is_cv <- inherits(model, "xgb.cv.synchronous")
-
-  if (is.null(model[["callbacks"]]) || is.null(model$callbacks[["cb.gblinear.history"]]))
-    stop("model must be trained while using the cb.gblinear.history() callback")
-
-  if (!is_cv) {
-    # extract num_class & num_feat from the internal model
-    dmp <- xgb.dump(model)
-    if(length(dmp) < 2 || dmp[2] != "bias:")
-      stop("It does not appear to be a gblinear model")
-    dmp <- dmp[-c(1,2)]
-    n <- which(dmp == 'weight:')
-    if(length(n) != 1)
-      stop("It does not appear to be a gblinear model")
-    num_class <- n - 1
-    num_feat <- (length(dmp) - 4) / num_class
-  } else {
-    # in case of CV, the object is expected to have this info
-    if (model$params$booster != "gblinear")
-      stop("It does not appear to be a gblinear model")
-    num_class <- NVL(model$params$num_class, 1)
-    num_feat <- model$nfeatures
-    if (is.null(num_feat))
-      stop("This xgb.cv result does not have nfeatures info")
-  }
-
-  if (!is.null(class_index) &&
-      num_class > 1 &&
-      (class_index[1] < 0 || class_index[1] >= num_class))
-    stop("class_index has to be within [0,", num_class - 1, "]")
-
-  coef_path <- environment(model$callbacks$cb.gblinear.history)[["coefs"]]
-  if (!is.null(class_index) && num_class > 1) {
-    coef_path <- if (is.list(coef_path)) {
-      lapply(coef_path,
-             function(x) x[, seq(1 + class_index, by=num_class, length.out=num_feat)])
-    } else {
-      coef_path <- coef_path[, seq(1 + class_index, by=num_class, length.out=num_feat)]
-    }
-  }
-  coef_path
-}
-
-
-#
-# Internal utility functions for callbacks ------------------------------------
-#
-
-# Format the evaluation metric string
-format.eval.string <- function(iter, eval_res, eval_err = NULL) {
-  if (length(eval_res) == 0)
-    stop('no evaluation results')
-  enames <- names(eval_res)
-  if (is.null(enames))
-    stop('evaluation results must have names')
-  iter <- sprintf('[%d]\t', iter)
-  if (!is.null(eval_err)) {
-    if (length(eval_res) != length(eval_err))
-      stop('eval_res & eval_err lengths mismatch')
-    res <- paste0(sprintf("%s:%f+%f", enames, eval_res, eval_err), collapse = '\t')
-  } else {
-    res <- paste0(sprintf("%s:%f", enames, eval_res), collapse = '\t')
-  }
-  return(paste0(iter, res))
-}
-
-# Extract callback names from the list of callbacks
-callback.names <- function(cb_list) {
-  unlist(lapply(cb_list, function(x) attr(x, 'name')))
-}
-
-# Extract callback calls from the list of callbacks
-callback.calls <- function(cb_list) {
-  unlist(lapply(cb_list, function(x) attr(x, 'call')))
-}
-
-# Add a callback cb to the list and make sure that
-# cb.early.stop and cb.cv.predict are at the end of the list
-# with cb.cv.predict being the last (when present)
-add.cb <- function(cb_list, cb) {
-  cb_list <- c(cb_list, cb)
-  names(cb_list) <- callback.names(cb_list)
-  if ('cb.early.stop' %in% names(cb_list)) {
-    cb_list <- c(cb_list, cb_list['cb.early.stop'])
-    # this removes only the first one
-    cb_list['cb.early.stop'] <- NULL
-  }
-  if ('cb.cv.predict' %in% names(cb_list)) {
-    cb_list <- c(cb_list, cb_list['cb.cv.predict'])
-    cb_list['cb.cv.predict'] <- NULL
-  }
-  cb_list
-}
-
-# Sort callbacks list into categories
-categorize.callbacks <- function(cb_list) {
-  list(
-    pre_iter = Filter(function(x) {
-        pre <- attr(x, 'is_pre_iteration')
-        !is.null(pre) && pre
-      }, cb_list),
-    post_iter = Filter(function(x) {
-        pre <- attr(x, 'is_pre_iteration')
-        is.null(pre) || !pre
-      }, cb_list),
-    finalize = Filter(function(x) {
-        'finalize' %in% names(formals(x))
-      }, cb_list)
-  )
-}
-
-# Check whether all callback functions with names given by 'query_names' are present in the 'cb_list'.
-has.callbacks <- function(cb_list, query_names) {
-  if (length(cb_list) < length(query_names))
-    return(FALSE)
-  if (!is.list(cb_list) ||
-      any(sapply(cb_list, class) != 'function')) {
-    stop('`cb_list` must be a list of callback functions')
-  }
-  cb_names <- callback.names(cb_list)
-  if (!is.character(cb_names) ||
-      length(cb_names) != length(cb_list) ||
-      any(cb_names == "")) {
-    stop('All callbacks in the `cb_list` must have a non-empty `name` attribute')
-  }
-  if (!is.character(query_names) ||
-      length(query_names) == 0 ||
-      any(query_names == "")) {
-    stop('query_names must be a non-empty vector of non-empty character names')
-  }
-  return(all(query_names %in% cb_names))
-}

R-package/R/utils.R

@@ -1,352 +0,0 @@
-#
-# This file is for the low level reuseable utility functions
-# that are not supposed to be visibe to a user.
-#
-
-#
-# General helper utilities ----------------------------------------------------
-#
-
-# SQL-style NVL shortcut.
-NVL <- function(x, val) {
-  if (is.null(x))
-    return(val)
-  if (is.vector(x)) {
-    x[is.na(x)] <- val
-    return(x)
-  }
-  if (typeof(x) == 'closure')
-    return(x)
-  stop("typeof(x) == ", typeof(x), " is not supported by NVL")
-}
-
-
-#
-# Low-level functions for boosting --------------------------------------------
-#
-
-# Merges booster params with whatever is provided in ...
-# plus runs some checks
-check.booster.params <- function(params, ...) {
-  if (typeof(params) != "list")
-    stop("params must be a list")
-
-  # in R interface, allow for '.' instead of '_' in parameter names
-  names(params) <- gsub("\\.", "_", names(params))
-
-  # merge parameters from the params and the dots-expansion
-  dot_params <- list(...)
-  names(dot_params) <- gsub("\\.", "_", names(dot_params))
-  if (length(intersect(names(params),
-                       names(dot_params))) > 0)
-    stop("Same parameters in 'params' and in the call are not allowed. Please check your 'params' list.")
-  params <- c(params, dot_params)
-
-  # providing a parameter multiple times makes sense only for 'eval_metric'
-  name_freqs <- table(names(params))
-  multi_names <- setdiff(names(name_freqs[name_freqs > 1]), 'eval_metric')
-  if (length(multi_names) > 0) {
-    warning("The following parameters were provided multiple times:\n\t",
-            paste(multi_names, collapse = ', '), "\n  Only the last value for each of them will be used.\n")
-    # While xgboost internals would choose the last value for a multiple-times parameter,
-    # enforce it here in R as well (b/c multi-parameters might be used further in R code,
-    # and R takes the 1st value when multiple elements with the same name are present in a list).
-    for (n in multi_names) {
-      del_idx <- which(n == names(params))
-      del_idx <- del_idx[-length(del_idx)]
-      params[[del_idx]] <- NULL
-    }
-  }
-
-  # for multiclass, expect num_class to be set
-  if (typeof(params[['objective']]) == "character" &&
-      substr(NVL(params[['objective']], 'x'), 1, 6) == 'multi:' &&
-      as.numeric(NVL(params[['num_class']], 0)) < 2) {
-        stop("'num_class' > 1 parameter must be set for multiclass classification")
-  }
-
-  # monotone_constraints parser
-
-  if (!is.null(params[['monotone_constraints']]) &&
-      typeof(params[['monotone_constraints']]) != "character") {
-        vec2str = paste(params[['monotone_constraints']], collapse = ',')
-        vec2str = paste0('(', vec2str, ')')
-        params[['monotone_constraints']] = vec2str
-  }
-
-  # interaction constraints parser (convert from list of column indices to string)
-  if (!is.null(params[['interaction_constraints']]) &&
-      typeof(params[['interaction_constraints']]) != "character"){
-    # check input class
-    if (class(params[['interaction_constraints']]) != 'list') stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric','integer'))) {
-      stop('interaction_constraints should be a list of numeric/integer vectors')
-    }
-
-    # recast parameter as string
-    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse=','), ']'))
-    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse=','), ']')
-  }
-  return(params)
-}
-
-
-# Performs some checks related to custom objective function.
-# WARNING: has side-effects and can modify 'params' and 'obj' in its calling frame
-check.custom.obj <- function(env = parent.frame()) {
-  if (!is.null(env$params[['objective']]) && !is.null(env$obj))
-    stop("Setting objectives in 'params' and 'obj' at the same time is not allowed")
-
-  if (!is.null(env$obj) && typeof(env$obj) != 'closure')
-    stop("'obj' must be a function")
-
-  # handle the case when custom objective function was provided through params
-  if (!is.null(env$params[['objective']]) &&
-      typeof(env$params$objective) == 'closure') {
-    env$obj <- env$params$objective
-    env$params$objective <- NULL
-  }
-}
-
-# Performs some checks related to custom evaluation function.
-# WARNING: has side-effects and can modify 'params' and 'feval' in its calling frame
-check.custom.eval <- function(env = parent.frame()) {
-  if (!is.null(env$params[['eval_metric']]) && !is.null(env$feval))
-    stop("Setting evaluation metrics in 'params' and 'feval' at the same time is not allowed")
-
-  if (!is.null(env$feval) && typeof(env$feval) != 'closure')
-    stop("'feval' must be a function")
-
-  # handle a situation when custom eval function was provided through params
-  if (!is.null(env$params[['eval_metric']]) &&
-      typeof(env$params$eval_metric) == 'closure') {
-    env$feval <- env$params$eval_metric
-    env$params$eval_metric <- NULL
-  }
-
-  # require maximize to be set when custom feval and early stopping are used together
-  if (!is.null(env$feval) &&
-      is.null(env$maximize) && (
-        !is.null(env$early_stopping_rounds) ||
-        has.callbacks(env$callbacks, 'cb.early.stop')))
-    stop("Please set 'maximize' to indicate whether the evaluation metric needs to be maximized or not")
-}
-
-
-# Update a booster handle for an iteration with dtrain data
-xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
-  if (!identical(class(booster_handle), "xgb.Booster.handle")) {
-    stop("booster_handle must be of xgb.Booster.handle class")
-  }
-  if (!inherits(dtrain, "xgb.DMatrix")) {
-    stop("dtrain must be of xgb.DMatrix class")
-  }
-
-  if (is.null(obj)) {
-    .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
-  } else {
-    pred <- predict(booster_handle, dtrain)
-    gpair <- obj(pred, dtrain)
-    .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
-  }
-  return(TRUE)
-}
-
-
-# Evaluate one iteration.
-# Returns a named vector of evaluation metrics
-# with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
-  if (!identical(class(booster_handle), "xgb.Booster.handle"))
-    stop("class of booster_handle must be xgb.Booster.handle")
-
-  if (length(watchlist) == 0)
-    return(NULL)
-
-  evnames <- names(watchlist)
-  if (is.null(feval)) {
-    msg <- .Call(XGBoosterEvalOneIter_R, booster_handle, as.integer(iter), watchlist, as.list(evnames))
-    msg <- stri_split_regex(msg, '(\\s+|:|\\s+)')[[1]][-1]
-    res <- as.numeric(msg[c(FALSE,TRUE)]) # even indices are the values
-    names(res) <- msg[c(TRUE,FALSE)]      # odds are the names
-  } else {
-    res <- sapply(seq_along(watchlist), function(j) {
-      w <- watchlist[[j]]
-      preds <- predict(booster_handle, w) # predict using all trees
-      eval_res <- feval(preds, w)
-      out <- eval_res$value
-      names(out) <- paste0(evnames[j], "-", eval_res$metric)
-      out
-    })
-  }
-  return(res)
-}
-
-
-#
-# Helper functions for cross validation ---------------------------------------
-#
-
-# Generates random (stratified if needed) CV folds
-generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
-
-  # cannot do it for rank
-  if (exists('objective', where = params) &&
-      is.character(params$objective) &&
-      strtrim(params$objective, 5) == 'rank:') {
-    stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
-         "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
-  }
-  # shuffle
-  rnd_idx <- sample.int(nrows)
-  if (stratified &&
-      length(label) == length(rnd_idx)) {
-    y <- label[rnd_idx]
-    # WARNING: some heuristic logic is employed to identify classification setting!
-    #  - For classification, need to convert y labels to factor before making the folds,
-    #    and then do stratification by factor levels.
-    #  - For regression, leave y numeric and do stratification by quantiles.
-    if (exists('objective', where = params) &&
-        is.character(params$objective)) {
-      # If 'objective' provided in params, assume that y is a classification label
-      # unless objective is reg:squarederror
-      if (params$objective != 'reg:squarederror')
-        y <- factor(y)
-    } else {
-      # If no 'objective' given in params, it means that user either wants to
-      # use the default 'reg:squarederror' objective or has provided a custom
-      # obj function.  Here, assume classification setting when y has 5 or less
-      # unique values:
-      if (length(unique(y)) <= 5)
-        y <- factor(y)
-    }
-    folds <- xgb.createFolds(y, nfold)
-  } else {
-    # make simple non-stratified folds
-    kstep <- length(rnd_idx) %/% nfold
-    folds <- list()
-    for (i in seq_len(nfold - 1)) {
-      folds[[i]] <- rnd_idx[seq_len(kstep)]
-      rnd_idx <- rnd_idx[-seq_len(kstep)]
-    }
-    folds[[nfold]] <- rnd_idx
-  }
-  return(folds)
-}
-
-# Creates CV folds stratified by the values of y.
-# It was borrowed from caret::createFolds and simplified
-# by always returning an unnamed list of fold indices.
-xgb.createFolds <- function(y, k = 10)
-{
-  if (is.numeric(y)) {
-    ## Group the numeric data based on their magnitudes
-    ## and sample within those groups.
-
-    ## When the number of samples is low, we may have
-    ## issues further slicing the numeric data into
-    ## groups. The number of groups will depend on the
-    ## ratio of the number of folds to the sample size.
-    ## At most, we will use quantiles. If the sample
-    ## is too small, we just do regular unstratified
-    ## CV
-    cuts <- floor(length(y) / k)
-    if (cuts < 2) cuts <- 2
-    if (cuts > 5) cuts <- 5
-    y <- cut(y,
-             unique(stats::quantile(y, probs = seq(0, 1, length = cuts))),
-             include.lowest = TRUE)
-  }
-
-  if (k < length(y)) {
-    ## reset levels so that the possible levels and
-    ## the levels in the vector are the same
-    y <- factor(as.character(y))
-    numInClass <- table(y)
-    foldVector <- vector(mode = "integer", length(y))
-
-    ## For each class, balance the fold allocation as far
-    ## as possible, then resample the remainder.
-    ## The final assignment of folds is also randomized.
-    for (i in seq_along(numInClass)) {
-      ## create a vector of integers from 1:k as many times as possible without
-      ## going over the number of samples in the class. Note that if the number
-      ## of samples in a class is less than k, nothing is producd here.
-      seqVector <- rep(seq_len(k), numInClass[i] %/% k)
-      ## add enough random integers to get  length(seqVector) == numInClass[i]
-      if (numInClass[i] %% k > 0) seqVector <- c(seqVector, sample.int(k, numInClass[i] %% k))
-      ## shuffle the integers for fold assignment and assign to this classes's data
-      ## seqVector[sample.int(length(seqVector))] is used to handle length(seqVector) == 1
-      foldVector[y == dimnames(numInClass)$y[i]] <- seqVector[sample.int(length(seqVector))]
-    }
-  } else {
-    foldVector <- seq(along = y)
-  }
-
-  out <- split(seq(along = y), foldVector)
-  names(out) <- NULL
-  out
-}
-
-
-#
-# Deprectaion notice utilities ------------------------------------------------
-#
-
-#' Deprecation notices.
-#'
-#' At this time, some of the parameter names were changed in order to make the code style more uniform.
-#' The deprecated parameters would be removed in the next release.
-#'
-#' To see all the current deprecated and new parameters, check the \code{xgboost:::depr_par_lut} table.
-#'
-#' A deprecation warning is shown when any of the deprecated parameters is used in a call.
-#' An additional warning is shown when there was a partial match to a deprecated parameter
-#' (as R is able to partially match parameter names).
-#'
-#' @name xgboost-deprecated
-NULL
-
-# Lookup table for the deprecated parameters bookkeeping
-depr_par_lut <- matrix(c(
-  'print.every.n', 'print_every_n',
-  'early.stop.round', 'early_stopping_rounds',
-  'training.data', 'data',
-  'with.stats', 'with_stats',
-  'numberOfClusters', 'n_clusters',
-  'features.keep', 'features_keep',
-  'plot.height','plot_height',
-  'plot.width','plot_width',
-  'n_first_tree', 'trees',
-  'dummy', 'DUMMY'
-), ncol = 2, byrow = TRUE)
-colnames(depr_par_lut) <- c('old', 'new')
-
-# Checks the dot-parameters for deprecated names
-# (including partial matching), gives a deprecation warning,
-# and sets new parameters to the old parameters' values within its parent frame.
-# WARNING: has side-effects
-check.deprecation <- function(..., env = parent.frame()) {
-  pars <- list(...)
-  # exact and partial matches
-  all_match <- pmatch(names(pars), depr_par_lut[,1])
-  # indices of matched pars' names
-  idx_pars <- which(!is.na(all_match))
-  if (length(idx_pars) == 0) return()
-  # indices of matched LUT rows
-  idx_lut <- all_match[idx_pars]
-  # which of idx_lut were the exact matches?
-  ex_match <- depr_par_lut[idx_lut,1] %in% names(pars)
-  for (i in seq_along(idx_pars)) {
-    pars_par <- names(pars)[idx_pars[i]]
-    old_par <- depr_par_lut[idx_lut[i], 1]
-    new_par <- depr_par_lut[idx_lut[i], 2]
-    if (!ex_match[i]) {
-      warning("'", pars_par, "' was partially matched to '", old_par,"'")
-    }
-    .Deprecated(new_par, old = old_par, package = 'xgboost')
-    if (new_par != 'NULL') {
-      eval(parse(text = paste(new_par, '<-', pars[[pars_par]])), envir = env)
-    }
-  }
-}

R-package/R/xgb.Booster.R

@@ -1,640 +0,0 @@
-# Construct an internal xgboost Booster and return a handle to it.
-# internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(), modelfile = NULL) {
-  if (typeof(cachelist) != "list" ||
-      !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
-    stop("cachelist must be a list of xgb.DMatrix objects")
-  }
-
-  handle <- .Call(XGBoosterCreate_R, cachelist)
-  if (!is.null(modelfile)) {
-    if (typeof(modelfile) == "character") {
-      .Call(XGBoosterLoadModel_R, handle, modelfile[1])
-    } else if (typeof(modelfile) == "raw") {
-      .Call(XGBoosterLoadModelFromRaw_R, handle, modelfile)
-    } else if (inherits(modelfile, "xgb.Booster")) {
-      bst <- xgb.Booster.complete(modelfile, saveraw = TRUE)
-      .Call(XGBoosterLoadModelFromRaw_R, handle, bst$raw)
-    } else {
-      stop("modelfile must be either character filename, or raw booster dump, or xgb.Booster object")
-    }
-  }
-  class(handle) <- "xgb.Booster.handle"
-  if (length(params) > 0) {
-    xgb.parameters(handle) <- params
-  }
-  return(handle)
-}
-
-# Convert xgb.Booster.handle to xgb.Booster
-# internal utility function
-xgb.handleToBooster <- function(handle, raw = NULL) {
-  bst <- list(handle = handle, raw = raw)
-  class(bst) <- "xgb.Booster"
-  return(bst)
-}
-
-# Check whether xgb.Booster.handle is null
-# internal utility function
-is.null.handle <- function(handle) {
-  if (is.null(handle)) return(TRUE)
-
-  if (!identical(class(handle), "xgb.Booster.handle"))
-    stop("argument type must be xgb.Booster.handle")
-
-  if (.Call(XGCheckNullPtr_R, handle))
-    return(TRUE)
-
-  return(FALSE)
-}
-
-# Return a verified to be valid handle out of either xgb.Booster.handle or xgb.Booster
-# internal utility function
-xgb.get.handle <- function(object) {
-  handle <- switch(class(object)[1],
-    xgb.Booster = object$handle,
-    xgb.Booster.handle = object,
-    stop("argument must be of either xgb.Booster or xgb.Booster.handle class")
-  )
-  if (is.null.handle(handle)) {
-    stop("invalid xgb.Booster.handle")
-  }
-  handle
-}
-
-#' Restore missing parts of an incomplete xgb.Booster object.
-#'
-#' It attempts to complete an \code{xgb.Booster} object by restoring either its missing
-#' raw model memory dump (when it has no \code{raw} data but its \code{xgb.Booster.handle} is valid)
-#' or its missing internal handle (when its \code{xgb.Booster.handle} is not valid
-#' but it has a raw Booster memory dump).
-#'
-#' @param object object of class \code{xgb.Booster}
-#' @param saveraw a flag indicating whether to append \code{raw} Booster memory dump data
-#'                when it doesn't already exist.
-#'
-#' @details
-#'
-#' While this method is primarily for internal use, it might be useful in some practical situations.
-#'
-#' E.g., when an \code{xgb.Booster} model is saved as an R object and then is loaded as an R object,
-#' its handle (pointer) to an internal xgboost model would be invalid. The majority of xgboost methods
-#' should still work for such a model object since those methods would be using
-#' \code{xgb.Booster.complete} internally. However, one might find it to be more efficient to call the
-#' \code{xgb.Booster.complete} function explicitly once after loading a model as an R-object.
-#' That would prevent further repeated implicit reconstruction of an internal booster model.
-#'
-#' @return
-#' An object of \code{xgb.Booster} class.
-#'
-#' @examples
-#'
-#' data(agaricus.train, package='xgboost')
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' saveRDS(bst, "xgb.model.rds")
-#'
-#' bst1 <- readRDS("xgb.model.rds")
-#' # the handle is invalid:
-#' print(bst1$handle)
-#'
-#' bst1 <- xgb.Booster.complete(bst1)
-#' # now the handle points to a valid internal booster model:
-#' print(bst1$handle)
-#'
-#' @export
-xgb.Booster.complete <- function(object, saveraw = TRUE) {
-  if (!inherits(object, "xgb.Booster"))
-    stop("argument type must be xgb.Booster")
-
-  if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(modelfile = object$raw)
-  } else {
-    if (is.null(object$raw) && saveraw)
-      object$raw <- xgb.save.raw(object$handle)
-  }
-  return(object)
-}
-
-#' Predict method for eXtreme Gradient Boosting model
-#'
-#' Predicted values based on either xgboost model or model handle object.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}
-#' @param newdata takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.
-#' @param missing Missing is only used when input is dense matrix. Pick a float value that represents
-#'        missing values in data (e.g., sometimes 0 or some other extreme value is used).
-#' @param outputmargin whether the prediction should be returned in the for of original untransformed
-#'        sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
-#'        logistic regression would result in predictions for log-odds instead of probabilities.
-#' @param ntreelimit limit the number of model's trees or boosting iterations used in prediction (see Details).
-#'        It will use all the trees by default (\code{NULL} value).
-#' @param predleaf whether predict leaf index.
-#' @param predcontrib whether to return feature contributions to individual predictions (see Details).
-#' @param approxcontrib whether to use a fast approximation for feature contributions (see Details).
-#' @param predinteraction whether to return contributions of feature interactions to individual predictions (see Details).
-#' @param reshape whether to reshape the vector of predictions to a matrix form when there are several
-#'        prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
-#'        or predinteraction flags is TRUE.
-#' @param ... Parameters passed to \code{predict.xgb.Booster}
-#'
-#' @details
-#' Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
-#' and it is not necessarily equal to the number of trees in a model.
-#' E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-#' But for multiclass classification, while there are multiple trees per iteration,
-#' \code{ntreelimit} limits the number of boosting iterations.
-#'
-#' Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
-#' since gblinear doesn't keep its boosting history.
-#'
-#' One possible practical applications of the \code{predleaf} option is to use the model
-#' as a generator of new features which capture non-linearity and interactions,
-#' e.g., as implemented in \code{\link{xgb.create.features}}.
-#'
-#' Setting \code{predcontrib = TRUE} allows to calculate contributions of each feature to
-#' individual predictions. For "gblinear" booster, feature contributions are simply linear terms
-#' (feature_beta * feature_value). For "gbtree" booster, feature contributions are SHAP
-#' values (Lundberg 2017) that sum to the difference between the expected output
-#' of the model and the current prediction (where the hessian weights are used to compute the expectations).
-#' Setting \code{approxcontrib = TRUE} approximates these values following the idea explained
-#' in \url{http://blog.datadive.net/interpreting-random-forests/}.
-#'
-#' With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
-#' are computed. Note that this operation might be rather expensive in terms of compute and memory.
-#' Since it quadratically depends on the number of features, it is recommended to perform selection
-#' of the most important features first. See below about the format of the returned results.
-#'
-#' @return
-#' For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
-#' For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
-#' a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
-#' the \code{reshape} value.
-#'
-#' When \code{predleaf = TRUE}, the output is a matrix object with the
-#' number of columns corresponding to the number of trees.
-#'
-#' When \code{predcontrib = TRUE} and it is not a multiclass setting, the output is a matrix object with
-#' \code{num_features + 1} columns. The last "+ 1" column in a matrix corresponds to bias.
-#' For a multiclass case, a list of \code{num_class} elements is returned, where each element is
-#' such a matrix. The contribution values are on the scale of untransformed margin
-#' (e.g., for binary classification would mean that the contributions are log-odds deviations from bias).
-#'
-#' When \code{predinteraction = TRUE} and it is not a multiclass setting, the output is a 3d array with
-#' dimensions \code{c(nrow, num_features + 1, num_features + 1)}. The off-diagonal (in the last two dimensions)
-#' elements represent different features interaction contributions. The array is symmetric WRT the last
-#' two dimensions. The "+ 1" columns corresponds to bias. Summing this array along the last dimension should
-#' produce practically the same result as predict with \code{predcontrib = TRUE}.
-#' For a multiclass case, a list of \code{num_class} elements is returned, where each element is
-#' such an array.
-#'
-#' @seealso
-#' \code{\link{xgb.train}}.
-#'
-#' @references
-#'
-#' Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
-#'
-#' Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
-#'
-#' @examples
-#' ## binary classification:
-#'
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 0.5, nthread = 2, nrounds = 5, objective = "binary:logistic")
-#' # use all trees by default
-#' pred <- predict(bst, test$data)
-#' # use only the 1st tree
-#' pred1 <- predict(bst, test$data, ntreelimit = 1)
-#'
-#' # Predicting tree leafs:
-#' # the result is an nsamples X ntrees matrix
-#' pred_leaf <- predict(bst, test$data, predleaf = TRUE)
-#' str(pred_leaf)
-#'
-#' # Predicting feature contributions to predictions:
-#' # the result is an nsamples X (nfeatures + 1) matrix
-#' pred_contr <- predict(bst, test$data, predcontrib = TRUE)
-#' str(pred_contr)
-#' # verify that contributions' sums are equal to log-odds of predictions (up to float precision):
-#' summary(rowSums(pred_contr) - qlogis(pred))
-#' # for the 1st record, let's inspect its features that had non-zero contribution to prediction:
-#' contr1 <- pred_contr[1,]
-#' contr1 <- contr1[-length(contr1)]    # drop BIAS
-#' contr1 <- contr1[contr1 != 0]        # drop non-contributing features
-#' contr1 <- contr1[order(abs(contr1))] # order by contribution magnitude
-#' old_mar <- par("mar")
-#' par(mar = old_mar + c(0,7,0,0))
-#' barplot(contr1, horiz = TRUE, las = 2, xlab = "contribution to prediction in log-odds")
-#' par(mar = old_mar)
-#'
-#'
-#' ## multiclass classification in iris dataset:
-#'
-#' lb <- as.numeric(iris$Species) - 1
-#' num_class <- 3
-#' set.seed(11)
-#' bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
-#'                max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
-#'                objective = "multi:softprob", num_class = num_class)
-#' # predict for softmax returns num_class probability numbers per case:
-#' pred <- predict(bst, as.matrix(iris[, -5]))
-#' str(pred)
-#' # reshape it to a num_class-columns matrix
-#' pred <- matrix(pred, ncol=num_class, byrow=TRUE)
-#' # convert the probabilities to softmax labels
-#' pred_labels <- max.col(pred) - 1
-#' # the following should result in the same error as seen in the last iteration
-#' sum(pred_labels != lb)/length(lb)
-#'
-#' # compare that to the predictions from softmax:
-#' set.seed(11)
-#' bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
-#'                max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
-#'                objective = "multi:softmax", num_class = num_class)
-#' pred <- predict(bst, as.matrix(iris[, -5]))
-#' str(pred)
-#' all.equal(pred, pred_labels)
-#' # prediction from using only 5 iterations should result
-#' # in the same error as seen in iteration 5:
-#' pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
-#' sum(pred5 != lb)/length(lb)
-#'
-#'
-#' ## random forest-like model of 25 trees for binary classification:
-#'
-#' set.seed(11)
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-#'                nthread = 2, nrounds = 1, objective = "binary:logistic",
-#'                num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-#' # Inspect the prediction error vs number of trees:
-#' lb <- test$label
-#' dtest <- xgb.DMatrix(test$data, label=lb)
-#' err <- sapply(1:25, function(n) {
-#'   pred <- predict(bst, dtest, ntreelimit=n)
-#'   sum((pred > 0.5) != lb)/length(lb)
-#' })
-#' plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-#'
-#' @rdname predict.xgb.Booster
-#' @export
-predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE, ntreelimit = NULL,
-                                predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, ...) {
-
-  object <- xgb.Booster.complete(object, saveraw = FALSE)
-  if (!inherits(newdata, "xgb.DMatrix"))
-    newdata <- xgb.DMatrix(newdata, missing = missing)
-  if (!is.null(object[["feature_names"]]) &&
-      !is.null(colnames(newdata)) &&
-      !identical(object[["feature_names"]], colnames(newdata)))
-    stop("Feature names stored in `object` and `newdata` are different!")
-  if (is.null(ntreelimit))
-    ntreelimit <- NVL(object$best_ntreelimit, 0)
-  if (NVL(object$params[['booster']], '') == 'gblinear')
-    ntreelimit <- 0
-  if (ntreelimit < 0)
-    stop("ntreelimit cannot be negative")
-
-  option <- 0L + 1L * as.logical(outputmargin) + 2L * as.logical(predleaf) + 4L * as.logical(predcontrib) +
-    8L * as.logical(approxcontrib) + 16L * as.logical(predinteraction)
-
-  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1], as.integer(ntreelimit))
-
-  n_ret <- length(ret)
-  n_row <- nrow(newdata)
-  npred_per_case <- n_ret / n_row
-
-  if (n_ret %% n_row != 0)
-    stop("prediction length ", n_ret, " is not multiple of nrows(newdata) ", n_row)
-
-  if (predleaf) {
-    ret <- if (n_ret == n_row) {
-      matrix(ret, ncol = 1)
-    } else {
-      matrix(ret, nrow = n_row, byrow = TRUE)
-    }
-  } else if (predcontrib) {
-    n_col1 <- ncol(newdata) + 1
-    n_group <- npred_per_case / n_col1
-    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
-    ret <- if (n_ret == n_row) {
-      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
-    } else if (n_group == 1) {
-      matrix(ret, nrow = n_row, byrow = TRUE, dimnames = list(NULL, cnames))
-    } else {
-      arr <- array(ret, c(n_col1, n_group, n_row),
-                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2,3,1)) # [group, row, col]
-      lapply(seq_len(n_group), function(g) arr[g,,])
-    }
-  } else if (predinteraction) {
-    n_col1 <- ncol(newdata) + 1
-    n_group <- npred_per_case / n_col1^2
-    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
-    ret <- if (n_ret == n_row) {
-      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
-    } else if (n_group == 1) {
-      array(ret, c(n_col1, n_col1, n_row), dimnames = list(cnames, cnames, NULL)) %>% aperm(c(3,1,2))
-    } else {
-      arr <- array(ret, c(n_col1, n_col1, n_group, n_row),
-                   dimnames = list(cnames, cnames, NULL, NULL)) %>% aperm(c(3,4,1,2)) # [group, row, col1, col2]
-      lapply(seq_len(n_group), function(g) arr[g,,,])
-    }
-  } else if (reshape && npred_per_case > 1) {
-    ret <- matrix(ret, nrow = n_row, byrow = TRUE)
-  }
-  return(ret)
-}
-
-#' @rdname predict.xgb.Booster
-#' @export
-predict.xgb.Booster.handle <- function(object, ...) {
-
-  bst <- xgb.handleToBooster(object)
-
-  ret <- predict(bst, ...)
-  return(ret)
-}
-
-
-#' Accessors for serializable attributes of a model.
-#'
-#' These methods allow to manipulate the key-value attribute strings of an xgboost model.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.
-#' @param name a non-empty character string specifying which attribute is to be accessed.
-#' @param value a value of an attribute for \code{xgb.attr<-}; for \code{xgb.attributes<-}
-#'        it's a list (or an object coercible to a list) with the names of attributes to set
-#'        and the elements corresponding to attribute values.
-#'        Non-character values are converted to character.
-#'        When attribute value is not a scalar, only the first index is used.
-#'        Use \code{NULL} to remove an attribute.
-#'
-#' @details
-#' The primary purpose of xgboost model attributes is to store some meta-data about the model.
-#' Note that they are a separate concept from the object attributes in R.
-#' Specifically, they refer to key-value strings that can be attached to an xgboost model,
-#' stored together with the model's binary representation, and accessed later
-#' (from R or any other interface).
-#' In contrast, any R-attribute assigned to an R-object of \code{xgb.Booster} class
-#' would not be saved by \code{xgb.save} because an xgboost model is an external memory object
-#' and its serialization is handled externally.
-#' Also, setting an attribute that has the same name as one of xgboost's parameters wouldn't
-#' change the value of that parameter for a model.
-#' Use \code{\link{xgb.parameters<-}} to set or change model parameters.
-#'
-#' The attribute setters would usually work more efficiently for \code{xgb.Booster.handle}
-#' than for \code{xgb.Booster}, since only just a handle (pointer) would need to be copied.
-#' That would only matter if attributes need to be set many times.
-#' Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
-#' the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-#' and it would be user's responsibility to call \code{xgb.save.raw} to update it.
-#'
-#' The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
-#' but it doesn't delete the other existing attributes.
-#'
-#' @return
-#' \code{xgb.attr} returns either a string value of an attribute
-#' or \code{NULL} if an attribute wasn't stored in a model.
-#'
-#' \code{xgb.attributes} returns a list of all attribute stored in a model
-#' or \code{NULL} if a model has no stored attributes.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' xgb.attr(bst, "my_attribute") <- "my attribute value"
-#' print(xgb.attr(bst, "my_attribute"))
-#' xgb.attributes(bst) <- list(a = 123, b = "abc")
-#'
-#' xgb.save(bst, 'xgb.model')
-#' bst1 <- xgb.load('xgb.model')
-#' print(xgb.attr(bst1, "my_attribute"))
-#' print(xgb.attributes(bst1))
-#'
-#' # deletion:
-#' xgb.attr(bst1, "my_attribute") <- NULL
-#' print(xgb.attributes(bst1))
-#' xgb.attributes(bst1) <- list(a = NULL, b = NULL)
-#' print(xgb.attributes(bst1))
-#'
-#' @rdname xgb.attr
-#' @export
-xgb.attr <- function(object, name) {
-  if (is.null(name) || nchar(as.character(name[1])) == 0) stop("invalid attribute name")
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterGetAttr_R, handle, as.character(name[1]))
-}
-
-#' @rdname xgb.attr
-#' @export
-`xgb.attr<-` <- function(object, name, value) {
-  if (is.null(name) || nchar(as.character(name[1])) == 0) stop("invalid attribute name")
-  handle <- xgb.get.handle(object)
-  if (!is.null(value)) {
-    # Coerce the elements to be scalar strings.
-    # Q: should we warn user about non-scalar elements?
-    if (is.numeric(value[1])) {
-      value <- format(value[1], digits = 17)
-    } else {
-      value <- as.character(value[1])
-    }
-  }
-  .Call(XGBoosterSetAttr_R, handle, as.character(name[1]), value)
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
-  }
-  object
-}
-
-#' @rdname xgb.attr
-#' @export
-xgb.attributes <- function(object) {
-  handle <- xgb.get.handle(object)
-  attr_names <- .Call(XGBoosterGetAttrNames_R, handle)
-  if (is.null(attr_names)) return(NULL)
-  res <- lapply(attr_names, function(x) {
-    .Call(XGBoosterGetAttr_R, handle, x)
-  })
-  names(res) <- attr_names
-  res
-}
-
-#' @rdname xgb.attr
-#' @export
-`xgb.attributes<-` <- function(object, value) {
-  a <- as.list(value)
-  if (is.null(names(a)) || any(nchar(names(a)) == 0)) {
-    stop("attribute names cannot be empty strings")
-  }
-  # Coerce the elements to be scalar strings.
-  # Q: should we warn a user about non-scalar elements?
-  a <- lapply(a, function(x) {
-    if (is.null(x)) return(NULL)
-    if (is.numeric(x[1])) {
-      format(x[1], digits = 17)
-    } else {
-      as.character(x[1])
-    }
-  })
-  handle <- xgb.get.handle(object)
-  for (i in seq_along(a)) {
-    .Call(XGBoosterSetAttr_R, handle, names(a[i]), a[[i]])
-  }
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
-  }
-  object
-}
-
-#' Accessors for model parameters.
-#'
-#' Only the setter for xgboost parameters is currently implemented.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.
-#' @param value a list (or an object coercible to a list) with the names of parameters to set
-#'        and the elements corresponding to parameter values.
-#'
-#' @details
-#' Note that the setter would usually work more efficiently for \code{xgb.Booster.handle}
-#' than for \code{xgb.Booster}, since only just a handle would need to be copied.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' xgb.parameters(bst) <- list(eta = 0.1)
-#'
-#' @rdname xgb.parameters
-#' @export
-`xgb.parameters<-` <- function(object, value) {
-  if (length(value) == 0) return(object)
-  p <- as.list(value)
-  if (is.null(names(p)) || any(nchar(names(p)) == 0)) {
-    stop("parameter names cannot be empty strings")
-  }
-  names(p) <- gsub("\\.", "_", names(p))
-  p <- lapply(p, function(x) as.character(x)[1])
-  handle <- xgb.get.handle(object)
-  for (i in seq_along(p)) {
-    .Call(XGBoosterSetParam_R, handle, names(p[i]), p[[i]])
-  }
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
-  }
-  object
-}
-
-# Extract the number of trees in a model.
-# TODO: either add a getter to C-interface, or simply set an 'ntree' attribute after each iteration.
-# internal utility function
-xgb.ntree <- function(bst) {
-  length(grep('^booster', xgb.dump(bst)))
-}
-
-
-#' Print xgb.Booster
-#'
-#' Print information about xgb.Booster.
-#'
-#' @param x an xgb.Booster object
-#' @param verbose whether to print detailed data (e.g., attribute values)
-#' @param ... not currently used
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' attr(bst, 'myattr') <- 'memo'
-#'
-#' print(bst)
-#' print(bst, verbose=TRUE)
-#'
-#' @method print xgb.Booster
-#' @export
-print.xgb.Booster <- function(x, verbose = FALSE, ...) {
-  cat('##### xgb.Booster\n')
-
-  valid_handle <- !is.null.handle(x$handle)
-  if (!valid_handle)
-    cat("Handle is invalid! Suggest using xgb.Booster.complete\n")
-
-  cat('raw: ')
-  if (!is.null(x$raw)) {
-    cat(format(object.size(x$raw), units = "auto"), '\n')
-  } else {
-    cat('NULL\n')
-  }
-  if (!is.null(x$call)) {
-    cat('call:\n  ')
-    print(x$call)
-  }
-
-  if (!is.null(x$params)) {
-    cat('params (as set within xgb.train):\n')
-    cat( '  ',
-         paste(names(x$params),
-               paste0('"', unlist(x$params), '"'),
-               sep = ' = ', collapse = ', '), '\n', sep = '')
-  }
-  # TODO: need an interface to access all the xgboosts parameters
-
-  attrs <- character(0)
-  if (valid_handle)
-    attrs <- xgb.attributes(x)
-  if (length(attrs) > 0) {
-    cat('xgb.attributes:\n')
-    if (verbose) {
-      cat( paste(paste0('  ',names(attrs)),
-                 paste0('"', unlist(attrs), '"'),
-                 sep = ' = ', collapse = '\n'), '\n', sep = '')
-    } else {
-      cat('  ', paste(names(attrs), collapse = ', '), '\n', sep = '')
-    }
-  }
-
-  if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
-    cat('callbacks:\n')
-    lapply(callback.calls(x$callbacks), function(x) {
-      cat('  ')
-      print(x)
-    })
-  }
-
-  if (!is.null(x$feature_names))
-    cat('# of features:', length(x$feature_names), '\n')
-
-  cat('niter: ', x$niter, '\n', sep = '')
-  # TODO: uncomment when faster xgb.ntree is implemented
-  #cat('ntree: ', xgb.ntree(x), '\n', sep='')
-
-  for (n in setdiff(names(x), c('handle', 'raw', 'call', 'params', 'callbacks',
-                                'evaluation_log','niter','feature_names'))) {
-    if (is.atomic(x[[n]])) {
-      cat(n, ':', x[[n]], '\n', sep = ' ')
-    } else {
-      cat(n, ':\n\t', sep = ' ')
-      print(x[[n]])
-    }
-  }
-
-  if (!is.null(x$evaluation_log)) {
-    cat('evaluation_log:\n')
-    print(x$evaluation_log, row.names = FALSE, topn = 2)
-  }
-
-  invisible(x)
-}

R-package/R/xgb.DMatrix.R

@@ -1,366 +0,0 @@
-#' Construct xgb.DMatrix object
-#'
-#' Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-#' Supported input file formats are either a libsvm text file or a binary file that was created previously by
-#' \code{\link{xgb.DMatrix.save}}).
-#'
-#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
-#'        string representing a filename.
-#' @param info a named list of additional information to store in the \code{xgb.DMatrix} object.
-#'        See \code{\link{setinfo}} for the specific allowed kinds of
-#' @param missing a float value to represents missing values in data (used only when input is a dense matrix).
-#'        It is useful when a 0 or some other extreme value represents missing values in data.
-#' @param silent whether to suppress printing an informational message after loading from a file.
-#' @param ... the \code{info} data could be passed directly as parameters, without creating an \code{info} list.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-#' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' @export
-xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
-  cnames <- NULL
-  if (typeof(data) == "character") {
-    if (length(data) > 1)
-      stop("'data' has class 'character' and length ", length(data),
-           ".\n  'data' accepts either a numeric matrix or a single filename.")
-    handle <- .Call(XGDMatrixCreateFromFile_R, data, as.integer(silent))
-  } else if (is.matrix(data)) {
-    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing)
-    cnames <- colnames(data)
-  } else if (inherits(data, "dgCMatrix")) {
-    handle <- .Call(XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data))
-    cnames <- colnames(data)
-  } else {
-    stop("xgb.DMatrix does not support construction from ", typeof(data))
-  }
-  dmat <- handle
-  attributes(dmat) <- list(.Dimnames = list(NULL, cnames), class = "xgb.DMatrix")
-
-  info <- append(info, list(...))
-  for (i in seq_along(info)) {
-    p <- info[i]
-    setinfo(dmat, names(p), p[[1]])
-  }
-  return(dmat)
-}
-
-
-# get dmatrix from data, label
-# internal helper method
-xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
-  if (inherits(data, "dgCMatrix") || is.matrix(data)) {
-    if (is.null(label)) {
-      stop("label must be provided when data is a matrix")
-    }
-    dtrain <- xgb.DMatrix(data, label = label, missing = missing)
-    if (!is.null(weight)){
-      setinfo(dtrain, "weight", weight)
-    }
-  } else {
-    if (!is.null(label)) {
-      warning("xgboost: label will be ignored.")
-    }
-    if (is.character(data)) {
-      dtrain <- xgb.DMatrix(data[1])
-    } else if (inherits(data, "xgb.DMatrix")) {
-      dtrain <- data
-    } else if (inherits(data, "data.frame")) {
-      stop("xgboost doesn't support data.frame as input. Convert it to matrix first.")
-    } else {
-      stop("xgboost: invalid input data")
-    }
-  }
-  return (dtrain)
-}
-
-
-#' Dimensions of xgb.DMatrix
-#'
-#' Returns a vector of numbers of rows and of columns in an \code{xgb.DMatrix}.
-#' @param x Object of class \code{xgb.DMatrix}
-#'
-#' @details
-#' Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
-#' be directly used with an \code{xgb.DMatrix} object.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#'
-#' stopifnot(nrow(dtrain) == nrow(train$data))
-#' stopifnot(ncol(dtrain) == ncol(train$data))
-#' stopifnot(all(dim(dtrain) == dim(train$data)))
-#'
-#' @export
-dim.xgb.DMatrix <- function(x) {
-  c(.Call(XGDMatrixNumRow_R, x), .Call(XGDMatrixNumCol_R, x))
-}
-
-
-#' Handling of column names of \code{xgb.DMatrix}
-#'
-#' Only column names are supported for \code{xgb.DMatrix}, thus setting of
-#' row names would have no effect and returned row names would be NULL.
-#'
-#' @param x object of class \code{xgb.DMatrix}
-#' @param value a list of two elements: the first one is ignored
-#'        and the second one is column names
-#'
-#' @details
-#' Generic \code{dimnames} methods are used by \code{colnames}.
-#' Since row names are irrelevant, it is recommended to use \code{colnames} directly.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#' dimnames(dtrain)
-#' colnames(dtrain)
-#' colnames(dtrain) <- make.names(1:ncol(train$data))
-#' print(dtrain, verbose=TRUE)
-#'
-#' @rdname dimnames.xgb.DMatrix
-#' @export
-dimnames.xgb.DMatrix <- function(x) {
-  attr(x, '.Dimnames')
-}
-
-#' @rdname dimnames.xgb.DMatrix
-#' @export
-`dimnames<-.xgb.DMatrix` <- function(x, value) {
-  if (!is.list(value) || length(value) != 2L)
-    stop("invalid 'dimnames' given: must be a list of two elements")
-  if (!is.null(value[[1L]]))
-    stop("xgb.DMatrix does not have rownames")
-  if (is.null(value[[2]])) {
-    attr(x, '.Dimnames') <- NULL
-    return(x)
-  }
-  if (ncol(x) != length(value[[2]]))
-    stop("can't assign ", length(value[[2]]), " colnames to a ",
-         ncol(x), " column xgb.DMatrix")
-  attr(x, '.Dimnames') <- value
-  x
-}
-
-
-#' Get information of an xgb.DMatrix object
-#'
-#' Get information of an xgb.DMatrix object
-#' @param object Object of class \code{xgb.DMatrix}
-#' @param name the name of the information field to get (see details)
-#' @param ... other parameters
-#'
-#' @details
-#' The \code{name} field can be one of the following:
-#'
-#' \itemize{
-#'     \item \code{label}: label Xgboost learn from ;
-#'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
-#'     \item \code{nrow}: number of rows of the \code{xgb.DMatrix}.
-#'
-#' }
-#'
-#' \code{group} can be setup by \code{setinfo} but can't be retrieved by \code{getinfo}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#'
-#' labels <- getinfo(dtrain, 'label')
-#' setinfo(dtrain, 'label', 1-labels)
-#'
-#' labels2 <- getinfo(dtrain, 'label')
-#' stopifnot(all(labels2 == 1-labels))
-#' @rdname getinfo
-#' @export
-getinfo <- function(object, ...) UseMethod("getinfo")
-
-#' @rdname getinfo
-#' @export
-getinfo.xgb.DMatrix <- function(object, name, ...) {
-  if (typeof(name) != "character" ||
-      length(name) != 1 ||
-      !name %in% c('label', 'weight', 'base_margin', 'nrow')) {
-    stop("getinfo: name must be one of the following\n",
-         "    'label', 'weight', 'base_margin', 'nrow'")
-  }
-  if (name != "nrow"){
-    ret <- .Call(XGDMatrixGetInfo_R, object, name)
-  } else {
-    ret <- nrow(object)
-  }
-  if (length(ret) == 0) return(NULL)
-  return(ret)
-}
-
-
-#' Set information of an xgb.DMatrix object
-#'
-#' Set information of an xgb.DMatrix object
-#'
-#' @param object Object of class "xgb.DMatrix"
-#' @param name the name of the field to get
-#' @param info the specific field of information to set
-#' @param ... other parameters
-#'
-#' @details
-#' The \code{name} field can be one of the following:
-#'
-#' \itemize{
-#'     \item \code{label}: label Xgboost learn from ;
-#'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
-#'     \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
-#' }
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#'
-#' labels <- getinfo(dtrain, 'label')
-#' setinfo(dtrain, 'label', 1-labels)
-#' labels2 <- getinfo(dtrain, 'label')
-#' stopifnot(all.equal(labels2, 1-labels))
-#' @rdname setinfo
-#' @export
-setinfo <- function(object, ...) UseMethod("setinfo")
-
-#' @rdname setinfo
-#' @export
-setinfo.xgb.DMatrix <- function(object, name, info, ...) {
-  if (name == "label") {
-    if (length(info) != nrow(object))
-      stop("The length of labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "weight") {
-    if (length(info) != nrow(object))
-      stop("The length of weights must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "base_margin") {
-    # if (length(info)!=nrow(object))
-    #   stop("The length of base margin must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "group") {
-    if (sum(info) != nrow(object))
-      stop("The sum of groups must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.integer(info))
-    return(TRUE)
-  }
-  stop("setinfo: unknown info name ", name)
-  return(FALSE)
-}
-
-
-#' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
-#'
-#' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
-#'
-#' @param object Object of class "xgb.DMatrix"
-#' @param idxset a integer vector of indices of rows needed
-#' @param colset currently not used (columns subsetting is not available)
-#' @param ... other parameters (currently not used)
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#'
-#' dsub <- slice(dtrain, 1:42)
-#' labels1 <- getinfo(dsub, 'label')
-#' dsub <- dtrain[1:42, ]
-#' labels2 <- getinfo(dsub, 'label')
-#' all.equal(labels1, labels2)
-#'
-#' @rdname slice.xgb.DMatrix
-#' @export
-slice <- function(object, ...) UseMethod("slice")
-
-#' @rdname slice.xgb.DMatrix
-#' @export
-slice.xgb.DMatrix <- function(object, idxset, ...) {
-  if (!inherits(object, "xgb.DMatrix")) {
-    stop("object must be xgb.DMatrix")
-  }
-  ret <- .Call(XGDMatrixSliceDMatrix_R, object, idxset)
-
-  attr_list <- attributes(object)
-  nr <- nrow(object)
-  len <- sapply(attr_list, NROW)
-  ind <- which(len == nr)
-  if (length(ind) > 0) {
-    nms <- names(attr_list)[ind]
-    for (i in seq_along(ind)) {
-      obj_attr <- attr(object, nms[i])
-      if (NCOL(obj_attr) > 1) {
-        attr(ret, nms[i]) <- obj_attr[idxset,]
-      } else {
-        attr(ret, nms[i]) <- obj_attr[idxset]
-      }
-    }
-  }
-  return(structure(ret, class = "xgb.DMatrix"))
-}
-
-#' @rdname slice.xgb.DMatrix
-#' @export
-`[.xgb.DMatrix` <- function(object, idxset, colset = NULL) {
-  slice(object, idxset)
-}
-
-
-#' Print xgb.DMatrix
-#'
-#' Print information about xgb.DMatrix.
-#' Currently it displays dimensions and presence of info-fields and colnames.
-#'
-#' @param x an xgb.DMatrix object
-#' @param verbose whether to print colnames (when present)
-#' @param ... not currently used
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#'
-#' dtrain
-#' print(dtrain, verbose=TRUE)
-#'
-#' @method print xgb.DMatrix
-#' @export
-print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
-  cat('xgb.DMatrix  dim:', nrow(x), 'x', ncol(x), ' info: ')
-  infos <- c()
-  if(length(getinfo(x, 'label')) > 0) infos <- 'label'
-  if(length(getinfo(x, 'weight')) > 0) infos <- c(infos, 'weight')
-  if(length(getinfo(x, 'base_margin')) > 0) infos <- c(infos, 'base_margin')
-  if (length(infos) == 0) infos <- 'NA'
-  cat(infos)
-  cnames <- colnames(x)
-  cat('  colnames:')
-  if (verbose & !is.null(cnames)) {
-    cat("\n'")
-    cat(cnames, sep = "','")
-    cat("'")
-  } else {
-    if (is.null(cnames)) cat(' no')
-    else cat(' yes')
-  }
-  cat("\n")
-  invisible(x)
-}

R-package/R/xgb.DMatrix.save.R

@@ -1,23 +0,0 @@
-#' Save xgb.DMatrix object to binary file
-#' 
-#' Save xgb.DMatrix object to binary file
-#' 
-#' @param dmatrix the \code{xgb.DMatrix} object
-#' @param fname the name of the file to write.
-#' 
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-#' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' @export
-xgb.DMatrix.save <- function(dmatrix, fname) {
-  if (typeof(fname) != "character")
-    stop("fname must be character")
-  if (!inherits(dmatrix, "xgb.DMatrix"))
-    stop("dmatrix must be xgb.DMatrix")
-  
-  .Call(XGDMatrixSaveBinary_R, dmatrix, fname[1], 0L)
-  return(TRUE)
-}

R-package/R/xgb.create.features.R

@@ -1,87 +0,0 @@
-#' Create new features from a previously learned model
-#' 
-#' May improve the learning by adding new features to the training data based on the decision trees from a previously learned model.
-#' 
-#' @param model decision tree boosting model learned on the original data
-#' @param data original data (usually provided as a \code{dgCMatrix} matrix)
-#' @param ... currently not used
-#' 
-#' @return \code{dgCMatrix} matrix including both the original data and the new features.
-#'
-#' @details 
-#' This is the function inspired from the paragraph 3.1 of the paper:
-#' 
-#' \strong{Practical Lessons from Predicting Clicks on Ads at Facebook}
-#' 
-#' \emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, 
-#' Joaquin Quinonero Candela)}
-#'  
-#' International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
-#' 
-#' \url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
-#' 
-#' Extract explaining the method:
-#' 
-#' "We found that boosted decision trees are a powerful and very
-#' convenient way to implement non-linear and tuple transformations
-#' of the kind we just described. We treat each individual
-#' tree as a categorical feature that takes as value the
-#' index of the leaf an instance ends up falling in. We use 
-#' 1-of-K coding of this type of features. 
-#' 
-#' For example, consider the boosted tree model in Figure 1 with 2 subtrees, 
-#' where the first subtree has 3 leafs and the second 2 leafs. If an
-#' instance ends up in leaf 2 in the first subtree and leaf 1 in
-#' second subtree, the overall input to the linear classifier will
-#' be the binary vector \code{[0, 1, 0, 1, 0]}, where the first 3 entries
-#' correspond to the leaves of the first subtree and last 2 to
-#' those of the second subtree.
-#' 
-#' [...]
-#' 
-#' We can understand boosted decision tree
-#' based transformation as a supervised feature encoding that
-#' converts a real-valued vector into a compact binary-valued
-#' vector. A traversal from root node to a leaf node represents
-#' a rule on certain features."
-#' 
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
-#' dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
-#'
-#' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-#' nrounds = 4
-#'
-#' bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
-#' 
-#' # Model accuracy without new features
-#' accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
-#'                    length(agaricus.test$label)
-#' 
-#' # Convert previous features to one hot encoding
-#' new.features.train <- xgb.create.features(model = bst, agaricus.train$data)
-#' new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
-#' 
-#' # learning with new features
-#' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
-#' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
-#' watchlist <- list(train = new.dtrain)
-#' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
-#' 
-#' # Model accuracy with new features
-#' accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /
-#'                   length(agaricus.test$label)
-#' 
-#' # Here the accuracy was already good and is now perfect.
-#' cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
-#'           accuracy.after, "!\n"))
-#' 
-#' @export
-xgb.create.features <- function(model, data, ...){
-  check.deprecation(...)
-  pred_with_leaf <- predict(model, data, predleaf = TRUE)
-  cols <- lapply(as.data.frame(pred_with_leaf), factor)
-  cbind(data, sparse.model.matrix( ~ . -1, cols))
-}

R-package/R/xgb.cv.R

@@ -1,305 +0,0 @@
-#' Cross Validation
-#'
-#' The cross validation function of xgboost
-#'
-#' @param params the list of parameters. Commonly used ones are:
-#' \itemize{
-#'   \item \code{objective} objective function, common ones are
-#'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss
-#'     \item \code{binary:logistic} logistic regression for classification
-#'   }
-#'   \item \code{eta} step size of each boosting step
-#'   \item \code{max_depth} maximum depth of the tree
-#'   \item \code{nthread} number of thread used in training, if not set, all threads are used
-#' }
-#'
-#'   See \code{\link{xgb.train}} for further details.
-#'   See also demo/ for walkthrough example in R.
-#' @param data takes an \code{xgb.DMatrix}, \code{matrix}, or \code{dgCMatrix} as the input.
-#' @param nrounds the max number of iterations
-#' @param nfold the original dataset is randomly partitioned into \code{nfold} equal size subsamples.
-#' @param label vector of response values. Should be provided only when data is an R-matrix.
-#' @param missing is only used when input is a dense matrix. By default is set to NA, which means
-#'        that NA values should be considered as 'missing' by the algorithm.
-#'        Sometimes, 0 or other extreme value might be used to represent missing values.
-#' @param prediction A logical value indicating whether to return the test fold predictions
-#'        from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callback.
-#' @param showsd \code{boolean}, whether to show standard deviation of cross validation
-#' @param metrics, list of evaluation metrics to be used in cross validation,
-#'   when it is not specified, the evaluation metric is chosen according to objective function.
-#'   Possible options are:
-#' \itemize{
-#'   \item \code{error} binary classification error rate
-#'   \item \code{rmse} Rooted mean square error
-#'   \item \code{logloss} negative log-likelihood function
-#'   \item \code{auc} Area under curve
-#'   \item \code{aucpr} Area under PR curve
-#'   \item \code{merror} Exact matching error, used to evaluate multi-class classification
-#' }
-#' @param obj customized objective function. Returns gradient and second order
-#'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
-#'        \code{list(metric='metric-name', value='metric-value')} with given
-#'        prediction and dtrain.
-#' @param stratified a \code{boolean} indicating whether sampling of folds should be stratified
-#'        by the values of outcome labels.
-#' @param folds \code{list} provides a possibility to use a list of pre-defined CV folds
-#'        (each element must be a vector of test fold's indices). When folds are supplied,
-#'        the \code{nfold} and \code{stratified} parameters are ignored.
-#' @param verbose \code{boolean}, print the statistics during the process
-#' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
-#'        Default is 1 which means all messages are printed. This parameter is passed to the
-#'        \code{\link{cb.print.evaluation}} callback.
-#' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
-#'        If set to an integer \code{k}, training with a validation set will stop if the performance
-#'        doesn't improve for \code{k} rounds.
-#'        Setting this parameter engages the \code{\link{cb.early.stop}} callback.
-#' @param maximize If \code{feval} and \code{early_stopping_rounds} are set,
-#'        then this parameter must be set as well.
-#'        When it is \code{TRUE}, it means the larger the evaluation score the better.
-#'        This parameter is passed to the \code{\link{cb.early.stop}} callback.
-#' @param callbacks a list of callback functions to perform various task during boosting.
-#'        See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
-#'        parameters' values. User can provide either existing or their own callback methods in order
-#'        to customize the training process.
-#' @param ... other parameters to pass to \code{params}.
-#'
-#' @details
-#' The original sample is randomly partitioned into \code{nfold} equal size subsamples.
-#'
-#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
-#'
-#' The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
-#'
-#' All observations are used for both training and validation.
-#'
-#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
-#'
-#' @return
-#' An object of class \code{xgb.cv.synchronous} with the following elements:
-#' \itemize{
-#'   \item \code{call} a function call.
-#'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not
-#'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
-#'   \item \code{callbacks} callback functions that were either automatically assigned or
-#'         explicitly passed.
-#'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
-#'         first column corresponding to iteration number and the rest corresponding to the
-#'         CV-based evaluation means and standard deviations for the training and test CV-sets.
-#'         It is created by the \code{\link{cb.evaluation.log}} callback.
-#'   \item \code{niter} number of boosting iterations.
-#'   \item \code{nfeatures} number of features in training data.
-#'   \item \code{folds} the list of CV folds' indices - either those passed through the \code{folds}
-#'         parameter or randomly generated.
-#'   \item \code{best_iteration} iteration number with the best evaluation metric value
-#'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
-#'   \item \code{pred} CV prediction values available when \code{prediction} is set.
-#'         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-#'   \item \code{models} a liost of the CV folds' models. It is only available with the explicit
-#'         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
-#' }
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-#' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-#'                   max_depth = 3, eta = 1, objective = "binary:logistic")
-#' print(cv)
-#' print(cv, verbose=TRUE)
-#'
-#' @export
-xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NA,
-                   prediction = FALSE, showsd = TRUE, metrics=list(),
-                   obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
-                   verbose = TRUE, print_every_n=1L,
-                   early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...) {
-
-  check.deprecation(...)
-
-  params <- check.booster.params(params, ...)
-  # TODO: should we deprecate the redundant 'metrics' parameter?
-  for (m in metrics)
-    params <- c(params, list("eval_metric" = m))
-
-  check.custom.obj()
-  check.custom.eval()
-
-  #if (is.null(params[['eval_metric']]) && is.null(feval))
-  #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
-
-  # Check the labels
-  if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
-       (!inherits(data, 'xgb.DMatrix') && is.null(label)))
-    stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
-
-  # CV folds
-  if(!is.null(folds)) {
-    if(!is.list(folds) || length(folds) < 2)
-      stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
-    nfold <- length(folds)
-  } else {
-    if (nfold <= 1)
-      stop("'nfold' must be > 1")
-    folds <- generate.cv.folds(nfold, nrow(data), stratified, label, params)
-  }
-
-  # Potential TODO: sequential CV
-  #if (strategy == 'sequential')
-  #  stop('Sequential CV strategy is not yet implemented')
-
-  # verbosity & evaluation printing callback:
-  params <- c(params, list(silent = 1))
-  print_every_n <- max( as.integer(print_every_n), 1L)
-  if (!has.callbacks(callbacks, 'cb.print.evaluation') && verbose) {
-    callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n, showsd = showsd))
-  }
-  # evaluation log callback: always is on in CV
-  evaluation_log <- list()
-  if (!has.callbacks(callbacks, 'cb.evaluation.log')) {
-    callbacks <- add.cb(callbacks, cb.evaluation.log())
-  }
-  # Early stopping callback
-  stop_condition <- FALSE
-  if (!is.null(early_stopping_rounds) &&
-      !has.callbacks(callbacks, 'cb.early.stop')) {
-    callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
-                                                 maximize = maximize, verbose = verbose))
-  }
-  # CV-predictions callback
-  if (prediction &&
-      !has.callbacks(callbacks, 'cb.cv.predict')) {
-    callbacks <- add.cb(callbacks, cb.cv.predict(save_models = FALSE))
-  }
-  # Sort the callbacks into categories
-  cb <- categorize.callbacks(callbacks)
-
-
-  # create the booster-folds
-  dall <- xgb.get.DMatrix(data, label, missing)
-  bst_folds <- lapply(seq_along(folds), function(k) {
-    dtest  <- slice(dall, folds[[k]])
-    dtrain <- slice(dall, unlist(folds[-k]))
-    handle <- xgb.Booster.handle(params, list(dtrain, dtest))
-    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test=dtest), index = folds[[k]])
-  })
-  rm(dall)
-  # a "basket" to collect some results from callbacks
-  basket <- list()
-
-  # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
-  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
-
-  # those are fixed for CV (no training continuation)
-  begin_iteration <- 1
-  end_iteration <- nrounds
-
-  # synchronous CV boosting: run CV folds' models within each iteration
-  for (iteration in begin_iteration:end_iteration) {
-
-    for (f in cb$pre_iter) f()
-
-    msg <- lapply(bst_folds, function(fd) {
-      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
-      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
-    })
-    msg <- simplify2array(msg)
-    bst_evaluation <- rowMeans(msg)
-    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
-
-    for (f in cb$post_iter) f()
-
-    if (stop_condition) break
-  }
-  for (f in cb$finalize) f(finalize = TRUE)
-
-  # the CV result
-  ret <- list(
-    call = match.call(),
-    params = params,
-    callbacks = callbacks,
-    evaluation_log = evaluation_log,
-    niter = end_iteration,
-    nfeatures = ncol(data),
-    folds = folds
-  )
-  ret <- c(ret, basket)
-
-  class(ret) <- 'xgb.cv.synchronous'
-  invisible(ret)
-}
-
-
-
-#' Print xgb.cv result
-#'
-#' Prints formatted results of \code{xgb.cv}.
-#'
-#' @param x an \code{xgb.cv.synchronous} object
-#' @param verbose whether to print detailed data
-#' @param ... passed to \code{data.table.print}
-#'
-#' @details
-#' When not verbose, it would only print the evaluation results,
-#' including the best iteration (when available).
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' cv <- xgb.cv(data = train$data, label = train$label, nfold = 5, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' print(cv)
-#' print(cv, verbose=TRUE)
-#'
-#' @rdname print.xgb.cv
-#' @method print xgb.cv.synchronous
-#' @export
-print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
-  cat('##### xgb.cv ', length(x$folds), '-folds\n', sep = '')
-
-  if (verbose) {
-    if (!is.null(x$call)) {
-      cat('call:\n  ')
-      print(x$call)
-    }
-    if (!is.null(x$params)) {
-      cat('params (as set within xgb.cv):\n')
-      cat( '  ',
-           paste(names(x$params),
-                 paste0('"', unlist(x$params), '"'),
-                 sep = ' = ', collapse = ', '), '\n', sep = '')
-    }
-    if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
-      cat('callbacks:\n')
-      lapply(callback.calls(x$callbacks), function(x) {
-        cat('  ')
-        print(x)
-      })
-    }
-
-    for (n in c('niter', 'best_iteration', 'best_ntreelimit')) {
-      if (is.null(x[[n]]))
-        next
-      cat(n, ': ', x[[n]], '\n', sep = '')
-    }
-
-    if (!is.null(x$pred)) {
-      cat('pred:\n')
-      str(x$pred)
-    }
-  }
-
-  if (verbose)
-    cat('evaluation_log:\n')
-  print(x$evaluation_log, row.names = FALSE, ...)
-
-  if (!is.null(x$best_iteration)) {
-    cat('Best iteration:\n')
-    print(x$evaluation_log[x$best_iteration], row.names = FALSE, ...)
-  }
-  invisible(x)
-}

R-package/R/xgb.dump.R

@@ -1,72 +0,0 @@
-#' Dump an xgboost model in text format.
-#' 
-#' Dump an xgboost model in text format.
-#' 
-#' @param model the model object.
-#' @param fname the name of the text file where to save the model text dump. 
-#'        If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.
-#' @param fmap feature map file representing feature types.
-#'        Detailed description could be found at 
-#'        \url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
-#'        See demo/ for walkthrough example in R, and
-#'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt} 
-#'        for example Format.
-#' @param with_stats whether to dump some additional statistics about the splits.
-#'        When this option is on, the model dump contains two additional values:
-#'        gain is the approximate loss function gain we get in each split;
-#'        cover is the sum of second order gradient in each node.
-#' @param dump_format either 'text' or 'json' format could be specified.
-#' @param ... currently not used
-#'
-#' @return
-#' If fname is not provided or set to \code{NULL} the function will return the model
-#' as a \code{character} vector. Otherwise it will return \code{TRUE}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' # save the model in file 'xgb.model.dump'
-#' dump_path = file.path(tempdir(), 'model.dump')
-#' xgb.dump(bst, dump_path, with_stats = TRUE)
-#' 
-#' # print the model without saving it to a file
-#' print(xgb.dump(bst, with_stats = TRUE))
-#' 
-#' # print in JSON format:
-#' cat(xgb.dump(bst, with_stats = TRUE, dump_format='json'))
-#' 
-#' @export
-xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
-                     dump_format = c("text", "json"), ...) {
-  check.deprecation(...)
-  dump_format <- match.arg(dump_format)
-  if (!inherits(model, "xgb.Booster"))
-    stop("model: argument must be of type xgb.Booster")
-  if (!(is.null(fname) || is.character(fname)))
-    stop("fname: argument must be a character string (when provided)")
-  if (!(is.null(fmap) || is.character(fmap)))
-    stop("fmap: argument must be a character string (when provided)")
-  
-  model <- xgb.Booster.complete(model)
-  model_dump <- .Call(XGBoosterDumpModel_R, model$handle, NVL(fmap, "")[1], as.integer(with_stats),
-                      as.character(dump_format))
-
-  if (is.null(fname)) 
-    model_dump <- stri_replace_all_regex(model_dump, '\t', '')
-  
-  if (dump_format == "text")
-    model_dump <- unlist(stri_split_regex(model_dump, '\n'))
-  
-  model_dump <- grep('^\\s*$', model_dump, invert = TRUE, value = TRUE)
-  
-  if (is.null(fname)) {
-    return(model_dump)
-  } else {
-    writeLines(model_dump, fname[1])
-    return(TRUE)
-  }
-}

R-package/R/xgb.ggplot.R

@@ -1,135 +0,0 @@
-# ggplot backend for the xgboost plotting facilities
-
-
-#' @rdname xgb.plot.importance
-#' @export
-xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL, 
-                                  rel_to_first = FALSE, n_clusters = c(1:10), ...) {
-  
-  importance_matrix <- xgb.plot.importance(importance_matrix, top_n = top_n, measure = measure,
-                                           rel_to_first = rel_to_first, plot = FALSE, ...)
-  if (!requireNamespace("ggplot2", quietly = TRUE)) {
-    stop("ggplot2 package is required", call. = FALSE)
-  }
-  if (!requireNamespace("Ckmeans.1d.dp", quietly = TRUE)) {
-    stop("Ckmeans.1d.dp package is required", call. = FALSE)
-  }
-  
-  clusters <- suppressWarnings(
-    Ckmeans.1d.dp::Ckmeans.1d.dp(importance_matrix$Importance, n_clusters)
-  )
-  importance_matrix[, Cluster := as.character(clusters$cluster)]
-
-  plot <-
-    ggplot2::ggplot(importance_matrix, 
-                    ggplot2::aes(x = factor(Feature, levels = rev(Feature)), y = Importance, width = 0.5),
-                    environment = environment()) + 
-    ggplot2::geom_bar(ggplot2::aes(fill = Cluster), stat = "identity", position = "identity") + 
-    ggplot2::coord_flip() + 
-    ggplot2::xlab("Features") + 
-    ggplot2::ggtitle("Feature importance") + 
-    ggplot2::theme(plot.title = ggplot2::element_text(lineheight = .9, face = "bold"), 
-                   panel.grid.major.y = ggplot2::element_blank())
-  return(plot)
-}
-
-
-#' @rdname xgb.plot.deepness
-#' @export
-xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.depth", "med.weight")) {
-
-  if (!requireNamespace("ggplot2", quietly = TRUE))
-    stop("ggplot2 package is required for plotting the graph deepness.", call. = FALSE)
-
-  which <- match.arg(which)
-  
-  dt_depths <- xgb.plot.deepness(model = model, plot = FALSE)
-  dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
-  setkey(dt_summaries, 'Depth')
-
-  if (which == "2x1") {
-    p1 <-
-      ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = N), stat = "Identity") +
-      ggplot2::xlab("") +
-      ggplot2::ylab("Number of leafs") +
-      ggplot2::ggtitle("Model complexity") +
-      ggplot2::theme(
-        plot.title = ggplot2::element_text(lineheight = 0.9, face = "bold"),
-        panel.grid.major.y = ggplot2::element_blank(),
-        axis.ticks = ggplot2::element_blank(),
-        axis.text.x = ggplot2::element_blank()
-      )
-  
-    p2 <- 
-      ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") + 
-      ggplot2::xlab("Leaf depth") +
-      ggplot2::ylab("Weighted cover")
-  
-    multiplot(p1, p2, cols = 1)
-    return(invisible(list(p1, p2)))
-    
-  } else if (which == "max.depth") {
-    p <-
-      ggplot2::ggplot(dt_depths[, max(Depth), Tree]) +
-      ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
-      ggplot2::xlab("tree #") +
-      ggplot2::ylab("Max tree leaf depth")
-    return(p)
-    
-  } else if (which == "med.depth") {
-    p <-
-      ggplot2::ggplot(dt_depths[, median(as.numeric(Depth)), Tree]) +
-      ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
-      ggplot2::xlab("tree #") +
-      ggplot2::ylab("Median tree leaf depth")
-    return(p)
-
-  } else if (which == "med.weight") {
-    p <-
-      ggplot2::ggplot(dt_depths[, median(abs(Weight)), Tree]) +
-      ggplot2::geom_point(ggplot2::aes(x = Tree, y = V1),
-                          alpha=0.4, size=3, stroke=0) + 
-      ggplot2::xlab("tree #") +
-      ggplot2::ylab("Median absolute leaf weight")
-    return(p)
-  }
-}
-
-# Plot multiple ggplot graph aligned by rows and columns.
-# ... the plots
-# cols number of columns
-# internal utility function
-multiplot <- function(..., cols = 1) {
-  plots <- list(...)
-  num_plots = length(plots)
-  
-  layout <- matrix(seq(1, cols * ceiling(num_plots / cols)),
-                   ncol = cols, nrow = ceiling(num_plots / cols))
-  
-  if (num_plots == 1) {
-    print(plots[[1]])
-  } else {
-    grid::grid.newpage()
-    grid::pushViewport(grid::viewport(layout = grid::grid.layout(nrow(layout), ncol(layout))))
-    for (i in 1:num_plots) {
-      # Get the i,j matrix positions of the regions that contain this subplot
-      matchidx <- as.data.table(which(layout == i, arr.ind = TRUE))
-      
-      print(
-        plots[[i]], vp = grid::viewport(
-          layout.pos.row = matchidx$row,
-          layout.pos.col = matchidx$col
-        )
-      )
-    }
-  }
-}
-
-globalVariables(c(
-  "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight"
-))

R-package/R/xgb.importance.R

@@ -1,139 +0,0 @@
-#' Importance of features in a model.
-#' 
-#' Creates a \code{data.table} of feature importances in a model.
-#' 
-#' @param feature_names character vector of feature names. If the model already
-#'       contains feature names, those would be used when \code{feature_names=NULL} (default value).
-#'       Non-null \code{feature_names} could be provided to override those in the model.
-#' @param model object of class \code{xgb.Booster}.
-#' @param trees (only for the gbtree booster) an integer vector of tree indices that should be included
-#'          into the importance calculation. If set to \code{NULL}, all trees of the model are parsed.
-#'          It could be useful, e.g., in multiclass classification to get feature importances 
-#'          for each class separately. IMPORTANT: the tree index in xgboost models
-#'          is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
-#' @param data deprecated.
-#' @param label deprecated.
-#' @param target deprecated.
-#'
-#' @details 
-#' 
-#' This function works for both linear and tree models.
-#' 
-#' For linear models, the importance is the absolute magnitude of linear coefficients. 
-#' For that reason, in order to obtain a meaningful ranking by importance for a linear model, 
-#' the features need to be on the same scale (which you also would want to do when using either 
-#' L1 or L2 regularization).
-#' 
-#' @return
-#' 
-#' For a tree model, a \code{data.table} with the following columns:
-#' \itemize{
-#'   \item \code{Features} names of the features used in the model;
-#'   \item \code{Gain} represents fractional contribution of each feature to the model based on
-#'        the total gain of this feature's splits. Higher percentage means a more important 
-#'        predictive feature.
-#'   \item \code{Cover} metric of the number of observation related to this feature;
-#'   \item \code{Frequency} percentage representing the relative number of times
-#'        a feature have been used in trees.
-#' }
-#' 
-#' A linear model's importance \code{data.table} has the following columns:
-#' \itemize{
-#'   \item \code{Features} names of the features used in the model;
-#'   \item \code{Weight} the linear coefficient of this feature;
-#'   \item \code{Class} (only for multiclass models) class label.
-#' }
-#' 
-#' If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names}, 
-#' index of the features will be used instead. Because the index is extracted from the model dump
-#' (based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
-#' 
-#' @examples
-#' 
-#' # binomial classification using gbtree:
-#' data(agaricus.train, package='xgboost')
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' xgb.importance(model = bst)
-#' 
-#' # binomial classification using gblinear:
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear", 
-#'                eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
-#' xgb.importance(model = bst)
-#' 
-#' # multiclass classification using gbtree:
-#' nclass <- 3
-#' nrounds <- 10
-#' mbst <- xgboost(data = as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1,
-#'                max_depth = 3, eta = 0.2, nthread = 2, nrounds = nrounds,
-#'                objective = "multi:softprob", num_class = nclass)
-#' # all classes clumped together:
-#' xgb.importance(model = mbst)
-#' # inspect importances separately for each class:
-#' xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
-#' xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
-#' xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
-#' 
-#' # multiclass classification using gblinear:
-#' mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
-#'                booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
-#'                objective = "multi:softprob", num_class = nclass)
-#' xgb.importance(model = mbst)
-#'
-#' @export
-xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
-                           data = NULL, label = NULL, target = NULL){
-  
-  if (!(is.null(data) && is.null(label) && is.null(target)))
-    warning("xgb.importance: parameters 'data', 'label' and 'target' are deprecated")
-  
-  if (!inherits(model, "xgb.Booster"))
-    stop("model: must be an object of class xgb.Booster")
-  
-  if (is.null(feature_names) && !is.null(model$feature_names))
-    feature_names <- model$feature_names
-  
-  if (!(is.null(feature_names) || is.character(feature_names)))
-    stop("feature_names: Has to be a character vector")
-
-  model_text_dump <- xgb.dump(model = model, with_stats = TRUE)
-  
-  # linear model
-  if(model_text_dump[2] == "bias:"){
-    weights <- which(model_text_dump == "weight:") %>%
-               {model_text_dump[(. + 1):length(model_text_dump)]} %>%
-               as.numeric
-    
-    num_class <- NVL(model$params$num_class, 1)
-    if(is.null(feature_names)) 
-      feature_names <- seq(to = length(weights) / num_class) - 1
-    if (length(feature_names) * num_class != length(weights))
-      stop("feature_names length does not match the number of features used in the model")
-    
-    result <- if (num_class == 1) {
-      data.table(Feature = feature_names, Weight = weights)[order(-abs(Weight))]
-    } else {
-      data.table(Feature = rep(feature_names, each = num_class),
-                 Weight = weights,
-                 Class = seq_len(num_class) - 1)[order(Class, -abs(Weight))]
-    }
-  } else { 
-  # tree model
-    result <- xgb.model.dt.tree(feature_names = feature_names,
-                                text = model_text_dump,
-                                trees = trees)[
-      Feature != "Leaf", .(Gain = sum(Quality), 
-                           Cover = sum(Cover), 
-                           Frequency = .N), by = Feature][
-      ,`:=`(Gain = Gain / sum(Gain), 
-            Cover = Cover / sum(Cover),
-            Frequency = Frequency / sum(Frequency))][
-      order(Gain, decreasing = TRUE)]
-  }
-  result
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(c(".", ".N", "Gain", "Cover", "Frequency", "Feature", "Class"))

R-package/R/xgb.load.R

@@ -1,46 +0,0 @@
-#' Load xgboost model from binary file
-#' 
-#' Load xgboost model from the binary model file. 
-#' 
-#' @param modelfile the name of the binary input file.
-#' 
-#' @details 
-#' The input file is expected to contain a model saved in an xgboost-internal binary format
-#' using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some 
-#' appropriate methods from other xgboost interfaces. E.g., a model trained in Python and 
-#' saved from there in xgboost format, could be loaded from R.
-#' 
-#' Note: a model saved as an R-object, has to be loaded using corresponding R-methods,
-#' not \code{xgb.load}.
-#' 
-#' @return 
-#' An object of \code{xgb.Booster} class.
-#' 
-#' @seealso 
-#' \code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}. 
-#' 
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' xgb.save(bst, 'xgb.model')
-#' bst <- xgb.load('xgb.model')
-#' pred <- predict(bst, test$data)
-#' @export
-xgb.load <- function(modelfile) {
-  if (is.null(modelfile))
-    stop("xgb.load: modelfile cannot be NULL")
-
-  handle <- xgb.Booster.handle(modelfile = modelfile)
-  # re-use modelfile if it is raw so we do not need to serialize
-  if (typeof(modelfile) == "raw") {
-    bst <- xgb.handleToBooster(handle, modelfile)
-  } else {
-    bst <- xgb.handleToBooster(handle, NULL)
-  }
-  bst <- xgb.Booster.complete(bst, saveraw = TRUE)
-  return(bst)
-}

R-package/R/xgb.model.dt.tree.R

@@ -1,159 +0,0 @@
-#' Parse a boosted tree model text dump
-#' 
-#' Parse a boosted tree model text dump into a \code{data.table} structure.
-#' 
-#' @param feature_names character vector of feature names. If the model already
-#'          contains feature names, those would be used when \code{feature_names=NULL} (default value).
-#'          Non-null \code{feature_names} could be provided to override those in the model.
-#' @param model object of class \code{xgb.Booster}
-#' @param text \code{character} vector previously generated by the \code{xgb.dump} 
-#'          function  (where parameter \code{with_stats = TRUE} should have been set).
-#'          \code{text} takes precedence over \code{model}.
-#' @param trees an integer vector of tree indices that should be parsed.
-#'          If set to \code{NULL}, all trees of the model are parsed.
-#'          It could be useful, e.g., in multiclass classification to get only
-#'          the trees of one certain class. IMPORTANT: the tree index in xgboost models
-#'          is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
-#' @param use_int_id a logical flag indicating whether nodes in columns "Yes", "No", "Missing" should be
-#'          represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).
-#' @param ... currently not used.
-#'
-#' @return 
-#' A \code{data.table} with detailed information about model trees' nodes.
-#'
-#' The columns of the \code{data.table} are:
-#' 
-#' \itemize{
-#'  \item \code{Tree}: integer ID of a tree in a model (zero-based index)
-#'  \item \code{Node}: integer ID of a node in a tree (zero-based index)
-#'  \item \code{ID}: character identifier of a node in a model (only when \code{use_int_id=FALSE})
-#'  \item \code{Feature}: for a branch node, it's a feature id or name (when available);
-#'              for a leaf note, it simply labels it as \code{'Leaf'}
-#'  \item \code{Split}: location of the split for a branch node (split condition is always "less than")
-#'  \item \code{Yes}: ID of the next node when the split condition is met
-#'  \item \code{No}: ID of the next node when the split condition is not met
-#'  \item \code{Missing}: ID of the next node when branch value is missing
-#'  \item \code{Quality}: either the split gain (change in loss) or the leaf value
-#'  \item \code{Cover}: metric related to the number of observation either seen by a split
-#'                      or collected by a leaf during training.
-#' } 
-#' 
-#' When \code{use_int_id=FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
-#' in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from 
-#' the corresponding trees in the "Node" column.
-#' 
-#' @examples
-#' # Basic use:
-#' 
-#' data(agaricus.train, package='xgboost')
-#' 
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' 
-#' (dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
-#' 
-#' # This bst model already has feature_names stored with it, so those would be used when 
-#' # feature_names is not set:
-#' (dt <- xgb.model.dt.tree(model = bst))
-#' 
-#' # How to match feature names of splits that are following a current 'Yes' branch:
-#' 
-#' merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
-#'  
-#' @export
-xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
-                              trees = NULL, use_int_id = FALSE, ...){
-  check.deprecation(...)
-  
-  if (!inherits(model, "xgb.Booster") && !is.character(text)) {
-    stop("Either 'model' must be an object of class xgb.Booster\n",
-         "  or 'text' must be a character vector with the result of xgb.dump\n",
-         "  (or NULL if 'model' was provided).")
-  }
-  
-  if (is.null(feature_names) && !is.null(model) && !is.null(model$feature_names))
-    feature_names <- model$feature_names
-  
-  if (!(is.null(feature_names) || is.character(feature_names))) {
-    stop("feature_names: must be a character vector")
-  }
-  
-  if (!(is.null(trees) || is.numeric(trees))) {
-    stop("trees: must be a vector of integers.")
-  }
-  
-  if (is.null(text)){
-    text <- xgb.dump(model = model, with_stats = TRUE)
-  }
-  
-  if (length(text) < 2 ||
-      sum(stri_detect_regex(text, 'yes=(\\d+),no=(\\d+)')) < 1) {
-    stop("Non-tree model detected! This function can only be used with tree models.")
-  }
-  
-  position <- which(!is.na(stri_match_first_regex(text, "booster")))
-  
-  add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
-  
-  anynumber_regex <- "[-+]?[0-9]*\\.?[0-9]+([eE][-+]?[0-9]+)?"
-  
-  td <- data.table(t = text)
-  td[position, Tree := 1L]
-  td[, Tree := cumsum(ifelse(is.na(Tree), 0L, Tree)) - 1L]
-  
-  if (is.null(trees)) {
-    trees <- 0:max(td$Tree)
-  } else {
-    trees <- trees[trees >= 0 & trees <= max(td$Tree)]
-  }
-  td <- td[Tree %in% trees & !grepl('^booster', t)]
-  
-  td[, Node := stri_match_first_regex(t, "(\\d+):")[,2] %>% as.integer ]
-  if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
-
-  # parse branch lines
-  branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
-                      "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
-  td[isLeaf == FALSE, 
-     (branch_cols) := {
-      # skip some indices with spurious capture groups from anynumber_regex
-      xtr <- stri_match_first_regex(t, branch_rx)[, c(2,3,5,6,7,8,10), drop = FALSE]
-      xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-      lapply(seq_len(ncol(xtr)), function(i) xtr[,i])
-    }]
-  # assign feature_names when available
-  if (!is.null(feature_names)) {
-    if (length(feature_names) <= max(as.numeric(td$Feature), na.rm = TRUE))
-      stop("feature_names has less elements than there are features used in the model")
-    td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1] ]
-  }
-  
-  # parse leaf lines
-  leaf_rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  leaf_cols <- c("Feature", "Quality", "Cover")
-  td[isLeaf == TRUE,
-     (leaf_cols) := {
-      xtr <- stri_match_first_regex(t, leaf_rx)[, c(2,4)]
-      c("Leaf", lapply(seq_len(ncol(xtr)), function(i) xtr[,i]))
-    }]
-  
-  # convert some columns to numeric
-  numeric_cols <- c("Split", "Quality", "Cover")
-  td[, (numeric_cols) := lapply(.SD, as.numeric), .SDcols = numeric_cols]
-  if (use_int_id) {
-    int_cols <- c("Yes", "No", "Missing")
-    td[, (int_cols) := lapply(.SD, as.integer), .SDcols = int_cols]
-  }
-  
-  td[, t := NULL]
-  td[, isLeaf := NULL]
-  
-  td[order(Tree, Node)]
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf",".SD", ".SDcols"))

R-package/R/xgb.plot.deepness.R

@@ -1,150 +0,0 @@
-#' Plot model trees deepness
-#'
-#' Visualizes distributions related to depth of tree leafs.
-#' \code{xgb.plot.deepness} uses base R graphics, while \code{xgb.ggplot.deepness} uses the ggplot backend.
-#' 
-#' @param model either an \code{xgb.Booster} model generated by the \code{xgb.train} function
-#'        or a data.table result of the \code{xgb.model.dt.tree} function.
-#' @param plot (base R barplot) whether a barplot should be produced. 
-#'        If FALSE, only a data.table is returned.
-#' @param which which distribution to plot (see details).
-#' @param ... other parameters passed to \code{barplot} or \code{plot}.
-#' 
-#' @details
-#' 
-#' When \code{which="2x1"}, two distributions with respect to the leaf depth
-#' are plotted on top of each other:
-#' \itemize{
-#'  \item the distribution of the number of leafs in a tree model at a certain depth;
-#'  \item the distribution of average weighted number of observations ("cover") 
-#'        ending up in leafs at certain depth.
-#' }
-#' Those could be helpful in determining sensible ranges of the \code{max_depth} 
-#' and \code{min_child_weight} parameters.
-#' 
-#' When \code{which="max.depth"} or \code{which="med.depth"}, plots of either maximum or median depth
-#' per tree with respect to tree number are created. And \code{which="med.weight"} allows to see how
-#' a tree's median absolute leaf weight changes through the iterations.
-#'
-#' This function was inspired by the blog post
-#' \url{https://github.com/aysent/random-forest-leaf-visualization}.
-#' 
-#' @return
-#' 
-#' Other than producing plots (when \code{plot=TRUE}), the \code{xgb.plot.deepness} function
-#' silently returns a processed data.table where each row corresponds to a terminal leaf in a tree model,
-#' and contains information about leaf's depth, cover, and weight (which is used in calculating predictions).
-#' 
-#' The \code{xgb.ggplot.deepness} silently returns either a list of two ggplot graphs when \code{which="2x1"}
-#' or a single ggplot graph for the other \code{which} options.
-#'
-#' @seealso 
-#' 
-#' \code{\link{xgb.train}}, \code{\link{xgb.model.dt.tree}}.
-#' 
-#' @examples
-#' 
-#' data(agaricus.train, package='xgboost')
-#'
-#' # Change max_depth to a higher number to get a more significant result
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 6,
-#'                eta = 0.1, nthread = 2, nrounds = 50, objective = "binary:logistic",
-#'                subsample = 0.5, min_child_weight = 2)
-#'
-#' xgb.plot.deepness(bst)
-#' xgb.ggplot.deepness(bst)
-#' 
-#' xgb.plot.deepness(bst, which='max.depth', pch=16, col=rgb(0,0,1,0.3), cex=2)
-#' 
-#' xgb.plot.deepness(bst, which='med.weight', pch=16, col=rgb(0,0,1,0.3), cex=2)
-#'
-#' @rdname xgb.plot.deepness
-#' @export
-xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.depth", "med.weight"),
-                              plot = TRUE, ...) {
-  
-  if (!(inherits(model, "xgb.Booster") || is.data.table(model)))
-    stop("model: Has to be either an xgb.Booster model generaged by the xgb.train function\n",
-         "or a data.table result of the xgb.importance function")
-
-  if (!requireNamespace("igraph", quietly = TRUE))
-    stop("igraph package is required for plotting the graph deepness.", call. = FALSE)
-
-  which <- match.arg(which)
-  
-  dt_tree <- model
-  if (inherits(model, "xgb.Booster"))
-    dt_tree <- xgb.model.dt.tree(model = model)
-  
-  if (!all(c("Feature", "Tree", "ID", "Yes", "No", "Cover") %in% colnames(dt_tree)))
-    stop("Model tree columns are not as expected!\n",
-         "  Note that this function works only for tree models.")
-  
-  dt_depths <- merge(get.leaf.depth(dt_tree), dt_tree[, .(ID, Cover, Weight = Quality)], by = "ID")
-  setkeyv(dt_depths, c("Tree", "ID"))
-  # count by depth levels, and also calculate average cover at a depth
-  dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
-  setkey(dt_summaries, "Depth")
-  
-  if (plot) {
-    if (which == "2x1") {
-      op <- par(no.readonly = TRUE)
-      par(mfrow = c(2,1),
-          oma = c(3,1,3,1) + 0.1,
-          mar = c(1,4,1,0) + 0.1)
-
-      dt_summaries[, barplot(N, border = NA, ylab = 'Number of leafs', ...)]
-
-      dt_summaries[, barplot(Cover, border = NA, ylab = "Weighted cover", names.arg = Depth, ...)]
-    
-      title("Model complexity", xlab = "Leaf depth", outer = TRUE, line = 1)
-      par(op)
-    } else if (which == "max.depth") {
-      dt_depths[, max(Depth), Tree][
-                , plot(jitter(V1, amount = 0.1) ~ Tree, ylab = 'Max tree leaf depth', xlab = "tree #", ...)]
-    } else if (which == "med.depth") {
-      dt_depths[, median(as.numeric(Depth)), Tree][
-                , plot(jitter(V1, amount = 0.1) ~ Tree, ylab = 'Median tree leaf depth', xlab = "tree #", ...)]
-    } else if (which == "med.weight") {
-      dt_depths[, median(abs(Weight)), Tree][
-                , plot(V1 ~ Tree, ylab = 'Median absolute leaf weight', xlab = "tree #", ...)]
-    }
-  }
-  invisible(dt_depths)
-}
-
-# Extract path depths from root to leaf
-# from data.table containing the nodes and edges of the trees.
-# internal utility function
-get.leaf.depth <- function(dt_tree) {
-  # extract tree graph's edges
-  dt_edges <- rbindlist(list(
-      dt_tree[Feature != "Leaf", .(ID, To = Yes, Tree)],
-      dt_tree[Feature != "Leaf", .(ID, To = No, Tree)]
-    ))
-  # whether "To" is a leaf:
-  dt_edges <- 
-    merge(dt_edges,
-          dt_tree[Feature == "Leaf", .(ID, Leaf = TRUE)],
-          all.x = TRUE, by.x = "To", by.y = "ID")
-  dt_edges[is.na(Leaf), Leaf := FALSE]
-
-  dt_edges[, {
-    graph <- igraph::graph_from_data_frame(.SD[,.(ID, To)])
-    # min(ID) in a tree is a root node
-    paths_tmp <- igraph::shortest_paths(graph, from = min(ID), to = To[Leaf == TRUE])
-    # list of paths to each leaf in a tree
-    paths <- lapply(paths_tmp$vpath, names)
-    # combine into a resulting path lengths table for a tree
-    data.table(Depth = sapply(paths, length), ID = To[Leaf == TRUE])
-  }, by = Tree]
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(
-  c(
-    ".N", "N", "Depth", "Quality", "Cover", "Tree", "ID", "Yes", "No", "Feature", "Leaf", "Weight"
-  )
-)

R-package/R/xgb.plot.importance.R

@@ -1,125 +0,0 @@
-#' Plot feature importance as a bar graph
-#'
-#' Represents previously calculated feature importance as a bar graph.
-#' \code{xgb.plot.importance} uses base R graphics, while \code{xgb.ggplot.importance} uses the ggplot backend.
-#'
-#' @param importance_matrix a \code{data.table} returned by \code{\link{xgb.importance}}.
-#' @param top_n maximal number of top features to include into the plot.
-#' @param measure the name of importance measure to plot.
-#'        When \code{NULL}, 'Gain' would be used for trees and 'Weight' would be used for gblinear.
-#' @param rel_to_first whether importance values should be represented as relative to the highest ranked feature.
-#'        See Details.
-#' @param left_margin (base R barplot) allows to adjust the left margin size to fit feature names.
-#'        When it is NULL, the existing \code{par('mar')} is used.
-#' @param cex (base R barplot) passed as \code{cex.names} parameter to \code{barplot}.
-#' @param plot (base R barplot) whether a barplot should be produced.
-#'        If FALSE, only a data.table is returned.
-#' @param n_clusters (ggplot only) a \code{numeric} vector containing the min and the max range
-#'        of the possible number of clusters of bars.
-#' @param ... other parameters passed to \code{barplot} (except horiz, border, cex.names, names.arg, and las).
-#'
-#' @details
-#' The graph represents each feature as a horizontal bar of length proportional to the importance of a feature.
-#' Features are shown ranked in a decreasing importance order.
-#' It works for importances from both \code{gblinear} and \code{gbtree} models.
-#'
-#' When \code{rel_to_first = FALSE}, the values would be plotted as they were in \code{importance_matrix}.
-#' For gbtree model, that would mean being normalized to the total of 1
-#' ("what is feature's importance contribution relative to the whole model?").
-#' For linear models, \code{rel_to_first = FALSE} would show actual values of the coefficients.
-#' Setting \code{rel_to_first = TRUE} allows to see the picture from the perspective of
-#' "what is feature's importance contribution relative to the most important feature?"
-#'
-#' The ggplot-backend method also performs 1-D clustering of the importance values,
-#' with bar colors corresponding to different clusters that have somewhat similar importance values.
-#'
-#' @return
-#' The \code{xgb.plot.importance} function creates a \code{barplot} (when \code{plot=TRUE})
-#' and silently returns a processed data.table with \code{n_top} features sorted by importance.
-#'
-#' The \code{xgb.ggplot.importance} function returns a ggplot graph which could be customized afterwards.
-#' E.g., to change the title of the graph, add \code{+ ggtitle("A GRAPH NAME")} to the result.
-#'
-#' @seealso
-#' \code{\link[graphics]{barplot}}.
-#'
-#' @examples
-#' data(agaricus.train)
-#'
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' importance_matrix <- xgb.importance(colnames(agaricus.train$data), model = bst)
-#'
-#' xgb.plot.importance(importance_matrix, rel_to_first = TRUE, xlab = "Relative importance")
-#'
-#' (gg <- xgb.ggplot.importance(importance_matrix, measure = "Frequency", rel_to_first = TRUE))
-#' gg + ggplot2::ylab("Frequency")
-#'
-#' @rdname xgb.plot.importance
-#' @export
-xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
-                                rel_to_first = FALSE, left_margin = 10, cex = NULL, plot = TRUE, ...) {
-  check.deprecation(...)
-  if (!is.data.table(importance_matrix))  {
-    stop("importance_matrix: must be a data.table")
-  }
-
-  imp_names <- colnames(importance_matrix)
-  if (is.null(measure)) {
-    if (all(c("Feature", "Gain") %in% imp_names)) {
-      measure <- "Gain"
-    } else if (all(c("Feature", "Weight") %in% imp_names)) {
-      measure <- "Weight"
-    } else {
-      stop("Importance matrix column names are not as expected!")
-    }
-  } else {
-    if (!measure %in% imp_names)
-      stop("Invalid `measure`")
-    if (!"Feature" %in% imp_names)
-      stop("Importance matrix column names are not as expected!")
-  }
-
-  # also aggregate, just in case when the values were not yet summed up by feature
-  importance_matrix <- importance_matrix[, Importance := sum(get(measure)), by = Feature]
-
-  # make sure it's ordered
-  importance_matrix <- importance_matrix[order(-abs(Importance))]
-
-  if (!is.null(top_n)) {
-    top_n <- min(top_n, nrow(importance_matrix))
-    importance_matrix <- head(importance_matrix, top_n)
-  }
-  if (rel_to_first) {
-    importance_matrix[, Importance := Importance/max(abs(Importance))]
-  }
-  if (is.null(cex)) {
-    cex <- 2.5/log2(1 + nrow(importance_matrix))
-  }
-
-  if (plot) {
-    op <- par(no.readonly = TRUE)
-    mar <- op$mar
-    if (!is.null(left_margin))
-      mar[2] <- left_margin
-    par(mar = mar)
-
-    # reverse the order of rows to have the highest ranked at the top
-    importance_matrix[nrow(importance_matrix):1,
-                      barplot(Importance, horiz = TRUE, border = NA, cex.names = cex,
-                              names.arg = Feature, las = 1, ...)]
-    grid(NULL, NA)
-    # redraw over the grid
-    importance_matrix[nrow(importance_matrix):1,
-                      barplot(Importance, horiz = TRUE, border = NA, add = TRUE)]
-    par(op)
-  }
-
-  invisible(importance_matrix)
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(c("Feature", "Importance"))

R-package/R/xgb.plot.multi.trees.R

@@ -1,148 +0,0 @@
-#' Project all trees on one tree and plot it
-#'
-#' Visualization of the ensemble of trees as a single collective unit.
-#'
-#' @param model produced by the \code{xgb.train} function.
-#' @param feature_names names of each feature as a \code{character} vector.
-#' @param features_keep number of features to keep in each position of the multi trees.
-#' @param plot_width width in pixels of the graph to produce
-#' @param plot_height height in pixels of the graph to produce
-#' @param render a logical flag for whether the graph should be rendered (see Value).
-#' @param ... currently not used
-#' 
-#' @details
-#'
-#' This function tries to capture the complexity of a gradient boosted tree model
-#' in a cohesive way by compressing an ensemble of trees into a single tree-graph representation.
-#' The goal is to improve the interpretability of a model generally seen as black box.
-#'
-#' Note: this function is applicable to tree booster-based models only.
-#'
-#' It takes advantage of the fact that the shape of a binary tree is only defined by
-#' its depth (therefore, in a boosting model, all trees have similar shape).
-#'
-#' Moreover, the trees tend to reuse the same features.
-#'
-#' The function projects each tree onto one, and keeps for each position the
-#' \code{features_keep} first features (based on the Gain per feature measure).
-#'
-#' This function is inspired by this blog post:
-#' \url{https://wellecks.wordpress.com/2015/02/21/peering-into-the-black-box-visualizing-lambdamart/}
-#'
-#' @return
-#'
-#' When \code{render = TRUE}:
-#' returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
-#' Similar to ggplot objects, it needs to be printed to see it when not running from command line.
-#'
-#' When \code{render = FALSE}:
-#' silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
-#' This could be useful if one wants to modify some of the graph attributes
-#' before rendering the graph with \code{\link[DiagrammeR]{render_graph}}.
-#'
-#' @examples
-#'
-#' data(agaricus.train, package='xgboost')
-#'
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 15,
-#'                eta = 1, nthread = 2, nrounds = 30, objective = "binary:logistic",
-#'                min_child_weight = 50, verbose = 0)
-#'
-#' p <- xgb.plot.multi.trees(model = bst, features_keep = 3)
-#' print(p)
-#'
-#' \dontrun{
-#' # Below is an example of how to save this plot to a file.
-#' # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
-#' library(DiagrammeR)
-#' gr <- xgb.plot.multi.trees(model=bst, features_keep = 3, render=FALSE)
-#' export_graph(gr, 'tree.pdf', width=1500, height=600)
-#' }
-#'
-#' @export
-xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5, plot_width = NULL, plot_height = NULL,
-                                 render = TRUE, ...){
-  check.deprecation(...)
-  tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
-
-  # first number of the path represents the tree, then the following numbers are related to the path to follow
-  # root init
-  root.nodes <- tree.matrix[stri_detect_regex(ID, "\\d+-0"), ID]
-  tree.matrix[ID %in% root.nodes, abs.node.position := root.nodes]
-
-  precedent.nodes <- root.nodes
-
-  while(tree.matrix[,sum(is.na(abs.node.position))] > 0) {
-    yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
-    no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
-    yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
-    no.nodes.abs.pos <- no.row.nodes[, abs.node.position] %>% paste0("_1")
-    
-    tree.matrix[ID %in% yes.row.nodes[, Yes], abs.node.position := yes.nodes.abs.pos]
-    tree.matrix[ID %in% no.row.nodes[, No], abs.node.position := no.nodes.abs.pos]
-    precedent.nodes <- c(yes.nodes.abs.pos, no.nodes.abs.pos)
-  }
-  
-  tree.matrix[!is.na(Yes), Yes := paste0(abs.node.position, "_0")]
-  tree.matrix[!is.na(No), No := paste0(abs.node.position, "_1")]
-  
-  remove.tree <- . %>% stri_replace_first_regex(pattern = "^\\d+-", replacement = "")
-  
-  tree.matrix[,`:=`(abs.node.position = remove.tree(abs.node.position),
-                    Yes = remove.tree(Yes),
-                    No = remove.tree(No))]
-  
-  nodes.dt <- tree.matrix[
-        , .(Quality = sum(Quality))
-        , by = .(abs.node.position, Feature)
-      ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
-                          " (",
-                          format(Quality[1:min(length(Quality), features_keep)], digits=5),
-                          ")") %>%
-                   paste0(collapse = "\n"))
-        , by = abs.node.position]
-  
-  edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
-    list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>%
-    rbindlist() %>%
-    setnames(c("From", "To")) %>%
-    .[, .N, .(From, To)] %>%
-    .[, N:=NULL]
-  
-  nodes <- DiagrammeR::create_node_df(
-    n = nrow(nodes.dt),
-    label = nodes.dt[,Text]
-  )
-  
-  edges <- DiagrammeR::create_edge_df(
-    from = match(edges.dt[,From], nodes.dt[,abs.node.position]),
-    to = match(edges.dt[,To], nodes.dt[,abs.node.position]),
-    rel = "leading_to")
-  
-  graph <- DiagrammeR::create_graph(
-      nodes_df = nodes,
-      edges_df = edges,
-      attr_theme = NULL
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "graph",
-      attr  = c("layout", "rankdir"),
-      value = c("dot", "LR")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "node",
-      attr  = c("color", "fillcolor", "style", "shape", "fontname"),
-      value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "edge",
-      attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
-
-  if (!render) return(invisible(graph))
-
-  DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
-}
-
-globalVariables(c(".N", "N", "From", "To", "Text", "Feature", "no.nodes.abs.pos",
-                  "ID", "Yes", "No", "Tree", "yes.nodes.abs.pos", "abs.node.position"))

R-package/R/xgb.plot.shap.R

@@ -1,218 +0,0 @@
-#' SHAP contribution dependency plots
-#'
-#' Visualizing the SHAP feature contribution to prediction dependencies on feature value.
-#'
-#' @param data data as a \code{matrix} or \code{dgCMatrix}.
-#' @param shap_contrib a matrix of SHAP contributions that was computed earlier for the above
-#'          \code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.
-#' @param features a vector of either column indices or of feature names to plot. When it is NULL,
-#'          feature importance is calculated, and \code{top_n} high ranked features are taken.
-#' @param top_n when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.
-#' @param model an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-#'          or \code{features} is missing.
-#' @param trees passed to \code{\link{xgb.importance}} when \code{features = NULL}.
-#' @param target_class is only relevant for multiclass models. When it is set to a 0-based class index,
-#'          only SHAP contributions for that specific class are used.
-#'          If it is not set, SHAP importances are averaged over all classes.
-#' @param approxcontrib passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.
-#' @param subsample a random fraction of data points to use for plotting. When it is NULL,
-#'          it is set so that up to 100K data points are used.
-#' @param n_col a number of columns in a grid of plots.
-#' @param col color of the scatterplot markers.
-#' @param pch scatterplot marker.
-#' @param discrete_n_uniq a maximal number of unique values in a feature to consider it as discrete.
-#' @param discrete_jitter an \code{amount} parameter of jitter added to discrete features' positions.
-#' @param ylab a y-axis label in 1D plots.
-#' @param plot_NA whether the contributions of cases with missing values should also be plotted.
-#' @param col_NA a color of marker for missing value contributions.
-#' @param pch_NA a marker type for NA values.
-#' @param pos_NA a relative position of the x-location where NA values are shown:
-#'          \code{min(x) + (max(x) - min(x)) * pos_NA}.
-#' @param plot_loess whether to plot loess-smoothed curves. The smoothing is only done for features with
-#'          more than 5 distinct values.
-#' @param col_loess a color to use for the loess curves.
-#' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
-#' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
-#' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
-#' @param ... other parameters passed to \code{plot}.
-#'
-#' @details
-#'
-#' These scatterplots represent how SHAP feature contributions depend of feature values.
-#' The similarity to partial dependency plots is that they also give an idea for how feature values
-#' affect predictions. However, in partial dependency plots, we usually see marginal dependencies
-#' of model prediction on feature value, while SHAP contribution dependency plots display the estimated
-#' contributions of a feature to model prediction for each individual case.
-#'
-#' When \code{plot_loess = TRUE} is set, feature values are rounded to 3 significant digits and
-#' weighted LOESS is computed and plotted, where weights are the numbers of data points
-#' at each rounded value.
-#'
-#' Note: SHAP contributions are shown on the scale of model margin. E.g., for a logistic binomial objective,
-#' the margin is prediction before a sigmoidal transform into probability-like values.
-#' Also, since SHAP stands for "SHapley Additive exPlanation" (model prediction = sum of SHAP
-#' contributions for all features + bias), depending on the objective used, transforming SHAP
-#' contributions for a feature from the marginal to the prediction space is not necessarily
-#' a meaningful thing to do.
-#'
-#' @return
-#'
-#' In addition to producing plots (when \code{plot=TRUE}), it silently returns a list of two matrices:
-#' \itemize{
-#'  \item \code{data} the values of selected features;
-#'  \item \code{shap_contrib} the contributions of selected features.
-#' }
-#'
-#' @references
-#'
-#' Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
-#'
-#' Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
-#'
-#' @examples
-#'
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#'
-#' bst <- xgboost(agaricus.train$data, agaricus.train$label, nrounds = 50,
-#'                eta = 0.1, max_depth = 3, subsample = .5,
-#'                method = "hist", objective = "binary:logistic", nthread = 2, verbose = 0)
-#'
-#' xgb.plot.shap(agaricus.test$data, model = bst, features = "odor=none")
-#' contr <- predict(bst, agaricus.test$data, predcontrib = TRUE)
-#' xgb.plot.shap(agaricus.test$data, contr, model = bst, top_n = 12, n_col = 3)
-#'
-#' # multiclass example - plots for each class separately:
-#' nclass <- 3
-#' nrounds <- 20
-#' x <- as.matrix(iris[, -5])
-#' set.seed(123)
-#' is.na(x[sample(nrow(x) * 4, 30)]) <- TRUE # introduce some missing values
-#' mbst <- xgboost(data = x, label = as.numeric(iris$Species) - 1, nrounds = nrounds,
-#'                 max_depth = 2, eta = 0.3, subsample = .5, nthread = 2,
-#'                 objective = "multi:softprob", num_class = nclass, verbose = 0)
-#' trees0 <- seq(from=0, by=nclass, length.out=nrounds)
-#' col <- rgb(0, 0, 1, 0.5)
-#' xgb.plot.shap(x, model = mbst, trees = trees0, target_class = 0, top_n = 4,
-#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
-#' xgb.plot.shap(x, model = mbst, trees = trees0 + 1, target_class = 1, top_n = 4,
-#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
-#' xgb.plot.shap(x, model = mbst, trees = trees0 + 2, target_class = 2, top_n = 4,
-#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
-#'
-#' @rdname xgb.plot.shap
-#' @export
-xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1, model = NULL,
-                          trees = NULL, target_class = NULL, approxcontrib = FALSE,
-                          subsample = NULL, n_col = 1, col = rgb(0, 0, 1, 0.2), pch = '.',
-                          discrete_n_uniq = 5, discrete_jitter = 0.01, ylab = "SHAP",
-                          plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6), pch_NA = '.', pos_NA = 1.07,
-                          plot_loess = TRUE, col_loess = 2, span_loess = 0.5,
-                          which = c("1d", "2d"), plot = TRUE, ...) {
-
-  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
-    stop("data: must be either matrix or dgCMatrix")
-
-  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
-
-  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
-
-  if (!is.null(shap_contrib) &&
-      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
-    stop("shap_contrib is not compatible with the provided data")
-
-  nsample <- if (is.null(subsample)) min(100000, nrow(data)) else as.integer(subsample * nrow(data))
-  idx <- sample(1:nrow(data), nsample)
-  data <- data[idx,]
-
-  if (is.null(shap_contrib)) {
-    shap_contrib <- predict(model, data, predcontrib = TRUE, approxcontrib = approxcontrib)
-  } else {
-    shap_contrib <- shap_contrib[idx,]
-  }
-
-  which <- match.arg(which)
-  if (which == "2d")
-    stop("2D plots are not implemented yet")
-
-  if (is.null(features)) {
-    imp <- xgb.importance(model = model, trees = trees)
-    top_n <- as.integer(top_n[1])
-    if (top_n < 1 && top_n > 100)
-      stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[1:min(top_n, NROW(imp))]
-  }
-
-  if (is.character(features)) {
-    if (is.null(colnames(data)))
-      stop("Either provide `data` with column names or provide `features` as column indices")
-    features <- match(features, colnames(data))
-  }
-
-  if (n_col > length(features)) n_col <- length(features)
-
-  if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-    shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]]
-                    else Reduce("+", lapply(shap_contrib, abs))
-  }
-
-  shap_contrib <- shap_contrib[, features, drop = FALSE]
-  data <- data[, features, drop = FALSE]
-  cols <- colnames(data)
-  if (is.null(cols)) cols <- colnames(shap_contrib)
-  if (is.null(cols)) cols <- paste0('X', 1:ncol(data))
-  colnames(data) <- cols
-  colnames(shap_contrib) <- cols
-
-  if (plot && which == "1d") {
-    op <- par(mfrow = c(ceiling(length(features) / n_col), n_col),
-              oma = c(0,0,0,0) + 0.2,
-              mar = c(3.5,3.5,0,0) + 0.1,
-              mgp = c(1.7, 0.6, 0))
-    for (f in cols) {
-      ord <- order(data[, f])
-      x <- data[, f][ord]
-      y <- shap_contrib[, f][ord]
-      x_lim <- range(x, na.rm = TRUE)
-      y_lim <- range(y, na.rm = TRUE)
-      do_na <- plot_NA && any(is.na(x))
-      if (do_na) {
-        x_range <- diff(x_lim)
-        loc_na <- min(x, na.rm = TRUE) + x_range * pos_NA
-        x_lim <- range(c(x_lim, loc_na))
-      }
-      x_uniq <- unique(x)
-      x2plot <- x
-      # add small jitter for discrete features with <= 5 distinct values
-      if (length(x_uniq) <= discrete_n_uniq)
-        x2plot <- jitter(x, amount = discrete_jitter * min(diff(x_uniq), na.rm = TRUE))
-      plot(x2plot, y, pch = pch, xlab = f, col = col, xlim = x_lim, ylim = y_lim, ylab = ylab, ...)
-      grid()
-      if (plot_loess) {
-        # compress x to 3 digits, and mean-aggredate y
-        zz <- data.table(x = signif(x, 3), y)[, .(.N, y=mean(y)), x]
-        if (nrow(zz) <= 5) {
-          lines(zz$x, zz$y, col = col_loess)
-        } else {
-          lo <- stats::loess(y ~ x, data = zz, weights = zz$N, span = span_loess)
-          zz$y_lo <- predict(lo, zz, type = "link")
-          lines(zz$x, zz$y_lo, col = col_loess)
-        }
-      }
-      if (do_na) {
-        i_na <- which(is.na(x))
-        x_na <- rep(loc_na, length(i_na))
-        x_na <- jitter(x_na, amount = x_range * 0.01)
-        points(x_na, y[i_na], pch = pch_NA, col = col_NA)
-      }
-    }
-    par(op)
-  }
-  if (plot && which == "2d") {
-    # TODO
-    warning("Bivariate plotting is currently not available.")
-  }
-  invisible(list(data = data, shap_contrib = shap_contrib))
-}

R-package/R/xgb.plot.tree.R

@@ -1,138 +0,0 @@
-#' Plot a boosted tree model
-#' 
-#' Read a tree model text dump and plot the model. 
-#' 
-#' @param feature_names names of each feature as a \code{character} vector.
-#' @param model produced by the \code{xgb.train} function.
-#' @param trees an integer vector of tree indices that should be visualized.
-#'          If set to \code{NULL}, all trees of the model are included.
-#'          IMPORTANT: the tree index in xgboost model is zero-based
-#'          (e.g., use \code{trees = 0:2} for the first 3 trees in a model).
-#' @param plot_width  the width of the diagram in pixels.
-#' @param plot_height	the height of the diagram in pixels.
-#' @param render a logical flag for whether the graph should be rendered (see Value).
-#' @param show_node_id a logical flag for whether to show node id's in the graph.
-#' @param ... currently not used.
-#'
-#' @details 
-#' 
-#' The content of each node is organised that way:
-#' 
-#' \itemize{
-#'  \item Feature name.
-#'  \item \code{Cover}: The sum of second order gradient of training data classified to the leaf.
-#'        If it is square loss, this simply corresponds to the number of instances seen by a split
-#'        or collected by a leaf during training.
-#'        The deeper in the tree a node is, the lower this metric will be.
-#'  \item \code{Gain} (for split nodes): the information gain metric of a split
-#'        (corresponds to the importance of the node in the model).
-#'  \item \code{Value} (for leafs): the margin value that the leaf may contribute to prediction.
-#' } 
-#' The tree root nodes also indicate the Tree index (0-based).
-#' 
-#' The "Yes" branches are marked by the "< split_value" label.
-#' The branches that also used for missing values are marked as bold
-#' (as in "carrying extra capacity").
-#' 
-#' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
-#'  
-#' @return
-#' 
-#' When \code{render = TRUE}:
-#' returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
-#' Similar to ggplot objects, it needs to be printed to see it when not running from command line.
-#' 
-#' When \code{render = FALSE}:
-#' silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
-#' This could be useful if one wants to modify some of the graph attributes
-#' before rendering the graph with \code{\link[DiagrammeR]{render_graph}}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' 
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' # plot all the trees
-#' xgb.plot.tree(model = bst)
-#' # plot only the first tree and display the node ID:
-#' xgb.plot.tree(model = bst, trees = 0, show_node_id = TRUE)
-#' 
-#' \dontrun{
-#' # Below is an example of how to save this plot to a file. 
-#' # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
-#' library(DiagrammeR)
-#' gr <- xgb.plot.tree(model=bst, trees=0:1, render=FALSE)
-#' export_graph(gr, 'tree.pdf', width=1500, height=1900)
-#' export_graph(gr, 'tree.png', width=1500, height=1900)
-#' }
-#' 
-#' @export
-xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot_width = NULL, plot_height = NULL,
-                          render = TRUE, show_node_id = FALSE, ...){
-  check.deprecation(...)
-  if (!inherits(model, "xgb.Booster")) {
-    stop("model: Has to be an object of class xgb.Booster")
-  }
-
-  if (!requireNamespace("DiagrammeR", quietly = TRUE)) {
-    stop("DiagrammeR package is required for xgb.plot.tree", call. = FALSE)
-  }
-  
-  dt <- xgb.model.dt.tree(feature_names = feature_names, model = model, trees = trees)
-
-  dt[, label:= paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
-  if (show_node_id)
-    dt[, label := paste0(ID, ": ", label)]
-  dt[Node == 0, label := paste0("Tree ", Tree, "\n", label)]
-  dt[, shape:= "rectangle"][Feature == "Leaf", shape:= "oval"]
-  dt[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"]
-  # in order to draw the first tree on top:
-  dt <- dt[order(-Tree)]
-  
-  nodes <- DiagrammeR::create_node_df(
-    n         = nrow(dt),
-    ID        = dt$ID,
-    label     = dt$label,
-    fillcolor = dt$filledcolor,
-    shape     = dt$shape,
-    data      = dt$Feature,
-    fontcolor = "black")
-  
-  edges <- DiagrammeR::create_edge_df(
-    from  = match(dt[Feature != "Leaf", c(ID)] %>% rep(2), dt$ID),
-    to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-    label = dt[Feature != "Leaf", paste("<", Split)] %>%
-            c(rep("", nrow(dt[Feature != "Leaf"]))),
-    style = dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")] %>%
-            c(dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]),
-    rel   = "leading_to")
-
-  graph <- DiagrammeR::create_graph(
-      nodes_df = nodes,
-      edges_df = edges,
-      attr_theme = NULL
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "graph",
-      attr  = c("layout", "rankdir"),
-      value = c("dot", "LR")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "node",
-      attr  = c("color", "style", "fontname"),
-      value = c("DimGray", "filled", "Helvetica")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
-      attr_type = "edge",
-      attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
-  
-  if (!render) return(invisible(graph))
-  
-  DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(c("Feature", "ID", "Cover", "Quality", "Split", "Yes", "No", "Missing", ".", "shape", "filledcolor", "label"))

R-package/R/xgb.save.R

@@ -1,42 +0,0 @@
-#' Save xgboost model to binary file
-#' 
-#' Save xgboost model to a file in binary format.
-#' 
-#' @param model model object of \code{xgb.Booster} class.
-#' @param fname name of the file to write.
-#' 
-#' @details 
-#' This methods allows to save a model in an xgboost-internal binary format which is universal 
-#' among the various xgboost interfaces. In R, the saved model file could be read-in later
-#' using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter 
-#' of \code{\link{xgb.train}}.
-#' 
-#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
-#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
-#' corresponding R-methods would need to be used to load it.
-#' 
-#' @seealso 
-#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}. 
-#' 
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' xgb.save(bst, 'xgb.model')
-#' bst <- xgb.load('xgb.model')
-#' pred <- predict(bst, test$data)
-#' @export
-xgb.save <- function(model, fname) {
-  if (typeof(fname) != "character")
-    stop("fname must be character")
-  if (!inherits(model, "xgb.Booster")) {
-    stop("model must be xgb.Booster.",
-         if (inherits(model, "xgb.DMatrix")) " Use xgb.DMatrix.save to save an xgb.DMatrix object." else "")
-  }
-  model <- xgb.Booster.complete(model, saveraw = FALSE)
-  .Call(XGBoosterSaveModel_R, model$handle, fname[1])
-  return(TRUE)
-}

R-package/R/xgb.save.raw.R

@@ -1,23 +0,0 @@
-#' Save xgboost model to R's raw vector,
-#' user can call xgb.load to load the model back from raw vector
-#' 
-#' Save xgboost model from xgboost or xgb.train
-#' 
-#' @param model the model object.
-#' 
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' raw <- xgb.save.raw(bst)
-#' bst <- xgb.load(raw)
-#' pred <- predict(bst, test$data)
-#'
-#' @export
-xgb.save.raw <- function(model) {
-  model <- xgb.get.handle(model)
-  .Call(XGBoosterModelToRaw_R, model)
-}

R-package/R/xgb.train.R

@@ -1,372 +0,0 @@
-#' eXtreme Gradient Boosting Training
-#'
-#' \code{xgb.train} is an advanced interface for training an xgboost model.
-#' The \code{xgboost} function is a simpler wrapper for \code{xgb.train}.
-#'
-#' @param params the list of parameters.
-#'        The complete list of parameters is available at \url{http://xgboost.readthedocs.io/en/latest/parameter.html}.
-#'        Below is a shorter summary:
-#'
-#' 1. General Parameters
-#'
-#' \itemize{
-#'   \item \code{booster} which booster to use, can be \code{gbtree} or \code{gblinear}. Default: \code{gbtree}.
-#' }
-#'
-#' 2. Booster Parameters
-#'
-#' 2.1. Parameter for Tree Booster
-#'
-#' \itemize{
-#'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
-#'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
-#'   \item \code{max_depth} maximum depth of a tree. Default: 6
-#'   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
-#'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
-#'   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
-#'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
-#'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
-#'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
-#' }
-#'
-#' 2.2. Parameter for Linear Booster
-#'
-#' \itemize{
-#'   \item \code{lambda} L2 regularization term on weights. Default: 0
-#'   \item \code{lambda_bias} L2 regularization term on bias. Default: 0
-#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-#' }
-#'
-#' 3. Task Parameters
-#'
-#' \itemize{
-#' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
-#'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss (Default).
-#'     \item \code{reg:logistic} logistic regression.
-#'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
-#'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
-#'     \item \code{num_class} set the number of classes. To use only with multiclass objectives.
-#'     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
-#'     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
-#'     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
-#'   }
-#'   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
-#'   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
-#' }
-#'
-#' @param data training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
-#'        \code{xgboost}, in addition, also accepts \code{matrix}, \code{dgCMatrix}, or name of a local data file.
-#' @param nrounds max number of boosting iterations.
-#' @param watchlist named list of xgb.DMatrix datasets to use for evaluating model performance.
-#'        Metrics specified in either \code{eval_metric} or \code{feval} will be computed for each
-#'        of these datasets during each boosting iteration, and stored in the end as a field named
-#'        \code{evaluation_log} in the resulting object. When either \code{verbose>=1} or
-#'        \code{\link{cb.print.evaluation}} callback is engaged, the performance results are continuously
-#'        printed out during the training.
-#'        E.g., specifying \code{watchlist=list(validation1=mat1, validation2=mat2)} allows to track
-#'        the performance of each round's model on mat1 and mat2.
-#' @param obj customized objective function. Returns gradient and second order
-#'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
-#'        \code{list(metric='metric-name', value='metric-value')} with given
-#'        prediction and dtrain.
-#' @param verbose If 0, xgboost will stay silent. If 1, it will print information about performance.
-#'        If 2, some additional information will be printed out.
-#'        Note that setting \code{verbose > 0} automatically engages the
-#'        \code{cb.print.evaluation(period=1)} callback function.
-#' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
-#'        Default is 1 which means all messages are printed. This parameter is passed to the
-#'        \code{\link{cb.print.evaluation}} callback.
-#' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
-#'        If set to an integer \code{k}, training with a validation set will stop if the performance
-#'        doesn't improve for \code{k} rounds.
-#'        Setting this parameter engages the \code{\link{cb.early.stop}} callback.
-#' @param maximize If \code{feval} and \code{early_stopping_rounds} are set,
-#'        then this parameter must be set as well.
-#'        When it is \code{TRUE}, it means the larger the evaluation score the better.
-#'        This parameter is passed to the \code{\link{cb.early.stop}} callback.
-#' @param save_period when it is non-NULL, model is saved to disk after every \code{save_period} rounds,
-#'        0 means save at the end. The saving is handled by the \code{\link{cb.save.model}} callback.
-#' @param save_name the name or path for periodically saved model file.
-#' @param xgb_model a previously built model to continue the training from.
-#'        Could be either an object of class \code{xgb.Booster}, or its raw data, or the name of a
-#'        file with a previously saved model.
-#' @param callbacks a list of callback functions to perform various task during boosting.
-#'        See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
-#'        parameters' values. User can provide either existing or their own callback methods in order
-#'        to customize the training process.
-#' @param ... other parameters to pass to \code{params}.
-#' @param label vector of response values. Should not be provided when data is
-#'        a local data file name or an \code{xgb.DMatrix}.
-#' @param missing by default is set to NA, which means that NA values should be considered as 'missing'
-#'        by the algorithm. Sometimes, 0 or other extreme value might be used to represent missing values.
-#'        This parameter is only used when input is a dense matrix.
-#' @param weight a vector indicating the weight for each row of the input.
-#'
-#' @details
-#' These are the training functions for \code{xgboost}.
-#'
-#' The \code{xgb.train} interface supports advanced features such as \code{watchlist},
-#' customized objective and evaluation metric functions, therefore it is more flexible
-#' than the \code{xgboost} interface.
-#'
-#' Parallelization is automatically enabled if \code{OpenMP} is present.
-#' Number of threads can also be manually specified via \code{nthread} parameter.
-#'
-#' The evaluation metric is chosen automatically by Xgboost (according to the objective)
-#' when the \code{eval_metric} parameter is not provided.
-#' User may set one or several \code{eval_metric} parameters.
-#' Note that when using a customized metric, only this single metric can be used.
-#' The following is the list of built-in metrics for which Xgboost provides optimized implementation:
-#'   \itemize{
-#'      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
-#'      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
-#'      \item \code{mlogloss} multiclass logloss. \url{http://wiki.fast.ai/index.php/Log_Loss}
-#'      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
-#'            Different threshold (e.g., 0.) could be specified as "error@0."
-#'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'      \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
-#'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
-#'   }
-#'
-#' The following callbacks are automatically created when certain parameters are set:
-#' \itemize{
-#'   \item \code{cb.print.evaluation} is turned on when \code{verbose > 0};
-#'         and the \code{print_every_n} parameter is passed to it.
-#'   \item \code{cb.evaluation.log} is on when \code{watchlist} is present.
-#'   \item \code{cb.early.stop}: when \code{early_stopping_rounds} is set.
-#'   \item \code{cb.save.model}: when \code{save_period > 0} is set.
-#' }
-#'
-#' @return
-#' An object of class \code{xgb.Booster} with the following elements:
-#' \itemize{
-#'   \item \code{handle} a handle (pointer) to the xgboost model in memory.
-#'   \item \code{raw} a cached memory dump of the xgboost model saved as R's \code{raw} type.
-#'   \item \code{niter} number of boosting iterations.
-#'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
-#'         first column corresponding to iteration number and the rest corresponding to evaluation
-#'         metrics' values. It is created by the \code{\link{cb.evaluation.log}} callback.
-#'   \item \code{call} a function call.
-#'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not
-#'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
-#'   \item \code{callbacks} callback functions that were either automatically assigned or
-#'         explicitly passed.
-#'   \item \code{best_iteration} iteration number with the best evaluation metric value
-#'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
-#'   \item \code{best_score} the best evaluation metric value during early stopping.
-#'         (only available with early stopping).
-#'   \item \code{feature_names} names of the training dataset features
-#'         (only when column names were defined in training data).
-#'   \item \code{nfeatures} number of features in training data.
-#' }
-#'
-#' @seealso
-#' \code{\link{callbacks}},
-#' \code{\link{predict.xgb.Booster}},
-#' \code{\link{xgb.cv}}
-#'
-#' @references
-#'
-#' Tianqi Chen and Carlos Guestrin, "XGBoost: A Scalable Tree Boosting System",
-#' 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016, \url{https://arxiv.org/abs/1603.02754}
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#'
-#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-#' dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-#' watchlist <- list(train = dtrain, eval = dtest)
-#'
-#' ## A simple xgb.train example:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
-#'               objective = "binary:logistic", eval_metric = "auc")
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
-#'
-#'
-#' ## An xgb.train example where custom objective and evaluation metric are used:
-#' logregobj <- function(preds, dtrain) {
-#'    labels <- getinfo(dtrain, "label")
-#'    preds <- 1/(1 + exp(-preds))
-#'    grad <- preds - labels
-#'    hess <- preds * (1 - preds)
-#'    return(list(grad = grad, hess = hess))
-#' }
-#' evalerror <- function(preds, dtrain) {
-#'   labels <- getinfo(dtrain, "label")
-#'   err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-#'   return(list(metric = "error", value = err))
-#' }
-#'
-#' # These functions could be used by passing them either:
-#' #  as 'objective' and 'eval_metric' parameters in the params list:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
-#'               objective = logregobj, eval_metric = evalerror)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
-#'
-#' #  or through the ... arguments:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
-#'                  objective = logregobj, eval_metric = evalerror)
-#'
-#' #  or as dedicated 'obj' and 'feval' parameters of xgb.train:
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
-#'                  obj = logregobj, feval = evalerror)
-#'
-#'
-#' ## An xgb.train example of using variable learning rates at each iteration:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
-#'               objective = "binary:logistic", eval_metric = "auc")
-#' my_etas <- list(eta = c(0.5, 0.1))
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
-#'                  callbacks = list(cb.reset.parameters(my_etas)))
-#'
-#' ## Early stopping:
-#' bst <- xgb.train(param, dtrain, nrounds = 25, watchlist,
-#'                  early_stopping_rounds = 3)
-#'
-#' ## An 'xgboost' interface example:
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label,
-#'                max_depth = 2, eta = 1, nthread = 2, nrounds = 2,
-#'                objective = "binary:logistic")
-#' pred <- predict(bst, agaricus.test$data)
-#'
-#' @rdname xgb.train
-#' @export
-xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
-                      obj = NULL, feval = NULL, verbose = 1, print_every_n = 1L,
-                      early_stopping_rounds = NULL, maximize = NULL,
-                      save_period = NULL, save_name = "xgboost.model",
-                      xgb_model = NULL, callbacks = list(), ...) {
-
-  check.deprecation(...)
-
-  params <- check.booster.params(params, ...)
-
-  check.custom.obj()
-  check.custom.eval()
-
-  # data & watchlist checks
-  dtrain <- data
-  if (!inherits(dtrain, "xgb.DMatrix"))
-    stop("second argument dtrain must be xgb.DMatrix")
-  if (length(watchlist) > 0) {
-    if (typeof(watchlist) != "list" ||
-        !all(vapply(watchlist, inherits, logical(1), what = 'xgb.DMatrix')))
-      stop("watchlist must be a list of xgb.DMatrix elements")
-    evnames <- names(watchlist)
-    if (is.null(evnames) || any(evnames == ""))
-      stop("each element of the watchlist must have a name tag")
-  }
-
-  # evaluation printing callback
-  params <- c(params, list(silent = ifelse(verbose > 1, 0, 1)))
-  print_every_n <- max( as.integer(print_every_n), 1L)
-  if (!has.callbacks(callbacks, 'cb.print.evaluation') &&
-      verbose) {
-    callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n))
-  }
-  # evaluation log callback:  it is automatically enabled when watchlist is provided
-  evaluation_log <- list()
-  if (!has.callbacks(callbacks, 'cb.evaluation.log') &&
-      length(watchlist) > 0) {
-    callbacks <- add.cb(callbacks, cb.evaluation.log())
-  }
-  # Model saving callback
-  if (!is.null(save_period) &&
-      !has.callbacks(callbacks, 'cb.save.model')) {
-    callbacks <- add.cb(callbacks, cb.save.model(save_period, save_name))
-  }
-  # Early stopping callback
-  stop_condition <- FALSE
-  if (!is.null(early_stopping_rounds) &&
-      !has.callbacks(callbacks, 'cb.early.stop')) {
-    callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
-                                                 maximize = maximize, verbose = verbose))
-  }
-  # Sort the callbacks into categories
-  cb <- categorize.callbacks(callbacks)
-
-  # The tree updating process would need slightly different handling
-  is_update <- NVL(params[['process_type']], '.') == 'update'
-
-  # Construct a booster (either a new one or load from xgb_model)
-  handle <- xgb.Booster.handle(params, append(watchlist, dtrain), xgb_model)
-  bst <- xgb.handleToBooster(handle)
-
-  # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
-  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
-
-  # When the 'xgb_model' was set, find out how many boosting iterations it has
-  niter_init <- 0
-  if (!is.null(xgb_model)) {
-    niter_init <- as.numeric(xgb.attr(bst, 'niter')) + 1
-    if (length(niter_init) == 0) {
-      niter_init <- xgb.ntree(bst) %/% (num_parallel_tree * num_class)
-    }
-  }
-  if(is_update && nrounds > niter_init)
-    stop("nrounds cannot be larger than ", niter_init, " (nrounds of xgb_model)")
-
-  # TODO: distributed code
-  rank <- 0
-
-  niter_skip <- ifelse(is_update, 0, niter_init)
-  begin_iteration <- niter_skip + 1
-  end_iteration <- niter_skip + nrounds
-
-  # the main loop for boosting iterations
-  for (iteration in begin_iteration:end_iteration) {
-
-    for (f in cb$pre_iter) f()
-
-    xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
-
-    bst_evaluation <- numeric(0)
-    if (length(watchlist) > 0)
-      bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
-
-    xgb.attr(bst$handle, 'niter') <- iteration - 1
-
-    for (f in cb$post_iter) f()
-
-    if (stop_condition) break
-  }
-  for (f in cb$finalize) f(finalize = TRUE)
-
-  bst <- xgb.Booster.complete(bst, saveraw = TRUE)
-
-  # store the total number of boosting iterations
-  bst$niter = end_iteration
-
-  # store the evaluation results
-  if (length(evaluation_log) > 0 &&
-      nrow(evaluation_log) > 0) {
-    # include the previous compatible history when available
-    if (inherits(xgb_model, 'xgb.Booster') &&
-        !is_update &&
-        !is.null(xgb_model$evaluation_log) &&
-        isTRUE(all.equal(colnames(evaluation_log),
-                         colnames(xgb_model$evaluation_log)))) {
-      evaluation_log <- rbindlist(list(xgb_model$evaluation_log, evaluation_log))
-    }
-    bst$evaluation_log <- evaluation_log
-  }
-
-  bst$call <- match.call()
-  bst$params <- params
-  bst$callbacks <- callbacks
-  if (!is.null(colnames(dtrain)))
-    bst$feature_names <- colnames(dtrain)
-  bst$nfeatures <- ncol(dtrain)
-
-  return(bst)
-}

R-package/R/xgboost.R

@@ -1,113 +0,0 @@
-# Simple interface for training an xgboost model that wraps \code{xgb.train}.
-# Its documentation is combined with xgb.train.
-#
-#' @rdname xgb.train
-#' @export
-xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
-                    params = list(), nrounds,
-                    verbose = 1, print_every_n = 1L, 
-                    early_stopping_rounds = NULL, maximize = NULL, 
-                    save_period = NULL, save_name = "xgboost.model",
-                    xgb_model = NULL, callbacks = list(), ...) {
-
-  dtrain <- xgb.get.DMatrix(data, label, missing, weight)
-
-  watchlist <- list(train = dtrain)
-
-  bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, print_every_n = print_every_n,
-                   early_stopping_rounds = early_stopping_rounds, maximize = maximize,
-                   save_period = save_period, save_name = save_name,
-                   xgb_model = xgb_model, callbacks = callbacks, ...)
-  return(bst)
-}
-
-#' Training part from Mushroom Data Set
-#' 
-#' This data set is originally from the Mushroom data set,
-#' UCI Machine Learning Repository.
-#' 
-#' This data set includes the following fields:
-#' 
-#' \itemize{
-#'  \item \code{label} the label for each record
-#'  \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
-#' }
-#'
-#' @references
-#' https://archive.ics.uci.edu/ml/datasets/Mushroom
-#' 
-#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
-#' School of Information and Computer Science.
-#' 
-#' @docType data
-#' @keywords datasets
-#' @name agaricus.train
-#' @usage data(agaricus.train)
-#' @format A list containing a label vector, and a dgCMatrix object with 6513 
-#' rows and 127 variables
-NULL
-
-#' Test part from Mushroom Data Set
-#'
-#' This data set is originally from the Mushroom data set,
-#' UCI Machine Learning Repository.
-#' 
-#' This data set includes the following fields:
-#' 
-#' \itemize{
-#'  \item \code{label} the label for each record
-#'  \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
-#' }
-#'
-#' @references
-#' https://archive.ics.uci.edu/ml/datasets/Mushroom
-#' 
-#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
-#' School of Information and Computer Science.
-#' 
-#' @docType data
-#' @keywords datasets
-#' @name agaricus.test
-#' @usage data(agaricus.test)
-#' @format A list containing a label vector, and a dgCMatrix object with 1611 
-#' rows and 126 variables
-NULL
-
-# Various imports
-#' @importClassesFrom Matrix dgCMatrix dgeMatrix
-#' @importFrom Matrix colSums
-#' @importFrom Matrix sparse.model.matrix
-#' @importFrom Matrix sparseVector
-#' @importFrom Matrix sparseMatrix
-#' @importFrom Matrix t
-#' @importFrom data.table data.table
-#' @importFrom data.table is.data.table
-#' @importFrom data.table as.data.table
-#' @importFrom data.table :=
-#' @importFrom data.table rbindlist
-#' @importFrom data.table setkey
-#' @importFrom data.table setkeyv
-#' @importFrom data.table setnames
-#' @importFrom magrittr %>%
-#' @importFrom stringi stri_detect_regex
-#' @importFrom stringi stri_match_first_regex
-#' @importFrom stringi stri_replace_first_regex
-#' @importFrom stringi stri_replace_all_regex
-#' @importFrom stringi stri_split_regex
-#' @importFrom utils object.size str tail
-#' @importFrom stats predict
-#' @importFrom stats median
-#' @importFrom utils head
-#' @importFrom graphics barplot
-#' @importFrom graphics lines
-#' @importFrom graphics points
-#' @importFrom graphics grid
-#' @importFrom graphics par
-#' @importFrom graphics title
-#' @importFrom grDevices rgb
-#' 
-#' @import methods
-#' @useDynLib xgboost, .registration = TRUE
-NULL

R-package/README.md

@@ -1,33 +0,0 @@
-XGBoost R Package for Scalable GBM
-==================================
-
-[![CRAN Status Badge](http://www.r-pkg.org/badges/version/xgboost)](https://cran.r-project.org/web/packages/xgboost)
-[![CRAN Downloads](http://cranlogs.r-pkg.org/badges/xgboost)](https://cran.rstudio.com/web/packages/xgboost/index.html)
-[![Documentation Status](https://readthedocs.org/projects/xgboost/badge/?version=latest)](http://xgboost.readthedocs.org/en/latest/R-package/index.html)
-
-Resources
----------
-* [XGBoost R Package Online Documentation](http://xgboost.readthedocs.org/en/latest/R-package/index.html)
-  - Check this out for detailed documents, examples and tutorials.
-
-Installation
-------------
-
-We are [on CRAN](https://cran.r-project.org/web/packages/xgboost/index.html) now. For stable/pre-compiled(for Windows and OS X) version, please install from CRAN:
-
-```r
-install.packages('xgboost')
-```
-
-For more detailed installation instructions, please see [here](http://xgboost.readthedocs.org/en/latest/build.html#r-package-installation).
-
-Examples
---------
-
-* Please visit [walk through example](demo).
-* See also the [example scripts](../demo/kaggle-higgs) for Kaggle Higgs Challenge, including [speedtest script](../demo/kaggle-higgs/speedtest.R) on this dataset and the one related to [Otto challenge](../demo/kaggle-otto), including a [RMarkdown documentation](../demo/kaggle-otto/understandingXGBoostModel.Rmd).
-
-Development
------------
-
-* See the [R Package section](https://xgboost.readthedocs.io/en/latest/contribute.html#r-package) of the contributors guide.

R-package/cleanup

@@ -1,3 +0,0 @@
-#!/bin/sh
-
-rm -f src/Makevars

R-package/configure.ac

@@ -1,31 +0,0 @@
-### configure.ac					-*- Autoconf -*-
-
-AC_PREREQ(2.62)
-
-AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
-
-OPENMP_CXXFLAGS=""
-
-if test `uname -s` = "Linux"
-then
-  OPENMP_CXXFLAGS="\$(SHLIB_OPENMP_CXXFLAGS)"
-fi
-
-if test `uname -s` = "Darwin"
-then
-  OPENMP_CXXFLAGS="\$(SHLIB_OPENMP_CXXFLAGS)"
-  ac_pkg_openmp=no
-  AC_MSG_CHECKING([whether OpenMP will work in a package])
-  AC_LANG_CONFTEST(
-  [AC_LANG_PROGRAM([[#include <omp.h>]], [[ return omp_get_num_threads (); ]])])
-  PKG_CFLAGS="${OPENMP_CFLAGS}" PKG_LIBS="${OPENMP_CFLAGS}" "$RBIN" CMD SHLIB conftest.c 1>&AS_MESSAGE_LOG_FD 2>&AS_MESSAGE_LOG_FD && "$RBIN" --vanilla -q -e "dyn.load(paste('conftest',.Platform\$dynlib.ext,sep=''))" 1>&AS_MESSAGE_LOG_FD 2>&AS_MESSAGE_LOG_FD && ac_pkg_openmp=yes
-  AC_MSG_RESULT([${ac_pkg_openmp}])
-  if test "${ac_pkg_openmp}" = no; then
-    OPENMP_CXXFLAGS=''
-  fi
-fi
-
-AC_SUBST(OPENMP_CXXFLAGS)
-AC_CONFIG_FILES([src/Makevars])
-AC_OUTPUT
-

R-package/demo/00Index

@@ -1,15 +0,0 @@
-basic_walkthrough               Basic feature walkthrough
-caret_wrapper                   Use xgboost to train in caret library
-custom_objective                Cutomize loss function, and evaluation metric
-boost_from_prediction           Boosting from existing prediction
-predict_first_ntree             Predicting using first n trees
-generalized_linear_model        Generalized Linear Model
-cross_validation                Cross validation
-create_sparse_matrix            Create Sparse Matrix
-predict_leaf_indices            Predicting the corresponding leaves
-early_stopping                  Early Stop in training
-poisson_regression              Poisson Regression on count data
-tweedie_regression              Tweddie Regression
-gpu_accelerated                 GPU-accelerated tree building algorithms
-interaction_constraints         Interaction constraints among features
-

R-package/demo/README.md

@@ -1,20 +0,0 @@
-XGBoost R Feature Walkthrough
-====
-* [Basic walkthrough of wrappers](basic_walkthrough.R)
-* [Train a xgboost model from caret library](caret_wrapper.R)
-* [Cutomize loss function, and evaluation metric](custom_objective.R)
-* [Boosting from existing prediction](boost_from_prediction.R)
-* [Predicting using first n trees](predict_first_ntree.R)
-* [Generalized Linear Model](generalized_linear_model.R)
-* [Cross validation](cross_validation.R)
-* [Create a sparse matrix from a dense one](create_sparse_matrix.R)
-* [Use GPU-accelerated tree building algorithms](gpu_accelerated.R)
-
-Benchmarks
-====
-* [Starter script for Kaggle Higgs Boson](../../demo/kaggle-higgs)
- 
-Notes
-====
-* Contribution of examples, benchmarks is more than welcomed!
-* If you like to share how you use xgboost to solve your problem, send a pull request:)

R-package/demo/basic_walkthrough.R

@@ -1,112 +0,0 @@
-require(xgboost)
-require(methods)
-
-# we load in the agaricus dataset
-# In this example, we are aiming to predict whether a mushroom is edible
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-# the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
-class(train$label)
-class(train$data)
-
-#-------------Basic Training using XGBoost-----------------
-# this is the basic usage of xgboost you can put matrix in data field
-# note: we are putting in sparse matrix here, xgboost naturally handles sparse input
-# use sparse matrix when your feature is sparse(e.g. when you are using one-hot encoding vector)
-print("Training xgboost with sparseMatrix")
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic")
-# alternatively, you can put in dense matrix, i.e. basic R-matrix
-print("Training xgboost with Matrix")
-bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic")
-
-# you can also put in xgb.DMatrix object, which stores label, data and other meta datas needed for advanced features
-print("Training xgboost with xgb.DMatrix")
-dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2, 
-               objective = "binary:logistic")
-
-# Verbose = 0,1,2
-print("Train xgboost with verbose 0, no message")
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic", verbose = 0)
-print("Train xgboost with verbose 1, print evaluation metric")
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic", verbose = 1)
-print("Train xgboost with verbose 2, also print information about tree")
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic", verbose = 2)
-
-# you can also specify data as file path to a LibSVM format input
-# since we do not have this file with us, the following line is just for illustration
-# bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nrounds = 2,objective = "binary:logistic")
-
-#--------------------basic prediction using xgboost--------------
-# you can do prediction using the following line
-# you can put in Matrix, sparseMatrix, or xgb.DMatrix 
-pred <- predict(bst, test$data)
-err <- mean(as.numeric(pred > 0.5) != test$label)
-print(paste("test-error=", err))
-
-#-------------------save and load models-------------------------
-# save model to binary local file
-xgb.save(bst, "xgboost.model")
-# load binary model to R
-bst2 <- xgb.load("xgboost.model")
-pred2 <- predict(bst2, test$data)
-# pred2 should be identical to pred
-print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
-
-# save model to R's raw vector
-raw = xgb.save.raw(bst)
-# load binary model to R
-bst3 <- xgb.load(raw)
-pred3 <- predict(bst3, test$data)
-# pred3 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
-
-#----------------Advanced features --------------
-# to use advanced features, we need to put data in xgb.DMatrix
-dtrain <- xgb.DMatrix(data = train$data, label=train$label)
-dtest <- xgb.DMatrix(data = test$data, label=test$label)
-#---------------Using watchlist----------------
-# watchlist is a list of xgb.DMatrix, each of them is tagged with name
-watchlist <- list(train=dtrain, test=dtest)
-# to train with watchlist, use xgb.train, which contains more advanced features
-# watchlist allows us to monitor the evaluation result on all data in the list 
-print("Train xgboost using xgb.train with watchlist")
-bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
-                 nthread = 2, objective = "binary:logistic")
-# we can change evaluation metrics, or use multiple evaluation metrics
-print("train xgboost using xgb.train with watchlist, watch logloss and error")
-bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
-                 eval_metric = "error", eval_metric = "logloss",
-                 nthread = 2, objective = "binary:logistic")
-
-# xgb.DMatrix can also be saved using xgb.DMatrix.save
-xgb.DMatrix.save(dtrain, "dtrain.buffer")
-# to load it in, simply call xgb.DMatrix
-dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data=dtrain2, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
-                 nthread = 2, objective = "binary:logistic")
-# information can be extracted from xgb.DMatrix using getinfo
-label = getinfo(dtest, "label")
-pred <- predict(bst, dtest)
-err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
-print(paste("test-error=", err))
-
-# You can dump the tree you learned using xgb.dump into a text file
-dump_path = file.path(tempdir(), 'dump.raw.txt')
-xgb.dump(bst, dump_path, with_stats = T)
-
-# Finally, you can check which features are the most important.
-print("Most important features (look at column Gain):")
-imp_matrix <- xgb.importance(feature_names = colnames(train$data), model = bst)
-print(imp_matrix)
-
-# Feature importance bar plot by gain
-print("Feature importance Plot : ")
-print(xgb.plot.importance(importance_matrix = imp_matrix))

R-package/demo/boost_from_prediction.R

@@ -1,26 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-
-watchlist <- list(eval = dtest, train = dtrain)
-###
-# advanced: start from a initial base prediction
-#
-print('start running example to start from a initial prediction')
-# train xgboost for 1 round
-param <- list(max_depth=2, eta=1, nthread = 2, silent=1, objective='binary:logistic')
-bst <- xgb.train(param, dtrain, 1, watchlist)
-# Note: we need the margin value instead of transformed prediction in set_base_margin
-# do predict with output_margin=TRUE, will always give you margin values before logistic transformation
-ptrain <- predict(bst, dtrain, outputmargin=TRUE)
-ptest  <- predict(bst, dtest, outputmargin=TRUE)
-# set the base_margin property of dtrain and dtest
-# base margin is the base prediction we will boost from
-setinfo(dtrain, "base_margin", ptrain)
-setinfo(dtest, "base_margin", ptest)
-
-print('this is result of boost from initial prediction')
-bst <- xgb.train(params = param, data = dtrain, nrounds = 1, watchlist = watchlist)

R-package/demo/caret_wrapper.R

@@ -1,35 +0,0 @@
-# install development version of caret library that contains xgboost models
-devtools::install_github("topepo/caret/pkg/caret") 
-require(caret)
-require(xgboost)
-require(data.table)
-require(vcd)
-require(e1071)
-
-# Load Arthritis dataset in memory.
-data(Arthritis)
-# Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = F)
-
-# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[,AgeDiscret:= as.factor(round(Age/10,0))]
-
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
-
-# We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[,ID:=NULL]
-
-#-------------Basic Training using XGBoost in caret Library-----------------
-# Set up control parameters for caret::train
-# Here we use 10-fold cross-validation, repeating twice, and using random search for tuning hyper-parameters.
-fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 2, search = "random")
-# train a xgbTree model using caret::train
-model <- train(factor(Improved)~., data = df, method = "xgbTree", trControl = fitControl)
-
-# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model using xgbLinear
-# model <- train(factor(Improved)~., data = df, method = "xgbLinear", trControl = fitControl)
-
-# See model results
-print(model)

R-package/demo/create_sparse_matrix.R

@@ -1,89 +0,0 @@
-require(xgboost)
-require(Matrix)
-require(data.table)
-if (!require(vcd)) {
-  install.packages('vcd') #Available in Cran. Used for its dataset with categorical values.
-  require(vcd)
-}
-# According to its documentation, Xgboost works only on numbers.
-# Sometimes the dataset we have to work on have categorical data. 
-# A categorical variable is one which have a fixed number of values. By example, if for each observation a variable called "Colour" can have only "red", "blue" or "green" as value, it is a categorical variable.
-#
-# In R, categorical variable is called Factor. 
-# Type ?factor in console for more information.
-#
-# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in Xgboost.
-# The method we are going to see is usually called "one hot encoding".
-
-#load Arthritis dataset in memory.
-data(Arthritis)
-
-# create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = F)
-
-# Let's have a look to the data.table
-cat("Print the dataset\n")
-print(df)
-
-# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values wich can be ordered, here: None > Some > Marked).
-cat("Structure of the dataset\n")
-str(df)
-
-# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
-
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[,AgeDiscret:= as.factor(round(Age/10,0))]
-
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
-
-# We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[,ID:=NULL]
-
-# List the different values for the column Treatment: Placebo, Treated.
-cat("Values of the categorical feature Treatment\n")
-print(levels(df[,Treatment]))
-
-# Next step, we will transform the categorical data to dummy variables.
-# This method is also called one hot encoding.
-# The purpose is to transform each value of each categorical feature in one binary feature.
-#
-# Let's take, the column Treatment will be replaced by two columns, Placebo, and Treated. Each of them will be binary. For example an observation which had the value Placebo in column Treatment before the transformation will have, after the transformation, the value 1 in the new column Placebo and the value 0 in the new column  Treated.
-#
-# Formulae Improved~.-1 used below means transform all categorical features but column Improved to binary values.
-# Column Improved is excluded because it will be our output column, the one we want to predict.
-sparse_matrix = sparse.model.matrix(Improved~.-1, data = df)
-
-cat("Encoding of the sparse Matrix\n")
-print(sparse_matrix)
-
-# Create the output vector (not sparse)
-# 1. Set, for all rows, field in Y column to 0; 
-# 2. set Y to 1 when Improved == Marked; 
-# 3. Return Y column
-output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
-
-# Following is the same process as other demo
-cat("Learning...\n")
-bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 9,
-               eta = 1, nthread = 2, nrounds = 10, objective = "binary:logistic")
-
-importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst)
-print(importance)
-# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age. The second most important feature is having received a placebo or not. The sex is third. Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
-
-# Does these result make sense?
-# Let's check some Chi2 between each of these features and the outcome.
-
-print(chisq.test(df$Age, df$Y))
-# Pearson correlation between Age and illness disappearing is 35
-
-print(chisq.test(df$AgeDiscret, df$Y))
-# Our first simplification of Age gives a Pearson correlation of 8.
-
-print(chisq.test(df$AgeCat, df$Y))
-# The perfectly random split I did between young and old at 30 years old have a low correlation of 2. It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that), but  for the illness we are studying, the age to be vulnerable is not the same. Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
-
-# As you can see, in general destroying information by simplifying it won't improve your model. Chi2 just demonstrates that. But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model. The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
-# However it's almost always worse when you add some arbitrary rules.
-# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.

R-package/demo/cross_validation.R

@@ -1,51 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-
-nrounds <- 2
-param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
-
-cat('running cross validation\n')
-# do cross validation, this will print result out as
-# [iteration]  metric_name:mean_value+std_value
-# std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold=5, metrics={'error'})
-
-cat('running cross validation, disable standard deviation display\n')
-# do cross validation, this will print result out as
-# [iteration]  metric_name:mean_value+std_value
-# std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold=5,
-       metrics='error', showsd = FALSE)
-
-###
-# you can also do cross validation with cutomized loss function
-# See custom_objective.R
-##
-print ('running cross validation, with cutomsized loss function')
-
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(metric = "error", value = err))
-}
-
-param <- list(max_depth=2, eta=1, silent=1,
-              objective = logregobj, eval_metric = evalerror)
-# train with customized objective
-xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)
-
-# do cross validation with prediction values for each fold
-res <- xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5, prediction = TRUE)
-res$evaluation_log
-length(res$pred)

R-package/demo/custom_objective.R

@@ -1,65 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-
-# note: for customized objective function, we leave objective as default
-# note: what we are getting is margin value in prediction
-# you must know what you are doing
-watchlist <- list(eval = dtest, train = dtrain)
-num_round <- 2
-
-# user define objective function, given prediction, return gradient and second order gradient
-# this is loglikelihood loss
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-
-# user defined evaluation function, return a pair metric_name, result
-# NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
-# Take this in mind when you use the customization, and maybe you need write customized evaluation function
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(metric = "error", value = err))
-}
-
-param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
-              objective=logregobj, eval_metric=evalerror)
-print ('start training with user customized objective')
-# training with customized objective, we can also do step by step training
-# simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, watchlist)
-
-#
-# there can be cases where you want additional information 
-# being considered besides the property of DMatrix you can get by getinfo
-# you can set additional information as attributes if DMatrix
-
-# set label attribute of dtrain to be label, we use label as an example, it can be anything 
-attr(dtrain, 'label') <- getinfo(dtrain, 'label')
-# this is new customized objective, where you can access things you set
-# same thing applies to customized evaluation function
-logregobjattr <- function(preds, dtrain) {
-  # now you can access the attribute in customized function
-  labels <- attr(dtrain, 'label')
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
-              objective=logregobjattr, eval_metric=evalerror)
-print ('start training with user customized objective, with additional attributes in DMatrix')
-# training with customized objective, we can also do step by step training
-# simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, watchlist)

R-package/demo/early_stopping.R

@@ -1,40 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-# note: for customized objective function, we leave objective as default
-# note: what we are getting is margin value in prediction
-# you must know what you are doing
-param <- list(max_depth=2, eta=1, nthread=2, verbosity=0)
-watchlist <- list(eval = dtest)
-num_round <- 20
-# user define objective function, given prediction, return gradient and second order gradient
-# this is loglikelihood loss
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-# user defined evaluation function, return a pair metric_name, result
-# NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
-# Take this in mind when you use the customization, and maybe you need write customized evaluation function
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(metric = "error", value = err))
-}
-print ('start training with early Stopping setting')
-
-bst <- xgb.train(param, dtrain, num_round, watchlist,
-                 objective = logregobj, eval_metric = evalerror, maximize = FALSE,
-                 early_stopping_round = 3)
-bst <- xgb.cv(param, dtrain, num_round, nfold = 5,
-              objective = logregobj, eval_metric = evalerror,
-              maximize = FALSE, early_stopping_rounds = 3)

R-package/demo/generalized_linear_model.R

@@ -1,34 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-##
-#  this script demonstrate how to fit generalized linear model in xgboost
-#  basically, we are using linear model, instead of tree for our boosters
-#  you can fit a linear regression, or logistic regression model
-##
-
-# change booster to gblinear, so that we are fitting a linear model
-# alpha is the L1 regularizer 
-# lambda is the L2 regularizer
-# you can also set lambda_bias which is L2 regularizer on the bias term
-param <- list(objective = "binary:logistic", booster = "gblinear",
-              nthread = 2, alpha = 0.0001, lambda = 1)
-
-# normally, you do not need to set eta (step_size)
-# XGBoost uses a parallel coordinate descent algorithm (shotgun), 
-# there could be affection on convergence with parallelization on certain cases
-# setting eta to be smaller value, e.g 0.5 can make the optimization more stable
-
-##
-# the rest of settings are the same
-##
-watchlist <- list(eval = dtest, train = dtrain)
-num_round <- 2
-bst <- xgb.train(param, dtrain, num_round, watchlist)
-ypred <- predict(bst, dtest)
-labels <- getinfo(dtest, 'label')
-cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
-

R-package/demo/gpu_accelerated.R

@@ -1,45 +0,0 @@
-# An example of using GPU-accelerated tree building algorithms
-# 
-# NOTE: it can only run if you have a CUDA-enable GPU and the package was 
-#       specially compiled with GPU support.
-#
-# For the current functionality, see 
-# https://xgboost.readthedocs.io/en/latest/gpu/index.html
-#
-
-library('xgboost')
-
-# Simulate N x p random matrix with some binomial response dependent on pp columns
-set.seed(111)
-N <- 1000000
-p <- 50
-pp <- 25
-X <- matrix(runif(N * p), ncol = p)
-betas <- 2 * runif(pp) - 1
-sel <- sort(sample(p, pp))
-m <- X[, sel] %*% betas - 1 + rnorm(N)
-y <- rbinom(N, 1, plogis(m))
-
-tr <- sample.int(N, N * 0.75)
-dtrain <- xgb.DMatrix(X[tr,], label = y[tr])
-dtest <- xgb.DMatrix(X[-tr,], label = y[-tr])
-wl <- list(train = dtrain, test = dtest)
-
-# An example of running 'gpu_hist' algorithm
-# which is
-# - similar to the 'hist'
-# - the fastest option for moderately large datasets
-# - current limitations: max_depth < 16, does not implement guided loss
-# You can use tree_method = 'gpu_exact' for another GPU accelerated algorithm,
-# which is slower, more memory-hungry, but does not use binning.
-param <- list(objective = 'reg:logistic', eval_metric = 'auc', subsample = 0.5, nthread = 4,
-              max_bin = 64, tree_method = 'gpu_hist')
-pt <- proc.time()
-bst_gpu <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
-proc.time() - pt
-
-# Compare to the 'hist' algorithm:
-param$tree_method <- 'hist'
-pt <- proc.time()
-bst_hist <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
-proc.time() - pt

R-package/demo/interaction_constraints.R

@@ -1,105 +0,0 @@
-library(xgboost)
-library(data.table)
-
-set.seed(1024)
-
-# Function to obtain a list of interactions fitted in trees, requires input of maximum depth
-treeInteractions <- function(input_tree, input_max_depth){
-  trees <- copy(input_tree)  # copy tree input to prevent overwriting
-  if (input_max_depth < 2) return(list())  # no interactions if max depth < 2
-  if (nrow(input_tree) == 1) return(list())
-
-  # Attach parent nodes
-  for (i in 2:input_max_depth){
-    if (i == 2) trees[, ID_merge:=ID] else trees[, ID_merge:=get(paste0('parent_',i-2))]
-    parents_left <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=Yes)]
-    parents_right <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=No)]
-
-    setorderv(trees, 'ID_merge')
-    setorderv(parents_left, 'ID_merge')
-    setorderv(parents_right, 'ID_merge')
-
-    trees <- merge(trees, parents_left, by='ID_merge', all.x=T)
-    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
-    trees[, c('i.id','i.feature'):=NULL]
-
-    trees <- merge(trees, parents_right, by='ID_merge', all.x=T)
-    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
-    trees[, c('i.id','i.feature'):=NULL]
-  }
-
-  # Extract nodes with interactions
-  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1), 
-                             c('Feature',paste0('parent_feat_',1:(input_max_depth-1))), with=F]
-  interaction_trees_split <- split(interaction_trees, 1:nrow(interaction_trees))
-  interaction_list <- lapply(interaction_trees_split, as.character)
-
-  # Remove NAs (no parent interaction)
-  interaction_list <- lapply(interaction_list, function(x) x[!is.na(x)])
-
-  # Remove non-interactions (same variable)
-  interaction_list <- lapply(interaction_list, unique)  # remove same variables
-  interaction_length <- sapply(interaction_list, length)
-  interaction_list <- interaction_list[interaction_length > 1]
-  interaction_list <- unique(lapply(interaction_list, sort))
-  return(interaction_list)
-}
-
-# Generate sample data
-x <- list()
-for (i in 1:10){
-  x[[i]] = i*rnorm(1000, 10)
-}
-x <- as.data.table(x)
-
-y = -1*x[, rowSums(.SD)] + x[['V1']]*x[['V2']] + x[['V3']]*x[['V4']]*x[['V5']] + rnorm(1000, 0.001) + 3*sin(x[['V7']])
-
-train = as.matrix(x)
-
-# Interaction constraint list (column names form)
-interaction_list <- list(c('V1','V2'),c('V3','V4','V5'))
-
-# Convert interaction constraint list into feature index form
-cols2ids <- function(object, col_names) {
-  LUT <- seq_along(col_names) - 1
-  names(LUT) <- col_names
-  rapply(object, function(x) LUT[x], classes="character", how="replace")
-}
-interaction_list_fid = cols2ids(interaction_list, colnames(train))
-
-# Fit model with interaction constraints
-bst = xgboost(data = train, label = y, max_depth = 4,
-              eta = 0.1, nthread = 2, nrounds = 1000,
-              interaction_constraints = interaction_list_fid)
-
-bst_tree <- xgb.model.dt.tree(colnames(train), bst)
-bst_interactions <- treeInteractions(bst_tree, 4)  # interactions constrained to combinations of V1*V2 and V3*V4*V5
-
-# Fit model without interaction constraints
-bst2 = xgboost(data = train, label = y, max_depth = 4,
-               eta = 0.1, nthread = 2, nrounds = 1000)
-
-bst2_tree <- xgb.model.dt.tree(colnames(train), bst2)
-bst2_interactions <- treeInteractions(bst2_tree, 4)  # much more interactions
-
-# Fit model with both interaction and monotonicity constraints
-bst3 = xgboost(data = train, label = y, max_depth = 4,
-               eta = 0.1, nthread = 2, nrounds = 1000,
-               interaction_constraints = interaction_list_fid,
-               monotone_constraints = c(-1,0,0,0,0,0,0,0,0,0))
-
-bst3_tree <- xgb.model.dt.tree(colnames(train), bst3)
-bst3_interactions <- treeInteractions(bst3_tree, 4)  # interactions still constrained to combinations of V1*V2 and V3*V4*V5
-
-# Show monotonic constraints still apply by checking scores after incrementing V1
-x1 <- sort(unique(x[['V1']]))
-for (i in 1:length(x1)){
-  testdata <- copy(x[, -c('V1')])
-  testdata[['V1']] <- x1[i]
-  testdata <- testdata[, paste0('V',1:10), with=F]
-  pred <- predict(bst3, as.matrix(testdata))
-  
-  # Should not print out anything due to monotonic constraints
-  if (i > 1) if (any(pred > prev_pred)) print(i)
-  prev_pred <- pred 
-}

R-package/demo/poisson_regression.R

@@ -1,7 +0,0 @@
-data(mtcars)
-head(mtcars)
-bst = xgboost(data=as.matrix(mtcars[,-11]),label=mtcars[,11],
-              objective='count:poisson',nrounds=5)
-pred = predict(bst,as.matrix(mtcars[,-11]))
-sqrt(mean((pred-mtcars[,11])^2))
-

R-package/demo/predict_first_ntree.R

@@ -1,23 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
-
-param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-watchlist <- list(eval = dtest, train = dtrain)
-nrounds = 2
-
-# training the model for two rounds
-bst = xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
-cat('start testing prediction from first n trees\n')
-labels <- getinfo(dtest,'label')
-
-### predict using first 1 tree
-ypred1 = predict(bst, dtest, ntreelimit=1)
-# by default, we predict using all the trees
-ypred2 = predict(bst, dtest)
-
-cat('error of ypred1=', mean(as.numeric(ypred1>0.5)!=labels),'\n')
-cat('error of ypred2=', mean(as.numeric(ypred2>0.5)!=labels),'\n')

R-package/demo/predict_leaf_indices.R

@@ -1,53 +0,0 @@
-require(xgboost)
-require(data.table)
-require(Matrix)
-
-set.seed(1982)
-
-# load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
-
-param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-nrounds = 4
-
-# training the model for two rounds
-bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
-
-# Model accuracy without new features
-accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
-
-# by default, we predict using all the trees
-
-pred_with_leaf = predict(bst, dtest, predleaf = TRUE)
-head(pred_with_leaf)
-
-create.new.tree.features <- function(model, original.features){
-  pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
-  cols <- list()
-  for(i in 1:model$niter){
-    # max is not the real max but it s not important for the purpose of adding features
-    leaf.id <- sort(unique(pred_with_leaf[,i]))
-    cols[[i]] <- factor(x = pred_with_leaf[,i], level = leaf.id)
-  }
-  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
-}
-
-# Convert previous features to one hot encoding
-new.features.train <- create.new.tree.features(bst, agaricus.train$data)
-new.features.test <- create.new.tree.features(bst, agaricus.test$data)
-colnames(new.features.test) <- colnames(new.features.train)
-
-# learning with new features
-new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
-new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
-watchlist <- list(train = new.dtrain)
-bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
-
-# Model accuracy with new features
-accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
-
-# Here the accuracy was already good and is now perfect.
-cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now", accuracy.after, "!\n"))

R-package/demo/runall.R

@@ -1,14 +0,0 @@
-# running all scripts in demo folder
-demo(basic_walkthrough)
-demo(custom_objective)
-demo(boost_from_prediction)
-demo(predict_first_ntree)
-demo(generalized_linear_model)
-demo(cross_validation)
-demo(create_sparse_matrix)
-demo(predict_leaf_indices)
-demo(early_stopping)
-demo(poisson_regression)
-demo(caret_wrapper)
-demo(tweedie_regression)
-#demo(gpu_accelerated) # can only run when built with GPU support

R-package/demo/tweedie_regression.R

@@ -1,49 +0,0 @@
-library(xgboost)
-library(data.table)
-library(cplm)
-
-data(AutoClaim)
-
-# auto insurance dataset analyzed by Yip and Yau (2005)
-dt <- data.table(AutoClaim)
-
-# exclude these columns from the model matrix
-exclude <-  c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
-
-# retains the missing values
-# NOTE: this dataset is comes ready out of the box
-options(na.action = 'na.pass')
-x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = F])
-options(na.action = 'na.omit')
-
-# response
-y <- dt[, CLM_AMT5]
-
-d_train <- xgb.DMatrix(data = x, label = y, missing = NA)
-
-# the tweedie_variance_power parameter determines the shape of 
-# distribution
-# - closer to 1 is more poisson like and the mass
-#   is more concentrated near zero 
-# - closer to 2 is more gamma like and the mass spreads to the 
-#   the right with less concentration near zero
-
-params <- list(
-  objective = 'reg:tweedie',
-  eval_metric = 'rmse', 
-  tweedie_variance_power = 1.4,
-  max_depth = 6,
-  eta = 1)
-
-bst <- xgb.train(
-  data = d_train, 
-  params = params, 
-  maximize = FALSE,
-  watchlist = list(train = d_train), 
-  nrounds = 20)
-
-var_imp <- xgb.importance(attr(x, 'Dimnames')[[2]], model = bst)
-
-preds <- predict(bst, d_train)
-
-rmse <- sqrt(sum(mean((y - preds)^2)))

R-package/man/agaricus.test.Rd

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgboost.R
-\docType{data}
-\name{agaricus.test}
-\alias{agaricus.test}
-\title{Test part from Mushroom Data Set}
-\format{A list containing a label vector, and a dgCMatrix object with 1611 
-rows and 126 variables}
-\usage{
-data(agaricus.test)
-}
-\description{
-This data set is originally from the Mushroom data set,
-UCI Machine Learning Repository.
-}
-\details{
-This data set includes the following fields:
-
-\itemize{
- \item \code{label} the label for each record
- \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
-}
-}
-\references{
-https://archive.ics.uci.edu/ml/datasets/Mushroom
-
-Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
-School of Information and Computer Science.
-}
-\keyword{datasets}

R-package/man/agaricus.train.Rd

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgboost.R
-\docType{data}
-\name{agaricus.train}
-\alias{agaricus.train}
-\title{Training part from Mushroom Data Set}
-\format{A list containing a label vector, and a dgCMatrix object with 6513 
-rows and 127 variables}
-\usage{
-data(agaricus.train)
-}
-\description{
-This data set is originally from the Mushroom data set,
-UCI Machine Learning Repository.
-}
-\details{
-This data set includes the following fields:
-
-\itemize{
- \item \code{label} the label for each record
- \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
-}
-}
-\references{
-https://archive.ics.uci.edu/ml/datasets/Mushroom
-
-Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
-School of Information and Computer Science.
-}
-\keyword{datasets}

R-package/man/callbacks.Rd

@@ -1,37 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{callbacks}
-\alias{callbacks}
-\title{Callback closures for booster training.}
-\description{
-These are used to perform various service tasks either during boosting iterations or at the end.
-This approach helps to modularize many of such tasks without bloating the main training methods,
-and it offers .
-}
-\details{
-By default, a callback function is run after each boosting iteration.
-An R-attribute \code{is_pre_iteration} could be set for a callback to define a pre-iteration function.
-
-When a callback function has \code{finalize} parameter, its finalizer part will also be run after
-the boosting is completed.
-
-WARNING: side-effects!!! Be aware that these callback functions access and modify things in
-the environment from which they are called from, which is a fairly uncommon thing to do in R.
-
-To write a custom callback closure, make sure you first understand the main concepts about R environments.
-Check either R documentation on \code{\link[base]{environment}} or the
-\href{http://adv-r.had.co.nz/Environments.html}{Environments chapter} from the "Advanced R"
-book by Hadley Wickham. Further, the best option is to read the code of some of the existing callbacks -
-choose ones that do something similar to what you want to achieve. Also, you would need to get familiar
-with the objects available inside of the \code{xgb.train} and \code{xgb.cv} internal environments.
-}
-\seealso{
-\code{\link{cb.print.evaluation}},
-\code{\link{cb.evaluation.log}},
-\code{\link{cb.reset.parameters}},
-\code{\link{cb.early.stop}},
-\code{\link{cb.save.model}},
-\code{\link{cb.cv.predict}},
-\code{\link{xgb.train}},
-\code{\link{xgb.cv}}
-}

R-package/man/cb.cv.predict.Rd

@@ -1,43 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.cv.predict}
-\alias{cb.cv.predict}
-\title{Callback closure for returning cross-validation based predictions.}
-\usage{
-cb.cv.predict(save_models = FALSE)
-}
-\arguments{
-\item{save_models}{a flag for whether to save the folds' models.}
-}
-\value{
-Predictions are returned inside of the \code{pred} element, which is either a vector or a matrix,
-depending on the number of prediction outputs per data row. The order of predictions corresponds
-to the order of rows in the original dataset. Note that when a custom \code{folds} list is
-provided in \code{xgb.cv}, the predictions would only be returned properly when this list is a
-non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be
-meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
-When some of the indices in the training dataset are not included into user-provided \code{folds},
-their prediction value would be \code{NA}.
-}
-\description{
-Callback closure for returning cross-validation based predictions.
-}
-\details{
-This callback function saves predictions for all of the test folds,
-and also allows to save the folds' models.
-
-It is a "finalizer" callback and it uses early stopping information whenever it is available,
-thus it must be run after the early stopping callback if the early stopping is used.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst_folds},
-\code{basket},
-\code{data},
-\code{end_iteration},
-\code{params},
-\code{num_parallel_tree},
-\code{num_class}.
-}
-\seealso{
-\code{\link{callbacks}}
-}

R-package/man/cb.early.stop.Rd

@@ -1,62 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.early.stop}
-\alias{cb.early.stop}
-\title{Callback closure to activate the early stopping.}
-\usage{
-cb.early.stop(stopping_rounds, maximize = FALSE, metric_name = NULL,
-  verbose = TRUE)
-}
-\arguments{
-\item{stopping_rounds}{The number of rounds with no improvement in
-the evaluation metric in order to stop the training.}
-
-\item{maximize}{whether to maximize the evaluation metric}
-
-\item{metric_name}{the name of an evaluation column to use as a criteria for early
-stopping. If not set, the last column would be used.
-Let's say the test data in \code{watchlist} was labelled as \code{dtest},
-and one wants to use the AUC in test data for early stopping regardless of where
-it is in the \code{watchlist}, then one of the following would need to be set:
-\code{metric_name='dtest-auc'} or \code{metric_name='dtest_auc'}.
-All dash '-' characters in metric names are considered equivalent to '_'.}
-
-\item{verbose}{whether to print the early stopping information.}
-}
-\description{
-Callback closure to activate the early stopping.
-}
-\details{
-This callback function determines the condition for early stopping
-by setting the \code{stop_condition = TRUE} flag in its calling frame.
-
-The following additional fields are assigned to the model's R object:
-\itemize{
-\item \code{best_score} the evaluation score at the best iteration
-\item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
-\item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
-     It differs from \code{best_iteration} in multiclass or random forest settings.
-}
-
-The Same values are also stored as xgb-attributes:
-\itemize{
-\item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)
-\item \code{best_msg} message string is also stored.
-}
-
-At least one data element is required in the evaluation watchlist for early stopping to work.
-
-Callback function expects the following values to be set in its calling frame:
-\code{stop_condition},
-\code{bst_evaluation},
-\code{rank},
-\code{bst} (or \code{bst_folds} and \code{basket}),
-\code{iteration},
-\code{begin_iteration},
-\code{end_iteration},
-\code{num_parallel_tree}.
-}
-\seealso{
-\code{\link{callbacks}},
-\code{\link{xgb.attr}}
-}

R-package/man/cb.evaluation.log.Rd

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.evaluation.log}
-\alias{cb.evaluation.log}
-\title{Callback closure for logging the evaluation history}
-\usage{
-cb.evaluation.log()
-}
-\description{
-Callback closure for logging the evaluation history
-}
-\details{
-This callback function appends the current iteration evaluation results \code{bst_evaluation}
-available in the calling parent frame to the \code{evaluation_log} list in a calling frame.
-
-The finalizer callback (called with \code{finalize = TURE} in the end) converts
-the \code{evaluation_log} list into a final data.table.
-
-The iteration evaluation result \code{bst_evaluation} must be a named numeric vector.
-
-Note: in the column names of the final data.table, the dash '-' character is replaced with
-the underscore '_' in order to make the column names more like regular R identifiers.
-
-Callback function expects the following values to be set in its calling frame:
-\code{evaluation_log},
-\code{bst_evaluation},
-\code{iteration}.
-}
-\seealso{
-\code{\link{callbacks}}
-}

R-package/man/cb.gblinear.history.Rd

@@ -1,95 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.gblinear.history}
-\alias{cb.gblinear.history}
-\title{Callback closure for collecting the model coefficients history of a gblinear booster
-during its training.}
-\usage{
-cb.gblinear.history(sparse = FALSE)
-}
-\arguments{
-\item{sparse}{when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
-Sparse format is useful when one expects only a subset of coefficients to be non-zero,
-when using the "thrifty" feature selector with fairly small number of top features
-selected per iteration.}
-}
-\value{
-Results are stored in the \code{coefs} element of the closure.
-The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
-With \code{xgb.train}, it is either a dense of a sparse matrix.
-While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
-}
-\description{
-Callback closure for collecting the model coefficients history of a gblinear booster
-during its training.
-}
-\details{
-To keep things fast and simple, gblinear booster does not internally store the history of linear
-model coefficients at each boosting iteration. This callback provides a workaround for storing
-the coefficients' path, by extracting them after each training iteration.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst} (or \code{bst_folds}).
-}
-\examples{
-#### Binary classification:
-#
-# In the iris dataset, it is hard to linearly separate Versicolor class from the rest
-# without considering the 2nd order interactions:
-require(magrittr)
-x <- model.matrix(Species ~ .^2, iris)[,-1]
-colnames(x)
-dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
-param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
-              lambda = 0.0003, alpha = 0.0003, nthread = 2)
-# For 'shotgun', which is a default linear updater, using high eta values may result in
-# unstable behaviour in some datasets. With this simple dataset, however, the high learning
-# rate does not break the convergence, but allows us to illustrate the typical pattern of
-# "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
-                 callbacks = list(cb.gblinear.history()))
-# Extract the coefficients' path and plot them vs boosting iteration number:
-coef_path <- xgb.gblinear.history(bst)
-matplot(coef_path, type = 'l')
-
-# With the deterministic coordinate descent updater, it is safer to use higher learning rates.
-# Will try the classical componentwise boosting which selects a single best feature per round:
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
-                 updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
-                 callbacks = list(cb.gblinear.history()))
-xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
-#  Componentwise boosting is known to have similar effect to Lasso regularization.
-# Try experimenting with various values of top_k, eta, nrounds,
-# as well as different feature_selectors.
-
-# For xgb.cv:
-bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-             callbacks = list(cb.gblinear.history()))
-# coefficients in the CV fold #3
-xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
-
-
-#### Multiclass classification:
-#
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
-param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-              lambda = 0.0003, alpha = 0.0003, nthread = 2)
-# For the default linear updater 'shotgun' it sometimes is helpful
-# to use smaller eta to reduce instability
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
-                 callbacks = list(cb.gblinear.history()))
-# Will plot the coefficient paths separately for each class:
-xgb.gblinear.history(bst, class_index = 0) \%>\% matplot(type = 'l')
-xgb.gblinear.history(bst, class_index = 1) \%>\% matplot(type = 'l')
-xgb.gblinear.history(bst, class_index = 2) \%>\% matplot(type = 'l')
-
-# CV:
-bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-              callbacks = list(cb.gblinear.history(FALSE)))
-# 1st forld of 1st class
-xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
-
-}
-\seealso{
-\code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
-}

R-package/man/cb.print.evaluation.Rd

@@ -1,29 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.print.evaluation}
-\alias{cb.print.evaluation}
-\title{Callback closure for printing the result of evaluation}
-\usage{
-cb.print.evaluation(period = 1, showsd = TRUE)
-}
-\arguments{
-\item{period}{results would be printed every number of periods}
-
-\item{showsd}{whether standard deviations should be printed (when available)}
-}
-\description{
-Callback closure for printing the result of evaluation
-}
-\details{
-The callback function prints the result of evaluation at every \code{period} iterations.
-The initial and the last iteration's evaluations are always printed.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst_evaluation} (also \code{bst_evaluation_err} when available),
-\code{iteration},
-\code{begin_iteration},
-\code{end_iteration}.
-}
-\seealso{
-\code{\link{callbacks}}
-}

R-package/man/cb.reset.parameters.Rd

@@ -1,36 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.reset.parameters}
-\alias{cb.reset.parameters}
-\title{Callback closure for resetting the booster's parameters at each iteration.}
-\usage{
-cb.reset.parameters(new_params)
-}
-\arguments{
-\item{new_params}{a list where each element corresponds to a parameter that needs to be reset.
-Each element's value must be either a vector of values of length \code{nrounds}
-to be set at each iteration,
-or a function of two parameters \code{learning_rates(iteration, nrounds)}
-which returns a new parameter value by using the current iteration number
-and the total number of boosting rounds.}
-}
-\description{
-Callback closure for resetting the booster's parameters at each iteration.
-}
-\details{
-This is a "pre-iteration" callback function used to reset booster's parameters
-at the beginning of each iteration.
-
-Note that when training is resumed from some previous model, and a function is used to
-reset a parameter value, the \code{nrounds} argument in this function would be the
-the number of boosting rounds in the current training.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst} or \code{bst_folds},
-\code{iteration},
-\code{begin_iteration},
-\code{end_iteration}.
-}
-\seealso{
-\code{\link{callbacks}}
-}

R-package/man/cb.save.model.Rd

@@ -1,33 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.save.model}
-\alias{cb.save.model}
-\title{Callback closure for saving a model file.}
-\usage{
-cb.save.model(save_period = 0, save_name = "xgboost.model")
-}
-\arguments{
-\item{save_period}{save the model to disk after every
-\code{save_period} iterations; 0 means save the model at the end.}
-
-\item{save_name}{the name or path for the saved model file.
-It can contain a \code{\link[base]{sprintf}} formatting specifier
-to include the integer iteration number in the file name.
-E.g., with \code{save_name} = 'xgboost_%04d.model',
-the file saved at iteration 50 would be named "xgboost_0050.model".}
-}
-\description{
-Callback closure for saving a model file.
-}
-\details{
-This callback function allows to save an xgb-model file, either periodically after each \code{save_period}'s or at the end.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst},
-\code{iteration},
-\code{begin_iteration},
-\code{end_iteration}.
-}
-\seealso{
-\code{\link{callbacks}}
-}

R-package/man/dim.xgb.DMatrix.Rd

@@ -1,28 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{dim.xgb.DMatrix}
-\alias{dim.xgb.DMatrix}
-\title{Dimensions of xgb.DMatrix}
-\usage{
-\method{dim}{xgb.DMatrix}(x)
-}
-\arguments{
-\item{x}{Object of class \code{xgb.DMatrix}}
-}
-\description{
-Returns a vector of numbers of rows and of columns in an \code{xgb.DMatrix}.
-}
-\details{
-Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
-be directly used with an \code{xgb.DMatrix} object.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-
-stopifnot(nrow(dtrain) == nrow(train$data))
-stopifnot(ncol(dtrain) == ncol(train$data))
-stopifnot(all(dim(dtrain) == dim(train$data)))
-
-}

R-package/man/dimnames.xgb.DMatrix.Rd

@@ -1,35 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{dimnames.xgb.DMatrix}
-\alias{dimnames.xgb.DMatrix}
-\alias{dimnames<-.xgb.DMatrix}
-\title{Handling of column names of \code{xgb.DMatrix}}
-\usage{
-\method{dimnames}{xgb.DMatrix}(x)
-
-\method{dimnames}{xgb.DMatrix}(x) <- value
-}
-\arguments{
-\item{x}{object of class \code{xgb.DMatrix}}
-
-\item{value}{a list of two elements: the first one is ignored
-and the second one is column names}
-}
-\description{
-Only column names are supported for \code{xgb.DMatrix}, thus setting of
-row names would have no effect and returned row names would be NULL.
-}
-\details{
-Generic \code{dimnames} methods are used by \code{colnames}.
-Since row names are irrelevant, it is recommended to use \code{colnames} directly.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-dimnames(dtrain)
-colnames(dtrain)
-colnames(dtrain) <- make.names(1:ncol(train$data))
-print(dtrain, verbose=TRUE)
-
-}

R-package/man/getinfo.Rd

@@ -1,45 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{getinfo}
-\alias{getinfo}
-\alias{getinfo.xgb.DMatrix}
-\title{Get information of an xgb.DMatrix object}
-\usage{
-getinfo(object, ...)
-
-\method{getinfo}{xgb.DMatrix}(object, name, ...)
-}
-\arguments{
-\item{object}{Object of class \code{xgb.DMatrix}}
-
-\item{...}{other parameters}
-
-\item{name}{the name of the information field to get (see details)}
-}
-\description{
-Get information of an xgb.DMatrix object
-}
-\details{
-The \code{name} field can be one of the following:
-
-\itemize{
-    \item \code{label}: label Xgboost learn from ;
-    \item \code{weight}: to do a weight rescale ;
-    \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
-    \item \code{nrow}: number of rows of the \code{xgb.DMatrix}.
-
-}
-
-\code{group} can be setup by \code{setinfo} but can't be retrieved by \code{getinfo}.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-
-labels <- getinfo(dtrain, 'label')
-setinfo(dtrain, 'label', 1-labels)
-
-labels2 <- getinfo(dtrain, 'label')
-stopifnot(all(labels2 == 1-labels))
-}

R-package/man/predict.xgb.Booster.Rd

@@ -1,189 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{predict.xgb.Booster}
-\alias{predict.xgb.Booster}
-\alias{predict.xgb.Booster.handle}
-\title{Predict method for eXtreme Gradient Boosting model}
-\usage{
-\method{predict}{xgb.Booster}(object, newdata, missing = NA,
-  outputmargin = FALSE, ntreelimit = NULL, predleaf = FALSE,
-  predcontrib = FALSE, approxcontrib = FALSE,
-  predinteraction = FALSE, reshape = FALSE, ...)
-
-\method{predict}{xgb.Booster.handle}(object, ...)
-}
-\arguments{
-\item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
-
-\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.}
-
-\item{missing}{Missing is only used when input is dense matrix. Pick a float value that represents
-missing values in data (e.g., sometimes 0 or some other extreme value is used).}
-
-\item{outputmargin}{whether the prediction should be returned in the for of original untransformed
-sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
-logistic regression would result in predictions for log-odds instead of probabilities.}
-
-\item{ntreelimit}{limit the number of model's trees or boosting iterations used in prediction (see Details).
-It will use all the trees by default (\code{NULL} value).}
-
-\item{predleaf}{whether predict leaf index.}
-
-\item{predcontrib}{whether to return feature contributions to individual predictions (see Details).}
-
-\item{approxcontrib}{whether to use a fast approximation for feature contributions (see Details).}
-
-\item{predinteraction}{whether to return contributions of feature interactions to individual predictions (see Details).}
-
-\item{reshape}{whether to reshape the vector of predictions to a matrix form when there are several
-prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
-or predinteraction flags is TRUE.}
-
-\item{...}{Parameters passed to \code{predict.xgb.Booster}}
-}
-\value{
-For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
-For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
-a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
-the \code{reshape} value.
-
-When \code{predleaf = TRUE}, the output is a matrix object with the
-number of columns corresponding to the number of trees.
-
-When \code{predcontrib = TRUE} and it is not a multiclass setting, the output is a matrix object with
-\code{num_features + 1} columns. The last "+ 1" column in a matrix corresponds to bias.
-For a multiclass case, a list of \code{num_class} elements is returned, where each element is
-such a matrix. The contribution values are on the scale of untransformed margin
-(e.g., for binary classification would mean that the contributions are log-odds deviations from bias).
-
-When \code{predinteraction = TRUE} and it is not a multiclass setting, the output is a 3d array with
-dimensions \code{c(nrow, num_features + 1, num_features + 1)}. The off-diagonal (in the last two dimensions)
-elements represent different features interaction contributions. The array is symmetric WRT the last
-two dimensions. The "+ 1" columns corresponds to bias. Summing this array along the last dimension should
-produce practically the same result as predict with \code{predcontrib = TRUE}.
-For a multiclass case, a list of \code{num_class} elements is returned, where each element is
-such an array.
-}
-\description{
-Predicted values based on either xgboost model or model handle object.
-}
-\details{
-Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
-and it is not necessarily equal to the number of trees in a model.
-E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-But for multiclass classification, while there are multiple trees per iteration,
-\code{ntreelimit} limits the number of boosting iterations.
-
-Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
-since gblinear doesn't keep its boosting history.
-
-One possible practical applications of the \code{predleaf} option is to use the model
-as a generator of new features which capture non-linearity and interactions,
-e.g., as implemented in \code{\link{xgb.create.features}}.
-
-Setting \code{predcontrib = TRUE} allows to calculate contributions of each feature to
-individual predictions. For "gblinear" booster, feature contributions are simply linear terms
-(feature_beta * feature_value). For "gbtree" booster, feature contributions are SHAP
-values (Lundberg 2017) that sum to the difference between the expected output
-of the model and the current prediction (where the hessian weights are used to compute the expectations).
-Setting \code{approxcontrib = TRUE} approximates these values following the idea explained
-in \url{http://blog.datadive.net/interpreting-random-forests/}.
-
-With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
-are computed. Note that this operation might be rather expensive in terms of compute and memory.
-Since it quadratically depends on the number of features, it is recommended to perform selection
-of the most important features first. See below about the format of the returned results.
-}
-\examples{
-## binary classification:
-
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 0.5, nthread = 2, nrounds = 5, objective = "binary:logistic")
-# use all trees by default
-pred <- predict(bst, test$data)
-# use only the 1st tree
-pred1 <- predict(bst, test$data, ntreelimit = 1)
-
-# Predicting tree leafs:
-# the result is an nsamples X ntrees matrix
-pred_leaf <- predict(bst, test$data, predleaf = TRUE)
-str(pred_leaf)
-
-# Predicting feature contributions to predictions:
-# the result is an nsamples X (nfeatures + 1) matrix
-pred_contr <- predict(bst, test$data, predcontrib = TRUE)
-str(pred_contr)
-# verify that contributions' sums are equal to log-odds of predictions (up to float precision):
-summary(rowSums(pred_contr) - qlogis(pred))
-# for the 1st record, let's inspect its features that had non-zero contribution to prediction:
-contr1 <- pred_contr[1,]
-contr1 <- contr1[-length(contr1)]    # drop BIAS
-contr1 <- contr1[contr1 != 0]        # drop non-contributing features
-contr1 <- contr1[order(abs(contr1))] # order by contribution magnitude
-old_mar <- par("mar")
-par(mar = old_mar + c(0,7,0,0))
-barplot(contr1, horiz = TRUE, las = 2, xlab = "contribution to prediction in log-odds")
-par(mar = old_mar)
-
-
-## multiclass classification in iris dataset:
-
-lb <- as.numeric(iris$Species) - 1
-num_class <- 3
-set.seed(11)
-bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
-               max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
-               objective = "multi:softprob", num_class = num_class)
-# predict for softmax returns num_class probability numbers per case:
-pred <- predict(bst, as.matrix(iris[, -5]))
-str(pred)
-# reshape it to a num_class-columns matrix
-pred <- matrix(pred, ncol=num_class, byrow=TRUE)
-# convert the probabilities to softmax labels
-pred_labels <- max.col(pred) - 1
-# the following should result in the same error as seen in the last iteration
-sum(pred_labels != lb)/length(lb)
-
-# compare that to the predictions from softmax:
-set.seed(11)
-bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
-               max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
-               objective = "multi:softmax", num_class = num_class)
-pred <- predict(bst, as.matrix(iris[, -5]))
-str(pred)
-all.equal(pred, pred_labels)
-# prediction from using only 5 iterations should result
-# in the same error as seen in iteration 5:
-pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
-sum(pred5 != lb)/length(lb)
-
-
-## random forest-like model of 25 trees for binary classification:
-
-set.seed(11)
-bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-               nthread = 2, nrounds = 1, objective = "binary:logistic",
-               num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-# Inspect the prediction error vs number of trees:
-lb <- test$label
-dtest <- xgb.DMatrix(test$data, label=lb)
-err <- sapply(1:25, function(n) {
-  pred <- predict(bst, dtest, ntreelimit=n)
-  sum((pred > 0.5) != lb)/length(lb)
-})
-plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-
-}
-\references{
-Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
-
-Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
-}
-\seealso{
-\code{\link{xgb.train}}.
-}

R-package/man/print.xgb.Booster.Rd

@@ -1,29 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{print.xgb.Booster}
-\alias{print.xgb.Booster}
-\title{Print xgb.Booster}
-\usage{
-\method{print}{xgb.Booster}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an xgb.Booster object}
-
-\item{verbose}{whether to print detailed data (e.g., attribute values)}
-
-\item{...}{not currently used}
-}
-\description{
-Print information about xgb.Booster.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-attr(bst, 'myattr') <- 'memo'
-
-print(bst)
-print(bst, verbose=TRUE)
-
-}

R-package/man/print.xgb.DMatrix.Rd

@@ -1,28 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{print.xgb.DMatrix}
-\alias{print.xgb.DMatrix}
-\title{Print xgb.DMatrix}
-\usage{
-\method{print}{xgb.DMatrix}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an xgb.DMatrix object}
-
-\item{verbose}{whether to print colnames (when present)}
-
-\item{...}{not currently used}
-}
-\description{
-Print information about xgb.DMatrix.
-Currently it displays dimensions and presence of info-fields and colnames.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-
-dtrain
-print(dtrain, verbose=TRUE)
-
-}

R-package/man/print.xgb.cv.Rd

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.cv.R
-\name{print.xgb.cv.synchronous}
-\alias{print.xgb.cv.synchronous}
-\title{Print xgb.cv result}
-\usage{
-\method{print}{xgb.cv.synchronous}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an \code{xgb.cv.synchronous} object}
-
-\item{verbose}{whether to print detailed data}
-
-\item{...}{passed to \code{data.table.print}}
-}
-\description{
-Prints formatted results of \code{xgb.cv}.
-}
-\details{
-When not verbose, it would only print the evaluation results,
-including the best iteration (when available).
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-cv <- xgb.cv(data = train$data, label = train$label, nfold = 5, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-print(cv)
-print(cv, verbose=TRUE)
-
-}

R-package/man/setinfo.Rd

@@ -1,43 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{setinfo}
-\alias{setinfo}
-\alias{setinfo.xgb.DMatrix}
-\title{Set information of an xgb.DMatrix object}
-\usage{
-setinfo(object, ...)
-
-\method{setinfo}{xgb.DMatrix}(object, name, info, ...)
-}
-\arguments{
-\item{object}{Object of class "xgb.DMatrix"}
-
-\item{...}{other parameters}
-
-\item{name}{the name of the field to get}
-
-\item{info}{the specific field of information to set}
-}
-\description{
-Set information of an xgb.DMatrix object
-}
-\details{
-The \code{name} field can be one of the following:
-
-\itemize{
-    \item \code{label}: label Xgboost learn from ;
-    \item \code{weight}: to do a weight rescale ;
-    \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
-    \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
-}
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-
-labels <- getinfo(dtrain, 'label')
-setinfo(dtrain, 'label', 1-labels)
-labels2 <- getinfo(dtrain, 'label')
-stopifnot(all.equal(labels2, 1-labels))
-}

R-package/man/slice.xgb.DMatrix.Rd

@@ -1,40 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{slice}
-\alias{slice}
-\alias{slice.xgb.DMatrix}
-\alias{[.xgb.DMatrix}
-\title{Get a new DMatrix containing the specified rows of
-original xgb.DMatrix object}
-\usage{
-slice(object, ...)
-
-\method{slice}{xgb.DMatrix}(object, idxset, ...)
-
-\method{[}{xgb.DMatrix}(object, idxset, colset = NULL)
-}
-\arguments{
-\item{object}{Object of class "xgb.DMatrix"}
-
-\item{...}{other parameters (currently not used)}
-
-\item{idxset}{a integer vector of indices of rows needed}
-
-\item{colset}{currently not used (columns subsetting is not available)}
-}
-\description{
-Get a new DMatrix containing the specified rows of
-original xgb.DMatrix object
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-
-dsub <- slice(dtrain, 1:42)
-labels1 <- getinfo(dsub, 'label')
-dsub <- dtrain[1:42, ]
-labels2 <- getinfo(dsub, 'label')
-all.equal(labels1, labels2)
-
-}

R-package/man/xgb.Booster.complete.Rd

@@ -1,49 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{xgb.Booster.complete}
-\alias{xgb.Booster.complete}
-\title{Restore missing parts of an incomplete xgb.Booster object.}
-\usage{
-xgb.Booster.complete(object, saveraw = TRUE)
-}
-\arguments{
-\item{object}{object of class \code{xgb.Booster}}
-
-\item{saveraw}{a flag indicating whether to append \code{raw} Booster memory dump data
-when it doesn't already exist.}
-}
-\value{
-An object of \code{xgb.Booster} class.
-}
-\description{
-It attempts to complete an \code{xgb.Booster} object by restoring either its missing
-raw model memory dump (when it has no \code{raw} data but its \code{xgb.Booster.handle} is valid)
-or its missing internal handle (when its \code{xgb.Booster.handle} is not valid
-but it has a raw Booster memory dump).
-}
-\details{
-While this method is primarily for internal use, it might be useful in some practical situations.
-
-E.g., when an \code{xgb.Booster} model is saved as an R object and then is loaded as an R object,
-its handle (pointer) to an internal xgboost model would be invalid. The majority of xgboost methods
-should still work for such a model object since those methods would be using
-\code{xgb.Booster.complete} internally. However, one might find it to be more efficient to call the
-\code{xgb.Booster.complete} function explicitly once after loading a model as an R-object.
-That would prevent further repeated implicit reconstruction of an internal booster model.
-}
-\examples{
-
-data(agaricus.train, package='xgboost')
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-saveRDS(bst, "xgb.model.rds")
-
-bst1 <- readRDS("xgb.model.rds")
-# the handle is invalid:
-print(bst1$handle)
-
-bst1 <- xgb.Booster.complete(bst1)
-# now the handle points to a valid internal booster model:
-print(bst1$handle)
-
-}

R-package/man/xgb.DMatrix.Rd

@@ -1,34 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{xgb.DMatrix}
-\alias{xgb.DMatrix}
-\title{Construct xgb.DMatrix object}
-\usage{
-xgb.DMatrix(data, info = list(), missing = NA, silent = FALSE, ...)
-}
-\arguments{
-\item{data}{a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
-string representing a filename.}
-
-\item{info}{a named list of additional information to store in the \code{xgb.DMatrix} object.
-See \code{\link{setinfo}} for the specific allowed kinds of}
-
-\item{missing}{a float value to represents missing values in data (used only when input is a dense matrix).
-It is useful when a 0 or some other extreme value represents missing values in data.}
-
-\item{silent}{whether to suppress printing an informational message after loading from a file.}
-
-\item{...}{the \code{info} data could be passed directly as parameters, without creating an \code{info} list.}
-}
-\description{
-Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-Supported input file formats are either a libsvm text file or a binary file that was created previously by
-\code{\link{xgb.DMatrix.save}}).
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-}

R-package/man/xgb.DMatrix.save.Rd

@@ -1,23 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.save.R
-\name{xgb.DMatrix.save}
-\alias{xgb.DMatrix.save}
-\title{Save xgb.DMatrix object to binary file}
-\usage{
-xgb.DMatrix.save(dmatrix, fname)
-}
-\arguments{
-\item{dmatrix}{the \code{xgb.DMatrix} object}
-
-\item{fname}{the name of the file to write.}
-}
-\description{
-Save xgb.DMatrix object to binary file
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-}

R-package/man/xgb.attr.Rd

@@ -1,85 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{xgb.attr}
-\alias{xgb.attr}
-\alias{xgb.attr<-}
-\alias{xgb.attributes}
-\alias{xgb.attributes<-}
-\title{Accessors for serializable attributes of a model.}
-\usage{
-xgb.attr(object, name)
-
-xgb.attr(object, name) <- value
-
-xgb.attributes(object)
-
-xgb.attributes(object) <- value
-}
-\arguments{
-\item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.}
-
-\item{name}{a non-empty character string specifying which attribute is to be accessed.}
-
-\item{value}{a value of an attribute for \code{xgb.attr<-}; for \code{xgb.attributes<-}
-it's a list (or an object coercible to a list) with the names of attributes to set
-and the elements corresponding to attribute values.
-Non-character values are converted to character.
-When attribute value is not a scalar, only the first index is used.
-Use \code{NULL} to remove an attribute.}
-}
-\value{
-\code{xgb.attr} returns either a string value of an attribute
-or \code{NULL} if an attribute wasn't stored in a model.
-
-\code{xgb.attributes} returns a list of all attribute stored in a model
-or \code{NULL} if a model has no stored attributes.
-}
-\description{
-These methods allow to manipulate the key-value attribute strings of an xgboost model.
-}
-\details{
-The primary purpose of xgboost model attributes is to store some meta-data about the model.
-Note that they are a separate concept from the object attributes in R.
-Specifically, they refer to key-value strings that can be attached to an xgboost model,
-stored together with the model's binary representation, and accessed later
-(from R or any other interface).
-In contrast, any R-attribute assigned to an R-object of \code{xgb.Booster} class
-would not be saved by \code{xgb.save} because an xgboost model is an external memory object
-and its serialization is handled externally.
-Also, setting an attribute that has the same name as one of xgboost's parameters wouldn't
-change the value of that parameter for a model.
-Use \code{\link{xgb.parameters<-}} to set or change model parameters.
-
-The attribute setters would usually work more efficiently for \code{xgb.Booster.handle}
-than for \code{xgb.Booster}, since only just a handle (pointer) would need to be copied.
-That would only matter if attributes need to be set many times.
-Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
-the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-and it would be user's responsibility to call \code{xgb.save.raw} to update it.
-
-The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
-but it doesn't delete the other existing attributes.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-
-xgb.attr(bst, "my_attribute") <- "my attribute value"
-print(xgb.attr(bst, "my_attribute"))
-xgb.attributes(bst) <- list(a = 123, b = "abc")
-
-xgb.save(bst, 'xgb.model')
-bst1 <- xgb.load('xgb.model')
-print(xgb.attr(bst1, "my_attribute"))
-print(xgb.attributes(bst1))
-
-# deletion:
-xgb.attr(bst1, "my_attribute") <- NULL
-print(xgb.attributes(bst1))
-xgb.attributes(bst1) <- list(a = NULL, b = NULL)
-print(xgb.attributes(bst1))
-
-}

R-package/man/xgb.create.features.Rd

@@ -1,92 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.create.features.R
-\name{xgb.create.features}
-\alias{xgb.create.features}
-\title{Create new features from a previously learned model}
-\usage{
-xgb.create.features(model, data, ...)
-}
-\arguments{
-\item{model}{decision tree boosting model learned on the original data}
-
-\item{data}{original data (usually provided as a \code{dgCMatrix} matrix)}
-
-\item{...}{currently not used}
-}
-\value{
-\code{dgCMatrix} matrix including both the original data and the new features.
-}
-\description{
-May improve the learning by adding new features to the training data based on the decision trees from a previously learned model.
-}
-\details{
-This is the function inspired from the paragraph 3.1 of the paper:
-
-\strong{Practical Lessons from Predicting Clicks on Ads at Facebook}
-
-\emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, 
-Joaquin Quinonero Candela)}
- 
-International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
-
-\url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
-
-Extract explaining the method:
-
-"We found that boosted decision trees are a powerful and very
-convenient way to implement non-linear and tuple transformations
-of the kind we just described. We treat each individual
-tree as a categorical feature that takes as value the
-index of the leaf an instance ends up falling in. We use 
-1-of-K coding of this type of features. 
-
-For example, consider the boosted tree model in Figure 1 with 2 subtrees, 
-where the first subtree has 3 leafs and the second 2 leafs. If an
-instance ends up in leaf 2 in the first subtree and leaf 1 in
-second subtree, the overall input to the linear classifier will
-be the binary vector \code{[0, 1, 0, 1, 0]}, where the first 3 entries
-correspond to the leaves of the first subtree and last 2 to
-those of the second subtree.
-
-[...]
-
-We can understand boosted decision tree
-based transformation as a supervised feature encoding that
-converts a real-valued vector into a compact binary-valued
-vector. A traversal from root node to a leaf node represents
-a rule on certain features."
-}
-\examples{
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
-
-param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-nrounds = 4
-
-bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
-
-# Model accuracy without new features
-accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
-                   length(agaricus.test$label)
-
-# Convert previous features to one hot encoding
-new.features.train <- xgb.create.features(model = bst, agaricus.train$data)
-new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
-
-# learning with new features
-new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
-new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
-watchlist <- list(train = new.dtrain)
-bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
-
-# Model accuracy with new features
-accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /
-                  length(agaricus.test$label)
-
-# Here the accuracy was already good and is now perfect.
-cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
-          accuracy.after, "!\\n"))
-
-}

R-package/man/xgb.cv.Rd

@@ -1,145 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.cv.R
-\name{xgb.cv}
-\alias{xgb.cv}
-\title{Cross Validation}
-\usage{
-xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
-  missing = NA, prediction = FALSE, showsd = TRUE,
-  metrics = list(), obj = NULL, feval = NULL, stratified = TRUE,
-  folds = NULL, verbose = TRUE, print_every_n = 1L,
-  early_stopping_rounds = NULL, maximize = NULL, callbacks = list(),
-  ...)
-}
-\arguments{
-\item{params}{the list of parameters. Commonly used ones are:
-\itemize{
-  \item \code{objective} objective function, common ones are
-  \itemize{
-    \item \code{reg:squarederror} Regression with squared loss
-    \item \code{binary:logistic} logistic regression for classification
-  }
-  \item \code{eta} step size of each boosting step
-  \item \code{max_depth} maximum depth of the tree
-  \item \code{nthread} number of thread used in training, if not set, all threads are used
-}
-
-  See \code{\link{xgb.train}} for further details.
-  See also demo/ for walkthrough example in R.}
-
-\item{data}{takes an \code{xgb.DMatrix}, \code{matrix}, or \code{dgCMatrix} as the input.}
-
-\item{nrounds}{the max number of iterations}
-
-\item{nfold}{the original dataset is randomly partitioned into \code{nfold} equal size subsamples.}
-
-\item{label}{vector of response values. Should be provided only when data is an R-matrix.}
-
-\item{missing}{is only used when input is a dense matrix. By default is set to NA, which means
-that NA values should be considered as 'missing' by the algorithm.
-Sometimes, 0 or other extreme value might be used to represent missing values.}
-
-\item{prediction}{A logical value indicating whether to return the test fold predictions
-from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callback.}
-
-\item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}
-
-\item{metrics, }{list of evaluation metrics to be used in cross validation,
-  when it is not specified, the evaluation metric is chosen according to objective function.
-  Possible options are:
-\itemize{
-  \item \code{error} binary classification error rate
-  \item \code{rmse} Rooted mean square error
-  \item \code{logloss} negative log-likelihood function
-  \item \code{auc} Area under curve
-  \item \code{aucpr} Area under PR curve
-  \item \code{merror} Exact matching error, used to evaluate multi-class classification
-}}
-
-\item{obj}{customized objective function. Returns gradient and second order
-gradient with given prediction and dtrain.}
-
-\item{feval}{customized evaluation function. Returns
-\code{list(metric='metric-name', value='metric-value')} with given
-prediction and dtrain.}
-
-\item{stratified}{a \code{boolean} indicating whether sampling of folds should be stratified
-by the values of outcome labels.}
-
-\item{folds}{\code{list} provides a possibility to use a list of pre-defined CV folds
-(each element must be a vector of test fold's indices). When folds are supplied,
-the \code{nfold} and \code{stratified} parameters are ignored.}
-
-\item{verbose}{\code{boolean}, print the statistics during the process}
-
-\item{print_every_n}{Print each n-th iteration evaluation messages when \code{verbose>0}.
-Default is 1 which means all messages are printed. This parameter is passed to the
-\code{\link{cb.print.evaluation}} callback.}
-
-\item{early_stopping_rounds}{If \code{NULL}, the early stopping function is not triggered.
-If set to an integer \code{k}, training with a validation set will stop if the performance
-doesn't improve for \code{k} rounds.
-Setting this parameter engages the \code{\link{cb.early.stop}} callback.}
-
-\item{maximize}{If \code{feval} and \code{early_stopping_rounds} are set,
-then this parameter must be set as well.
-When it is \code{TRUE}, it means the larger the evaluation score the better.
-This parameter is passed to the \code{\link{cb.early.stop}} callback.}
-
-\item{callbacks}{a list of callback functions to perform various task during boosting.
-See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
-parameters' values. User can provide either existing or their own callback methods in order
-to customize the training process.}
-
-\item{...}{other parameters to pass to \code{params}.}
-}
-\value{
-An object of class \code{xgb.cv.synchronous} with the following elements:
-\itemize{
-  \item \code{call} a function call.
-  \item \code{params} parameters that were passed to the xgboost library. Note that it does not
-        capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
-  \item \code{callbacks} callback functions that were either automatically assigned or
-        explicitly passed.
-  \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
-        first column corresponding to iteration number and the rest corresponding to the
-        CV-based evaluation means and standard deviations for the training and test CV-sets.
-        It is created by the \code{\link{cb.evaluation.log}} callback.
-  \item \code{niter} number of boosting iterations.
-  \item \code{nfeatures} number of features in training data.
-  \item \code{folds} the list of CV folds' indices - either those passed through the \code{folds}
-        parameter or randomly generated.
-  \item \code{best_iteration} iteration number with the best evaluation metric value
-        (only available with early stopping).
-  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-        which could further be used in \code{predict} method
-        (only available with early stopping).
-  \item \code{pred} CV prediction values available when \code{prediction} is set.
-        It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-  \item \code{models} a liost of the CV folds' models. It is only available with the explicit
-        setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
-}
-}
-\description{
-The cross validation function of xgboost
-}
-\details{
-The original sample is randomly partitioned into \code{nfold} equal size subsamples.
-
-Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
-
-The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
-
-All observations are used for both training and validation.
-
-Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
-}
-\examples{
-data(agaricus.train, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-                  max_depth = 3, eta = 1, objective = "binary:logistic")
-print(cv)
-print(cv, verbose=TRUE)
-
-}

R-package/man/xgb.dump.Rd

@@ -1,56 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.dump.R
-\name{xgb.dump}
-\alias{xgb.dump}
-\title{Dump an xgboost model in text format.}
-\usage{
-xgb.dump(model, fname = NULL, fmap = "", with_stats = FALSE,
-  dump_format = c("text", "json"), ...)
-}
-\arguments{
-\item{model}{the model object.}
-
-\item{fname}{the name of the text file where to save the model text dump. 
-If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.}
-
-\item{fmap}{feature map file representing feature types.
-Detailed description could be found at 
-\url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
-See demo/ for walkthrough example in R, and
-\url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt} 
-for example Format.}
-
-\item{with_stats}{whether to dump some additional statistics about the splits.
-When this option is on, the model dump contains two additional values:
-gain is the approximate loss function gain we get in each split;
-cover is the sum of second order gradient in each node.}
-
-\item{dump_format}{either 'text' or 'json' format could be specified.}
-
-\item{...}{currently not used}
-}
-\value{
-If fname is not provided or set to \code{NULL} the function will return the model
-as a \code{character} vector. Otherwise it will return \code{TRUE}.
-}
-\description{
-Dump an xgboost model in text format.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-# save the model in file 'xgb.model.dump'
-dump_path = file.path(tempdir(), 'model.dump')
-xgb.dump(bst, dump_path, with_stats = TRUE)
-
-# print the model without saving it to a file
-print(xgb.dump(bst, with_stats = TRUE))
-
-# print in JSON format:
-cat(xgb.dump(bst, with_stats = TRUE, dump_format='json'))
-
-}

R-package/man/xgb.gblinear.history.Rd

@@ -1,29 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{xgb.gblinear.history}
-\alias{xgb.gblinear.history}
-\title{Extract gblinear coefficients history.}
-\usage{
-xgb.gblinear.history(model, class_index = NULL)
-}
-\arguments{
-\item{model}{either an \code{xgb.Booster} or a result of \code{xgb.cv()}, trained
-using the \code{cb.gblinear.history()} callback.}
-
-\item{class_index}{zero-based class index to extract the coefficients for only that
-specific class in a multinomial multiclass model. When it is NULL, all the
-coefficients are returned. Has no effect in non-multiclass models.}
-}
-\value{
-For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns
-corresponding to iteration's coefficients (in the order as \code{xgb.dump()} would
-return) and the rows corresponding to boosting iterations.
-
-For an \code{xgb.cv} result, a list of such matrices is returned with the elements
-corresponding to CV folds.
-}
-\description{
-A helper function to extract the matrix of linear coefficients' history
-from a gblinear model created while using the \code{cb.gblinear.history()}
-callback.
-}

R-package/man/xgb.importance.Rd

@@ -1,95 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.importance.R
-\name{xgb.importance}
-\alias{xgb.importance}
-\title{Importance of features in a model.}
-\usage{
-xgb.importance(feature_names = NULL, model = NULL, trees = NULL,
-  data = NULL, label = NULL, target = NULL)
-}
-\arguments{
-\item{feature_names}{character vector of feature names. If the model already
-contains feature names, those would be used when \code{feature_names=NULL} (default value).
-Non-null \code{feature_names} could be provided to override those in the model.}
-
-\item{model}{object of class \code{xgb.Booster}.}
-
-\item{trees}{(only for the gbtree booster) an integer vector of tree indices that should be included
-into the importance calculation. If set to \code{NULL}, all trees of the model are parsed.
-It could be useful, e.g., in multiclass classification to get feature importances 
-for each class separately. IMPORTANT: the tree index in xgboost models
-is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).}
-
-\item{data}{deprecated.}
-
-\item{label}{deprecated.}
-
-\item{target}{deprecated.}
-}
-\value{
-For a tree model, a \code{data.table} with the following columns:
-\itemize{
-  \item \code{Features} names of the features used in the model;
-  \item \code{Gain} represents fractional contribution of each feature to the model based on
-       the total gain of this feature's splits. Higher percentage means a more important 
-       predictive feature.
-  \item \code{Cover} metric of the number of observation related to this feature;
-  \item \code{Frequency} percentage representing the relative number of times
-       a feature have been used in trees.
-}
-
-A linear model's importance \code{data.table} has the following columns:
-\itemize{
-  \item \code{Features} names of the features used in the model;
-  \item \code{Weight} the linear coefficient of this feature;
-  \item \code{Class} (only for multiclass models) class label.
-}
-
-If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names}, 
-index of the features will be used instead. Because the index is extracted from the model dump
-(based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
-}
-\description{
-Creates a \code{data.table} of feature importances in a model.
-}
-\details{
-This function works for both linear and tree models.
-
-For linear models, the importance is the absolute magnitude of linear coefficients. 
-For that reason, in order to obtain a meaningful ranking by importance for a linear model, 
-the features need to be on the same scale (which you also would want to do when using either 
-L1 or L2 regularization).
-}
-\examples{
-
-# binomial classification using gbtree:
-data(agaricus.train, package='xgboost')
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-xgb.importance(model = bst)
-
-# binomial classification using gblinear:
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear", 
-               eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
-xgb.importance(model = bst)
-
-# multiclass classification using gbtree:
-nclass <- 3
-nrounds <- 10
-mbst <- xgboost(data = as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1,
-               max_depth = 3, eta = 0.2, nthread = 2, nrounds = nrounds,
-               objective = "multi:softprob", num_class = nclass)
-# all classes clumped together:
-xgb.importance(model = mbst)
-# inspect importances separately for each class:
-xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
-xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
-xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
-
-# multiclass classification using gblinear:
-mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
-               booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
-               objective = "multi:softprob", num_class = nclass)
-xgb.importance(model = mbst)
-
-}

R-package/man/xgb.load.Rd

@@ -1,40 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.load.R
-\name{xgb.load}
-\alias{xgb.load}
-\title{Load xgboost model from binary file}
-\usage{
-xgb.load(modelfile)
-}
-\arguments{
-\item{modelfile}{the name of the binary input file.}
-}
-\value{
-An object of \code{xgb.Booster} class.
-}
-\description{
-Load xgboost model from the binary model file.
-}
-\details{
-The input file is expected to contain a model saved in an xgboost-internal binary format
-using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some 
-appropriate methods from other xgboost interfaces. E.g., a model trained in Python and 
-saved from there in xgboost format, could be loaded from R.
-
-Note: a model saved as an R-object, has to be loaded using corresponding R-methods,
-not \code{xgb.load}.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
-               eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-xgb.save(bst, 'xgb.model')
-bst <- xgb.load('xgb.model')
-pred <- predict(bst, test$data)
-}
-\seealso{
-\code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}.
-}

R-package/man/xgb.model.dt.tree.Rd

@@ -1,77 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.model.dt.tree.R
-\name{xgb.model.dt.tree}
-\alias{xgb.model.dt.tree}
-\title{Parse a boosted tree model text dump}
-\usage{
-xgb.model.dt.tree(feature_names = NULL, model = NULL, text = NULL,
-  trees = NULL, use_int_id = FALSE, ...)
-}
-\arguments{
-\item{feature_names}{character vector of feature names. If the model already
-contains feature names, those would be used when \code{feature_names=NULL} (default value).
-Non-null \code{feature_names} could be provided to override those in the model.}
-
-\item{model}{object of class \code{xgb.Booster}}
-
-\item{text}{\code{character} vector previously generated by the \code{xgb.dump} 
-function  (where parameter \code{with_stats = TRUE} should have been set).
-\code{text} takes precedence over \code{model}.}
-
-\item{trees}{an integer vector of tree indices that should be parsed.
-If set to \code{NULL}, all trees of the model are parsed.
-It could be useful, e.g., in multiclass classification to get only
-the trees of one certain class. IMPORTANT: the tree index in xgboost models
-is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).}
-
-\item{use_int_id}{a logical flag indicating whether nodes in columns "Yes", "No", "Missing" should be
-represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).}
-
-\item{...}{currently not used.}
-}
-\value{
-A \code{data.table} with detailed information about model trees' nodes.
-
-The columns of the \code{data.table} are:
-
-\itemize{
- \item \code{Tree}: integer ID of a tree in a model (zero-based index)
- \item \code{Node}: integer ID of a node in a tree (zero-based index)
- \item \code{ID}: character identifier of a node in a model (only when \code{use_int_id=FALSE})
- \item \code{Feature}: for a branch node, it's a feature id or name (when available);
-             for a leaf note, it simply labels it as \code{'Leaf'}
- \item \code{Split}: location of the split for a branch node (split condition is always "less than")
- \item \code{Yes}: ID of the next node when the split condition is met
- \item \code{No}: ID of the next node when the split condition is not met
- \item \code{Missing}: ID of the next node when branch value is missing
- \item \code{Quality}: either the split gain (change in loss) or the leaf value
- \item \code{Cover}: metric related to the number of observation either seen by a split
-                     or collected by a leaf during training.
-} 
-
-When \code{use_int_id=FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
-in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from 
-the corresponding trees in the "Node" column.
-}
-\description{
-Parse a boosted tree model text dump into a \code{data.table} structure.
-}
-\examples{
-# Basic use:
-
-data(agaricus.train, package='xgboost')
-
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
-               eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-
-(dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
-
-# This bst model already has feature_names stored with it, so those would be used when 
-# feature_names is not set:
-(dt <- xgb.model.dt.tree(model = bst))
-
-# How to match feature names of splits that are following a current 'Yes' branch:
-
-merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
- 
-}

R-package/man/xgb.parameters.Rd

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{xgb.parameters<-}
-\alias{xgb.parameters<-}
-\title{Accessors for model parameters.}
-\usage{
-xgb.parameters(object) <- value
-}
-\arguments{
-\item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.}
-
-\item{value}{a list (or an object coercible to a list) with the names of parameters to set
-and the elements corresponding to parameter values.}
-}
-\description{
-Only the setter for xgboost parameters is currently implemented.
-}
-\details{
-Note that the setter would usually work more efficiently for \code{xgb.Booster.handle}
-than for \code{xgb.Booster}, since only just a handle would need to be copied.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-
-xgb.parameters(bst) <- list(eta = 0.1)
-
-}

R-package/man/xgb.plot.deepness.Rd

@@ -1,74 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R, R/xgb.plot.deepness.R
-\name{xgb.ggplot.deepness}
-\alias{xgb.ggplot.deepness}
-\alias{xgb.plot.deepness}
-\title{Plot model trees deepness}
-\usage{
-xgb.ggplot.deepness(model = NULL, which = c("2x1", "max.depth",
-  "med.depth", "med.weight"))
-
-xgb.plot.deepness(model = NULL, which = c("2x1", "max.depth",
-  "med.depth", "med.weight"), plot = TRUE, ...)
-}
-\arguments{
-\item{model}{either an \code{xgb.Booster} model generated by the \code{xgb.train} function
-or a data.table result of the \code{xgb.model.dt.tree} function.}
-
-\item{which}{which distribution to plot (see details).}
-
-\item{plot}{(base R barplot) whether a barplot should be produced. 
-If FALSE, only a data.table is returned.}
-
-\item{...}{other parameters passed to \code{barplot} or \code{plot}.}
-}
-\value{
-Other than producing plots (when \code{plot=TRUE}), the \code{xgb.plot.deepness} function
-silently returns a processed data.table where each row corresponds to a terminal leaf in a tree model,
-and contains information about leaf's depth, cover, and weight (which is used in calculating predictions).
-
-The \code{xgb.ggplot.deepness} silently returns either a list of two ggplot graphs when \code{which="2x1"}
-or a single ggplot graph for the other \code{which} options.
-}
-\description{
-Visualizes distributions related to depth of tree leafs.
-\code{xgb.plot.deepness} uses base R graphics, while \code{xgb.ggplot.deepness} uses the ggplot backend.
-}
-\details{
-When \code{which="2x1"}, two distributions with respect to the leaf depth
-are plotted on top of each other:
-\itemize{
- \item the distribution of the number of leafs in a tree model at a certain depth;
- \item the distribution of average weighted number of observations ("cover") 
-       ending up in leafs at certain depth.
-}
-Those could be helpful in determining sensible ranges of the \code{max_depth} 
-and \code{min_child_weight} parameters.
-
-When \code{which="max.depth"} or \code{which="med.depth"}, plots of either maximum or median depth
-per tree with respect to tree number are created. And \code{which="med.weight"} allows to see how
-a tree's median absolute leaf weight changes through the iterations.
-
-This function was inspired by the blog post
-\url{https://github.com/aysent/random-forest-leaf-visualization}.
-}
-\examples{
-
-data(agaricus.train, package='xgboost')
-
-# Change max_depth to a higher number to get a more significant result
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 6,
-               eta = 0.1, nthread = 2, nrounds = 50, objective = "binary:logistic",
-               subsample = 0.5, min_child_weight = 2)
-
-xgb.plot.deepness(bst)
-xgb.ggplot.deepness(bst)
-
-xgb.plot.deepness(bst, which='max.depth', pch=16, col=rgb(0,0,1,0.3), cex=2)
-
-xgb.plot.deepness(bst, which='med.weight', pch=16, col=rgb(0,0,1,0.3), cex=2)
-
-}
-\seealso{
-\code{\link{xgb.train}}, \code{\link{xgb.model.dt.tree}}.
-}

R-package/man/xgb.plot.importance.Rd

@@ -1,81 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R, R/xgb.plot.importance.R
-\name{xgb.ggplot.importance}
-\alias{xgb.ggplot.importance}
-\alias{xgb.plot.importance}
-\title{Plot feature importance as a bar graph}
-\usage{
-xgb.ggplot.importance(importance_matrix = NULL, top_n = NULL,
-  measure = NULL, rel_to_first = FALSE, n_clusters = c(1:10), ...)
-
-xgb.plot.importance(importance_matrix = NULL, top_n = NULL,
-  measure = NULL, rel_to_first = FALSE, left_margin = 10,
-  cex = NULL, plot = TRUE, ...)
-}
-\arguments{
-\item{importance_matrix}{a \code{data.table} returned by \code{\link{xgb.importance}}.}
-
-\item{top_n}{maximal number of top features to include into the plot.}
-
-\item{measure}{the name of importance measure to plot.
-When \code{NULL}, 'Gain' would be used for trees and 'Weight' would be used for gblinear.}
-
-\item{rel_to_first}{whether importance values should be represented as relative to the highest ranked feature.
-See Details.}
-
-\item{n_clusters}{(ggplot only) a \code{numeric} vector containing the min and the max range
-of the possible number of clusters of bars.}
-
-\item{...}{other parameters passed to \code{barplot} (except horiz, border, cex.names, names.arg, and las).}
-
-\item{left_margin}{(base R barplot) allows to adjust the left margin size to fit feature names.
-When it is NULL, the existing \code{par('mar')} is used.}
-
-\item{cex}{(base R barplot) passed as \code{cex.names} parameter to \code{barplot}.}
-
-\item{plot}{(base R barplot) whether a barplot should be produced.
-If FALSE, only a data.table is returned.}
-}
-\value{
-The \code{xgb.plot.importance} function creates a \code{barplot} (when \code{plot=TRUE})
-and silently returns a processed data.table with \code{n_top} features sorted by importance.
-
-The \code{xgb.ggplot.importance} function returns a ggplot graph which could be customized afterwards.
-E.g., to change the title of the graph, add \code{+ ggtitle("A GRAPH NAME")} to the result.
-}
-\description{
-Represents previously calculated feature importance as a bar graph.
-\code{xgb.plot.importance} uses base R graphics, while \code{xgb.ggplot.importance} uses the ggplot backend.
-}
-\details{
-The graph represents each feature as a horizontal bar of length proportional to the importance of a feature.
-Features are shown ranked in a decreasing importance order.
-It works for importances from both \code{gblinear} and \code{gbtree} models.
-
-When \code{rel_to_first = FALSE}, the values would be plotted as they were in \code{importance_matrix}.
-For gbtree model, that would mean being normalized to the total of 1
-("what is feature's importance contribution relative to the whole model?").
-For linear models, \code{rel_to_first = FALSE} would show actual values of the coefficients.
-Setting \code{rel_to_first = TRUE} allows to see the picture from the perspective of
-"what is feature's importance contribution relative to the most important feature?"
-
-The ggplot-backend method also performs 1-D clustering of the importance values,
-with bar colors corresponding to different clusters that have somewhat similar importance values.
-}
-\examples{
-data(agaricus.train)
-
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-
-importance_matrix <- xgb.importance(colnames(agaricus.train$data), model = bst)
-
-xgb.plot.importance(importance_matrix, rel_to_first = TRUE, xlab = "Relative importance")
-
-(gg <- xgb.ggplot.importance(importance_matrix, measure = "Frequency", rel_to_first = TRUE))
-gg + ggplot2::ylab("Frequency")
-
-}
-\seealso{
-\code{\link[graphics]{barplot}}.
-}

R-package/man/xgb.plot.multi.trees.Rd

@@ -1,75 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.plot.multi.trees.R
-\name{xgb.plot.multi.trees}
-\alias{xgb.plot.multi.trees}
-\title{Project all trees on one tree and plot it}
-\usage{
-xgb.plot.multi.trees(model, feature_names = NULL, features_keep = 5,
-  plot_width = NULL, plot_height = NULL, render = TRUE, ...)
-}
-\arguments{
-\item{model}{produced by the \code{xgb.train} function.}
-
-\item{feature_names}{names of each feature as a \code{character} vector.}
-
-\item{features_keep}{number of features to keep in each position of the multi trees.}
-
-\item{plot_width}{width in pixels of the graph to produce}
-
-\item{plot_height}{height in pixels of the graph to produce}
-
-\item{render}{a logical flag for whether the graph should be rendered (see Value).}
-
-\item{...}{currently not used}
-}
-\value{
-When \code{render = TRUE}:
-returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
-Similar to ggplot objects, it needs to be printed to see it when not running from command line.
-
-When \code{render = FALSE}:
-silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
-This could be useful if one wants to modify some of the graph attributes
-before rendering the graph with \code{\link[DiagrammeR]{render_graph}}.
-}
-\description{
-Visualization of the ensemble of trees as a single collective unit.
-}
-\details{
-This function tries to capture the complexity of a gradient boosted tree model
-in a cohesive way by compressing an ensemble of trees into a single tree-graph representation.
-The goal is to improve the interpretability of a model generally seen as black box.
-
-Note: this function is applicable to tree booster-based models only.
-
-It takes advantage of the fact that the shape of a binary tree is only defined by
-its depth (therefore, in a boosting model, all trees have similar shape).
-
-Moreover, the trees tend to reuse the same features.
-
-The function projects each tree onto one, and keeps for each position the
-\code{features_keep} first features (based on the Gain per feature measure).
-
-This function is inspired by this blog post:
-\url{https://wellecks.wordpress.com/2015/02/21/peering-into-the-black-box-visualizing-lambdamart/}
-}
-\examples{
-
-data(agaricus.train, package='xgboost')
-
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 15,
-               eta = 1, nthread = 2, nrounds = 30, objective = "binary:logistic",
-               min_child_weight = 50, verbose = 0)
-
-p <- xgb.plot.multi.trees(model = bst, features_keep = 3)
-print(p)
-
-\dontrun{
-# Below is an example of how to save this plot to a file.
-# Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
-library(DiagrammeR)
-gr <- xgb.plot.multi.trees(model=bst, features_keep = 3, render=FALSE)
-export_graph(gr, 'tree.pdf', width=1500, height=600)
-}
-
-}

R-package/man/xgb.plot.shap.Rd

@@ -1,138 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.plot.shap.R
-\name{xgb.plot.shap}
-\alias{xgb.plot.shap}
-\title{SHAP contribution dependency plots}
-\usage{
-xgb.plot.shap(data, shap_contrib = NULL, features = NULL, top_n = 1,
-  model = NULL, trees = NULL, target_class = NULL,
-  approxcontrib = FALSE, subsample = NULL, n_col = 1, col = rgb(0,
-  0, 1, 0.2), pch = ".", discrete_n_uniq = 5, discrete_jitter = 0.01,
-  ylab = "SHAP", plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6),
-  pch_NA = ".", pos_NA = 1.07, plot_loess = TRUE, col_loess = 2,
-  span_loess = 0.5, which = c("1d", "2d"), plot = TRUE, ...)
-}
-\arguments{
-\item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
-
-\item{shap_contrib}{a matrix of SHAP contributions that was computed earlier for the above
-\code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.}
-
-\item{features}{a vector of either column indices or of feature names to plot. When it is NULL,
-feature importance is calculated, and \code{top_n} high ranked features are taken.}
-
-\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.}
-
-\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-or \code{features} is missing.}
-
-\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.}
-
-\item{target_class}{is only relevant for multiclass models. When it is set to a 0-based class index,
-only SHAP contributions for that specific class are used.
-If it is not set, SHAP importances are averaged over all classes.}
-
-\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.}
-
-\item{subsample}{a random fraction of data points to use for plotting. When it is NULL,
-it is set so that up to 100K data points are used.}
-
-\item{n_col}{a number of columns in a grid of plots.}
-
-\item{col}{color of the scatterplot markers.}
-
-\item{pch}{scatterplot marker.}
-
-\item{discrete_n_uniq}{a maximal number of unique values in a feature to consider it as discrete.}
-
-\item{discrete_jitter}{an \code{amount} parameter of jitter added to discrete features' positions.}
-
-\item{ylab}{a y-axis label in 1D plots.}
-
-\item{plot_NA}{whether the contributions of cases with missing values should also be plotted.}
-
-\item{col_NA}{a color of marker for missing value contributions.}
-
-\item{pch_NA}{a marker type for NA values.}
-
-\item{pos_NA}{a relative position of the x-location where NA values are shown:
-\code{min(x) + (max(x) - min(x)) * pos_NA}.}
-
-\item{plot_loess}{whether to plot loess-smoothed curves. The smoothing is only done for features with
-more than 5 distinct values.}
-
-\item{col_loess}{a color to use for the loess curves.}
-
-\item{span_loess}{the \code{span} parameter in \code{\link[stats]{loess}}'s call.}
-
-\item{which}{whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.}
-
-\item{plot}{whether a plot should be drawn. If FALSE, only a lits of matrices is returned.}
-
-\item{...}{other parameters passed to \code{plot}.}
-}
-\value{
-In addition to producing plots (when \code{plot=TRUE}), it silently returns a list of two matrices:
-\itemize{
- \item \code{data} the values of selected features;
- \item \code{shap_contrib} the contributions of selected features.
-}
-}
-\description{
-Visualizing the SHAP feature contribution to prediction dependencies on feature value.
-}
-\details{
-These scatterplots represent how SHAP feature contributions depend of feature values.
-The similarity to partial dependency plots is that they also give an idea for how feature values
-affect predictions. However, in partial dependency plots, we usually see marginal dependencies
-of model prediction on feature value, while SHAP contribution dependency plots display the estimated
-contributions of a feature to model prediction for each individual case.
-
-When \code{plot_loess = TRUE} is set, feature values are rounded to 3 significant digits and
-weighted LOESS is computed and plotted, where weights are the numbers of data points
-at each rounded value.
-
-Note: SHAP contributions are shown on the scale of model margin. E.g., for a logistic binomial objective,
-the margin is prediction before a sigmoidal transform into probability-like values.
-Also, since SHAP stands for "SHapley Additive exPlanation" (model prediction = sum of SHAP
-contributions for all features + bias), depending on the objective used, transforming SHAP
-contributions for a feature from the marginal to the prediction space is not necessarily
-a meaningful thing to do.
-}
-\examples{
-
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-
-bst <- xgboost(agaricus.train$data, agaricus.train$label, nrounds = 50,
-               eta = 0.1, max_depth = 3, subsample = .5,
-               method = "hist", objective = "binary:logistic", nthread = 2, verbose = 0)
-
-xgb.plot.shap(agaricus.test$data, model = bst, features = "odor=none")
-contr <- predict(bst, agaricus.test$data, predcontrib = TRUE)
-xgb.plot.shap(agaricus.test$data, contr, model = bst, top_n = 12, n_col = 3)
-
-# multiclass example - plots for each class separately:
-nclass <- 3
-nrounds <- 20
-x <- as.matrix(iris[, -5])
-set.seed(123)
-is.na(x[sample(nrow(x) * 4, 30)]) <- TRUE # introduce some missing values
-mbst <- xgboost(data = x, label = as.numeric(iris$Species) - 1, nrounds = nrounds,
-                max_depth = 2, eta = 0.3, subsample = .5, nthread = 2,
-                objective = "multi:softprob", num_class = nclass, verbose = 0)
-trees0 <- seq(from=0, by=nclass, length.out=nrounds)
-col <- rgb(0, 0, 1, 0.5)
-xgb.plot.shap(x, model = mbst, trees = trees0, target_class = 0, top_n = 4,
-              n_col = 2, col = col, pch = 16, pch_NA = 17)
-xgb.plot.shap(x, model = mbst, trees = trees0 + 1, target_class = 1, top_n = 4,
-              n_col = 2, col = col, pch = 16, pch_NA = 17)
-xgb.plot.shap(x, model = mbst, trees = trees0 + 2, target_class = 2, top_n = 4,
-              n_col = 2, col = col, pch = 16, pch_NA = 17)
-
-}
-\references{
-Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
-
-Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
-}