Release 1.1.0

Co-authored-by: fis <jm.yuan@outlook.com>

.github/workflows/main.yml

@@ -1,138 +0,0 @@
-# This is a basic workflow to help you get started with Actions
-
-name: XGBoost-CI
-
-# Controls when the action will run. Triggers the workflow on push or pull request
-# events but only for the master branch
-on: [push, pull_request]
-
-env:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'stringi', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools')
-
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
-jobs:
-  test-with-jvm:
-    name: Test JVM on OS ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [windows-latest, windows-2016, ubuntu-latest]
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: actions/setup-java@v1
-      with:
-        java-version: 1.8
-
-    - name: Cache Maven packages
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2
-        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2
-
-    - name: Test JVM packages
-      run: |
-        cd jvm-packages
-        mvn test -pl :xgboost4j_2.12
-
-
-  lintr:
-    runs-on: ${{ matrix.config.os }}
-
-    name: Run R linters on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-
-    strategy:
-      matrix:
-        config:
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-1-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Run lintr
-      run: |
-        cd R-package
-        R.exe CMD INSTALL .
-        Rscript.exe tests/run_lint.R
-
-
-  test-with-R:
-    runs-on: ${{ matrix.config.os }}
-
-    name: Test R on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'autotools'}
-          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'autotools'}
-          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-1-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.6' # Version range or exact version of a Python version to use, using SemVer's version range syntax
-        architecture: 'x64' # optional x64 or x86. Defaults to x64 if not specified
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --compiler="${{ matrix.config.compiler }}" --build-tool="${{ matrix.config.build }}"

.gitignore

@@ -51,7 +51,6 @@ Debug
 #.Rbuildignore
 R-package.Rproj
 *.cache*
-.mypy_cache/
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -93,7 +92,6 @@ metastore_db
 # files from R-package source install
 **/config.status
 R-package/src/Makevars
-*.lib
 
 # Visual Studio Code
 /.vscode/

.travis.yml

@@ -43,7 +43,6 @@ addons:
       - graphviz
       - openssl
       - libgit2
-      - lz4
       - wget
       - r
     update: true

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.2.0)
+project(xgboost LANGUAGES CXX C VERSION 1.1.0)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)
@@ -32,9 +32,6 @@ option(R_LIB "Build shared library for R package" OFF)
 ## Dev
 option(USE_DEBUG_OUTPUT "Dump internal training results like gradients and predictions to stdout.
 Should only be used for debugging." OFF)
-option(FORCE_COLORED_OUTPUT "Force colored output from compilers, useful when ninja is used instead of make." OFF)
-option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC/Clang" OFF)
-option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
 option(GOOGLE_TEST "Build google tests" OFF)
 option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
 option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
@@ -60,7 +57,6 @@ address, leak, undefined and thread.")
 ## Plugins
 option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
 option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
-option(ADD_PKGCONFIG "Add xgboost.pc into system." ON)
 
 #-- Checks for building XGBoost
 if (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
@@ -82,11 +78,6 @@ endif (R_LIB AND GOOGLE_TEST)
 if (USE_AVX)
   message(SEND_ERROR  "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from XGBoost.")
 endif (USE_AVX)
-if (ENABLE_ALL_WARNINGS)
-  if ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-    message(SEND_ERROR "ENABLE_ALL_WARNINGS is only available for Clang and GCC.")
-  endif ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-endif (ENABLE_ALL_WARNINGS)
 
 #-- Sanitizer
 if (USE_SANITIZER)
@@ -101,20 +92,11 @@ if (USE_CUDA)
   message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
 
   enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.0)
-    message(FATAL_ERROR "CUDA version must be at least 10.0!")
-  endif()
   set(GEN_CODE "")
   format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
   message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
 endif (USE_CUDA)
 
-if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
-    ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
-      (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-color=always")
-endif()
-
 find_package(Threads REQUIRED)
 
 if (USE_OPENMP)
@@ -126,28 +108,14 @@ if (USE_OPENMP)
   find_package(OpenMP REQUIRED)
 endif (USE_OPENMP)
 
-# core xgboost
-add_subdirectory(${xgboost_SOURCE_DIR}/src)
-
 # dmlc-core
 msvc_use_static_runtime()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
 set_target_properties(dmlc PROPERTIES
-  CXX_STANDARD 14
+  CXX_STANDARD 11
   CXX_STANDARD_REQUIRED ON
   POSITION_INDEPENDENT_CODE ON)
-if (MSVC)
-  target_compile_options(dmlc PRIVATE
-                         -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  if (TARGET dmlc_unit_tests)
-    target_compile_options(dmlc_unit_tests PRIVATE
-                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  endif (TARGET dmlc_unit_tests)
-endif (MSVC)
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(dmlc PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
-target_link_libraries(objxgboost PUBLIC dmlc)
+list(APPEND LINKED_LIBRARIES_PRIVATE dmlc)
 
 # rabit
 set(RABIT_BUILD_DMLC OFF)
@@ -156,17 +124,9 @@ set(RABIT_WITH_R_LIB ${R_LIB})
 add_subdirectory(rabit)
 
 if (RABIT_MOCK)
-  target_link_libraries(objxgboost PUBLIC rabit_mock_static)
-  if (MSVC)
-    target_compile_options(rabit_mock_static PRIVATE
-                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  endif (MSVC)
+  list(APPEND LINKED_LIBRARIES_PRIVATE rabit_mock_static)
 else()
-  target_link_libraries(objxgboost PUBLIC rabit)
-  if (MSVC)
-    target_compile_options(rabit PRIVATE
-                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  endif (MSVC)
+  list(APPEND LINKED_LIBRARIES_PRIVATE rabit)
 endif(RABIT_MOCK)
 foreach(lib rabit rabit_base rabit_empty rabit_mock rabit_mock_static)
   # Explicitly link dmlc to rabit, so that configured header (build_config.h)
@@ -176,9 +136,6 @@ foreach(lib rabit rabit_base rabit_empty rabit_mock rabit_mock_static)
     if (HIDE_CXX_SYMBOLS)  # Hide all C++ symbols from Rabit
       set_target_properties(${lib} PROPERTIES CXX_VISIBILITY_PRESET hidden)
     endif (HIDE_CXX_SYMBOLS)
-    if (ENABLE_ALL_WARNINGS)
-      target_compile_options(${lib} PRIVATE -Wall -Wextra)
-    endif (ENABLE_ALL_WARNINGS)
   endif (TARGET ${lib})
 endforeach()
 
@@ -187,20 +144,19 @@ if (R_LIB)
   add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
 endif (R_LIB)
 
-# Plugin
+# core xgboost
+list(APPEND LINKED_LIBRARIES_PRIVATE Threads::Threads ${CMAKE_THREAD_LIBS_INIT})
 add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
+add_subdirectory(${xgboost_SOURCE_DIR}/src)
+target_link_libraries(objxgboost PUBLIC dmlc)
+set(XGBOOST_OBJ_SOURCES "${XGBOOST_OBJ_SOURCES};$<TARGET_OBJECTS:objxgboost>")
 
 #-- library
 if (BUILD_STATIC_LIB)
-  add_library(xgboost STATIC)
+  add_library(xgboost STATIC ${XGBOOST_OBJ_SOURCES})
 else (BUILD_STATIC_LIB)
-  add_library(xgboost SHARED)
+  add_library(xgboost SHARED ${XGBOOST_OBJ_SOURCES})
 endif (BUILD_STATIC_LIB)
-target_link_libraries(xgboost PRIVATE objxgboost)
-
-if (USE_NVTX)
-  enable_nvtx(xgboost)
-endif (USE_NVTX)
 
 #-- Hide all C++ symbols
 if (HIDE_CXX_SYMBOLS)
@@ -212,6 +168,7 @@ 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)
@@ -220,21 +177,18 @@ endif (JVM_BINDINGS)
 #-- End shared library
 
 #-- CLI for xgboost
-add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
-target_link_libraries(runxgboost PRIVATE objxgboost)
-if (USE_NVTX)
-  enable_nvtx(runxgboost)
-endif (USE_NVTX)
+add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc ${XGBOOST_OBJ_SOURCES})
 
 target_include_directories(runxgboost
   PRIVATE
   ${xgboost_SOURCE_DIR}/include
   ${xgboost_SOURCE_DIR}/dmlc-core/include
   ${xgboost_SOURCE_DIR}/rabit/include)
+target_link_libraries(runxgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
 set_target_properties(
   runxgboost PROPERTIES
   OUTPUT_NAME xgboost
-  CXX_STANDARD 14
+  CXX_STANDARD 11
   CXX_STANDARD_REQUIRED ON)
 #-- End CLI for xgboost
 
@@ -245,12 +199,11 @@ add_dependencies(xgboost runxgboost)
 
 #-- Installing XGBoost
 if (R_LIB)
-  include(cmake/RPackageInstallTargetSetup.cmake)
   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}/R-package-install")
+  setup_rpackage_install_target(xgboost ${CMAKE_CURRENT_BINARY_DIR})
   set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
 endif (R_LIB)
 if (MINGW)
@@ -321,12 +274,3 @@ endif (GOOGLE_TEST)
 # 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()
-
-# Add xgboost.pc
-if (ADD_PKGCONFIG)
-  configure_file(${xgboost_SOURCE_DIR}/cmake/xgboost.pc.in ${xgboost_BINARY_DIR}/xgboost.pc @ONLY)
-
-  install(
-    FILES ${xgboost_BINARY_DIR}/xgboost.pc
-    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
-endif (ADD_PKGCONFIG)

CONTRIBUTORS.md

@@ -10,8 +10,8 @@ The Project Management Committee(PMC) consists group of active committers that m
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [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 Group
-  - Yuan is a software engineer in Ant Group. He contributed mostly in R and Python packages.
+* [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.
 * [Jiaming Yuan](https://github.com/trivialfis)
@@ -37,8 +37,6 @@ Committers are people who have made substantial contribution to the project and
   - Sergei is a software engineer in Criteo. He contributed mostly in JVM packages.
 * [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.
-* [Egor Smirnov](https://github.com/SmirnovEgorRu), Intel
-  - Egor has led a major effort to improve the performance of XGBoost on multi-core CPUs.
 
 
 Become a Committer

Jenkinsfile

@@ -6,9 +6,6 @@
 // Command to run command inside a docker container
 dockerRun = 'tests/ci_build/ci_build.sh'
 
-// Which CUDA version to use when building reference distribution wheel
-ref_cuda_ver = '10.0'
-
 import groovy.transform.Field
 
 @Field
@@ -34,14 +31,13 @@ pipeline {
 
   // Build stages
   stages {
-    stage('Jenkins Linux: Initialize') {
-      agent { label 'job_initializer' }
+    stage('Jenkins Linux: Get sources') {
+      agent { label 'linux && cpu' }
       steps {
         script {
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
-        sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
         milestone ordinal: 1
       }
@@ -68,15 +64,9 @@ pipeline {
             'build-cpu': { BuildCPU() },
             'build-cpu-rabit-mock': { BuildCPUMock() },
             'build-cpu-non-omp': { BuildCPUNonOmp() },
-            // Build reference, distribution-ready Python wheel with CUDA 10.0
-            // using CentOS 6 image
             'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            // The build-gpu-* builds below use Ubuntu image
             'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-gpu-cuda10.2': { BuildCUDA(cuda_version: '10.2') },
-            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0') },
-            'build-jvm-packages-gpu-cuda10.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '10.0') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
             'build-jvm-doc': { BuildJVMDoc() }
           ])
         }
@@ -89,14 +79,13 @@ pipeline {
         script {
           parallel ([
             'test-python-cpu': { TestPythonCPU() },
-            'test-python-gpu-cuda10.2': { TestPythonGPU(host_cuda_version: '10.2') },
-            'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '11.0') },
-            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2', multi_gpu: true) },
-            'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2') },
-            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-jvm-jdk8-cuda10.0': { CrossTestJVMwithJDKGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.0') },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
+            '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-3.5.3': { TestR(use_r35: true) }
@@ -110,7 +99,7 @@ pipeline {
       steps {
         script {
           parallel ([
-            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '3.0.0') }
+            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '2.4.3') }
           ])
         }
         milestone ordinal: 5
@@ -134,12 +123,8 @@ def checkoutSrcs() {
   }
 }
 
-def GetCUDABuildContainerType(cuda_version) {
-  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos6' : 'gpu_build'
-}
-
 def ClangTidy() {
-  node('linux && cpu_build') {
+  node('linux && cpu') {
     unstash name: 'srcs'
     echo "Running clang-tidy job..."
     def container_type = "clang_tidy"
@@ -159,7 +144,7 @@ def Lint() {
     def container_type = "cpu"
     def docker_binary = "docker"
     sh """
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate cpu_test && make lint"
+    ${dockerRun} ${container_type} ${docker_binary} make lint
     """
     deleteDir()
   }
@@ -173,7 +158,7 @@ def SphinxDoc() {
     def docker_binary = "docker"
     def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
     sh """#!/bin/bash
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate cpu_test && make -C doc html"
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} make -C doc html
     """
     deleteDir()
   }
@@ -188,10 +173,8 @@ def Doxygen() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
     """
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading doc...'
-      s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
-    }
+    echo 'Uploading doc...'
+    s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
     deleteDir()
   }
 }
@@ -207,7 +190,7 @@ def BuildCPU() {
       # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
       # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
       # See discussion at https://github.com/dmlc/xgboost/issues/5510
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh
     ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
     """
     // Sanitizer test
@@ -256,52 +239,26 @@ def BuildCPUNonOmp() {
 }
 
 def BuildCUDA(args) {
-  node('linux && cpu_build') {
+  node('linux && cpu') {
     unstash name: 'srcs'
     echo "Build with CUDA ${args.cuda_version}"
-    def container_type = GetCUDABuildContainerType(args.cuda_version)
+    def container_type = "gpu_build"
     def docker_binary = "docker"
     def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
     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 -DHIDE_CXX_SYMBOLS=ON ${arch_flag}
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOLS=ON
     ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
     """
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-    if (args.cuda_version == ref_cuda_ver && (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release'))) {
-      echo 'Uploading Python wheel...'
+    // Stash wheel for CUDA 10.0 target
+    if (args.cuda_version == '10.0') {
+      echo 'Stashing Python wheel...'
+      stash name: 'xgboost_whl_cuda10', includes: 'python-package/dist/*.whl'
       path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
       s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+      echo 'Stashing C++ test executable (testxgboost)...'
+      stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost'
     }
-    echo 'Stashing C++ test executable (testxgboost)...'
-    stash name: "xgboost_cpp_tests_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    deleteDir()
-  }
-}
-
-def BuildJVMPackagesWithCUDA(args) {
-  node('linux && mgpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
-    def container_type = "jvm_gpu_build"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    // 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} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
-    """
-    echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
-    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
     deleteDir()
   }
 }
@@ -332,17 +289,15 @@ def BuildJVMDoc() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
     """
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading doc...'
-      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
-    }
+    echo 'Uploading doc...'
+    s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
     deleteDir()
   }
 }
 
 def TestPythonCPU() {
   node('linux && cpu') {
-    unstash name: "xgboost_whl_cuda${ref_cuda_ver}"
+    unstash name: 'xgboost_whl_cuda10'
     unstash name: 'srcs'
     unstash name: 'xgboost_cli'
     echo "Test Python CPU"
@@ -350,35 +305,45 @@ def TestPythonCPU() {
     def docker_binary = "docker"
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-py35
     """
     deleteDir()
   }
 }
 
 def TestPythonGPU(args) {
-  def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
+  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
   node(nodeReq) {
-    unstash name: "xgboost_whl_cuda${artifact_cuda_version}"
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
+    unstash name: 'xgboost_whl_cuda10'
     unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.host_cuda_version}"
+    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.host_cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
     if (args.multi_gpu) {
       echo "Using multiple GPUs"
-      // Allocate extra space in /dev/shm to enable NCCL
-      def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'"
       sh """
-      ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
       """
+      if (args.cuda_version != '9.0') {
+        echo "Running tests with cuDF..."
+        sh """
+        ${dockerRun} cudf ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu-cudf
+        """
+      }
     } else {
       echo "Using a single GPU"
       sh """
       ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
       """
+      if (args.cuda_version != '9.0') {
+        echo "Running tests with cuDF..."
+        sh """
+        ${dockerRun} cudf ${docker_binary} ${docker_args} tests/ci_build/test_python.sh cudf
+        """
+      }
     }
+    // For CUDA 10.0 target, run cuDF tests too
     deleteDir()
   }
 }
@@ -398,34 +363,21 @@ def TestCppRabit() {
 }
 
 def TestCppGPU(args) {
-  def nodeReq = 'linux && mgpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
+  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
   node(nodeReq) {
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
+    unstash name: 'xgboost_cpp_tests'
     unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.host_cuda_version}"
+    echo "Test C++, CUDA ${args.cuda_version}"
     def container_type = "gpu"
     def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.host_cuda_version}"
-    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
-    deleteDir()
-  }
-}
-
-def CrossTestJVMwithJDKGPU(args) {
-  def nodeReq = 'linux && mgpu'
-  node(nodeReq) {
-    unstash name: "xgboost4j_jar_gpu"
-    unstash name: 'srcs'
-    if (args.spark_version != null) {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}, CUDA ${args.host_cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION=${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 "Test XGBoost4J on a machine with JDK ${args.jdk_version}, CUDA ${args.host_cuda_version}"
+      echo "Using a single GPU"
+      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=-*.MGPU_*"
     }
-    def container_type = "gpu_jvm"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.host_cuda_version}"
-    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_gpu_cross.sh"
     deleteDir()
   }
 }
@@ -472,11 +424,10 @@ def DeployJVMPackages(args) {
     unstash name: 'srcs'
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Deploying to xgboost-maven-repo S3 repo...'
+      def container_type = "jvm"
+      def docker_binary = "docker"
       sh """
-      ${dockerRun} jvm docker tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 0
-      """
-      sh """
-      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 1
+      ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
       """
     }
     deleteDir()

Jenkinsfile-win64

@@ -10,25 +10,15 @@ def commit_id   // necessary to pass a variable from one stage to another
 
 pipeline {
   agent none
-
-  // Setup common job properties
-  options {
-    timestamps()
-    timeout(time: 240, unit: 'MINUTES')
-    buildDiscarder(logRotator(numToKeepStr: '10'))
-    preserveStashes()
-  }
-
   // Build stages
   stages {
-    stage('Jenkins Win64: Initialize') {
-      agent { label 'job_initializer' }
+    stage('Jenkins Win64: Get sources') {
+      agent { label 'win64 && build' }
       steps {
         script {
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
-        sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
         milestone ordinal: 1
       }
@@ -38,7 +28,7 @@ pipeline {
       steps {
         script {
           parallel ([
-            'build-win64-cuda10.1': { BuildWin64() }
+            'build-win64-cuda9.0': { BuildWin64() }
           ])
         }
         milestone ordinal: 2
@@ -49,7 +39,10 @@ pipeline {
       steps {
         script {
           parallel ([
-            'test-win64-cuda10.1': { TestWin64() },
+            '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
@@ -74,18 +67,14 @@ def checkoutSrcs() {
 }
 
 def BuildWin64() {
-  node('win64 && cuda10_unified') {
+  node('win64 && build') {
     unstash name: 'srcs'
     echo "Building XGBoost for Windows AMD64 target..."
     bat "nvcc --version"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
     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 ${arch_flag}
+    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
     """
     bat """
     cd build
@@ -103,11 +92,8 @@ def BuildWin64() {
     """
     echo 'Stashing Python wheel...'
     stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
+    path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+    s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
     echo 'Stashing C++ test executable (testxgboost)...'
     stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
     stash name: 'xgboost_cli', includes: 'xgboost.exe'
@@ -115,29 +101,51 @@ def BuildWin64() {
   }
 }
 
-def TestWin64() {
-  node('win64 && cuda10_unified') {
+def TestWin64CPU() {
+  node('win64 && cpu') {
     unstash name: 'srcs'
     unstash name: 'xgboost_whl'
     unstash name: 'xgboost_cli'
-    unstash name: 'xgboost_cpp_tests'
-    echo "Test Win64"
-    bat "nvcc --version"
-    echo "Running C++ tests..."
-    bat "build\\testxgboost.exe"
-    echo "Installing Python dependencies..."
-    def env_name = 'win64_' + UUID.randomUUID().toString().replaceAll('-', '')
-    bat "conda env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
+    echo "Test Win64 CPU"
     echo "Installing Python wheel..."
+    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
     bat """
-    conda activate ${env_name} && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
+    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
+    """
+    echo "Installing Python dependencies..."
+    bat """
+     conda activate && conda upgrade scikit-learn pandas numpy
     """
     echo "Running Python tests..."
-    bat "conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace tests\\python"
-    bat """
-    conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
-    """
-    bat "conda env remove --name ${env_name}"
+    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 "Installing Python dependencies..."
+    bat """
+     conda activate && conda upgrade scikit-learn pandas numpy
+    """
+    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()
   }
 }

Makefile

@@ -44,7 +44,7 @@ export CXX = g++
 endif
 endif
 
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++14 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
+export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
 CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
 
 ifeq ($(TEST_COVER), 1)

NEWS.md

@@ -3,206 +3,6 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
-## v1.1.0 (2020.05.17)
-
-### Better performance on multi-core CPUs (#5244, #5334, #5522)
-* Poor performance scaling of the `hist` algorithm for multi-core CPUs has been under investigation (#3810). #5244 concludes the ongoing effort to improve performance scaling on multi-CPUs, in particular Intel CPUs. Roadmap: #5104
-* #5334 makes steps toward reducing memory consumption for the `hist` tree method on CPU.
-* #5522 optimizes random number generation for data sampling.
-
-### Deterministic GPU algorithm for regression and classification (#5361)
-* GPU algorithm for regression and classification tasks is now deterministic.
-* Roadmap: #5023. Currently only single-GPU training is deterministic. Distributed training with multiple GPUs is not yet deterministic.
-
-### Improve external memory support on GPUs (#5093, #5365)
-* Starting from 1.0.0 release, we added support for external memory on GPUs to enable training with larger datasets. Gradient-based sampling (#5093) speeds up the external memory algorithm by intelligently sampling a subset of the training data to copy into the GPU memory. [Learn more about out-of-core GPU gradient boosting.](https://arxiv.org/abs/2005.09148)
-* GPU-side data sketching now works with data from external memory (#5365).
-
-### Parameter validation: detection of unused or incorrect parameters (#5477, #5569, #5508)
-* Mis-spelled training parameter is a common user mistake. In previous versions of XGBoost, mis-spelled parameters were silently ignored. Starting with 1.0.0 release, XGBoost will produce a warning message if there is any unused training parameters. The 1.1.0 release makes parameter validation available to the scikit-learn interface (#5477) and the R binding (#5569).
-
-### Thread-safe, in-place prediction method (#5389, #5512)
-* Previously, the prediction method was not thread-safe (#5339). This release adds a new API function `inplace_predict()` that is thread-safe. It is now possible to serve concurrent requests for prediction using a shared model object.
-* It is now possible to compute prediction in-place for selected data formats (`numpy.ndarray` / `scipy.sparse.csr_matrix` / `cupy.ndarray` / `cudf.DataFrame` / `pd.DataFrame`) without creating a `DMatrix` object.
-
-### Addition of Accelerated Failure Time objective for survival analysis (#4763, #5473, #5486, #5552, #5553)
-* Survival analysis (regression) models the time it takes for an event of interest to occur. The target label is potentially censored, i.e. the label is a range rather than a single number. We added a new objective `survival:aft` to support survival analysis. Also added is the new API to specify the ranged labels. Check out [the tutorial](https://xgboost.readthedocs.io/en/release_1.1.0/tutorials/aft_survival_analysis.html) and the [demos](https://github.com/dmlc/xgboost/tree/release_1.1.0/demo/aft_survival).
-* GPU support is work in progress (#5714).
-
-### Improved installation experience on Mac OSX (#5597, #5602, #5606, #5701)
-* It only takes two commands to install the XGBoost Python package: `brew install libomp` followed by `pip install xgboost`. The installed XGBoost will use all CPU cores. Even better, starting with this release, we distribute pre-compiled binary wheels targeting Mac OSX. Now the install command `pip install xgboost` finishes instantly, as it no longer compiles the C++ source of XGBoost. The last three Mac versions (High Sierra, Mojave, Catalina) are supported.
-* R package: the 1.1.0 release fixes the error `Initializing libomp.dylib, but found libomp.dylib already initialized` (#5701)
-
-### Ranking metrics are now accelerated on GPUs (#5380, #5387, #5398)
-
-### GPU-side data matrix to ingest data directly from other GPU libraries (#5420, #5465)
-* Previously, data on GPU memory had to be copied back to the main memory before it could be used by XGBoost. Starting with 1.1.0 release, XGBoost provides a dedicated interface (`DeviceQuantileDMatrix`) so that it can ingest data from GPU memory directly. The result is that XGBoost interoperates better with GPU-accelerated data science libraries, such as cuDF, cuPy, and PyTorch.
-* Set device in device dmatrix. (#5596)
-
-### Robust model serialization with JSON (#5123, #5217)
-* We continue efforts from the 1.0.0 release to adopt JSON as the format to save and load models robustly. Refer to the release note for 1.0.0 to learn more.
-* It is now possible to store internal configuration of the trained model (`Booster`) object in R as a JSON string (#5123, #5217).
-
-### Improved integration with Dask
-* Pass through `verbose` parameter for dask fit (#5413)
-* Use `DMLC_TASK_ID`. (#5415)
-* Order the prediction result. (#5416)
-* Honor `nthreads` from dask worker. (#5414)
-* Enable grid searching with scikit-learn. (#5417)
-* Check non-equal when setting threads. (#5421)
-* Accept other inputs for prediction. (#5428)
-* Fix missing value for scikit-learn interface. (#5435)
-
-### XGBoost4J-Spark: Check number of columns in the data iterator (#5202, #5303)
-* Before, the native layer in XGBoost did not know the number of columns (features) ahead of time and had to guess the number of columns by counting the feature index when ingesting data. This method has a failure more in distributed setting: if the training data is highly sparse, some features may be completely missing in one or more worker partitions. Thus, one or more workers may deduce an incorrect data shape, leading to crashes or silently wrong models.
-* Enforce correct data shape by passing the number of columns explicitly from the JVM layer into the native layer.
-
-### Major refactoring of the `DMatrix` class
-* Continued from 1.0.0 release.
-* Remove update prediction cache from predictors. (#5312)
-* Predict on Ellpack. (#5327)
-* Partial rewrite EllpackPage (#5352)
-* Use ellpack for prediction only when sparsepage doesn't exist. (#5504)
-* RFC: #4354, Roadmap: #5143
-
-### Breaking: XGBoost Python package now requires Pip 19.0 and higher (#5589)
-* Your Linux machine may have an old version of Pip and may attempt to install a source package, leading to long installation time. This is because we are now using `manylinux2010` tag in the binary wheel release. Ensure you have Pip 19.0 or newer by running `python3 -m pip -V` to check the version. Upgrade Pip with command
-```
-python3 -m pip install --upgrade pip
-```
-Upgrading to latest pip allows us to depend on newer versions of system libraries. [TensorFlow](https://www.tensorflow.org/install/pip) also requires Pip 19.0+.
-
-### Breaking: GPU algorithm now requires CUDA 10.0 and higher (#5649)
-* CUDA 10.0 is necessary to make the GPU algorithm deterministic (#5361).
-
-### Breaking: `silent` parameter is now removed (#5476)
-* Please use `verbosity` instead.
-
-### Breaking: Set `output_margin` to True for custom objectives (#5564)
-* Now both R and Python interface custom objectives get un-transformed (raw) prediction outputs.
-
-### Breaking: `Makefile` is now removed. We use CMake exclusively to build XGBoost (#5513)
-* Exception: the R package uses Autotools, as the CRAN ecosystem did not yet adopt CMake widely.
-
-### Breaking: `distcol` updater is now removed (#5507)
-* The `distcol` updater has been long broken, and currently we lack resources to implement a working implementation from scratch.
-
-### Deprecation notices
-* **Python 3.5**. This release is the last release to support Python 3.5. The following release (1.2.0) will require Python 3.6.
-* **Scala 2.11**. Currently XGBoost4J supports Scala 2.11. However, if a future release of XGBoost adopts Spark 3, it will not support Scala 2.11, as Spark 3 requires Scala 2.12+. We do not yet know which XGBoost release will adopt Spark 3.
-
-### Known limitations
-* (Python package) When early stopping is activated with `early_stopping_rounds` at training time, the prediction method (`xgb.predict()`) behaves in a surprising way. If XGBoost runs for M rounds and chooses iteration N (N < M) as the best iteration, then the prediction method will use M trees by default. To use the best iteration (N trees), users will need to manually take the best iteration field `bst.best_iteration` and pass it as the `ntree_limit` argument to `xgb.predict()`. See #5209 and #4052 for additional context.
-* GPU ranking objective is currently not deterministic (#5561).
-* When training parameter `reg_lambda` is set to zero, some leaf nodes may be assigned a NaN value. (See [discussion](https://discuss.xgboost.ai/t/still-getting-unexplained-nans-new-replication-code/1383/9).) For now, please set `reg_lambda` to a nonzero value.
-
-### Community and Governance
-* The XGBoost Project Management Committee (PMC) is pleased to announce a new committer: Egor Smirnov (@SmirnovEgorRu). He has led a major initiative to improve the performance of XGBoost on multi-core CPUs.
-
-### Bug-fixes
-* Improved compatibility with scikit-learn (#5255, #5505, #5538)
-* Remove f-string, since it's not supported by Python 3.5 (#5330). Note that Python 3.5 support is deprecated and schedule to be dropped in the upcoming release (1.2.0).
-* Fix the pruner so that it doesn't prune the same branch twice (#5335)
-* Enforce only major version in JSON model schema (#5336). Any major revision of the model schema would bump up the major version.
-* Fix a small typo in sklearn.py that broke multiple eval metrics (#5341)
-* Restore loading model from a memory buffer (#5360)
-* Define lazy isinstance for Python compat (#5364)
-* [R] fixed uses of `class()` (#5426)
-* Force compressed buffer to be 4 bytes aligned, to keep cuda-memcheck happy (#5441)
-* Remove warning for calling host function (`std::max`) on a GPU device (#5453)
-* Fix uninitialized value bug in xgboost callback (#5463)
-* Fix model dump in CLI (#5485)
-* Fix out-of-bound array access in `WQSummary::SetPrune()` (#5493)
-* Ensure that configured `dmlc/build_config.h` is picked up by Rabit and XGBoost, to fix build on Alpine (#5514)
-* Fix a misspelled method, made in a git merge (#5509)
-* Fix a bug in binary model serialization (#5532)
-* Fix CLI model IO (#5535)
-* Don't use `uint` for threads (#5542)
-* Fix R interaction constraints to handle more than 100000 features (#5543)
-* [jvm-packages] XGBoost Spark should deal with NaN when parsing evaluation output (#5546)
-* GPU-side data sketching is now aware of query groups in learning-to-rank data (#5551)
-* Fix DMatrix slicing for newly added fields (#5552)
-* Fix configuration status with loading binary model (#5562)
-* Fix build when OpenMP is disabled (#5566)
-* R compatibility patches (#5577, #5600)
-* gpu\_hist performance fixes (#5558)
-* Don't set seed on CLI interface (#5563)
-* [R] When serializing model, preserve model attributes related to early stopping (#5573)
-* Avoid rabit calls in learner configuration (#5581)
-* Hide C++ symbols in libxgboost.so when building Python wheel (#5590). This fixes apache/incubator-tvm#4953.
-* Fix compilation on Mac OSX High Sierra (10.13) (#5597)
-* Fix build on big endian CPUs (#5617)
-* Resolve crash due to use of `vector<bool>::iterator` (#5642)
-* Validation JSON model dump using JSON schema (#5660)
-
-### Performance improvements
-* Wide dataset quantile performance improvement (#5306)
-* Reduce memory usage of GPU-side data sketching (#5407)
-* Reduce span check overhead (#5464)
-* Serialise booster after training to free up GPU memory (#5484)
-* Use the maximum amount of GPU shared memory available to speed up the histogram kernel (#5491)
-* Use non-synchronising scan in Thrust (#5560)
-* Use `cudaDeviceGetAttribute()` instead of `cudaGetDeviceProperties()` for speed (#5570)
-
-### API changes
-* Support importing data from a Pandas SparseArray (#5431)
-* `HostDeviceVector` (vector shared between CPU and GPU memory) now exposes `HostSpan` interface, to enable access on the CPU side with bound check (#5459)
-* Accept other gradient types for `SplitEntry` (#5467)
-
-### Usability Improvements, Documentation
-* Add `JVM_CHECK_CALL` to prevent C++ exceptions from leaking into the JVM layer (#5199)
-* Updated Windows build docs (#5283)
-* Update affiliation of @hcho3 (#5292)
-* Display Sponsor button, link to OpenCollective (#5325)
-* Update docs for GPU external memory (#5332)
-* Add link to GPU documentation (#5437)
-* Small updates to GPU documentation (#5483)
-* Edits on tutorial for XGBoost job on Kubernetes (#5487)
-* Add reference to GPU external memory (#5490)
-* Fix typos (#5346, #5371, #5384, #5399, #5482, #5515)
-* Update Python doc (#5517)
-* Add Neptune and Optuna to list of examples (#5528)
-* Raise error if the number of data weights doesn't match the number of data sets (#5540)
-* Add a note about GPU ranking (#5572)
-* Clarify meaning of `training` parameter in the C API function `XGBoosterPredict()` (#5604)
-* Better error handling for situations where existing trees cannot be modified (#5406, #5418). This feature is enabled when `process_type` is set to `update`.
-
-### Maintenance: testing, continuous integration, build system
-* Add C++ test coverage for data sketching (#5251)
-* Ignore gdb\_history (#5257)
-* Rewrite setup.py. (#5271, #5280)
-* Use `scikit-learn` in extra dependencies (#5310)
-* Add CMake option to build static library (#5397)
-* [R] changed FindLibR to take advantage of CMake cache (#5427)
-* [R] fixed inconsistency in R -e calls in FindLibR.cmake (#5438)
-* Refactor tests with data generator (#5439)
-* Resolve failing Travis CI (#5445)
-* Update dmlc-core. (#5466)
-* [CI] Use clang-tidy 10 (#5469)
-* De-duplicate code for checking maximum number of nodes (#5497)
-* [CI] Use Ubuntu 18.04 LTS in JVM CI, because 19.04 is EOL (#5537)
-* [jvm-packages] [CI] Create a Maven repository to host SNAPSHOT JARs (#5533)
-* [jvm-packages] [CI] Publish XGBoost4J JARs with Scala 2.11 and 2.12 (#5539)
-* [CI] Use Vault repository to re-gain access to devtoolset-4 (#5589)
-
-### Maintenance: Refactor code for legibility and maintainability
-* Move prediction cache to Learner (#5220, #5302)
-* Remove SimpleCSRSource (#5315)
-* Refactor SparsePageSource, delete cache files after use (#5321)
-* Remove unnecessary DMatrix methods (#5324)
-* Split up `LearnerImpl` (#5350)
-* Move segment sorter to common (#5378)
-* Move thread local entry into Learner (#5396)
-* Split up test helpers header (#5455)
-* Requires setting leaf stat when expanding tree (#5501)
-* Purge device\_helpers.cuh (#5534)
-* Use thrust functions instead of custom functions (#5544)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Andrew Kane (@ankane), Avinash Barnwal (@avinashbarnwal), Bart Broere (@bartbroere), Andy Adinets (@canonizer), Chen Qin (@chenqin), Daiki Katsuragawa (@daikikatsuragawa), David Díaz Vico (@daviddiazvico), Darius Kharazi (@dkharazi), Darby Payne (@dpayne), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), Jan Borchmann (@jborchma), Kamil A. Kaczmarek (@kamil-kaczmarek), Melissa Kohl (@mjkohl32), Nicolas Scozzaro (@nscozzaro), Paul Kaefer (@paulkaefer), Rong Ou (@rongou), Samrat Pandiri (@samratp), Sriram Chandramouli (@sriramch), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), Liang-Chi Hsieh (@viirya), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10),
-
-**Reviewers**: Nan Zhu (@CodingCat), @LeZhengThu, Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Steve Bronder (@SteveBronder), Nikita Titov (@StrikerRUS), Andrew Kane (@ankane), Avinash Barnwal (@avinashbarnwal), @brydag, Andy Adinets (@canonizer), Chandra Shekhar Reddy (@chandrureddy), Chen Qin (@chenqin), Codecov (@codecov-io), David Díaz Vico (@daviddiazvico), Darby Payne (@dpayne), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), @johnny-cat, Mu Li (@mli), Mate Soos (@msoos), @rnyak, Rong Ou (@rongou), Sriram Chandramouli (@sriramch), Toby Dylan Hocking (@tdhock), Yuan Tang (@terrytangyuan), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Liang-Chi Hsieh (@viirya), Bobby Wang (@wbo4958),
-
 ## v1.0.0 (2020.02.19)
 This release marks a major milestone for the XGBoost project.
 

R-package/CMakeLists.txt

@@ -6,11 +6,8 @@ file(GLOB_RECURSE R_SOURCES
   ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
 # Use object library to expose symbols
 add_library(xgboost-r OBJECT ${R_SOURCES})
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(xgboost-r PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
-target_compile_definitions(xgboost-r
-  PUBLIC
+
+set(R_DEFINITIONS
   -DXGBOOST_STRICT_R_MODE=1
   -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
   -DDMLC_LOG_BEFORE_THROW=0
@@ -18,27 +15,24 @@ target_compile_definitions(xgboost-r
   -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)
-target_link_libraries(xgboost-r PUBLIC ${LIBR_CORE_LIBRARY})
-if (USE_OPENMP)
-  find_package(OpenMP REQUIRED)
-  target_link_libraries(xgboost-r PUBLIC OpenMP::OpenMP_CXX OpenMP::OpenMP_C)
-endif (USE_OPENMP)
 set_target_properties(
   xgboost-r PROPERTIES
-  CXX_STANDARD 14
+  CXX_STANDARD 11
   CXX_STANDARD_REQUIRED ON
   POSITION_INDEPENDENT_CODE ON)
 
-# Get compilation and link flags of xgboost-r and propagate to objxgboost
-target_link_libraries(objxgboost PUBLIC xgboost-r)
-# Add all objects of xgboost-r to objxgboost
-target_sources(objxgboost INTERFACE $<TARGET_OBJECTS:xgboost-r>)
+set(XGBOOST_DEFINITIONS "${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)
 
-set(LIBR_HOME "${LIBR_HOME}" PARENT_SCOPE)
-set(LIBR_EXECUTABLE "${LIBR_EXECUTABLE}" PARENT_SCOPE)
+if (USE_OPENMP)
+  target_link_libraries(xgboost-r PRIVATE OpenMP::OpenMP_CXX)
+endif ()

R-package/DESCRIPTION

@@ -1,7 +1,7 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.2.0.1
+Version: 1.1.0.1
 Date: 2020-02-21
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
@@ -31,9 +31,9 @@ Authors@R: c(
   )
 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
+    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
@@ -54,8 +54,7 @@ Suggests:
     lintr,
     igraph (>= 1.0.1),
     jsonlite,
-    float,
-    crayon
+    float
 Depends:
     R (>= 3.3.0)
 Imports:
@@ -64,5 +63,5 @@ Imports:
     data.table (>= 1.9.6),
     magrittr (>= 1.5),
     stringi (>= 0.5.2)
-RoxygenNote: 7.1.1
-SystemRequirements: GNU make, C++14
+RoxygenNote: 7.1.0
+SystemRequirements: GNU make, C++11

R-package/R/callbacks.R

@@ -62,11 +62,11 @@ 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)
+        NVL(env$rank, 0) != 0 )
       return()
 
     i <- env$iteration
-    if ((i - 1) %% period == 0 ||
+    if ((i-1) %% period == 0 ||
         i == env$begin_iteration ||
         i == env$end_iteration) {
       stdev <- if (showsd) env$bst_evaluation_err else NULL
@@ -115,7 +115,7 @@ cb.evaluation.log <- function() {
       stop("bst_evaluation must have non-empty names")
 
     mnames <<- gsub('-', '_', names(env$bst_evaluation))
-    if (!is.null(env$bst_evaluation_err))
+    if(!is.null(env$bst_evaluation_err))
       mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
   }
 
@@ -123,12 +123,12 @@ cb.evaluation.log <- function() {
     env$evaluation_log <- as.data.table(t(simplify2array(env$evaluation_log)))
     setnames(env$evaluation_log, c('iter', mnames))
 
-    if (!is.null(env$bst_evaluation_err)) {
+    if(!is.null(env$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]
+      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
@@ -144,7 +144,7 @@ cb.evaluation.log <- function() {
       return(finalizer(env))
 
     ev <- env$bst_evaluation
-    if (!is.null(env$bst_evaluation_err))
+    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)))
@@ -351,13 +351,13 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
 
   finalizer <- function(env) {
     if (!is.null(env$bst)) {
-      attr_best_score <- as.numeric(xgb.attr(env$bst$handle, 'best_score'))
+      attr_best_score = as.numeric(xgb.attr(env$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$best_score <- best_score
+      env$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
@@ -372,9 +372,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
       return(finalizer(env))
 
     i <- env$iteration
-    score <- env$bst_evaluation[metric_idx]
+    score = env$bst_evaluation[metric_idx]
 
-    if ((maximize && score > best_score) ||
+    if (( maximize && score > best_score) ||
         (!maximize && score < best_score)) {
 
       best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
@@ -500,7 +500,7 @@ cb.cv.predict <- function(save_models = FALSE) {
     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
+        pred[fd$index,] <- pr
       } else {
         pred[fd$index] <- pr
       }
@@ -613,7 +613,9 @@ cb.gblinear.history <- function(sparse=FALSE) {
 
   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'")
   }
 
@@ -703,11 +705,11 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   if (!is_cv) {
     # extract num_class & num_feat from the internal model
     dmp <- xgb.dump(model)
-    if (length(dmp) < 2 || dmp[2] != "bias:")
+    if(length(dmp) < 2 || dmp[2] != "bias:")
       stop("It does not appear to be a gblinear model")
-    dmp <- dmp[-c(1, 2)]
+    dmp <- dmp[-c(1,2)]
     n <- which(dmp == 'weight:')
-    if (length(n) != 1)
+    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
@@ -730,9 +732,9 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   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)])
+             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 <- coef_path[, seq(1 + class_index, by=num_class, length.out=num_feat)]
     }
   }
   coef_path

R-package/R/utils.R

@@ -69,23 +69,23 @@ check.booster.params <- function(params, ...) {
 
   if (!is.null(params[['monotone_constraints']]) &&
       typeof(params[['monotone_constraints']]) != "character") {
-        vec2str <- paste(params[['monotone_constraints']], collapse = ',')
-        vec2str <- paste0('(', vec2str, ')')
-        params[['monotone_constraints']] <- vec2str
+        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 (!identical(class(params[['interaction_constraints']]), 'list')) stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric', 'integer'))) {
+    if (!identical(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 = ','), ']')
+    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse=','), ']'))
+    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse=','), ']')
   }
   return(params)
 }
@@ -145,8 +145,7 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
   if (is.null(obj)) {
     .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
   } else {
-    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE,
-                    ntreelimit = 0)
+    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE)
     gpair <- obj(pred, dtrain)
     .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
   }
@@ -168,12 +167,12 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
   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
+    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, outputmargin = TRUE, ntreelimit = 0) # predict using all trees
+      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)
@@ -308,66 +307,6 @@ xgb.createFolds <- function(y, k = 10)
 #' @name xgboost-deprecated
 NULL
 
-#' Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
-#' models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.
-#'
-#' It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
-#' \code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
-#' \code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
-#' the model is to be accessed in the future. If you train a model with the current version of
-#' XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
-#' accessible in later releases of XGBoost. To ensure that your model can be accessed in future
-#' releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
-#'
-#' @details
-#' Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-#' the JSON format by specifying the JSON extension. To read the model back, use
-#' \code{\link{xgb.load}}.
-#'
-#' Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-#' in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-#' re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-#' The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-#' as part of another R object.
-#'
-#' Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
-#' model but also internal configurations and parameters, and its format is not stable across
-#' multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
-#'
-#' For more details and explanation about model persistence and archival, consult the page
-#' \url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-#'
-#' @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")
-#'
-#' # Save as a stand-alone file; load it with xgb.load()
-#' xgb.save(bst, 'xgb.model')
-#' bst2 <- xgb.load('xgb.model')
-#'
-#' # Save as a stand-alone file (JSON); load it with xgb.load()
-#' xgb.save(bst, 'xgb.model.json')
-#' bst2 <- xgb.load('xgb.model.json')
-#'
-#' # Save as a raw byte vector; load it with xgb.load.raw()
-#' xgb_bytes <- xgb.save.raw(bst)
-#' bst2 <- xgb.load.raw(xgb_bytes)
-#'
-#' # Persist XGBoost model as part of another R object
-#' obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-#' # Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-#' # xgb.Booster directly. What's being persisted is the future-proof byte representation
-#' # as given by xgb.save.raw().
-#' saveRDS(obj, 'my_object.rds')
-#' # Read back the R object
-#' obj2 <- readRDS('my_object.rds')
-#' # Re-construct xgb.Booster object from the bytes
-#' bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-#'
-#' @name a-compatibility-note-for-saveRDS-save
-NULL
-
 # Lookup table for the deprecated parameters bookkeeping
 depr_par_lut <- matrix(c(
   'print.every.n', 'print_every_n',
@@ -376,8 +315,8 @@ depr_par_lut <- matrix(c(
   'with.stats', 'with_stats',
   'numberOfClusters', 'n_clusters',
   'features.keep', 'features_keep',
-  'plot.height', 'plot_height',
-  'plot.width', 'plot_width',
+  'plot.height','plot_height',
+  'plot.width','plot_width',
   'n_first_tree', 'trees',
   'dummy', 'DUMMY'
 ), ncol = 2, byrow = TRUE)
@@ -390,20 +329,20 @@ colnames(depr_par_lut) <- c('old', 'new')
 check.deprecation <- function(..., env = parent.frame()) {
   pars <- list(...)
   # exact and partial matches
-  all_match <- pmatch(names(pars), depr_par_lut[, 1])
+  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)
+  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, "'")
+      warning("'", pars_par, "' was partially matched to '", old_par,"'")
     }
     .Deprecated(new_par, old = old_par, package = 'xgboost')
     if (new_par != 'NULL') {

R-package/R/xgb.Booster.R

@@ -1,7 +1,6 @@
 # Construct an internal xgboost Booster and return a handle to it.
 # internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(),
-                               modelfile = NULL) {
+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")
@@ -63,8 +62,8 @@ is.null.handle <- function(handle) {
   return(FALSE)
 }
 
-# Return a verified to be valid handle out of either xgb.Booster.handle or
-# xgb.Booster internal utility function
+# Return a verified to be valid handle out of either xgb.Booster.handle or xgb.Booster
+# internal utility function
 xgb.get.handle <- function(object) {
   if (inherits(object, "xgb.Booster")) {
     handle <- object$handle
@@ -111,8 +110,6 @@ xgb.get.handle <- function(object) {
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' saveRDS(bst, "xgb.model.rds")
 #'
-#' # Warning: The resulting RDS file is only compatible with the current XGBoost version.
-#' # Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 #' bst1 <- readRDS("xgb.model.rds")
 #' if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 #' # the handle is invalid:
@@ -372,8 +369,8 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       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, , ])
+                   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
@@ -382,11 +379,11 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
     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))
+      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, , , ])
+                   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)
@@ -659,7 +656,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
 
   if (!is.null(x$params)) {
     cat('params (as set within xgb.train):\n')
-    cat('  ',
+    cat( '  ',
          paste(names(x$params),
                paste0('"', unlist(x$params), '"'),
                sep = ' = ', collapse = ', '), '\n', sep = '')
@@ -672,9 +669,9 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   if (length(attrs) > 0) {
     cat('xgb.attributes:\n')
     if (verbose) {
-        cat(paste(paste0('  ', names(attrs)),
-                  paste0('"', unlist(attrs), '"'),
-                  sep = ' = ', collapse = '\n'), '\n', sep = '')
+      cat( paste(paste0('  ',names(attrs)),
+                 paste0('"', unlist(attrs), '"'),
+                 sep = ' = ', collapse = '\n'), '\n', sep = '')
     } else {
       cat('  ', paste(names(attrs), collapse = ', '), '\n', sep = '')
     }
@@ -696,7 +693,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   #cat('ntree: ', xgb.ntree(x), '\n', sep='')
 
   for (n in setdiff(names(x), c('handle', 'raw', 'call', 'params', 'callbacks',
-                                'evaluation_log', 'niter', 'feature_names'))) {
+                                'evaluation_log','niter','feature_names'))) {
     if (is.atomic(x[[n]])) {
       cat(n, ':', x[[n]], '\n', sep = ' ')
     } else {

R-package/R/xgb.DMatrix.R

@@ -257,6 +257,8 @@ setinfo.xgb.DMatrix <- function(object, name, 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)
   }
@@ -320,7 +322,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
     for (i in seq_along(ind)) {
       obj_attr <- attr(object, nms[i])
       if (NCOL(obj_attr) > 1) {
-        attr(ret, nms[i]) <- obj_attr[idxset, ]
+        attr(ret, nms[i]) <- obj_attr[idxset,]
       } else {
         attr(ret, nms[i]) <- obj_attr[idxset]
       }
@@ -358,9 +360,9 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 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(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)

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

@@ -1,10 +1,10 @@
 #' 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
@@ -18,7 +18,7 @@ xgb.DMatrix.save <- function(dmatrix, fname) {
     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

@@ -1,50 +1,50 @@
 #' 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
+#' @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,
+#' 
+#' \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,
+#' 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')
@@ -55,33 +55,33 @@
 #' 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)) # nolint
+  cbind(data, sparse.model.matrix( ~ . -1, cols))
 }

R-package/R/xgb.cv.R

@@ -2,15 +2,12 @@
 #'
 #' The cross validation function of xgboost
 #'
-#' @param params the list of parameters. The complete list of parameters is
-#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @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 See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
+#'     \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
@@ -137,20 +134,20 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   #  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))) {
+  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")
   } else if (inherits(data, 'xgb.DMatrix')) {
     if (!is.null(label))
       warning("xgb.cv: label will be ignored, since data is of type xgb.DMatrix")
-    cv_label <- getinfo(data, 'label')
+    cv_label = getinfo(data, 'label')
   } else {
-    cv_label <- label
+    cv_label = label
   }
 
   # CV folds
-  if (!is.null(folds)) {
-    if (!is.list(folds) || length(folds) < 2)
+  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 {
@@ -165,7 +162,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
-  print_every_n <- max(as.integer(print_every_n), 1L)
+  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))
   }
@@ -196,20 +193,20 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   bst_folds <- lapply(seq_along(folds), function(k) {
     dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow
-    if (is.null(train_folds))
+    if(is.null(train_folds))
        dtrain <- slice(dall, unlist(folds[-k]))
     else
        dtrain <- slice(dall, train_folds[[k]])
     handle <- xgb.Booster.handle(params, list(dtrain, dtest))
-    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test = dtest), index = folds[[k]])
+    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) # nolint
-  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1) # nolint
+  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
@@ -226,7 +223,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
     })
     msg <- simplify2array(msg)
     bst_evaluation <- rowMeans(msg)
-    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2) # nolint
+    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
 
     for (f in cb$post_iter) f()
 
@@ -285,10 +282,10 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
     }
     if (!is.null(x$params)) {
       cat('params (as set within xgb.cv):\n')
-      cat('  ',
-          paste(names(x$params),
-                paste0('"', unlist(x$params), '"'),
-                sep = ' = ', collapse = ', '), '\n', sep = '')
+      cat( '  ',
+           paste(names(x$params),
+                 paste0('"', unlist(x$params), '"'),
+                 sep = ' = ', collapse = ', '), '\n', sep = '')
     }
     if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
       cat('callbacks:\n')

R-package/R/xgb.dump.R

@@ -1,15 +1,15 @@
 #' 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.
+#' @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
+#'        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}
+#'        \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:
@@ -27,18 +27,18 @@
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+#' 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"), ...) {
@@ -50,19 +50,19 @@ xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
     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))
+  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 {

R-package/R/xgb.ggplot.R

@@ -3,9 +3,9 @@
 
 #' @rdname xgb.plot.importance
 #' @export
-xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
+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)) {
@@ -14,21 +14,21 @@ xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measur
   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::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"),
+                    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)
 }
@@ -42,7 +42,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     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')
@@ -60,30 +60,30 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
         axis.ticks = ggplot2::element_blank(),
         axis.text.x = ggplot2::element_blank()
       )
-
-    p2 <-
+  
+    p2 <- 
       ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") +
+      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) +
+                           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) +
+                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median tree leaf depth")
     return(p)
@@ -92,7 +92,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     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) +
+                          alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median absolute leaf weight")
     return(p)
@@ -105,11 +105,11 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
 # internal utility function
 multiplot <- function(..., cols = 1) {
   plots <- list(...)
-  num_plots <- length(plots)
-
+  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 {
@@ -118,7 +118,7 @@ multiplot <- function(..., cols = 1) {
     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,

R-package/R/xgb.importance.R

@@ -1,66 +1,66 @@
 #' 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
+#'          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
-#'
+#' @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
+#' 
+#' 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
+#'        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},
+#' 
+#' 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,
+#' 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",
+#' 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
@@ -73,7 +73,7 @@
 #' 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$Species) - 1,
 #'                booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
@@ -83,33 +83,33 @@
 #' @export
 xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
                            data = NULL, label = NULL, target = NULL){
-
+  
   if (!(is.null(data) && is.null(label) && is.null(target)))
     warning("xgb.importance: parameters 'data', 'label' and 'target' are deprecated")
-
+  
   if (!inherits(model, "xgb.Booster"))
     stop("model: must be an object of class xgb.Booster")
-
+  
   if (is.null(feature_names) && !is.null(model$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:"){
+  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))
+    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 {
@@ -117,17 +117,18 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
                  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)]
+  } 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
 }

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

@@ -1,12 +1,12 @@
 #' 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}
+#' @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.
@@ -18,11 +18,11 @@
 #'          represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).
 #' @param ... currently not used.
 #'
-#' @return
+#' @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)
@@ -36,79 +36,79 @@
 #'  \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
+#' 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,
+#' 
+#' 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$data), bst))
-#'
-#' # This bst model already has feature_names stored with it, so those would be used when
+#' 
+#' # This bst model already has feature_names stored with it, so those would be used when 
 #' # feature_names is not set:
 #' (dt <- xgb.model.dt.tree(model = bst))
-#'
+#' 
 #' # How to match feature names of splits that are following a current 'Yes' branch:
-#'
+#' 
 #' merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
-#'
+#'  
 #' @export
 xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
                               trees = NULL, use_int_id = FALSE, ...){
   check.deprecation(...)
-
+  
   if (!inherits(model, "xgb.Booster") && !is.character(text)) {
     stop("Either 'model' must be an object of class xgb.Booster\n",
          "  or 'text' must be a character vector with the result of xgb.dump\n",
          "  (or NULL if 'model' was provided).")
   }
-
+  
   if (is.null(feature_names) && !is.null(model) && !is.null(model$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]
+  
+  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"))]
 
@@ -116,29 +116,29 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   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,
+  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 <- 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])
+      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]]
+    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]))
+      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]
@@ -146,14 +146,14 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
     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"))
+globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf",".SD", ".SDcols"))

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

@@ -2,48 +2,48 @@
 #'
 #' 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.
+#' @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")
+#'  \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}
+#' 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
-#'
+#' @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
@@ -53,16 +53,16 @@
 #'
 #' 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")
@@ -71,32 +71,32 @@ xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.d
     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)
+      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") {
@@ -123,14 +123,14 @@ get.leaf.depth <- function(dt_tree) {
       dt_tree[Feature != "Leaf", .(ID, To = No, Tree)]
     ))
   # whether "To" is a leaf:
-  dt_edges <-
+  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)])
+    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

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

@@ -92,10 +92,10 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
     importance_matrix <- head(importance_matrix, top_n)
   }
   if (rel_to_first) {
-    importance_matrix[, Importance := Importance / max(abs(Importance))]
+    importance_matrix[, Importance := Importance/max(abs(Importance))]
   }
   if (is.null(cex)) {
-    cex <- 2.5 / log2(1 + nrow(importance_matrix))
+    cex <- 2.5/log2(1 + nrow(importance_matrix))
   }
 
   if (plot) {

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

@@ -9,7 +9,7 @@
 #' @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
@@ -72,53 +72,53 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
 
   precedent.nodes <- root.nodes
 
-  while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
+  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))]
-
+  
+  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),
+                          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)]) %>%
+    list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>%
     rbindlist() %>%
     setnames(c("From", "To")) %>%
     .[, .N, .(From, To)] %>%
-    .[, N := NULL]
-
+    .[, N:=NULL]
+  
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
-    label = nodes.dt[, Text]
+    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]),
+    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,

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

@@ -125,12 +125,12 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 
   nsample <- if (is.null(subsample)) min(100000, nrow(data)) else as.integer(subsample * nrow(data))
   idx <- sample(1:nrow(data), nsample)
-  data <- data[idx, ]
+  data <- data[idx,]
 
   if (is.null(shap_contrib)) {
     shap_contrib <- predict(model, data, predcontrib = TRUE, approxcontrib = approxcontrib)
   } else {
-    shap_contrib <- shap_contrib[idx, ]
+    shap_contrib <- shap_contrib[idx,]
   }
 
   which <- match.arg(which)
@@ -168,8 +168,8 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 
   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,
+              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])
@@ -192,7 +192,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       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]
+        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 {

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

@@ -1,7 +1,7 @@
 #' Plot a boosted tree model
-#'
-#' Read a tree model text dump and plot the 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.
@@ -14,10 +14,10 @@
 #' @param show_node_id a logical flag for whether to show node id's in the graph.
 #' @param ... currently not used.
 #'
-#' @details
-#'
+#' @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.
@@ -27,21 +27,21 @@
 #'  \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
@@ -49,23 +49,23 @@
 #'
 #' @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.
+#' # 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, ...){
@@ -77,18 +77,18 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
   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)]
+  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"]
+  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$ID,
@@ -97,7 +97,7 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
     shape     = dt$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),
@@ -126,9 +126,9 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
       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)
 }
 

R-package/R/xgb.save.R

@@ -1,33 +1,29 @@
 #' 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
+#' 
+#' @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
+#' 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. Moreover, persisting the model with
-#' \code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
-#' future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-#' how to persist models in a future-proof way, i.e. to make the model accessible in future
-#' releases of XGBoost.
-#'
-#' @seealso
-#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}.
-#'
+#' 
+#' 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,
+#' 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')

R-package/R/xgb.train.R

@@ -3,9 +3,9 @@
 #' \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 in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @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
 #'
@@ -43,23 +43,13 @@
 #' \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:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
 #'     \item \code{reg:logistic} logistic regression.
-#'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \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{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
-#'     \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
-#'     \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
-#'     \item \code{aft_loss_distribution}: Probabilty Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+#'     \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{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
-#'     \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
-#'     \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
-#'     \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
 #'   }
 #'   \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.
@@ -278,7 +268,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
 
   # evaluation printing callback
   params <- c(params)
-  print_every_n <- max(as.integer(print_every_n), 1L)
+  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))
@@ -328,9 +318,12 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
       niter_init <- xgb.ntree(bst) %/% (num_parallel_tree * num_class)
     }
   }
-  if (is_update && nrounds > niter_init)
+  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
@@ -342,6 +335,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
 
     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)
 
@@ -356,7 +350,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   bst <- xgb.Booster.complete(bst, saveraw = TRUE)
 
   # store the total number of boosting iterations
-  bst$niter <- end_iteration
+  bst$niter = end_iteration
 
   # store the evaluation results
   if (length(evaluation_log) > 0 &&

R-package/R/xgb.unserialize.R

@@ -6,26 +6,7 @@
 xgb.unserialize <- function(buffer) {
   cachelist <- list()
   handle <- .Call(XGBoosterCreate_R, cachelist)
-  tryCatch(
-    .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer),
-    error = function(e) {
-      error_msg <- conditionMessage(e)
-      m <- regexec("(src[\\\\/]learner.cc:[0-9]+): Check failed: (header == serialisation_header_)",
-                   error_msg, perl = TRUE)
-      groups <- regmatches(error_msg, m)[[1]]
-      if (length(groups) == 3) {
-        warning(paste("The model had been generated by XGBoost version 1.0.0 or earlier and was ",
-                      "loaded from a RDS file. We strongly ADVISE AGAINST using saveRDS() ",
-                      "function, to ensure that your model can be read in current and upcoming ",
-                      "XGBoost releases. Please use xgb.save() instead to preserve models for the ",
-                      "long term. For more details and explanation, see ",
-                      "https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html",
-                      sep = ""))
-        .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
-      } else {
-        stop(e)
-      }
-    })
+  .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer)
   class(handle) <- "xgb.Booster.handle"
   return (handle)
 }

R-package/configure

@@ -613,7 +613,6 @@ infodir
 docdir
 oldincludedir
 includedir
-runstatedir
 localstatedir
 sharedstatedir
 sysconfdir
@@ -683,7 +682,6 @@ datadir='${datarootdir}'
 sysconfdir='${prefix}/etc'
 sharedstatedir='${prefix}/com'
 localstatedir='${prefix}/var'
-runstatedir='${localstatedir}/run'
 includedir='${prefix}/include'
 oldincludedir='/usr/include'
 docdir='${datarootdir}/doc/${PACKAGE_TARNAME}'
@@ -936,15 +934,6 @@ do
   | -silent | --silent | --silen | --sile | --sil)
     silent=yes ;;
 
-  -runstatedir | --runstatedir | --runstatedi | --runstated \
-  | --runstate | --runstat | --runsta | --runst | --runs \
-  | --run | --ru | --r)
-    ac_prev=runstatedir ;;
-  -runstatedir=* | --runstatedir=* | --runstatedi=* | --runstated=* \
-  | --runstate=* | --runstat=* | --runsta=* | --runst=* | --runs=* \
-  | --run=* | --ru=* | --r=*)
-    runstatedir=$ac_optarg ;;
-
   -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb)
     ac_prev=sbindir ;;
   -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \
@@ -1082,7 +1071,7 @@ fi
 for ac_var in	exec_prefix prefix bindir sbindir libexecdir datarootdir \
 		datadir sysconfdir sharedstatedir localstatedir includedir \
 		oldincludedir docdir infodir htmldir dvidir pdfdir psdir \
-		libdir localedir mandir runstatedir
+		libdir localedir mandir
 do
   eval ac_val=\$$ac_var
   # Remove trailing slashes.
@@ -1235,7 +1224,6 @@ Fine tuning of the installation directories:
   --sysconfdir=DIR        read-only single-machine data [PREFIX/etc]
   --sharedstatedir=DIR    modifiable architecture-independent data [PREFIX/com]
   --localstatedir=DIR     modifiable single-machine data [PREFIX/var]
-  --runstatedir=DIR       modifiable per-process data [LOCALSTATEDIR/run]
   --libdir=DIR            object code libraries [EPREFIX/lib]
   --includedir=DIR        C header files [PREFIX/include]
   --oldincludedir=DIR     C header files for non-gcc [/usr/include]
@@ -2710,7 +2698,7 @@ fi
 if test `uname -s` = "Darwin"
 then
   OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='-lomp'
+  OPENMP_LIB='/usr/local/lib/libomp.dylib'
   ac_pkg_openmp=no
   { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether OpenMP will work in a package" >&5
 $as_echo_n "checking whether OpenMP will work in a package... " >&6; }
@@ -2725,7 +2713,7 @@ main ()
   return 0;
 }
 _ACEOF
-  ${CC} -o conftest conftest.c ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   { $as_echo "$as_me:${as_lineno-$LINENO}: result: ${ac_pkg_openmp}" >&5
 $as_echo "${ac_pkg_openmp}" >&6; }
   if test "${ac_pkg_openmp}" = no; then

R-package/configure.ac

@@ -1,6 +1,6 @@
 ### configure.ac					-*- Autoconf -*-
 
-AC_PREREQ(2.69)
+AC_PREREQ(2.62)
 
 AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
@@ -29,11 +29,11 @@ fi
 if test `uname -s` = "Darwin"
 then
   OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='-lomp'
+  OPENMP_LIB='/usr/local/lib/libomp.dylib'
   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_max_threads() <= 1); ]])])
-  ${CC} -o conftest conftest.c ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''

R-package/demo/README.md

@@ -17,4 +17,4 @@ Benchmarks
 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 :)
+* If you like to share how you use xgboost to solve your problem, send a pull request:)

R-package/demo/basic_walkthrough.R

@@ -3,8 +3,8 @@ 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')
+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}
@@ -26,7 +26,7 @@ bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2,
 # 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,
+bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2, 
                objective = "binary:logistic")
 
 # Verbose = 0,1,2
@@ -46,7 +46,7 @@ bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
 
 #--------------------basic prediction using xgboost--------------
 # you can do prediction using the following line
-# you can put in Matrix, sparseMatrix, or xgb.DMatrix
+# 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))
@@ -58,31 +58,31 @@ xgb.save(bst, "xgboost.model")
 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))))
+print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
 
 # save model to R's raw vector
-raw <- xgb.save.raw(bst)
+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))))
+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)
+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)
+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
+# 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,
+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,
+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")
 
@@ -90,17 +90,17 @@ bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist =
 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,
+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")
+label = getinfo(dtest, "label")
 pred <- predict(bst, dtest)
-err <- as.numeric(sum(as.integer(pred > 0.5) != label)) / length(label)
+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 = TRUE)
+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):")

R-package/demo/boost_from_prediction.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)
 
@@ -11,12 +11,12 @@ watchlist <- list(eval = dtest, train = dtrain)
 #
 print('start running example to start from a initial prediction')
 # train xgboost for 1 round
-param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
+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)
+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)

R-package/demo/caret_wrapper.R

@@ -1,5 +1,5 @@
 # install development version of caret library that contains xgboost models
-devtools::install_github("topepo/caret/pkg/caret")
+devtools::install_github("topepo/caret/pkg/caret") 
 require(caret)
 require(xgboost)
 require(data.table)
@@ -9,17 +9,17 @@ 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 = FALSE)
+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))]
+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"))]
+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]
+df[,ID:=NULL]
 
 #-------------Basic Training using XGBoost in caret Library-----------------
 # Set up control parameters for caret::train

R-package/demo/create_sparse_matrix.R

@@ -6,10 +6,10 @@ if (!require(vcd)) {
   require(vcd)
 }
 # According to its documentation, Xgboost works only on numbers.
-# Sometimes the dataset we have to work on have categorical data.
+# 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.
+# 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.
@@ -19,7 +19,7 @@ if (!require(vcd)) {
 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 = FALSE)
+df <- data.table(Arthritis, keep.rownames = F)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
@@ -32,17 +32,17 @@ 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))]
+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"))]
+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]
+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]))
+print(levels(df[,Treatment]))
 
 # Next step, we will transform the categorical data to dummy variables.
 # This method is also called one hot encoding.
@@ -52,16 +52,16 @@ print(levels(df[, Treatment]))
 #
 # 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)
+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;
+# 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]
+output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
 
 # Following is the same process as other demo
 cat("Learning...\n")

R-package/demo/cross_validation.R

@@ -1,25 +1,25 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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, nthread = 2, objective = 'binary:logistic')
+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'})
+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)
+xgb.cv(param, dtrain, nrounds, nfold=5,
+       metrics='error', showsd = FALSE)
 
 ###
 # you can also do cross validation with cutomized loss function
@@ -29,18 +29,18 @@ print ('running cross validation, with cutomsized loss function')
 
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  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)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1,
+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)

R-package/demo/custom_objective.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)
 
@@ -15,7 +15,7 @@ num_round <- 2
 # this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -29,36 +29,36 @@ logregobj <- function(preds, dtrain) {
 # 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)
+  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)
+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
+# 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
+# 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))
+  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)
+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

R-package/demo/early_stopping.R

@@ -1,20 +1,20 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)
+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))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -27,7 +27,7 @@ logregobj <- function(preds, dtrain) {
 # 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)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 print ('start training with early Stopping setting')

R-package/demo/generalized_linear_model.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)
 ##
@@ -11,14 +11,14 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
 
 # change booster to gblinear, so that we are fitting a linear model
-# alpha is the L1 regularizer
+# 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),
+# 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
 
@@ -30,4 +30,5 @@ 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')
+cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
+

R-package/demo/gpu_accelerated.R

@@ -1,9 +1,9 @@
 # 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
+# 
+# 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
+# For the current functionality, see 
 # https://xgboost.readthedocs.io/en/latest/gpu/index.html
 #
 
@@ -21,8 +21,8 @@ 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])
+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

R-package/demo/interaction_constraints.R

@@ -4,38 +4,33 @@ 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) {
-  ID_merge <- i.id <- i.feature <- NULL  # Suppress warning "no visible binding for global variable"
-
-  trees <- data.table::copy(input_tree)  # copy tree input to prevent overwriting
+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)]
+  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)]
 
-    data.table::setorderv(trees, 'ID_merge')
-    data.table::setorderv(parents_left, 'ID_merge')
-    data.table::setorderv(parents_right, 'ID_merge')
+    setorderv(trees, 'ID_merge')
+    setorderv(parents_left, 'ID_merge')
+    setorderv(parents_right, 'ID_merge')
 
-    trees <- merge(trees, parents_left, by = 'ID_merge', all.x = TRUE)
-    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_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 = TRUE)
-    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 = FALSE]
+  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)
 
@@ -52,62 +47,59 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
 # Generate sample data
 x <- list()
-for (i in 1:10) {
-  x[[i]] <- i * rnorm(1000, 10)
+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']])
+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)
+train = as.matrix(x)
 
 # Interaction constraint list (column names form)
-interaction_list <- list(c('V1', 'V2'), c('V3', 'V4', 'V5'))
+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")
+  rapply(object, function(x) LUT[x], classes="character", how="replace")
 }
-interaction_list_fid <- cols2ids(interaction_list, colnames(train))
+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 = 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
+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 = 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 = 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
+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 = FALSE]
+  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
+  prev_pred <- pred 
 }

R-package/demo/poisson_regression.R

@@ -1,6 +1,7 @@
 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))
+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 +1,23 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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, objective = 'binary:logistic')
+param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 watchlist <- list(eval = dtest, train = dtrain)
-nrounds <- 2
+nrounds = 2
 
 # training the model for two rounds
-bst <- xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
+bst = xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
 cat('start testing prediction from first n trees\n')
-labels <- getinfo(dtest, 'label')
+labels <- getinfo(dtest,'label')
 
 ### predict using first 1 tree
-ypred1 <- predict(bst, dtest, ntreelimit = 1)
+ypred1 = predict(bst, dtest, ntreelimit=1)
 # by default, we predict using all the trees
-ypred2 <- predict(bst, dtest)
+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')
+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

@@ -5,34 +5,34 @@ require(Matrix)
 set.seed(1982)
 
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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, objective = 'binary:logistic')
-nrounds <- 4
+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)
+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$label))
+accuracy.before <- sum((predict(bst, agaricus.test$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)
+
+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$niter) {
+  for(i in 1:model$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)
+    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)))
+  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
 }
 
 # Convert previous features to one hot encoding
@@ -47,9 +47,7 @@ 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))
+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"))
+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 +1,14 @@
 # running all scripts in demo folder
-demo(basic_walkthrough, package = 'xgboost')
-demo(custom_objective, package = 'xgboost')
-demo(boost_from_prediction, package = 'xgboost')
-demo(predict_first_ntree, package = 'xgboost')
-demo(generalized_linear_model, package = 'xgboost')
-demo(cross_validation, package = 'xgboost')
-demo(create_sparse_matrix, package = 'xgboost')
-demo(predict_leaf_indices, package = 'xgboost')
-demo(early_stopping, package = 'xgboost')
-demo(poisson_regression, package = 'xgboost')
-demo(caret_wrapper, package = 'xgboost')
-demo(tweedie_regression, package = 'xgboost')
-#demo(gpu_accelerated, package = 'xgboost')  # can only run when built with GPU support
+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

@@ -8,12 +8,12 @@ data(AutoClaim)
 dt <- data.table(AutoClaim)
 
 # exclude these columns from the model matrix
-exclude <- c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
+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 = FALSE])
+x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = F])
 options(na.action = 'na.omit')
 
 # response
@@ -21,29 +21,29 @@ y <- dt[, CLM_AMT5]
 
 d_train <- xgb.DMatrix(data = x, label = y, missing = NA)
 
-# the tweedie_variance_power parameter determines the shape of
+# 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
+#   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',
+  eval_metric = 'rmse', 
   tweedie_variance_power = 1.4,
   max_depth = 6,
   eta = 1)
 
 bst <- xgb.train(
-  data = d_train,
-  params = params,
+  data = d_train, 
+  params = params, 
   maximize = FALSE,
-  watchlist = list(train = d_train),
+  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)))
+rmse <- sqrt(sum(mean((y - preds)^2)))

R-package/inst/make-r-def.R

@@ -1,96 +0,0 @@
-# [description]
-#     Create a definition file (.def) from a .dll file, using objdump. This
-#     is used by FindLibR.cmake when building the R package with MSVC.
-#
-# [usage]
-#
-#     Rscript make-r-def.R something.dll something.def
-#
-# [references]
-#    * https://www.cs.colorado.edu/~main/cs1300/doc/mingwfaq.html
-
-args <- commandArgs(trailingOnly = TRUE)
-
-IN_DLL_FILE <- args[[1L]]
-OUT_DEF_FILE <- args[[2L]]
-DLL_BASE_NAME <- basename(IN_DLL_FILE)
-
-message(sprintf("Creating '%s' from '%s'", OUT_DEF_FILE, IN_DLL_FILE))
-
-# system() will not raise an R exception if the process called
-# fails. Wrapping it here to get that behavior.
-#
-# system() introduces a lot of overhead, at least on Windows,
-# so trying processx if it is available
-.pipe_shell_command_to_stdout <- function(command, args, out_file) {
-    has_processx <- suppressMessages({
-        suppressWarnings({
-            require("processx")  # nolint
-        })
-    })
-    if (has_processx) {
-        p <- processx::process$new(
-            command = command
-            , args = args
-            , stdout = out_file
-            , windows_verbatim_args = FALSE
-        )
-        invisible(p$wait())
-    } else {
-        message(paste0(
-            "Using system2() to run shell commands. Installing "
-            , "'processx' with install.packages('processx') might "
-            , "make this faster."
-        ))
-        exit_code <- system2(
-            command = command
-            , args = shQuote(args)
-            , stdout = out_file
-        )
-        if (exit_code != 0L) {
-            stop(paste0("Command failed with exit code: ", exit_code))
-        }
-    }
-    return(invisible(NULL))
-}
-
-# use objdump to dump all the symbols
-OBJDUMP_FILE <- "objdump-out.txt"
-.pipe_shell_command_to_stdout(
-    command = "objdump"
-    , args = c("-p", IN_DLL_FILE)
-    , out_file = OBJDUMP_FILE
-)
-
-objdump_results <- readLines(OBJDUMP_FILE)
-result <- file.remove(OBJDUMP_FILE)
-
-# Only one table in the objdump results matters for our purposes,
-# see https://www.cs.colorado.edu/~main/cs1300/doc/mingwfaq.html
-start_index <- which(
-    grepl(
-        pattern = "[Ordinal/Name Pointer] Table"
-        , x = objdump_results
-        , fixed = TRUE
-    )
-)
-empty_lines <- which(objdump_results == "")
-end_of_table <- empty_lines[empty_lines > start_index][1L]
-
-# Read the contents of the table
-exported_symbols <- objdump_results[(start_index + 1L):end_of_table]
-exported_symbols <- gsub("\t", "", exported_symbols)
-exported_symbols <- gsub(".*\\] ", "", exported_symbols)
-exported_symbols <- gsub(" ", "", exported_symbols)
-
-# Write R.def file
-writeLines(
-    text = c(
-        paste0("LIBRARY \"", DLL_BASE_NAME, "\"")
-        , "EXPORTS"
-        , exported_symbols
-    )
-    , con = OUT_DEF_FILE
-    , sep = "\n"
-)
-message(sprintf("Successfully created '%s'", OUT_DEF_FILE))

R-package/man/a-compatibility-note-for-saveRDS-save.Rd

@@ -1,62 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/utils.R
-\name{a-compatibility-note-for-saveRDS-save}
-\alias{a-compatibility-note-for-saveRDS-save}
-\title{Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
-models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.}
-\description{
-It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
-\code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
-\code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
-the model is to be accessed in the future. If you train a model with the current version of
-XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
-accessible in later releases of XGBoost. To ensure that your model can be accessed in future
-releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
-}
-\details{
-Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-the JSON format by specifying the JSON extension. To read the model back, use
-\code{\link{xgb.load}}.
-
-Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-as part of another R object.
-
-Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
-model but also internal configurations and parameters, and its format is not stable across
-multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
-
-For more details and explanation about model persistence and archival, consult the page
-\url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-}
-\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")
-
-# Save as a stand-alone file; load it with xgb.load()
-xgb.save(bst, 'xgb.model')
-bst2 <- xgb.load('xgb.model')
-
-# Save as a stand-alone file (JSON); load it with xgb.load()
-xgb.save(bst, 'xgb.model.json')
-bst2 <- xgb.load('xgb.model.json')
-
-# Save as a raw byte vector; load it with xgb.load.raw()
-xgb_bytes <- xgb.save.raw(bst)
-bst2 <- xgb.load.raw(xgb_bytes)
-
-# Persist XGBoost model as part of another R object
-obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-# Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-# xgb.Booster directly. What's being persisted is the future-proof byte representation
-# as given by xgb.save.raw().
-saveRDS(obj, 'my_object.rds')
-# Read back the R object
-obj2 <- readRDS('my_object.rds')
-# Re-construct xgb.Booster object from the bytes
-bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-
-}

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

@@ -38,8 +38,6 @@ bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_dep
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 saveRDS(bst, "xgb.model.rds")
 
-# Warning: The resulting RDS file is only compatible with the current XGBoost version.
-# Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 bst1 <- readRDS("xgb.model.rds")
 if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 # the handle is invalid:

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

@@ -24,9 +24,9 @@ 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,
+\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/}.
@@ -37,10 +37,10 @@ Extract explaining the method:
 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.
+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,
+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

R-package/man/xgb.cv.Rd

@@ -28,15 +28,12 @@ xgb.cv(
 )
 }
 \arguments{
-\item{params}{the list of parameters. The complete list of parameters is
-  available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-  is a shorter summary:
+\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 See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
+    \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

R-package/man/xgb.dump.Rd

@@ -16,14 +16,14 @@ xgb.dump(
 \arguments{
 \item{model}{the model object.}
 
-\item{fname}{the name of the text file where to save the model text dump.
+\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
+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}
+\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.
@@ -47,7 +47,7 @@ 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,
+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')

R-package/man/xgb.importance.Rd

@@ -22,7 +22,7 @@ Non-null \code{feature_names} could be provided to override those in the model.}
 
 \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
+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).}
 
@@ -37,7 +37,7 @@ 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
+       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
@@ -51,7 +51,7 @@ A linear model's importance \code{data.table} has the following columns:
   \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},
+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).
 }
@@ -61,21 +61,21 @@ 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
+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,
+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",
+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)
 

R-package/man/xgb.load.Rd

@@ -17,8 +17,8 @@ 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
+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,
@@ -29,7 +29,7 @@ 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,
+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')

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

@@ -20,7 +20,7 @@ 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}
+\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}.}
 
@@ -53,10 +53,10 @@ The columns of the \code{data.table} are:
  \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
+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{
@@ -67,17 +67,17 @@ Parse a boosted tree model text dump into a \code{data.table} structure.
 
 data(agaricus.train, package='xgboost')
 
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
+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
+# 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.plot.deepness.Rd

@@ -23,7 +23,7 @@ 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.
+\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}.}
@@ -45,10 +45,10 @@ 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")
+ \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}
+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

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

@@ -60,7 +60,7 @@ The content of each node is organised that way:
  \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.
@@ -80,7 +80,7 @@ xgb.plot.tree(model = bst)
 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.
+# 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)

R-package/man/xgb.save.Rd

@@ -15,25 +15,21 @@ xgb.save(model, fname)
 Save xgboost model to a file in binary format.
 }
 \details{
-This methods allows to save a model in an xgboost-internal binary format which is universal
+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
+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. Moreover, persisting the model with
-\code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
-future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-how to persist models in a future-proof way, i.e. to make the model accessible in future
-releases of XGBoost.
+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.
 }
 \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,
+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')

R-package/man/xgb.train.Rd

@@ -42,9 +42,9 @@ xgboost(
 )
 }
 \arguments{
-\item{params}{the list of parameters. The complete list of parameters is
-  available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-  is a shorter summary:
+\item{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
 
@@ -82,23 +82,13 @@ xgboost(
 \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:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
     \item \code{reg:logistic} logistic regression.
-    \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
     \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{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-    \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
-    \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
-    \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
-    \item \code{aft_loss_distribution}: Probabilty Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+    \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{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
-    \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
-    \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
-    \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
   }
   \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.

R-package/src/Makevars.in

@@ -3,7 +3,7 @@ PKGROOT=../../
 ENABLE_STD_THREAD=1
 # _*_ mode: Makefile; _*_
 
-CXX_STD = CXX14
+CXX_STD = CXX11
 
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\

R-package/src/Makevars.win

@@ -15,7 +15,7 @@ xgblib:
 	cp -r ../../include .
 	cp -r ../../amalgamation .
 
-CXX_STD = CXX14
+CXX_STD = CXX11
 
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\

R-package/src/xgboost_R.cc

@@ -375,7 +375,7 @@ SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
 
 SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
   R_API_BEGIN();
-  CHECK_CALL(XGBoosterLoadJsonConfig(R_ExternalPtrAddr(handle), CHAR(asChar(value))));
+  XGBoosterLoadJsonConfig(R_ExternalPtrAddr(handle), CHAR(asChar(value)));
   R_API_END();
   return R_NilValue;
 }
@@ -397,9 +397,9 @@ SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
 
 SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
-  CHECK_CALL(XGBoosterUnserializeFromBuffer(R_ExternalPtrAddr(handle),
+  XGBoosterUnserializeFromBuffer(R_ExternalPtrAddr(handle),
                                  RAW(raw),
-                                 length(raw)));
+                                 length(raw));
   R_API_END();
   return R_NilValue;
 }

R-package/tests/generate_models.R

@@ -1,94 +0,0 @@
-# Script to generate reference models. The reference models are used to test backward compatibility
-# of saved model files from XGBoost version 0.90 and 1.0.x.
-library(xgboost)
-library(Matrix)
-source('./generate_models_params.R')
-
-set.seed(0)
-metadata <- model_generator_metadata()
-X <- Matrix(data = rnorm(metadata$kRows * metadata$kCols), nrow = metadata$kRows,
-            ncol = metadata$kCols, sparse = TRUE)
-w <- runif(metadata$kRows)
-
-version <- packageVersion('xgboost')
-target_dir <- 'models'
-
-save_booster <- function (booster, model_name) {
-  booster_bin <- function (model_name) {
-    return (file.path(target_dir, paste('xgboost-', version, '.', model_name, '.bin', sep = '')))
-  }
-  booster_json <- function (model_name) {
-    return (file.path(target_dir, paste('xgboost-', version, '.', model_name, '.json', sep = '')))
-  }
-  booster_rds <- function (model_name) {
-    return (file.path(target_dir, paste('xgboost-', version, '.', model_name, '.rds', sep = '')))
-  }
-  xgb.save(booster, booster_bin(model_name))
-  saveRDS(booster, booster_rds(model_name))
-  if (version >= '1.0.0') {
-    xgb.save(booster, booster_json(model_name))
-  }
-}
-
-generate_regression_model <- function () {
-  print('Regression')
-  y <- rnorm(metadata$kRows)
-
-  data <- xgb.DMatrix(X, label = y)
-  params <- list(tree_method = 'hist', num_parallel_tree = metadata$kForests,
-                 max_depth = metadata$kMaxDepth)
-  booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-  save_booster(booster, 'reg')
-}
-
-generate_logistic_model <- function () {
-  print('Binary classification with logistic loss')
-  y <- sample(0:1, size = metadata$kRows, replace = TRUE)
-  stopifnot(max(y) == 1, min(y) == 0)
-
-  data <- xgb.DMatrix(X, label = y, weight = w)
-  params <- list(tree_method = 'hist', num_parallel_tree = metadata$kForests,
-                 max_depth = metadata$kMaxDepth, objective = 'binary:logistic')
-  booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-  save_booster(booster, 'logit')
-}
-
-generate_classification_model <- function () {
-  print('Multi-class classification')
-  y <- sample(0:(metadata$kClasses - 1), size = metadata$kRows, replace = TRUE)
-  stopifnot(max(y) == metadata$kClasses - 1, min(y) == 0)
-
-  data <- xgb.DMatrix(X, label = y, weight = w)
-  params <- list(num_class = metadata$kClasses, tree_method = 'hist',
-                 num_parallel_tree = metadata$kForests, max_depth = metadata$kMaxDepth,
-                 objective = 'multi:softmax')
-  booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-  save_booster(booster, 'cls')
-}
-
-generate_ranking_model <- function () {
-  print('Learning to rank')
-  y <- sample(0:4, size = metadata$kRows, replace = TRUE)
-  stopifnot(max(y) == 4, min(y) == 0)
-  kGroups <- 20
-  w <- runif(kGroups)
-  g <- rep(50, times = kGroups)
-
-  data <- xgb.DMatrix(X, label = y, group = g)
-  # setinfo(data, 'weight', w)
-  # ^^^ does not work in version <= 1.1.0; see https://github.com/dmlc/xgboost/issues/5942
-  # So call low-level function XGDMatrixSetInfo_R directly. Since this function is not an exported
-  # symbol, use the triple-colon operator.
-  .Call(xgboost:::XGDMatrixSetInfo_R, data, 'weight', as.numeric(w))
-  params <- list(objective = 'rank:ndcg', num_parallel_tree = metadata$kForests,
-                 tree_method = 'hist', max_depth = metadata$kMaxDepth)
-  booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-  save_booster(booster, 'ltr')
-}
-
-dir.create(target_dir)
-
-invisible(generate_regression_model())
-invisible(generate_logistic_model())
-invisible(generate_classification_model())
-invisible(generate_ranking_model())

R-package/tests/generate_models_params.R

@@ -1,10 +0,0 @@
-model_generator_metadata <- function() {
-  return (list(
-    kRounds = 2,
-    kRows = 1000,
-    kCols = 4,
-    kForests = 2,
-    kMaxDepth = 2,
-    kClasses = 3
-  ))
-}

R-package/tests/run_lint.R

@@ -1,71 +0,0 @@
-library(lintr)
-library(crayon)
-
-my_linters <- list(
-  absolute_path_linter = lintr::absolute_path_linter,
-  assignment_linter = lintr::assignment_linter,
-  closed_curly_linter = lintr::closed_curly_linter,
-  commas_linter = lintr::commas_linter,
-  # commented_code_linter = lintr::commented_code_linter,
-  infix_spaces_linter = lintr::infix_spaces_linter,
-  line_length_linter = lintr::line_length_linter,
-  no_tab_linter = lintr::no_tab_linter,
-  object_usage_linter = lintr::object_usage_linter,
-  # snake_case_linter = lintr::snake_case_linter,
-  # multiple_dots_linter = lintr::multiple_dots_linter,
-  object_length_linter = lintr::object_length_linter,
-  open_curly_linter = lintr::open_curly_linter,
-  # single_quotes_linter = lintr::single_quotes_linter,
-  spaces_inside_linter = lintr::spaces_inside_linter,
-  spaces_left_parentheses_linter = lintr::spaces_left_parentheses_linter,
-  trailing_blank_lines_linter = lintr::trailing_blank_lines_linter,
-  trailing_whitespace_linter = lintr::trailing_whitespace_linter,
-  true_false = lintr::T_and_F_symbol_linter
-)
-
-results <- lapply(
-  list.files(path = '.', pattern = '\\.[Rr]$', recursive = TRUE),
-  function (r_file) {
-    cat(sprintf("Processing %s ...\n", r_file))
-    list(r_file = r_file,
-         output = lintr::lint(filename = r_file, linters = my_linters))
-  })
-num_issue <- Reduce(sum, lapply(results, function (e) length(e$output)))
-
-lint2str <- function(lint_entry) {
-  color <- function(type) {
-    switch(type,
-      "warning" = crayon::magenta,
-      "error" = crayon::red,
-      "style" = crayon::blue,
-      crayon::bold
-    )
-  }
-
-  paste0(
-    lapply(lint_entry$output,
-      function (lint_line) {
-        paste0(
-          crayon::bold(lint_entry$r_file, ":",
-          as.character(lint_line$line_number), ":",
-          as.character(lint_line$column_number), ": ", sep = ""),
-          color(lint_line$type)(lint_line$type, ": ", sep = ""),
-          crayon::bold(lint_line$message), "\n",
-          lint_line$line, "\n",
-          lintr:::highlight_string(lint_line$message, lint_line$column_number, lint_line$ranges),
-          "\n",
-          collapse = "")
-      }),
-    collapse = "")
-}
-
-if (num_issue > 0) {
-  cat(sprintf('R linters found %d issues:\n', num_issue))
-  for (entry in results) {
-    if (length(entry$output)) {
-      cat(paste0('**** ', crayon::bold(entry$r_file), '\n'))
-      cat(paste0(lint2str(entry), collapse = ''))
-    }
-  }
-  quit(save = 'no', status = 1)  # Signal error to parent shell
-}

R-package/tests/testthat.R

@@ -1,4 +1,4 @@
 library(testthat)
 library(xgboost)
 
-test_check("xgboost", reporter = ProgressReporter)
+test_check("xgboost")

R-package/tests/testthat/test_basic.R

@@ -2,19 +2,19 @@ require(xgboost)
 
 context("basic functions")
 
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
 set.seed(1994)
 
 # disable some tests for Win32
-windows_flag <- .Platform$OS.type == "windows" &&
+windows_flag = .Platform$OS.type == "windows" &&
                .Machine$sizeof.pointer != 8
-solaris_flag <- (Sys.info()['sysname'] == "SunOS")
+solaris_flag = (Sys.info()['sysname'] == "SunOS")
 
 test_that("train and predict binary classification", {
-  nrounds <- 2
+  nrounds = 2
   expect_output(
     bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
                   eta = 1, nthread = 2, nrounds = nrounds, objective = "binary:logistic")
@@ -30,24 +30,24 @@ test_that("train and predict binary classification", {
 
   pred1 <- predict(bst, train$data, ntreelimit = 1)
   expect_length(pred1, 6513)
-  err_pred1 <- sum((pred1 > 0.5) != train$label) / length(train$label)
+  err_pred1 <- sum((pred1 > 0.5) != train$label)/length(train$label)
   err_log <- bst$evaluation_log[1, train_error]
   expect_lt(abs(err_pred1 - err_log), 10e-6)
 })
 
 test_that("parameter validation works", {
   p <- list(foo = "bar")
-  nrounds <- 1
+  nrounds = 1
   set.seed(1994)
 
   d <- cbind(
     x1 = rnorm(10),
     x2 = rnorm(10),
     x3 = rnorm(10))
-  y <- d[, "x1"] + d[, "x2"]^2 +
-    ifelse(d[, "x3"] > .5, d[, "x3"]^2, 2^d[, "x3"]) +
+  y <- d[,"x1"] + d[,"x2"]^2 +
+    ifelse(d[,"x3"] > .5, d[,"x3"]^2, 2^d[,"x3"]) +
     rnorm(10)
-  dtrain <- xgb.DMatrix(data = d, info = list(label = y))
+  dtrain <- xgb.DMatrix(data=d, info = list(label=y))
 
   correct <- function() {
     params <- list(max_depth = 2, booster = "dart",
@@ -70,15 +70,15 @@ test_that("parameter validation works", {
 
 
 test_that("dart prediction works", {
-  nrounds <- 32
+  nrounds = 32
   set.seed(1994)
 
   d <- cbind(
     x1 = rnorm(100),
     x2 = rnorm(100),
     x3 = rnorm(100))
-  y <- d[, "x1"] + d[, "x2"]^2 +
-    ifelse(d[, "x3"] > .5, d[, "x3"]^2, 2^d[, "x3"]) +
+  y <- d[,"x1"] + d[,"x2"]^2 +
+    ifelse(d[,"x3"] > .5, d[,"x3"]^2, 2^d[,"x3"]) +
     rnorm(100)
 
   set.seed(1994)
@@ -87,23 +87,23 @@ test_that("dart prediction works", {
                                 eta = 1, nthread = 2, nrounds = nrounds, objective = "reg:squarederror")
   pred_by_xgboost_0 <- predict(booster_by_xgboost, newdata = d, ntreelimit = 0)
   pred_by_xgboost_1 <- predict(booster_by_xgboost, newdata = d, ntreelimit = nrounds)
-  expect_true(all(matrix(pred_by_xgboost_0, byrow = TRUE) == matrix(pred_by_xgboost_1, byrow = TRUE)))
+  expect_true(all(matrix(pred_by_xgboost_0, byrow=TRUE) == matrix(pred_by_xgboost_1, byrow=TRUE)))
 
   pred_by_xgboost_2 <- predict(booster_by_xgboost, newdata = d, training = TRUE)
-  expect_false(all(matrix(pred_by_xgboost_0, byrow = TRUE) == matrix(pred_by_xgboost_2, byrow = TRUE)))
+  expect_false(all(matrix(pred_by_xgboost_0, byrow=TRUE) == matrix(pred_by_xgboost_2, byrow=TRUE)))
 
   set.seed(1994)
-  dtrain <- xgb.DMatrix(data = d, info = list(label = y))
-  booster_by_train <- xgb.train(params = list(
-                                    booster = "dart",
-                                    max_depth = 2,
-                                    eta = 1,
-                                    rate_drop = 0.5,
-                                    one_drop = TRUE,
-                                    nthread = 1,
-                                    tree_method = "exact",
-                                    objective = "reg:squarederror"
-                                ),
+  dtrain <- xgb.DMatrix(data=d, info = list(label=y))
+  booster_by_train <- xgb.train( params = list(
+                                   booster = "dart",
+                                   max_depth = 2,
+                                   eta = 1,
+                                   rate_drop = 0.5,
+                                   one_drop = TRUE,
+                                   nthread = 1,
+                                   tree_method= "exact",
+                                   objective = "reg:squarederror"
+                                 ),
                                 data = dtrain,
                                 nrounds = nrounds
                                 )
@@ -111,9 +111,9 @@ test_that("dart prediction works", {
   pred_by_train_1 <- predict(booster_by_train, newdata = dtrain, ntreelimit = nrounds)
   pred_by_train_2 <- predict(booster_by_train, newdata = dtrain, training = TRUE)
 
-  expect_true(all(matrix(pred_by_train_0, byrow = TRUE) == matrix(pred_by_xgboost_0, byrow = TRUE)))
-  expect_true(all(matrix(pred_by_train_1, byrow = TRUE) == matrix(pred_by_xgboost_1, byrow = TRUE)))
-  expect_true(all(matrix(pred_by_train_2, byrow = TRUE) == matrix(pred_by_xgboost_2, byrow = TRUE)))
+  expect_true(all(matrix(pred_by_train_0, byrow=TRUE) == matrix(pred_by_xgboost_0, byrow=TRUE)))
+  expect_true(all(matrix(pred_by_train_1, byrow=TRUE) == matrix(pred_by_xgboost_1, byrow=TRUE)))
+  expect_true(all(matrix(pred_by_train_2, byrow=TRUE) == matrix(pred_by_xgboost_2, byrow=TRUE)))
 })
 
 test_that("train and predict softprob", {
@@ -122,7 +122,7 @@ test_that("train and predict softprob", {
   expect_output(
     bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                    max_depth = 3, eta = 0.5, nthread = 2, nrounds = 5,
-                   objective = "multi:softprob", num_class = 3)
+                   objective = "multi:softprob", num_class=3)
   , "train-merror")
   expect_false(is.null(bst$evaluation_log))
   expect_lt(bst$evaluation_log[, min(train_merror)], 0.025)
@@ -130,17 +130,17 @@ test_that("train and predict softprob", {
   pred <- predict(bst, as.matrix(iris[, -5]))
   expect_length(pred, nrow(iris) * 3)
   # row sums add up to total probability of 1:
-  expect_equal(rowSums(matrix(pred, ncol = 3, byrow = TRUE)), rep(1, nrow(iris)), tolerance = 1e-7)
+  expect_equal(rowSums(matrix(pred, ncol=3, byrow=TRUE)), rep(1, nrow(iris)), tolerance = 1e-7)
   # manually calculate error at the last iteration:
   mpred <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE)
   expect_equal(as.numeric(t(mpred)), pred)
   pred_labels <- max.col(mpred) - 1
-  err <- sum(pred_labels != lb) / length(lb)
+  err <- sum(pred_labels != lb)/length(lb)
   expect_equal(bst$evaluation_log[5, train_merror], err, tolerance = 5e-6)
   # manually calculate error at the 1st iteration:
   mpred <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE, ntreelimit = 1)
   pred_labels <- max.col(mpred) - 1
-  err <- sum(pred_labels != lb) / length(lb)
+  err <- sum(pred_labels != lb)/length(lb)
   expect_equal(bst$evaluation_log[1, train_merror], err, tolerance = 5e-6)
 })
 
@@ -150,7 +150,7 @@ test_that("train and predict softmax", {
   expect_output(
     bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                    max_depth = 3, eta = 0.5, nthread = 2, nrounds = 5,
-                   objective = "multi:softmax", num_class = 3)
+                   objective = "multi:softmax", num_class=3)
   , "train-merror")
   expect_false(is.null(bst$evaluation_log))
   expect_lt(bst$evaluation_log[, min(train_merror)], 0.025)
@@ -158,7 +158,7 @@ test_that("train and predict softmax", {
 
   pred <- predict(bst, as.matrix(iris[, -5]))
   expect_length(pred, nrow(iris))
-  err <- sum(pred != lb) / length(lb)
+  err <- sum(pred != lb)/length(lb)
   expect_equal(bst$evaluation_log[5, train_merror], err, tolerance = 5e-6)
 })
 
@@ -173,12 +173,12 @@ test_that("train and predict RF", {
   expect_equal(xgb.ntree(bst), 20)
 
   pred <- predict(bst, train$data)
-  pred_err <- sum((pred > 0.5) != lb) / length(lb)
+  pred_err <- sum((pred > 0.5) != lb)/length(lb)
   expect_lt(abs(bst$evaluation_log[1, train_error] - pred_err), 10e-6)
   #expect_lt(pred_err, 0.03)
 
   pred <- predict(bst, train$data, ntreelimit = 20)
-  pred_err_20 <- sum((pred > 0.5) != lb) / length(lb)
+  pred_err_20 <- sum((pred > 0.5) != lb)/length(lb)
   expect_equal(pred_err_20, pred_err)
 
   #pred <- predict(bst, train$data, ntreelimit = 1)
@@ -193,19 +193,19 @@ test_that("train and predict RF with softprob", {
   set.seed(11)
   bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                  max_depth = 3, eta = 0.9, nthread = 2, nrounds = nrounds,
-                 objective = "multi:softprob", num_class = 3, verbose = 0,
+                 objective = "multi:softprob", num_class=3, verbose = 0,
                  num_parallel_tree = 4, subsample = 0.5, colsample_bytree = 0.5)
   expect_equal(bst$niter, 15)
-  expect_equal(xgb.ntree(bst), 15 * 3 * 4)
+  expect_equal(xgb.ntree(bst), 15*3*4)
   # predict for all iterations:
-  pred <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE)
+  pred <- predict(bst, as.matrix(iris[, -5]), reshape=TRUE)
   expect_equal(dim(pred), c(nrow(iris), 3))
   pred_labels <- max.col(pred) - 1
-  err <- sum(pred_labels != lb) / length(lb)
+  err <- sum(pred_labels != lb)/length(lb)
   expect_equal(bst$evaluation_log[nrounds, train_merror], err, tolerance = 5e-6)
   # predict for 7 iterations and adjust for 4 parallel trees per iteration
-  pred <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE, ntreelimit = 7 * 4)
-  err <- sum((max.col(pred) - 1) != lb) / length(lb)
+  pred <- predict(bst, as.matrix(iris[, -5]), reshape=TRUE, ntreelimit = 7 * 4)
+  err <- sum((max.col(pred) - 1) != lb)/length(lb)
   expect_equal(bst$evaluation_log[7, train_merror], err, tolerance = 5e-6)
 })
 
@@ -223,7 +223,7 @@ test_that("use of multiple eval metrics works", {
 
 test_that("training continuation works", {
   dtrain <- xgb.DMatrix(train$data, label = train$label)
-  watchlist <- list(train = dtrain)
+  watchlist = list(train=dtrain)
   param <- list(objective = "binary:logistic", max_depth = 2, eta = 1, nthread = 2)
 
   # for the reference, use 4 iterations at once:
@@ -255,7 +255,7 @@ test_that("training continuation works", {
 test_that("model serialization works", {
   out_path <- "model_serialization"
   dtrain <- xgb.DMatrix(train$data, label = train$label)
-  watchlist <- list(train = dtrain)
+  watchlist = list(train=dtrain)
   param <- list(objective = "binary:logistic")
   booster <- xgb.train(param, dtrain, nrounds = 4, watchlist)
   raw <- xgb.serialize(booster)
@@ -273,7 +273,7 @@ test_that("xgb.cv works", {
   expect_output(
     cv <- xgb.cv(data = train$data, label = train$label, max_depth = 2, nfold = 5,
                  eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
-                 verbose = TRUE)
+                 verbose=TRUE)
   , "train-error:")
   expect_is(cv, 'xgb.cv.synchronous')
   expect_false(is.null(cv$evaluation_log))
@@ -292,11 +292,11 @@ test_that("xgb.cv works with stratified folds", {
   set.seed(314159)
   cv <- xgb.cv(data = dtrain, max_depth = 2, nfold = 5,
                eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
-               verbose = TRUE, stratified = FALSE)
+               verbose=TRUE, stratified = FALSE)
   set.seed(314159)
   cv2 <- xgb.cv(data = dtrain, max_depth = 2, nfold = 5,
                 eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
-                verbose = TRUE, stratified = TRUE)
+                verbose=TRUE, stratified = TRUE)
   # Stratified folds should result in a different evaluation logs
   expect_true(all(cv$evaluation_log[, test_error_mean] != cv2$evaluation_log[, test_error_mean]))
 })
@@ -319,7 +319,7 @@ test_that("train and predict with non-strict classes", {
   expect_equal(pr0, pr)
 
   # dense matrix-like input of non-matrix class with some inheritance
-  class(train_dense) <- c('pphmatrix', 'shmatrix')
+  class(train_dense) <- c('pphmatrix','shmatrix')
   expect_true(is.matrix(train_dense))
   expect_error(
     bst <- xgboost(data = train_dense, label = train$label, max_depth = 2,
@@ -337,15 +337,15 @@ test_that("train and predict with non-strict classes", {
 test_that("max_delta_step works", {
   dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
   watchlist <- list(train = dtrain)
-  param <- list(objective = "binary:logistic", eval_metric = "logloss", max_depth = 2, nthread = 2, eta = 0.5)
-  nrounds <- 5
+  param <- list(objective = "binary:logistic", eval_metric="logloss", max_depth = 2, nthread = 2, eta = 0.5)
+  nrounds = 5
   # model with no restriction on max_delta_step
   bst1 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1)
   # model with restricted max_delta_step
   bst2 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1, max_delta_step = 1)
   # the no-restriction model is expected to have consistently lower loss during the initial interations
   expect_true(all(bst1$evaluation_log$train_logloss < bst2$evaluation_log$train_logloss))
-  expect_lt(mean(bst1$evaluation_log$train_logloss) / mean(bst2$evaluation_log$train_logloss), 0.8)
+  expect_lt(mean(bst1$evaluation_log$train_logloss)/mean(bst2$evaluation_log$train_logloss), 0.8)
 })
 
 test_that("colsample_bytree works", {

R-package/tests/testthat/test_callbacks.R

@@ -5,8 +5,8 @@ require(data.table)
 
 context("callbacks")
 
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
 
@@ -21,24 +21,24 @@ ltrain <- add.noise(train$label, 0.2)
 ltest <- add.noise(test$label, 0.2)
 dtrain <- xgb.DMatrix(train$data, label = ltrain)
 dtest <- xgb.DMatrix(test$data, label = ltest)
-watchlist <- list(train = dtrain, test = dtest)
+watchlist = list(train=dtrain, test=dtest)
 
 
-err <- function(label, pr) sum((pr > 0.5) != label) / length(label)
+err <- function(label, pr) sum((pr > 0.5) != label)/length(label)
 
 param <- list(objective = "binary:logistic", max_depth = 2, nthread = 2)
 
 
 test_that("cb.print.evaluation works as expected", {
 
-  bst_evaluation <- c('train-auc' = 0.9, 'test-auc' = 0.8)
+  bst_evaluation <- c('train-auc'=0.9, 'test-auc'=0.8)
   bst_evaluation_err <- NULL
   begin_iteration <- 1
   end_iteration <- 7
 
-  f0 <- cb.print.evaluation(period = 0)
-  f1 <- cb.print.evaluation(period = 1)
-  f5 <- cb.print.evaluation(period = 5)
+  f0 <- cb.print.evaluation(period=0)
+  f1 <- cb.print.evaluation(period=1)
+  f5 <- cb.print.evaluation(period=5)
 
   expect_false(is.null(attr(f1, 'call')))
   expect_equal(attr(f1, 'name'), 'cb.print.evaluation')
@@ -57,13 +57,13 @@ test_that("cb.print.evaluation works as expected", {
   expect_output(f1(), "\\[7\\]\ttrain-auc:0.900000\ttest-auc:0.800000")
   expect_output(f5(), "\\[7\\]\ttrain-auc:0.900000\ttest-auc:0.800000")
 
-  bst_evaluation_err  <- c('train-auc' = 0.1, 'test-auc' = 0.2)
+  bst_evaluation_err  <- c('train-auc'=0.1, 'test-auc'=0.2)
   expect_output(f1(), "\\[7\\]\ttrain-auc:0.900000\\+0.100000\ttest-auc:0.800000\\+0.200000")
 })
 
 test_that("cb.evaluation.log works as expected", {
 
-  bst_evaluation <- c('train-auc' = 0.9, 'test-auc' = 0.8)
+  bst_evaluation <- c('train-auc'=0.9, 'test-auc'=0.8)
   bst_evaluation_err <- NULL
 
   evaluation_log <- list()
@@ -75,33 +75,33 @@ test_that("cb.evaluation.log works as expected", {
   iteration <- 1
   expect_silent(f())
   expect_equal(evaluation_log,
-               list(c(iter = 1, bst_evaluation)))
+               list(c(iter=1, bst_evaluation)))
   iteration <- 2
   expect_silent(f())
   expect_equal(evaluation_log,
-               list(c(iter = 1, bst_evaluation), c(iter = 2, bst_evaluation)))
+               list(c(iter=1, bst_evaluation), c(iter=2, bst_evaluation)))
   expect_silent(f(finalize = TRUE))
   expect_equal(evaluation_log,
-               data.table(iter = 1:2, train_auc = c(0.9, 0.9), test_auc = c(0.8, 0.8)))
+               data.table(iter=1:2, train_auc=c(0.9,0.9), test_auc=c(0.8,0.8)))
 
-  bst_evaluation_err  <- c('train-auc' = 0.1, 'test-auc' = 0.2)
+  bst_evaluation_err  <- c('train-auc'=0.1, 'test-auc'=0.2)
   evaluation_log <- list()
   f <- cb.evaluation.log()
 
   iteration <- 1
   expect_silent(f())
   expect_equal(evaluation_log,
-               list(c(iter = 1, c(bst_evaluation, bst_evaluation_err))))
+               list(c(iter=1, c(bst_evaluation, bst_evaluation_err))))
   iteration <- 2
   expect_silent(f())
   expect_equal(evaluation_log,
-               list(c(iter = 1, c(bst_evaluation, bst_evaluation_err)),
-                    c(iter = 2, c(bst_evaluation, bst_evaluation_err))))
+               list(c(iter=1, c(bst_evaluation, bst_evaluation_err)),
+                    c(iter=2, c(bst_evaluation, bst_evaluation_err))))
   expect_silent(f(finalize = TRUE))
   expect_equal(evaluation_log,
-               data.table(iter = 1:2,
-                          train_auc_mean = c(0.9, 0.9), train_auc_std = c(0.1, 0.1),
-                          test_auc_mean = c(0.8, 0.8), test_auc_std = c(0.2, 0.2)))
+               data.table(iter=1:2,
+                          train_auc_mean=c(0.9,0.9), train_auc_std=c(0.1,0.1),
+                          test_auc_mean=c(0.8,0.8), test_auc_std=c(0.2,0.2)))
 })
 
 
@@ -237,7 +237,7 @@ test_that("early stopping using a specific metric works", {
   set.seed(11)
   expect_output(
     bst <- xgb.train(param, dtrain, nrounds = 20, watchlist, eta = 0.6,
-                     eval_metric = "logloss", eval_metric = "auc",
+                     eval_metric="logloss", eval_metric="auc",
                      callbacks = list(cb.early.stop(stopping_rounds = 3, maximize = FALSE,
                                                     metric_name = 'test_logloss')))
   , "Stopping. Best iteration")
@@ -267,12 +267,12 @@ test_that("early stopping xgb.cv works", {
 
 test_that("prediction in xgb.cv works", {
   set.seed(11)
-  nrounds <- 4
+  nrounds = 4
   cv <- xgb.cv(param, dtrain, nfold = 5, eta = 0.5, nrounds = nrounds, prediction = TRUE, verbose = 0)
   expect_false(is.null(cv$evaluation_log))
   expect_false(is.null(cv$pred))
   expect_length(cv$pred, nrow(train$data))
-  err_pred <- mean(sapply(cv$folds, function(f) mean(err(ltrain[f], cv$pred[f]))))
+  err_pred <- mean( sapply(cv$folds, function(f) mean(err(ltrain[f], cv$pred[f]))) )
   err_log <- cv$evaluation_log[nrounds, test_error_mean]
   expect_equal(err_pred, err_log, tolerance = 1e-6)
 
@@ -308,7 +308,7 @@ test_that("prediction in early-stopping xgb.cv works", {
   expect_false(is.null(cv$pred))
   expect_length(cv$pred, nrow(train$data))
 
-  err_pred <- mean(sapply(cv$folds, function(f) mean(err(ltrain[f], cv$pred[f]))))
+  err_pred <- mean( sapply(cv$folds, function(f) mean(err(ltrain[f], cv$pred[f]))) )
   err_log <- cv$evaluation_log[cv$best_iteration, test_error_mean]
   expect_equal(err_pred, err_log, tolerance = 1e-6)
   err_log_last <- cv$evaluation_log[cv$niter, test_error_mean]

R-package/tests/testthat/test_custom_objective.R

@@ -4,8 +4,8 @@ require(xgboost)
 
 set.seed(1994)
 
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)
@@ -20,12 +20,12 @@ logregobj <- function(preds, dtrain) {
 
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0.5))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1, nthread = 2,
-              objective = logregobj, eval_metric = evalerror)
+param <- list(max_depth=2, eta=1, nthread = 2,
+              objective=logregobj, eval_metric=evalerror)
 num_round <- 2
 
 test_that("custom objective works", {
@@ -37,19 +37,12 @@ test_that("custom objective works", {
 })
 
 test_that("custom objective in CV works", {
-  cv <- xgb.cv(param, dtrain, num_round, nfold = 10, verbose = FALSE)
+  cv <- xgb.cv(param, dtrain, num_round, nfold=10, verbose=FALSE)
   expect_false(is.null(cv$evaluation_log))
   expect_equal(dim(cv$evaluation_log), c(2, 5))
   expect_lt(cv$evaluation_log[num_round, test_error_mean], 0.03)
 })
 
-test_that("custom objective with early stop works", {
-  bst <- xgb.train(param, dtrain, 10, watchlist)
-  expect_equal(class(bst), "xgb.Booster")
-  train_log <- bst$evaluation_log$train_error
-  expect_true(all(diff(train_log)) <= 0)
-})
-
 test_that("custom objective using DMatrix attr works", {
 
   attr(dtrain, 'label') <- getinfo(dtrain, 'label')
@@ -61,14 +54,14 @@ test_that("custom objective using DMatrix attr works", {
     hess <- preds * (1 - preds)
     return(list(grad = grad, hess = hess))
   }
-  param$objective <- logregobjattr
+  param$objective = logregobjattr
   bst <- xgb.train(param, dtrain, num_round, watchlist)
   expect_equal(class(bst), "xgb.Booster")
 })
 
 test_that("custom objective with multi-class works", {
-  data <- as.matrix(iris[, -5])
-  label <-  as.numeric(iris$Species) - 1
+  data = as.matrix(iris[, -5])
+  label =  as.numeric(iris$Species) - 1
   dtrain <- xgb.DMatrix(data = data, label = label)
   nclasses <- 3
 
@@ -79,10 +72,6 @@ test_that("custom objective with multi-class works", {
     hess <- rnorm(dim(as.matrix(preds))[1])
     return (list(grad = grad, hess = hess))
   }
-  fake_merror <- function(preds, dtrain) {
-    expect_equal(dim(data)[1] * nclasses, dim(as.matrix(preds))[1])
-  }
-  param$objective <- fake_softprob
-  param$eval_metric <- fake_merror
-  bst <- xgb.train(param, dtrain, 1, num_class = nclasses)
+  param$objective = fake_softprob
+  bst <- xgb.train(param, dtrain, 1, num_class=nclasses)
 })

R-package/tests/testthat/test_dmatrix.R

@@ -3,29 +3,29 @@ require(Matrix)
 
 context("testing xgb.DMatrix functionality")
 
-data(agaricus.test, package = 'xgboost')
-test_data <- agaricus.test$data[1:100, ]
+data(agaricus.test, package='xgboost')
+test_data <- agaricus.test$data[1:100,]
 test_label <- agaricus.test$label[1:100]
 
 test_that("xgb.DMatrix: basic construction", {
   # from sparse matrix
-  dtest1 <- xgb.DMatrix(test_data, label = test_label)
+  dtest1 <- xgb.DMatrix(test_data, label=test_label)
 
   # from dense matrix
-  dtest2 <- xgb.DMatrix(as.matrix(test_data), label = test_label)
+  dtest2 <- xgb.DMatrix(as.matrix(test_data), label=test_label)
   expect_equal(getinfo(dtest1, 'label'), getinfo(dtest2, 'label'))
   expect_equal(dim(dtest1), dim(dtest2))
 
   #from dense integer matrix
   int_data <- as.matrix(test_data)
   storage.mode(int_data) <- "integer"
-  dtest3 <- xgb.DMatrix(int_data, label = test_label)
+  dtest3 <- xgb.DMatrix(int_data, label=test_label)
   expect_equal(dim(dtest1), dim(dtest3))
 })
 
 test_that("xgb.DMatrix: saving, loading", {
   # save to a local file
-  dtest1 <- xgb.DMatrix(test_data, label = test_label)
+  dtest1 <- xgb.DMatrix(test_data, label=test_label)
   tmp_file <- tempfile('xgb.DMatrix_')
   expect_true(xgb.DMatrix.save(dtest1, tmp_file))
   # read from a local file
@@ -35,12 +35,12 @@ test_that("xgb.DMatrix: saving, loading", {
   expect_equal(getinfo(dtest1, 'label'), getinfo(dtest3, 'label'))
 
   # from a libsvm text file
-  tmp <- c("0 1:1 2:1", "1 3:1", "0 1:1")
+  tmp <- c("0 1:1 2:1","1 3:1","0 1:1")
   tmp_file <- 'tmp.libsvm'
   writeLines(tmp, tmp_file)
   dtest4 <- xgb.DMatrix(tmp_file, silent = TRUE)
   expect_equal(dim(dtest4), c(3, 4))
-  expect_equal(getinfo(dtest4, 'label'), c(0, 1, 0))
+  expect_equal(getinfo(dtest4, 'label'), c(0,1,0))
   unlink(tmp_file)
 })
 
@@ -61,7 +61,7 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
 
   expect_true(setinfo(dtest, 'weight', test_label))
   expect_true(setinfo(dtest, 'base_margin', test_label))
-  expect_true(setinfo(dtest, 'group', c(50, 50)))
+  expect_true(setinfo(dtest, 'group', c(50,50)))
   expect_error(setinfo(dtest, 'group', test_label))
 
   # providing character values will give a warning
@@ -72,35 +72,35 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
 })
 
 test_that("xgb.DMatrix: slice, dim", {
-  dtest <- xgb.DMatrix(test_data, label = test_label)
+  dtest <- xgb.DMatrix(test_data, label=test_label)
   expect_equal(dim(dtest), dim(test_data))
   dsub1 <- slice(dtest, 1:42)
   expect_equal(nrow(dsub1), 42)
   expect_equal(ncol(dsub1), ncol(test_data))
 
-  dsub2 <- dtest[1:42, ]
+  dsub2 <- dtest[1:42,]
   expect_equal(dim(dtest), dim(test_data))
   expect_equal(getinfo(dsub1, 'label'), getinfo(dsub2, 'label'))
 })
 
 test_that("xgb.DMatrix: slice, trailing empty rows", {
-  data(agaricus.train, package = 'xgboost')
+  data(agaricus.train, package='xgboost')
   train_data <- agaricus.train$data
   train_label <- agaricus.train$label
-  dtrain <- xgb.DMatrix(data = train_data, label = train_label)
+  dtrain <- xgb.DMatrix(data=train_data, label=train_label)
   slice(dtrain, 6513L)
   train_data[6513, ] <- 0
-  dtrain <- xgb.DMatrix(data = train_data, label = train_label)
+  dtrain <- xgb.DMatrix(data=train_data, label=train_label)
   slice(dtrain, 6513L)
   expect_equal(nrow(dtrain), 6513)
 })
 
 test_that("xgb.DMatrix: colnames", {
-  dtest <- xgb.DMatrix(test_data, label = test_label)
+  dtest <- xgb.DMatrix(test_data, label=test_label)
   expect_equal(colnames(dtest), colnames(test_data))
-  expect_error(colnames(dtest) <- 'asdf')
+  expect_error( colnames(dtest) <- 'asdf')
   new_names <- make.names(1:ncol(test_data))
-  expect_silent(colnames(dtest) <- new_names)
+  expect_silent( colnames(dtest) <- new_names)
   expect_equal(colnames(dtest), new_names)
   expect_silent(colnames(dtest) <- NULL)
   expect_null(colnames(dtest))
@@ -109,7 +109,7 @@ test_that("xgb.DMatrix: colnames", {
 test_that("xgb.DMatrix: nrow is correct for a very sparse matrix", {
   set.seed(123)
   nr <- 1000
-  x <- rsparsematrix(nr, 100, density = 0.0005)
+  x <- rsparsematrix(nr, 100, density=0.0005)
   # we want it very sparse, so that last rows are empty
   expect_lt(max(x@i), nr)
   dtest <- xgb.DMatrix(x)

R-package/tests/testthat/test_gc_safety.R

@@ -3,8 +3,8 @@ require(xgboost)
 context("Garbage Collection Safety Check")
 
 test_that("train and prediction when gctorture is on", {
-  data(agaricus.train, package = 'xgboost')
-  data(agaricus.test, package = 'xgboost')
+  data(agaricus.train, package='xgboost')
+  data(agaricus.test, package='xgboost')
   train <- agaricus.train
   test <- agaricus.test
   gctorture(TRUE)

R-package/tests/testthat/test_glm.R

@@ -3,8 +3,8 @@ context('Test generalized linear models')
 require(xgboost)
 
 test_that("gblinear works", {
-  data(agaricus.train, package = 'xgboost')
-  data(agaricus.test, package = 'xgboost')
+  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)
 
@@ -16,7 +16,7 @@ test_that("gblinear works", {
   ERR_UL <- 0.005 # upper limit for the test set error
   VERB <- 0      # chatterbox switch
 
-  param$updater <- 'shotgun'
+  param$updater = 'shotgun'
   bst <- xgb.train(param, dtrain, n, watchlist, verbose = VERB, feature_selector = 'shuffle')
   ypred <- predict(bst, dtest)
   expect_equal(length(getinfo(dtest, 'label')), 1611)
@@ -29,7 +29,7 @@ test_that("gblinear works", {
   expect_equal(dim(h), c(n, ncol(dtrain) + 1))
   expect_is(h, "matrix")
 
-  param$updater <- 'coord_descent'
+  param$updater = 'coord_descent'
   bst <- xgb.train(param, dtrain, n, watchlist, verbose = VERB, feature_selector = 'cyclic')
   expect_lt(bst$evaluation_log$eval_error[n], ERR_UL)
 

R-package/tests/testthat/test_helpers.R

@@ -5,18 +5,18 @@ require(data.table)
 require(Matrix)
 require(vcd, quietly = TRUE)
 
-float_tolerance <- 5e-6
+float_tolerance = 5e-6
 
 # disable some tests for 32-bit environment
-flag_32bit <- .Machine$sizeof.pointer != 8
+flag_32bit = .Machine$sizeof.pointer != 8
 
 set.seed(1982)
 data(Arthritis)
-df <- data.table(Arthritis, keep.rownames = FALSE)
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
-df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
-df[, ID := NULL]
-sparse_matrix <- sparse.model.matrix(Improved~.-1, data = df) # nolint
+df <- data.table(Arthritis, keep.rownames = F)
+df[,AgeDiscret := as.factor(round(Age / 10,0))]
+df[,AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[,ID := NULL]
+sparse_matrix <- sparse.model.matrix(Improved~.-1, data = df)
 label <- df[, ifelse(Improved == "Marked", 1, 0)]
 
 # binary
@@ -46,8 +46,8 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 test_that("xgb.dump works", {
   if (!flag_32bit)
     expect_length(xgb.dump(bst.Tree), 200)
-  dump_file <- file.path(tempdir(), 'xgb.model.dump')
-  expect_true(xgb.dump(bst.Tree, dump_file, with_stats = TRUE))
+  dump_file = file.path(tempdir(), 'xgb.model.dump')
+  expect_true(xgb.dump(bst.Tree, dump_file, with_stats = T))
   expect_true(file.exists(dump_file))
   expect_gt(file.size(dump_file), 8000)
 
@@ -63,7 +63,7 @@ test_that("xgb.dump works for gblinear", {
   # also make sure that it works properly for a sparse model where some coefficients
   # are 0 from setting large L1 regularization:
   bst.GLM.sp <- xgboost(data = sparse_matrix, label = label, eta = 1, nthread = 2, nrounds = 1,
-                        alpha = 2, objective = "binary:logistic", booster = "gblinear")
+                        alpha=2, objective = "binary:logistic", booster = "gblinear")
   d.sp <- xgb.dump(bst.GLM.sp)
   expect_length(d.sp, 14)
   expect_gt(sum(d.sp == "0"), 0)
@@ -110,9 +110,9 @@ test_that("predict feature contributions works", {
   pred <- predict(bst.GLM, sparse_matrix, outputmargin = TRUE)
   expect_lt(max(abs(rowSums(pred_contr) - pred)), 1e-5)
   # manual calculation of linear terms
-  coefs <- xgb.dump(bst.GLM)[-c(1, 2, 4)] %>% as.numeric
+  coefs <- xgb.dump(bst.GLM)[-c(1,2,4)] %>% as.numeric
   coefs <- c(coefs[-1], coefs[1]) # intercept must be the last
-  pred_contr_manual <- sweep(cbind(sparse_matrix, 1), 2, coefs, FUN = "*")
+  pred_contr_manual <- sweep(cbind(sparse_matrix, 1), 2, coefs, FUN="*")
   expect_equal(as.numeric(pred_contr), as.numeric(pred_contr_manual),
                tolerance = float_tolerance)
 
@@ -130,13 +130,13 @@ test_that("predict feature contributions works", {
   pred <- predict(mbst.GLM, as.matrix(iris[, -5]), outputmargin = TRUE, reshape = TRUE)
   pred_contr <- predict(mbst.GLM, as.matrix(iris[, -5]), predcontrib = TRUE)
   expect_length(pred_contr, 3)
-  coefs_all <- xgb.dump(mbst.GLM)[-c(1, 2, 6)] %>% as.numeric %>% matrix(ncol = 3, byrow = TRUE)
+  coefs_all <- xgb.dump(mbst.GLM)[-c(1,2,6)] %>% as.numeric %>% matrix(ncol = 3, byrow = TRUE)
   for (g in seq_along(pred_contr)) {
     expect_equal(colnames(pred_contr[[g]]), c(colnames(iris[, -5]), "BIAS"))
     expect_lt(max(abs(rowSums(pred_contr[[g]]) - pred[, g])), float_tolerance)
     # manual calculation of linear terms
     coefs <- c(coefs_all[-1, g], coefs_all[1, g]) # intercept needs to be the last
-    pred_contr_manual <- sweep(as.matrix(cbind(iris[, -5], 1)), 2, coefs, FUN = "*")
+    pred_contr_manual <- sweep(as.matrix(cbind(iris[,-5], 1)), 2, coefs, FUN="*")
     expect_equal(as.numeric(pred_contr[[g]]), as.numeric(pred_contr_manual),
                  tolerance = float_tolerance)
   }
@@ -147,8 +147,8 @@ test_that("SHAPs sum to predictions, with or without DART", {
     x1 = rnorm(100),
     x2 = rnorm(100),
     x3 = rnorm(100))
-  y <- d[, "x1"] + d[, "x2"]^2 +
-    ifelse(d[, "x3"] > .5, d[, "x3"]^2, 2^d[, "x3"]) +
+  y <- d[,"x1"] + d[,"x2"]^2 +
+    ifelse(d[,"x3"] > .5, d[,"x3"]^2, 2^d[,"x3"]) +
     rnorm(100)
   nrounds <- 30
 
@@ -160,7 +160,7 @@ test_that("SHAPs sum to predictions, with or without DART", {
           objective = "reg:squarederror",
           eval_metric = "rmse"),
         if (booster == "dart")
-          list(rate_drop = .01, one_drop = TRUE)),
+          list(rate_drop = .01, one_drop = T)),
       data = d,
       label = y,
       nrounds = nrounds)
@@ -168,21 +168,21 @@ test_that("SHAPs sum to predictions, with or without DART", {
     pr <- function(...)
       predict(fit, newdata = d, ...)
     pred <- pr()
-    shap <- pr(predcontrib = TRUE)
-    shapi <- pr(predinteraction = TRUE)
-    tol <- 1e-5
+    shap <- pr(predcontrib = T)
+    shapi <- pr(predinteraction = T)
+    tol = 1e-5
 
     expect_equal(rowSums(shap), pred, tol = tol)
     expect_equal(apply(shapi, 1, sum), pred, tol = tol)
     for (i in 1 : nrow(d))
       for (f in list(rowSums, colSums))
-        expect_equal(f(shapi[i, , ]), shap[i, ], tol = tol)
+        expect_equal(f(shapi[i,,]), shap[i,], tol = tol)
   }
 })
 
 test_that("xgb-attribute functionality", {
   val <- "my attribute value"
-  list.val <- list(my_attr = val, a = 123, b = 'ok')
+  list.val <- list(my_attr=val, a=123, b='ok')
   list.ch <- list.val[order(names(list.val))]
   list.ch <- lapply(list.ch, as.character)
   # note: iter is 0-index in xgb attributes
@@ -208,9 +208,9 @@ test_that("xgb-attribute functionality", {
   xgb.attr(bst, "my_attr") <- NULL
   expect_null(xgb.attr(bst, "my_attr"))
   expect_equal(xgb.attributes(bst), list.ch[c("a", "b", "niter")])
-  xgb.attributes(bst) <- list(a = NULL, b = NULL)
+  xgb.attributes(bst) <- list(a=NULL, b=NULL)
   expect_equal(xgb.attributes(bst), list.default)
-  xgb.attributes(bst) <- list(niter = NULL)
+  xgb.attributes(bst) <- list(niter=NULL)
   expect_null(xgb.attributes(bst))
 })
 
@@ -268,7 +268,7 @@ test_that("xgb.model.dt.tree works with and without feature names", {
   bst.Tree.x$feature_names <- NULL
   dt.tree.x <- xgb.model.dt.tree(model = bst.Tree.x)
   expect_output(str(dt.tree.x), 'Feature.*\\"3\\"')
-  expect_equal(dt.tree[, -4, with = FALSE], dt.tree.x[, -4, with = FALSE])
+  expect_equal(dt.tree[, -4, with=FALSE], dt.tree.x[, -4, with=FALSE])
 
   # using integer node ID instead of character
   dt.tree.int <- xgb.model.dt.tree(model = bst.Tree, use_int_id = TRUE)
@@ -295,7 +295,7 @@ test_that("xgb.importance works with and without feature names", {
   bst.Tree.x <- bst.Tree
   bst.Tree.x$feature_names <- NULL
   importance.Tree.x <- xgb.importance(model = bst.Tree)
-  expect_equal(importance.Tree[, -1, with = FALSE], importance.Tree.x[, -1, with = FALSE],
+  expect_equal(importance.Tree[, -1, with=FALSE], importance.Tree.x[, -1, with=FALSE],
                tolerance = float_tolerance)
 
   imp2plot <- xgb.plot.importance(importance_matrix = importance.Tree)
@@ -305,7 +305,7 @@ test_that("xgb.importance works with and without feature names", {
   # for multiclass
   imp.Tree <- xgb.importance(model = mbst.Tree)
   expect_equal(dim(imp.Tree), c(4, 4))
-  xgb.importance(model = mbst.Tree, trees = seq(from = 0, by = nclass, length.out = nrounds))
+  xgb.importance(model = mbst.Tree, trees = seq(from=0, by=nclass, length.out=nrounds))
 })
 
 test_that("xgb.importance works with GLM model", {
@@ -320,7 +320,7 @@ test_that("xgb.importance works with GLM model", {
   # for multiclass
   imp.GLM <- xgb.importance(model = mbst.GLM)
   expect_equal(dim(imp.GLM), c(12, 3))
-  expect_equal(imp.GLM$Class, rep(0:2, each = 4))
+  expect_equal(imp.GLM$Class, rep(0:2, each=4))
 })
 
 test_that("xgb.model.dt.tree and xgb.importance work with a single split model", {

R-package/tests/testthat/test_interaction_constraints.R

@@ -5,20 +5,20 @@ context("interaction constraints")
 set.seed(1024)
 x1 <- rnorm(1000, 1)
 x2 <- rnorm(1000, 1)
-x3 <- sample(c(1, 2, 3), size = 1000, replace = TRUE)
-y <- x1 + x2 + x3 + x1 * x2 * x3 + rnorm(1000, 0.001) + 3 * sin(x1)
-train <- matrix(c(x1, x2, x3), ncol = 3)
+x3 <- sample(c(1,2,3), size=1000, replace=TRUE)
+y <- x1 + x2 + x3 + x1*x2*x3 + rnorm(1000, 0.001) + 3*sin(x1)
+train <- matrix(c(x1,x2,x3), ncol = 3)
 
 test_that("interaction constraints for regression", {
   # Fit a model that only allows interaction between x1 and x2
   bst <- xgboost(data = train, label = y, max_depth = 3,
                  eta = 0.1, nthread = 2, nrounds = 100, verbose = 0,
-                 interaction_constraints = list(c(0, 1)))
+                 interaction_constraints = list(c(0,1)))
 
   # Set all observations to have the same x3 values then increment
   #  by the same amount
-  preds <- lapply(c(1, 2, 3), function(x){
-    tmat <- matrix(c(x1, x2, rep(x, 1000)), ncol = 3)
+  preds <- lapply(c(1,2,3), function(x){
+    tmat <- matrix(c(x1,x2,rep(x,1000)), ncol=3)
     return(predict(bst, tmat))
   })
 
@@ -40,16 +40,16 @@ test_that("interaction constraints scientific representation", {
   rows <- 10
   ## When number exceeds 1e5, R paste function uses scientific representation.
   ## See: https://github.com/dmlc/xgboost/issues/5179
-  cols <- 1e5 + 10
+  cols <- 1e5+10
 
-  d <- matrix(rexp(rows, rate = .1), nrow = rows, ncol = cols)
+  d <- matrix(rexp(rows, rate=.1), nrow=rows, ncol=cols)
   y <- rnorm(rows)
 
-  dtrain <- xgb.DMatrix(data = d, info = list(label = y))
+  dtrain <- xgb.DMatrix(data=d, info = list(label=y))
   inc <- list(c(seq.int(from = 0, to = cols, by = 1)))
 
-  with_inc <- xgb.train(data = dtrain, tree_method = 'hist',
-                        interaction_constraints = inc, nrounds = 10)
-  without_inc <- xgb.train(data = dtrain, tree_method = 'hist', nrounds = 10)
+  with_inc <- xgb.train(data=dtrain, tree_method='hist',
+                        interaction_constraints=inc, nrounds=10)
+  without_inc <- xgb.train(data=dtrain, tree_method='hist', nrounds=10)
   expect_equal(xgb.save.raw(with_inc), xgb.save.raw(without_inc))
 })

R-package/tests/testthat/test_interactions.R

@@ -9,9 +9,9 @@ test_that("predict feature interactions works", {
   # simulate some binary data and a linear outcome with an interaction term
   N <- 1000
   P <- 5
-  X <- matrix(rbinom(N * P, 1, 0.5), ncol = P, dimnames = list(NULL, letters[1:P]))
+  X <- matrix(rbinom(N * P, 1, 0.5), ncol=P, dimnames = list(NULL, letters[1:P]))
   # center the data (as contributions are computed WRT feature means)
-  X <- scale(X, scale = FALSE)
+  X <- scale(X, scale=FALSE)
 
   # outcome without any interactions, without any noise:
   f <- function(x) 2 * x[, 1] - 3 * x[, 2]
@@ -23,14 +23,14 @@ test_that("predict feature interactions works", {
   y <- f_int(X)
 
   dm <- xgb.DMatrix(X, label = y)
-  param <- list(eta = 0.1, max_depth = 4, base_score = mean(y), lambda = 0, nthread = 2)
+  param <- list(eta=0.1, max_depth=4, base_score=mean(y), lambda=0, nthread=2)
   b <- xgb.train(param, dm, 100)
-
-  pred <- predict(b, dm, outputmargin = TRUE)
+  
+  pred = predict(b, dm, outputmargin=TRUE)
 
   # SHAP contributions:
-  cont <- predict(b, dm, predcontrib = TRUE)
-  expect_equal(dim(cont), c(N, P + 1))
+  cont <- predict(b, dm, predcontrib=TRUE)
+  expect_equal(dim(cont), c(N, P+1))
   # make sure for each row they add up to marginal predictions
   max(abs(rowSums(cont) - pred)) %>% expect_lt(0.001)
   # Hand-construct the 'ground truth' feature contributions:
@@ -39,43 +39,43 @@ test_that("predict feature interactions works", {
      -3. * X[, 2] + 1. * X[, 2] * X[, 3], # attribute a HALF of the interaction term to feature #2
       1. * X[, 2] * X[, 3]               # and another HALF of the interaction term to feature #3
      )
-  gt_cont <- cbind(gt_cont, matrix(0, nrow = N, ncol = P + 1 - 3))
+  gt_cont <- cbind(gt_cont, matrix(0, nrow=N, ncol=P + 1 - 3))
   # These should be relatively close:
   expect_lt(max(abs(cont - gt_cont)), 0.05)
 
 
   # SHAP interaction contributions:
-  intr <- predict(b, dm, predinteraction = TRUE)
-  expect_equal(dim(intr), c(N, P + 1, P + 1))
+  intr <- predict(b, dm, predinteraction=TRUE)
+  expect_equal(dim(intr), c(N, P+1, P+1))
   # check assigned colnames
   cn <- c(letters[1:P], "BIAS")
   expect_equal(dimnames(intr), list(NULL, cn, cn))
 
   # check the symmetry
-  max(abs(aperm(intr, c(1, 3, 2)) - intr)) %>% expect_lt(0.00001)
+  max(abs(aperm(intr, c(1,3,2)) - intr)) %>% expect_lt(0.00001)
 
   # sums WRT columns must be close to feature contributions
-  max(abs(apply(intr, c(1, 2), sum) - cont)) %>% expect_lt(0.00001)
+  max(abs(apply(intr, c(1,2), sum) - cont)) %>% expect_lt(0.00001)
 
   # diagonal terms for features 3,4,5 must be close to zero
   Reduce(max, sapply(3:P, function(i) max(abs(intr[, i, i])))) %>% expect_lt(0.05)
 
   # BIAS must have no interactions
-  max(abs(intr[, 1:P, P + 1])) %>% expect_lt(0.00001)
+  max(abs(intr[, 1:P, P+1])) %>% expect_lt(0.00001)
 
   # interactions other than 2 x 3 must be close to zero
   intr23 <- intr
-  intr23[, 2, 3] <- 0
-  Reduce(max, sapply(1:P, function(i) max(abs(intr23[, i, (i + 1):(P + 1)])))) %>% expect_lt(0.05)
+  intr23[,2,3] <- 0
+  Reduce(max, sapply(1:P, function(i) max(abs(intr23[, i, (i+1):(P+1)])))) %>% expect_lt(0.05)
 
   # Construct the 'ground truth' contributions of interactions directly from the linear terms:
-  gt_intr <- array(0, c(N, P + 1, P + 1))
-  gt_intr[, 2, 3] <- 1. * X[, 2] * X[, 3] # attribute a HALF of the interaction term to each symmetric element
-  gt_intr[, 3, 2] <- gt_intr[, 2, 3]
+  gt_intr <- array(0, c(N, P+1, P+1))
+  gt_intr[,2,3] <- 1. * X[, 2] * X[, 3] # attribute a HALF of the interaction term to each symmetric element
+  gt_intr[,3,2] <- gt_intr[, 2, 3]
   # merge-in the diagonal based on 'ground truth' feature contributions
-  intr_diag <- gt_cont - apply(gt_intr, c(1, 2), sum)
-  for (j in seq_len(P)) {
-    gt_intr[, j, j] <- intr_diag[, j]
+  intr_diag = gt_cont - apply(gt_intr, c(1,2), sum)
+  for(j in seq_len(P)) {
+    gt_intr[,j,j] = intr_diag[,j]
   }
   # These should be relatively close:
   expect_lt(max(abs(intr - gt_intr)), 0.1)
@@ -107,7 +107,7 @@ test_that("SHAP contribution values are not NAN", {
 
   shaps <- as.data.frame(predict(fit,
     newdata = as.matrix(subset(d, fold == 1)[, ivs]),
-    predcontrib = TRUE))
+    predcontrib = T))
   result <- cbind(shaps, sum = rowSums(shaps), pred = predict(fit,
       newdata = as.matrix(subset(d, fold == 1)[, ivs])))
 
@@ -116,26 +116,26 @@ test_that("SHAP contribution values are not NAN", {
 
 
 test_that("multiclass feature interactions work", {
-  dm <- xgb.DMatrix(as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1)
-  param <- list(eta = 0.1, max_depth = 4, objective = 'multi:softprob', num_class = 3)
+  dm <- xgb.DMatrix(as.matrix(iris[,-5]), label=as.numeric(iris$Species)-1)
+  param <- list(eta=0.1, max_depth=4, objective='multi:softprob', num_class=3)
   b <- xgb.train(param, dm, 40)
-  pred <- predict(b, dm, outputmargin = TRUE) %>% array(c(3, 150)) %>% t
+  pred = predict(b, dm, outputmargin=TRUE) %>% array(c(3, 150)) %>% t
 
   # SHAP contributions:
-  cont <- predict(b, dm, predcontrib = TRUE)
+  cont <- predict(b, dm, predcontrib=TRUE)
   expect_length(cont, 3)
   # rewrap them as a 3d array
   cont <- unlist(cont) %>% array(c(150, 5, 3))
   # make sure for each row they add up to marginal predictions
-  max(abs(apply(cont, c(1, 3), sum) - pred)) %>% expect_lt(0.001)
+  max(abs(apply(cont, c(1,3), sum) - pred)) %>% expect_lt(0.001)
 
   # SHAP interaction contributions:
-  intr <- predict(b, dm, predinteraction = TRUE)
+  intr <- predict(b, dm, predinteraction=TRUE)
   expect_length(intr, 3)
   # rewrap them as a 4d array
   intr <- unlist(intr) %>% array(c(150, 5, 5, 3)) %>% aperm(c(4, 1, 2, 3)) # [grp, row, col, col]
   # check the symmetry
-  max(abs(aperm(intr, c(1, 2, 4, 3)) - intr)) %>% expect_lt(0.00001)
+  max(abs(aperm(intr, c(1,2,4,3)) - intr)) %>% expect_lt(0.00001)
   # sums WRT columns must be close to feature contributions
-  max(abs(apply(intr, c(1, 2, 3), sum) - aperm(cont, c(3, 1, 2)))) %>% expect_lt(0.00001)
+  max(abs(apply(intr, c(1,2,3), sum) - aperm(cont, c(3,1,2)))) %>% expect_lt(0.00001)
 })

R-package/tests/testthat/test_lint.R

@@ -0,0 +1,27 @@
+context("Code is of high quality and lint free")
+test_that("Code Lint", {
+  skip_on_cran()
+  skip_on_travis()
+  skip_if_not_installed("lintr")
+  my_linters <- list(
+    absolute_paths_linter=lintr::absolute_paths_linter,
+    assignment_linter=lintr::assignment_linter,
+    closed_curly_linter=lintr::closed_curly_linter,
+    commas_linter=lintr::commas_linter,
+    # commented_code_linter=lintr::commented_code_linter,
+    infix_spaces_linter=lintr::infix_spaces_linter,
+    line_length_linter=lintr::line_length_linter,
+    no_tab_linter=lintr::no_tab_linter,
+    object_usage_linter=lintr::object_usage_linter,
+    # snake_case_linter=lintr::snake_case_linter,
+    # multiple_dots_linter=lintr::multiple_dots_linter,
+    object_length_linter=lintr::object_length_linter,
+    open_curly_linter=lintr::open_curly_linter,
+    # single_quotes_linter=lintr::single_quotes_linter,
+    spaces_inside_linter=lintr::spaces_inside_linter,
+    spaces_left_parentheses_linter=lintr::spaces_left_parentheses_linter,
+    trailing_blank_lines_linter=lintr::trailing_blank_lines_linter,
+    trailing_whitespace_linter=lintr::trailing_whitespace_linter
+  )
+  # lintr::expect_lint_free(linters=my_linters) # uncomment this if you want to check code quality
+})

R-package/tests/testthat/test_model_compatibility.R

@@ -1,78 +0,0 @@
-require(xgboost)
-require(jsonlite)
-source('../generate_models_params.R')
-
-context("Models from previous versions of XGBoost can be loaded")
-
-metadata <- model_generator_metadata()
-
-run_model_param_check <- function (config) {
-  testthat::expect_equal(config$learner$learner_model_param$num_feature, '4')
-  testthat::expect_equal(config$learner$learner_train_param$booster, 'gbtree')
-}
-
-get_num_tree <- function (booster) {
-  dump <- xgb.dump(booster)
-  m <- regexec('booster\\[[0-9]+\\]', dump, perl = TRUE)
-  m <- regmatches(dump, m)
-  num_tree <- Reduce('+', lapply(m, length))
-  return (num_tree)
-}
-
-run_booster_check <- function (booster, name) {
-  # If given a handle, we need to call xgb.Booster.complete() prior to using xgb.config().
-  if (inherits(booster, "xgb.Booster") && xgboost:::is.null.handle(booster$handle)) {
-    booster <- xgb.Booster.complete(booster)
-  }
-  config <- jsonlite::fromJSON(xgb.config(booster))
-  run_model_param_check(config)
-  if (name == 'cls') {
-    testthat::expect_equal(get_num_tree(booster),
-                           metadata$kForests * metadata$kRounds * metadata$kClasses)
-    testthat::expect_equal(as.numeric(config$learner$learner_model_param$base_score), 0.5)
-    testthat::expect_equal(config$learner$learner_train_param$objective, 'multi:softmax')
-    testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class),
-                           metadata$kClasses)
-  } else if (name == 'logit') {
-    testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
-    testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
-    testthat::expect_equal(config$learner$learner_train_param$objective, 'binary:logistic')
-  } else if (name == 'ltr') {
-    testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
-    testthat::expect_equal(config$learner$learner_train_param$objective, 'rank:ndcg')
-  } else {
-    testthat::expect_equal(name, 'reg')
-    testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
-    testthat::expect_equal(as.numeric(config$learner$learner_model_param$base_score), 0.5)
-    testthat::expect_equal(config$learner$learner_train_param$objective, 'reg:squarederror')
-  }
-}
-
-test_that("Models from previous versions of XGBoost can be loaded", {
-  bucket <- 'xgboost-ci-jenkins-artifacts'
-  region <- 'us-west-2'
-  file_name <- 'xgboost_r_model_compatibility_test.zip'
-  zipfile <- file.path(getwd(), file_name)
-  model_dir <- file.path(getwd(), 'models')
-  download.file(paste('https://', bucket, '.s3-', region, '.amazonaws.com/', file_name, sep = ''),
-                destfile = zipfile, mode = 'wb')
-  unzip(zipfile, overwrite = TRUE)
-
-  pred_data <- xgb.DMatrix(matrix(c(0, 0, 0, 0), nrow = 1, ncol = 4))
-
-  lapply(list.files(model_dir), function (x) {
-    model_file <- file.path(model_dir, x)
-    m <- regexec("xgboost-([0-9\\.]+)\\.([a-z]+)\\.[a-z]+", model_file, perl = TRUE)
-    m <- regmatches(model_file, m)[[1]]
-    model_xgb_ver <- m[2]
-    name <- m[3]
-
-    if (endsWith(model_file, '.rds')) {
-      booster <- readRDS(model_file)
-    } else {
-      booster <- xgb.load(model_file)
-    }
-    predict(booster, newdata = pred_data)
-    run_booster_check(booster, name)
-  })
-})

R-package/tests/testthat/test_monotone.R

@@ -3,21 +3,22 @@ require(xgboost)
 context("monotone constraints")
 
 set.seed(1024)
-x <- rnorm(1000, 10)
-y <- -1 * x + rnorm(1000, 0.001) + 3 * sin(x)
-train <- matrix(x, ncol = 1)
+x = rnorm(1000, 10)
+y = -1*x + rnorm(1000, 0.001) + 3*sin(x)
+train = matrix(x, ncol = 1)
 
 
 test_that("monotone constraints for regression", {
-    bst <- xgboost(data = train, label = y, max_depth = 2,
-                   eta = 0.1, nthread = 2, nrounds = 100, verbose = 0,
-                   monotone_constraints = -1)
-
-    pred <- predict(bst, train)
-
-    ind <- order(train[, 1])
-    pred.ord <- pred[ind]
-    expect_true({
-        !any(diff(pred.ord) > 0)
-    }, "Monotone Contraint Satisfied")
+  bst = xgboost(data = train, label = y, max_depth = 2,
+                eta = 0.1, nthread = 2, nrounds = 100, verbose = 0,
+                monotone_constraints = -1)
+  
+  pred = predict(bst, train)
+  
+  ind = order(train[,1])
+  pred.ord = pred[ind]
+  expect_true({
+    !any(diff(pred.ord) > 0)
+  }, "Monotone Contraint Satisfied")
+  
 })

R-package/tests/testthat/test_parameter_exposure.R

@@ -2,8 +2,8 @@ context('Test model params and call are exposed to R')
 
 require(xgboost)
 
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+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)

R-package/tests/testthat/test_poisson_regression.R

@@ -5,10 +5,10 @@ set.seed(1994)
 
 test_that("poisson regression works", {
   data(mtcars)
-  bst <- xgboost(data = as.matrix(mtcars[, -11]), label = mtcars[, 11],
-                objective = 'count:poisson', nrounds = 10, verbose = 0)
+  bst <- xgboost(data = as.matrix(mtcars[,-11]), label = mtcars[,11],
+                objective = 'count:poisson', nrounds=10, verbose=0)
   expect_equal(class(bst), "xgb.Booster")
   pred <- predict(bst, as.matrix(mtcars[, -11]))
   expect_equal(length(pred), 32)
-  expect_lt(sqrt(mean((pred - mtcars[, 11])^2)), 1.2)
+  expect_lt(sqrt(mean( (pred - mtcars[,11])^2 )), 1.2)
 })

R-package/tests/testthat/test_ranking.R

@@ -1,51 +0,0 @@
-require(xgboost)
-require(Matrix)
-
-context('Learning to rank')
-
-test_that('Test ranking with unweighted data', {
-  X <- sparseMatrix(i = c(2, 3, 7, 9, 12, 15, 17, 18),
-                    j = c(1, 1, 2, 2,  3,  3,  4,  4),
-                    x = rep(1.0, 8), dims = c(20, 4))
-  y <- c(0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0)
-  group <- c(5, 5, 5, 5)
-  dtrain <- xgb.DMatrix(X, label = y, group = group)
-
-  params <- list(eta = 1, tree_method = 'exact', objective = 'rank:pairwise', max_depth = 1,
-                 eval_metric = 'auc', eval_metric = 'aucpr')
-  bst <- xgb.train(params, dtrain, nrounds = 10, watchlist = list(train = dtrain))
-  # Check if the metric is monotone increasing
-  expect_true(all(diff(bst$evaluation_log$train_auc) >= 0))
-  expect_true(all(diff(bst$evaluation_log$train_aucpr) >= 0))
-})
-
-test_that('Test ranking with weighted data', {
-  X <- sparseMatrix(i = c(2, 3, 7, 9, 12, 15, 17, 18),
-                    j = c(1, 1, 2, 2,  3,  3,  4,  4),
-                    x = rep(1.0, 8), dims = c(20, 4))
-  y <- c(0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0)
-  group <- c(5, 5, 5, 5)
-  weight <- c(1.0, 2.0, 3.0, 4.0)
-  dtrain <- xgb.DMatrix(X, label = y, group = group, weight = weight)
-
-  params <- list(eta = 1, tree_method = 'exact', objective = 'rank:pairwise', max_depth = 1,
-                 eval_metric = 'auc', eval_metric = 'aucpr')
-  bst <- xgb.train(params, dtrain, nrounds = 10, watchlist = list(train = dtrain))
-  # Check if the metric is monotone increasing
-  expect_true(all(diff(bst$evaluation_log$train_auc) >= 0))
-  expect_true(all(diff(bst$evaluation_log$train_aucpr) >= 0))
-  for (i in 1:10) {
-    pred <- predict(bst, newdata = dtrain, ntreelimit = i)
-    # is_sorted[i]: is i-th group correctly sorted by the ranking predictor?
-    is_sorted <- lapply(seq(1, 20, by = 5),
-      function (k) {
-        ind <- order(-pred[k:(k + 4)])
-        z <- y[ind + (k - 1)]
-        all(diff(z) <= 0)  # Check if z is monotone decreasing
-      })
-    # Since we give weights 1, 2, 3, 4 to the four query groups,
-    # the ranking predictor will first try to correctly sort the last query group
-    # before correctly sorting other groups.
-    expect_true(all(diff(as.numeric(is_sorted)) >= 0))
-  }
-})

R-package/tests/testthat/test_update.R

@@ -9,23 +9,23 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 # Disable flaky tests for 32-bit Windows.
 # See https://github.com/dmlc/xgboost/issues/3720
-win32_flag <- .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
+win32_flag = .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
 
 test_that("updating the model works", {
-  watchlist <- list(train = dtrain, test = dtest)
+  watchlist = list(train = dtrain, test = dtest)
 
   # no-subsampling
   p1 <- list(objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2)
   set.seed(11)
   bst1 <- xgb.train(p1, dtrain, nrounds = 10, watchlist, verbose = 0)
   tr1 <- xgb.model.dt.tree(model = bst1)
-
+  
   # with subsampling
   p2 <- modifyList(p1, list(subsample = 0.1))
   set.seed(11)
   bst2 <- xgb.train(p2, dtrain, nrounds = 10, watchlist, verbose = 0)
   tr2 <- xgb.model.dt.tree(model = bst2)
-
+  
   # the same no-subsampling boosting with an extra 'refresh' updater:
   p1r <- modifyList(p1, list(updater = 'grow_colmaker,prune,refresh', refresh_leaf = FALSE))
   set.seed(11)
@@ -57,7 +57,7 @@ test_that("updating the model works", {
   # all should be the same when no subsampling
   expect_equal(bst1$evaluation_log, bst1u$evaluation_log)
   expect_equal(tr1, tr1u, tolerance = 0.00001, check.attributes = FALSE)
-
+  
   # process type 'update' for model with subsampling, refreshing only the tree stats from training data:
   p2u <- modifyList(p2, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))
   bst2u <- xgb.train(p2u, dtrain, nrounds = 10, watchlist, verbose = 0, xgb_model = bst2)
@@ -72,7 +72,7 @@ test_that("updating the model works", {
   if (!win32_flag) {
     expect_equal(tr2r, tr2u, tolerance = 0.00001, check.attributes = FALSE)
   }
-
+  
   # process type 'update' for no-subsampling model, refreshing only the tree stats from TEST data:
   p1ut <- modifyList(p1, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))
   bst1ut <- xgb.train(p1ut, dtest, nrounds = 10, watchlist, verbose = 0, xgb_model = bst1)
@@ -93,12 +93,12 @@ test_that("updating works for multiclass & multitree", {
   set.seed(121)
   bst0 <- xgb.train(p0, dtr, 5, watchlist, verbose = 0)
   tr0 <- xgb.model.dt.tree(model = bst0)
-
+  
   # run update process for an original model with subsampling
-  p0u <- modifyList(p0, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))
+  p0u <- modifyList(p0, list(process_type='update', updater='refresh', refresh_leaf=FALSE))
   bst0u <- xgb.train(p0u, dtr, nrounds = bst0$niter, watchlist, xgb_model = bst0, verbose = 0)
   tr0u <- xgb.model.dt.tree(model = bst0u)
-
+  
   # should be the same evaluation but different gains and larger cover
   expect_equal(bst0$evaluation_log, bst0u$evaluation_log)
   expect_equal(tr0[Feature == 'Leaf']$Quality, tr0u[Feature == 'Leaf']$Quality)

R-package/vignettes/discoverYourData.Rmd

@@ -63,7 +63,7 @@ The first step is to load `Arthritis` dataset in memory and wrap it with `data.t
 
 ```{r, results='hide'}
 data(Arthritis)
-df <- data.table(Arthritis, keep.rownames = FALSE)
+df <- data.table(Arthritis, keep.rownames = F)
 ```
 
 > `data.table` is 100% compliant with **R** `data.frame` but its syntax is more consistent and its performance for large dataset is [best in class](http://stackoverflow.com/questions/21435339/data-table-vs-dplyr-can-one-do-something-well-the-other-cant-or-does-poorly) (`dplyr` from **R** and `Pandas` from **Python** [included](https://github.com/Rdatatable/data.table/wiki/Benchmarks-%3A-Grouping)). Some parts of **Xgboost** **R** package use `data.table`.

R-package/vignettes/xgboost.Rnw

@@ -47,15 +47,15 @@ xgboost.version <- packageDescription("xgboost")$Version
 
 \section{Introduction}
 
-This is an introductory document of using the \verb@xgboost@ package in R.
+This is an introductory document of using the \verb@xgboost@ package in R. 
 
 \verb@xgboost@ is short for eXtreme Gradient Boosting package. It is an efficient
- and scalable implementation of gradient boosting framework by \citep{friedman2001greedy} \citep{friedman2000additive}.
+ and scalable implementation of gradient boosting framework by \citep{friedman2001greedy} \citep{friedman2000additive}. 
 The package includes efficient linear model solver and tree learning algorithm.
 It supports various objective functions, including regression, classification
 and ranking. The package is made to be extendible, so that users are also allowed to define their own objectives easily. It has several features:
 \begin{enumerate}
-    \item{Speed: }{\verb@xgboost@ can automatically do parallel computation on
+    \item{Speed: }{\verb@xgboost@ can automatically do parallel computation on 
     Windows and Linux, with openmp. It is generally over 10 times faster than
     \verb@gbm@.}
     \item{Input Type: }{\verb@xgboost@ takes several types of input data:}
@@ -65,9 +65,9 @@ and ranking. The package is made to be extendible, so that users are also allowe
         \item{Data File: }{Local data files}
         \item{xgb.DMatrix: }{\verb@xgboost@'s own class. Recommended.}
     \end{itemize}
-    \item{Sparsity: }{\verb@xgboost@ accepts sparse input for both tree booster
+    \item{Sparsity: }{\verb@xgboost@ accepts sparse input for both tree booster 
     and linear booster, and is optimized for sparse input.}
-    \item{Customization: }{\verb@xgboost@ supports customized objective function
+    \item{Customization: }{\verb@xgboost@ supports customized objective function 
     and evaluation function}
     \item{Performance: }{\verb@xgboost@ has better performance on several different
     datasets.}
@@ -76,8 +76,8 @@ and ranking. The package is made to be extendible, so that users are also allowe
 
 \section{Example with Mushroom data}
 
-In this section, we will illustrate some common usage of \verb@xgboost@. The
-Mushroom data is cited from UCI Machine Learning Repository. \citep{Bache+Lichman:2013}
+In this section, we will illustrate some common usage of \verb@xgboost@. The 
+Mushroom data is cited from UCI Machine Learning Repository. \citep{Bache+Lichman:2013} 
 
 <<Training and prediction with iris>>=
 library(xgboost)
@@ -85,7 +85,7 @@ 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,
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, 
                nrounds = 2, objective = "binary:logistic")
 xgb.save(bst, 'model.save')
 bst = xgb.load('model.save')
@@ -97,12 +97,12 @@ pred <- predict(bst, test$data)
 
 Here we can save the model to a binary local file, and load it when needed.
 We can't inspect the trees inside. However we have another function to save the
-model in plain text.
+model in plain text. 
 <<Dump Model>>=
 xgb.dump(bst, 'model.dump')
 @
 
-The output looks like
+The output looks like 
 
 \begin{verbatim}
 booster[0]:
@@ -122,8 +122,8 @@ booster[1]:
 \end{verbatim}
 
 It is important to know \verb@xgboost@'s own data type: \verb@xgb.DMatrix@.
-It speeds up \verb@xgboost@, and is needed for advanced features such as
-training from initial prediction value, weighted training instance.
+It speeds up \verb@xgboost@, and is needed for advanced features such as 
+training from initial prediction value, weighted training instance. 
 
 We can use \verb@xgb.DMatrix@ to construct an \verb@xgb.DMatrix@ object:
 <<xgb.DMatrix>>=
@@ -132,7 +132,7 @@ class(dtrain)
 head(getinfo(dtrain,'label'))
 @
 
-We can also save the matrix to a binary file. Then load it simply with
+We can also save the matrix to a binary file. Then load it simply with 
 \verb@xgb.DMatrix@
 <<save model>>=
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix')
@@ -163,51 +163,51 @@ evalerror <- function(preds, dtrain) {
 
 dtest <- xgb.DMatrix(test$data, label = test$label)
 watchlist <- list(eval = dtest, train = dtrain)
-param <- list(max_depth = 2, eta = 1)
+param <- list(max_depth = 2, eta = 1, silent = 1)
 
 bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, logregobj, evalerror, maximize = FALSE)
 @
 
-The gradient and second order gradient is required for the output of customized
-objective function.
+The gradient and second order gradient is required for the output of customized 
+objective function. 
 
-We also have \verb@slice@ for row extraction. It is useful in
+We also have \verb@slice@ for row extraction. It is useful in 
 cross-validation.
 
-For a walkthrough demo, please see \verb@R-package/demo/@ for further
+For a walkthrough demo, please see \verb@R-package/demo/@ for further 
 details.
 
 \section{The Higgs Boson competition}
 
-We have made a demo for \href{http://www.kaggle.com/c/higgs-boson}{the Higgs
-Boson Machine Learning Challenge}.
+We have made a demo for \href{http://www.kaggle.com/c/higgs-boson}{the Higgs 
+Boson Machine Learning Challenge}. 
 
 Here are the instructions to make a submission
 \begin{enumerate}
     \item Download the \href{http://www.kaggle.com/c/higgs-boson/data}{datasets}
     and extract them to \verb@data/@.
-    \item Run scripts under \verb@xgboost/demo/kaggle-higgs/@:
-    \href{https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/higgs-train.R}{higgs-train.R}
-    and \href{https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/higgs-pred.R}{higgs-pred.R}.
-    The computation will take less than a minute on Intel i7.
-    \item Go to the \href{http://www.kaggle.com/c/higgs-boson/submissions/attach}{submission page}
+    \item Run scripts under \verb@xgboost/demo/kaggle-higgs/@: 
+    \href{https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/higgs-train.R}{higgs-train.R} 
+    and \href{https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/higgs-pred.R}{higgs-pred.R}. 
+    The computation will take less than a minute on Intel i7. 
+    \item Go to the \href{http://www.kaggle.com/c/higgs-boson/submissions/attach}{submission page} 
     and submit your result.
 \end{enumerate}
 
 We provide \href{https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/speedtest.R}{a script}
-to compare the time cost on the higgs dataset with \verb@gbm@ and \verb@xgboost@.
-The training set contains 350000 records and 30 features.
+to compare the time cost on the higgs dataset with \verb@gbm@ and \verb@xgboost@. 
+The training set contains 350000 records and 30 features. 
 
 \verb@xgboost@ can automatically do parallel computation. On a machine with Intel
 i7-4700MQ and 24GB memories, we found that \verb@xgboost@ costs about 35 seconds, which is about 20 times faster
-than \verb@gbm@. When we limited \verb@xgboost@ to use only one thread, it was
-still about two times faster than \verb@gbm@.
+than \verb@gbm@. When we limited \verb@xgboost@ to use only one thread, it was 
+still about two times faster than \verb@gbm@. 
 
-Meanwhile, the result from \verb@xgboost@ reaches
-\href{http://www.kaggle.com/c/higgs-boson/details/evaluation}{3.60@AMS} with a
-single model. This results stands in the
-\href{http://www.kaggle.com/c/higgs-boson/leaderboard}{top 30\%} of the
-competition.
+Meanwhile, the result from \verb@xgboost@ reaches 
+\href{http://www.kaggle.com/c/higgs-boson/details/evaluation}{3.60@AMS} with a 
+single model. This results stands in the 
+\href{http://www.kaggle.com/c/higgs-boson/leaderboard}{top 30\%} of the 
+competition. 
 
 \bibliographystyle{jss}
 \nocite{*} % list uncited references

R-package/vignettes/xgboostPresentation.Rmd

@@ -363,7 +363,7 @@ xgb.plot.importance(importance_matrix = importance_matrix)
 You can dump the tree you learned using `xgb.dump` into a text file.
 
 ```{r dump, message=T, warning=F}
-xgb.dump(bst, with_stats = TRUE)
+xgb.dump(bst, with_stats = T)
 ```
 
 You can plot the trees from your model using ```xgb.plot.tree``

amalgamation/xgboost-all0.cc

@@ -69,13 +69,13 @@
 #include "../src/learner.cc"
 #include "../src/logging.cc"
 #include "../src/common/common.cc"
-#include "../src/common/charconv.cc"
 #include "../src/common/timer.cc"
 #include "../src/common/host_device_vector.cc"
 #include "../src/common/hist_util.cc"
 #include "../src/common/json.cc"
 #include "../src/common/io.cc"
 #include "../src/common/survival_util.cc"
+#include "../src/common/probability_distribution.cc"
 #include "../src/common/version.cc"
 
 // c_api

appveyor.yml

@@ -1,4 +1,6 @@
 environment:
+    R_ARCH: x64
+    USE_RTOOLS: true
     matrix:
         - target: msvc
           ver: 2015
@@ -10,6 +12,13 @@ environment:
           configuration: Release
         - target: mingw
           generator: "Unix Makefiles"
+        - target: jvm
+        - target: rmsvc
+          ver: 2015
+          generator: "Visual Studio 14 2015 Win64"
+          configuration: Release
+        - target: rmingw
+          generator: "Unix Makefiles"
 
 #matrix:
 #    fast_finish: true
@@ -35,9 +44,21 @@ install:
     - if /i "%DO_PYTHON%" == "on" (
         conda config --set always_yes true &&
         conda update -q conda &&
-        conda install -y numpy scipy pandas matplotlib pytest scikit-learn graphviz python-graphviz hypothesis
+        conda install -y numpy scipy pandas matplotlib pytest scikit-learn graphviz python-graphviz
       )
     - set PATH=C:\Miniconda3-x64\Library\bin\graphviz;%PATH%
+    # R: based on https://github.com/krlmlr/r-appveyor
+    - ps: |
+        if($env:target -eq 'rmingw' -or $env:target -eq 'rmsvc') {
+          #$ErrorActionPreference = "Stop"
+          Invoke-WebRequest https://raw.githubusercontent.com/krlmlr/r-appveyor/master/scripts/appveyor-tool.ps1 -OutFile "$Env:TEMP\appveyor-tool.ps1"
+          Import-Module "$Env:TEMP\appveyor-tool.ps1"
+          Bootstrap
+          $BINARY_DEPS = "c('XML','igraph')"
+          cmd.exe /c "R.exe -q -e ""install.packages($BINARY_DEPS, repos='$CRAN', type='win.binary')"" 2>&1"
+          $DEPS = "c('data.table','magrittr','stringi','ggplot2','DiagrammeR','Ckmeans.1d.dp','vcd','testthat','lintr','knitr','rmarkdown')"
+          cmd.exe /c "R.exe -q -e ""install.packages($DEPS, repos='$CRAN', type='both')"" 2>&1"
+        }
 
 build_script:
     - cd %APPVEYOR_BUILD_FOLDER%
@@ -60,12 +81,53 @@ build_script:
         mkdir wheel &&
         python setup.py bdist_wheel --universal --plat-name win-amd64 -d wheel
       )
+    # R package: make + mingw standard CRAN packaging (only x64 for now)
+    - if /i "%target%" == "rmingw" (
+        make Rbuild &&
+        ls -l &&
+        R.exe CMD INSTALL xgboost*.tar.gz
+      )
+    # R package: cmake + VC2015
+    - if /i "%target%" == "rmsvc" (
+        mkdir build_rmsvc%ver% &&
+        cd build_rmsvc%ver% &&
+        cmake .. -G"%generator%" -DCMAKE_CONFIGURATION_TYPES="Release" -DR_LIB=ON &&
+        cmake --build . --target install --config Release
+      )
+    - if /i "%target%" == "jvm" cd jvm-packages && mvn test -pl :xgboost4j_2.12
 
 test_script:
     - cd %APPVEYOR_BUILD_FOLDER%
     - if /i "%DO_PYTHON%" == "on" python -m pytest tests/python
+    # mingw R package: run the R check (which includes unit tests), and also keep the built binary package
+    - if /i "%target%" == "rmingw" (
+        set _R_CHECK_CRAN_INCOMING_=FALSE&&
+        set _R_CHECK_FORCE_SUGGESTS_=FALSE&&
+        R.exe CMD check xgboost*.tar.gz --no-manual --no-build-vignettes --as-cran --install-args=--build
+      )
+    # MSVC R package: run only the unit tests
+    - if /i "%target%" == "rmsvc" (
+        cd build_rmsvc%ver%\R-package &&
+        R.exe -q -e "library(testthat); setwd('tests'); source('testthat.R')"
+      )
+
+on_failure:
+    # keep the whole output of R check
+    - if /i "%target%" == "rmingw" (
+        7z a failure.zip *.Rcheck\* &&
+        appveyor PushArtifact failure.zip
+      )
 
 artifacts:
+    # log from R check
+    - path: '*.Rcheck\**\*.log'
+      name: Logs
+    # source R-package
+    - path: '\xgboost_*.tar.gz'
+      name: Bits
+    # binary R-package
+    - path: '**\xgboost_*.zip'
+      name: Bits
     # binary Python wheel package
     - path: '**\*.whl'
       name: Bits

cmake/Python_version.in

@@ -1 +1 @@
-@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@rc2
+@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@

cmake/RPackageInstall.cmake.in

@@ -1,34 +0,0 @@
-# Commands to install the R package as a CMake install target
-
-function(check_call)
-  set(cmd COMMAND)
-  cmake_parse_arguments(
-    PARSE_ARGV 0
-    CALL_ARG "" "" "${cmd}"
-  )
-  string(REPLACE ";" " " commands "${CALL_ARG_COMMAND}")
-  message("Command: ${commands}")
-  execute_process(COMMAND ${CALL_ARG_COMMAND}
-                  OUTPUT_VARIABLE _out
-				  ERROR_VARIABLE _err
-				  RESULT_VARIABLE _res)
-  if(NOT "${_res}" EQUAL "0")
-    message(FATAL_ERROR "out: ${_out}, err: ${_err}, res: ${_res}")
-  endif()
-endfunction()
-
-# Important paths
-set(build_dir "@build_dir@")
-set(LIBR_EXECUTABLE "@LIBR_EXECUTABLE@")
-
-# Back up cmake_install.cmake
-file(WRITE "${build_dir}/R-package/src/Makevars" "all:")
-file(WRITE "${build_dir}/R-package/src/Makevars.win" "all:")
-
-# Install dependencies
-set(XGB_DEPS_SCRIPT
-    "deps = setdiff(c('data.table', 'magrittr', 'stringi'), rownames(installed.packages())); if(length(deps)>0) install.packages(deps, repo = 'https://cloud.r-project.org/')")
-check_call(COMMAND "${LIBR_EXECUTABLE}" -q -e "${XGB_DEPS_SCRIPT}")
-
-# Install the XGBoost R package
-check_call(COMMAND "${LIBR_EXECUTABLE}" CMD INSTALL --no-multiarch --build "${build_dir}/R-package")

cmake/RPackageInstallTargetSetup.cmake

@@ -1,16 +0,0 @@
-# Assembles the R-package files in build_dir;
-# if necessary, installs the main R package dependencies;
-# runs R CMD INSTALL.
-function(setup_rpackage_install_target rlib_target build_dir)
-  configure_file(${PROJECT_SOURCE_DIR}/cmake/RPackageInstall.cmake.in ${PROJECT_BINARY_DIR}/RPackageInstall.cmake @ONLY)
-  install(
-    DIRECTORY "${xgboost_SOURCE_DIR}/R-package"
-    DESTINATION "${build_dir}"
-    REGEX "src/*" EXCLUDE
-    REGEX "R-package/configure" EXCLUDE
-  )
-  install(TARGETS ${rlib_target}
-    LIBRARY DESTINATION "${build_dir}/R-package/src/"
-    RUNTIME DESTINATION "${build_dir}/R-package/src/")
-  install(SCRIPT ${PROJECT_BINARY_DIR}/RPackageInstall.cmake)
-endfunction()

cmake/Utils.cmake

@@ -110,9 +110,34 @@ function(format_gencode_flags flags out)
   set(${out} "${${out}}" PARENT_SCOPE)
 endfunction(format_gencode_flags flags)
 
-macro(enable_nvtx target)
-  find_package(NVTX REQUIRED)
-  target_include_directories(${target} PRIVATE "${NVTX_INCLUDE_DIR}")
-  target_link_libraries(${target} PRIVATE "${NVTX_LIBRARY}")
-  target_compile_definitions(${target} PRIVATE -DXGBOOST_USE_NVTX=1)
-endmacro()
+# Assembles the R-package files in build_dir;
+# if necessary, installs the main R package dependencies;
+# runs R CMD INSTALL.
+function(setup_rpackage_install_target rlib_target build_dir)
+  # backup cmake_install.cmake
+  install(CODE "file(COPY \"${build_dir}/R-package/cmake_install.cmake\"
+DESTINATION \"${build_dir}/bak\")")
+
+  install(CODE "file(REMOVE_RECURSE \"${build_dir}/R-package\")")
+  install(
+    DIRECTORY "${xgboost_SOURCE_DIR}/R-package"
+    DESTINATION "${build_dir}"
+    REGEX "src/*" EXCLUDE
+    REGEX "R-package/configure" EXCLUDE
+  )
+  install(TARGETS ${rlib_target}
+    LIBRARY DESTINATION "${build_dir}/R-package/src/"
+    RUNTIME DESTINATION "${build_dir}/R-package/src/")
+  install(CODE "file(WRITE \"${build_dir}/R-package/src/Makevars\" \"all:\")")
+  install(CODE "file(WRITE \"${build_dir}/R-package/src/Makevars.win\" \"all:\")")
+  set(XGB_DEPS_SCRIPT
+    "deps = setdiff(c('data.table', 'magrittr', 'stringi'), rownames(installed.packages()));\
+    if(length(deps)>0) install.packages(deps, repo = 'https://cloud.r-project.org/')")
+  install(CODE "execute_process(COMMAND \"${LIBR_EXECUTABLE}\" \"-q\" \"-e\" \"${XGB_DEPS_SCRIPT}\")")
+  install(CODE "execute_process(COMMAND \"${LIBR_EXECUTABLE}\" CMD INSTALL\
+    \"--no-multiarch\" \"--build\" \"${build_dir}/R-package\")")
+
+  # restore cmake_install.cmake
+  install(CODE "file(RENAME \"${build_dir}/bak/cmake_install.cmake\"
+ \"${build_dir}/R-package/cmake_install.cmake\")")
+endfunction(setup_rpackage_install_target)

cmake/modules/FindLibR.cmake

@@ -15,15 +15,15 @@
 #  R_VERSION (for win)
 #  R_ARCH (for win 64 when want 32 bit build)
 #
-# TODO:
-# - someone to verify OSX detection,
+# TODO: 
+# - someone to verify OSX detection, 
 # - possibly, add OSX detection based on current R in PATH or LIBR_EXECUTABLE
 # - improve registry-based R_HOME detection in Windows (from a set of R_VERSION's)
 
 
 # Windows users might want to change this to their R version:
 if(NOT R_VERSION)
-  set(R_VERSION "4.0.0")
+  set(R_VERSION "3.4.1")
 endif()
 if(NOT R_ARCH)
   if("${CMAKE_SIZEOF_VOID_P}" STREQUAL "4")
@@ -37,32 +37,22 @@ endif()
 # Creates R.lib and R.def in the build directory for linking with MSVC
 function(create_rlib_for_msvc)
   # various checks and warnings
-  if(NOT WIN32 OR (NOT MSVC AND NOT MINGW))
-    message(FATAL_ERROR "create_rlib_for_msvc() can only be used with MSVC or MINGW")
+  if(NOT WIN32 OR NOT MSVC)
+    message(FATAL_ERROR "create_rlib_for_msvc() can only be used with MSVC")
   endif()
   if(NOT EXISTS "${LIBR_LIB_DIR}")
     message(FATAL_ERROR "LIBR_LIB_DIR was not set!")
   endif()
+  find_program(GENDEF_EXE gendef)
   find_program(DLLTOOL_EXE dlltool)
-  if(NOT DLLTOOL_EXE)
-    message(FATAL_ERROR "\ndlltool.exe not found!\
+  if(NOT GENDEF_EXE OR NOT DLLTOOL_EXE)
+    message(FATAL_ERROR "\nEither gendef.exe or dlltool.exe not found!\
       \nDo you have Rtools installed with its MinGW's bin/ in PATH?")
-  endif()
-
+  endif()  
   # extract symbols from R.dll into R.def and R.lib import library
-  get_filename_component(
-    LIBR_RSCRIPT_EXECUTABLE_DIR
-    ${LIBR_EXECUTABLE}
-    DIRECTORY
-  )
-  set(LIBR_RSCRIPT_EXECUTABLE "${LIBR_RSCRIPT_EXECUTABLE_DIR}/Rscript")
-
-  execute_process(
-    COMMAND ${LIBR_RSCRIPT_EXECUTABLE}
-    "${CMAKE_CURRENT_BINARY_DIR}/../../R-package/inst/make-r-def.R"
-    "${LIBR_LIB_DIR}/R.dll" "${CMAKE_CURRENT_BINARY_DIR}/R.def"
-  )
-
+  execute_process(COMMAND ${GENDEF_EXE}
+    "-" "${LIBR_LIB_DIR}/R.dll"
+    OUTPUT_FILE "${CMAKE_CURRENT_BINARY_DIR}/R.def")
   execute_process(COMMAND ${DLLTOOL_EXE}
     "--input-def" "${CMAKE_CURRENT_BINARY_DIR}/R.def"
     "--output-lib" "${CMAKE_CURRENT_BINARY_DIR}/R.lib")
@@ -90,7 +80,7 @@ if(APPLE)
     set(LIBR_INCLUDE_DIRS "${LIBR_HOME}/include" CACHE PATH "R include directory")
     set(LIBR_LIB_DIR "${LIBR_HOME}/lib" CACHE PATH "R lib directory")
   endif()
-
+  
 # detection for UNIX & Win32
 else()
 
@@ -98,7 +88,7 @@ else()
   if(NOT LIBR_EXECUTABLE)
     find_program(LIBR_EXECUTABLE NAMES R R.exe)
   endif()
-
+  
   if(UNIX)
 
     if(NOT LIBR_EXECUTABLE)
@@ -124,7 +114,7 @@ else()
 
   # Windows
   else()
-    # ask R for R_HOME
+    # ask R for R_HOME 
     if(LIBR_EXECUTABLE)
       execute_process(
         COMMAND ${LIBR_EXECUTABLE} "--slave" "--no-save" "-e" "cat(normalizePath(R.home(),winslash='/'))"
@@ -147,7 +137,7 @@ else()
     # set other R paths based on home path
     set(LIBR_INCLUDE_DIRS "${LIBR_HOME}/include")
     set(LIBR_LIB_DIR "${LIBR_HOME}/bin/${R_ARCH}")
-
+ 
 message(STATUS "LIBR_HOME [${LIBR_HOME}]")
 message(STATUS "LIBR_EXECUTABLE [${LIBR_EXECUTABLE}]")
 message(STATUS "LIBR_INCLUDE_DIRS [${LIBR_INCLUDE_DIRS}]")
@@ -158,7 +148,7 @@ message(STATUS "LIBR_CORE_LIBRARY [${LIBR_CORE_LIBRARY}]")
 
 endif()
 
-if((WIN32 AND MSVC) OR (WIN32 AND MINGW))
+if(WIN32 AND MSVC)
   # create a local R.lib import library for R.dll if it doesn't exist
   if(NOT EXISTS "${CMAKE_CURRENT_BINARY_DIR}/R.lib")
     create_rlib_for_msvc()

cmake/modules/FindNVTX.cmake

@@ -1,26 +0,0 @@
-if (NVTX_LIBRARY)
-  unset(NVTX_LIBRARY CACHE)
-endif (NVTX_LIBRARY)
-
-set(NVTX_LIB_NAME nvToolsExt)
-
-
-find_path(NVTX_INCLUDE_DIR
-  NAMES nvToolsExt.h
-  PATHS ${CUDA_HOME}/include ${CUDA_INCLUDE} /usr/local/cuda/include)
-
-
-find_library(NVTX_LIBRARY
-  NAMES nvToolsExt
-  PATHS ${CUDA_HOME}/lib64 /usr/local/cuda/lib64)
-
-message(STATUS "Using nvtx library: ${NVTX_LIBRARY}")
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NVTX DEFAULT_MSG
-                                  NVTX_INCLUDE_DIR NVTX_LIBRARY)
-
-mark_as_advanced(
-  NVTX_INCLUDE_DIR
-  NVTX_LIBRARY
-)

cmake/xgboost.pc.in

@@ -1,12 +0,0 @@
-prefix=@CMAKE_INSTALL_PREFIX@
-version=@xgboost_VERSION@
-exec_prefix=${prefix}/bin
-libdir=${prefix}/lib
-includedir=${prefix}/include
-
-Name: xgboost
-Description: XGBoost - Scalable and Flexible Gradient Boosting.
-Version: ${version}
-
-Cflags: -I${includedir}
-Libs: -L${libdir} -lxgboost

demo/aft_survival/aft_survival_demo.py

@@ -1,7 +1,6 @@
 """
 Demo for survival analysis (regression) using Accelerated Failure Time (AFT) model
 """
-import os
 from sklearn.model_selection import ShuffleSplit
 import pandas as pd
 import numpy as np
@@ -9,8 +8,7 @@ import xgboost as xgb
 
 # The Veterans' Administration Lung Cancer Trial
 # The Statistical Analysis of Failure Time Data by Kalbfleisch J. and Prentice R (1980)
-CURRENT_DIR = os.path.dirname(__file__)
-df = pd.read_csv(os.path.join(CURRENT_DIR, '../data/veterans_lung_cancer.csv'))
+df = pd.read_csv('../data/veterans_lung_cancer.csv')
 print('Training data:')
 print(df)
 
@@ -41,7 +39,7 @@ params = {'verbosity': 0,
           'lambda': 0.01,
           'alpha': 0.02}
 bst = xgb.train(params, dtrain, num_boost_round=10000,
-                evals=[(dtrain, 'train'), (dvalid, 'valid')],
+                evals=[(dtrain, 'train'), (dvalid, 'valid')], 
                 early_stopping_rounds=50)
 
 # Run prediction on the validation set

demo/c-api/.gitignore

@@ -1 +0,0 @@
-c-api-demo

demo/c-api/c-api-demo.c

@@ -20,12 +20,12 @@ if (err != 0) {                                                         \
 int main(int argc, char** argv) {
   int silent = 0;
   int use_gpu = 0;  // set to 1 to use the GPU for training
-
+  
   // load the data
   DMatrixHandle dtrain, dtest;
   safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.train", silent, &dtrain));
   safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.test", silent, &dtest));
-
+  
   // create the booster
   BoosterHandle booster;
   DMatrixHandle eval_dmats[2] = {dtrain, dtest};
@@ -49,7 +49,7 @@ int main(int argc, char** argv) {
   safe_xgboost(XGBoosterSetParam(booster, "gamma", "0.1"));
   safe_xgboost(XGBoosterSetParam(booster, "max_depth", "3"));
   safe_xgboost(XGBoosterSetParam(booster, "verbosity", silent ? "0" : "1"));
-
+  
   // train and evaluate for 10 iterations
   int n_trees = 10;
   const char* eval_names[2] = {"train", "test"};
@@ -60,10 +60,6 @@ int main(int argc, char** argv) {
     printf("%s\n", eval_result);
   }
 
-  bst_ulong num_feature = 0;
-  safe_xgboost(XGBoosterGetNumFeature(booster, &num_feature));
-  printf("num_feature: %llu\n", num_feature);
-
   // predict
   bst_ulong out_len = 0;
   const float* out_result = NULL;