fix R-devel errors (#4251)

.clang-tidy

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

.github/FUNDING.yml

@@ -1 +0,0 @@
-open_collective: xgboost

.gitignore

@@ -17,7 +17,7 @@
 *.tar.gz
 *conf
 *buffer
-*.model
+*model
 *pyc
 *.train
 *.test
@@ -65,11 +65,14 @@ nb-configuration*
 .pydevproject
 .settings/
 build
+config.mk
 /xgboost
 *.data
 build_plugin
+.idea
 recommonmark/
 tags
+*.iml
 *.class
 target
 *.swp
@@ -87,19 +90,5 @@ lib/
 # spark
 metastore_db
 
+plugin/updater_gpu/test/cpp/data
 /include/xgboost/build_config.h
-
-# files from R-package source install
-**/config.status
-R-package/src/Makevars
-
-# Visual Studio Code
-/.vscode/
-
-# IntelliJ/CLion
-.idea
-*.iml
-/cmake-build-debug/
-
-# GDB
-.gdb_history

.travis.yml

@@ -1,55 +1,80 @@
 # disable sudo for container build.
 sudo: required
 
-# Enabling test OS X
+# Enabling test on Linux and OS X
 os:
   - linux
   - osx
 
-osx_image: xcode10.1
-dist: bionic
+osx_image: xcode9.3
 
 # Use Build Matrix to do lint and build seperately
 env:
   matrix:
+    # code lint
+    - TASK=lint
+    # r package test
+    - TASK=r_test
     # python package test
     - TASK=python_test
-    # test installation of Python source distribution
-    - TASK=python_sdist_test
+    - TASK=python_lightweight_test
     # java package test
     - TASK=java_test
     # cmake test
     - TASK=cmake_test
-
-  global:
-    - secure: "PR16i9F8QtNwn99C5NDp8nptAS+97xwDtXEJJfEiEVhxPaaRkOp0MPWhogCaK0Eclxk1TqkgWbdXFknwGycX620AzZWa/A1K3gAs+GrpzqhnPMuoBJ0Z9qxXTbSJvCyvMbYwVrjaxc/zWqdMU8waWz8A7iqKGKs/SqbQ3rO6v7c="
-    - secure: "dAGAjBokqm/0nVoLMofQni/fWIBcYSmdq4XvCBX1ZAMDsWnuOfz/4XCY6h2lEI1rVHZQ+UdZkc9PioOHGPZh5BnvE49/xVVWr9c4/61lrDOlkD01ZjSAeoV0fAZq+93V/wPl4QV+MM+Sem9hNNzFSbN5VsQLAiWCSapWsLdKzqA="
+    # c++ test
+    - TASK=cpp_test
+    # distributed test
+    - TASK=distributed_test
+    # address sanitizer test
+    - TASK=sanitizer_test
 
 matrix:
   exclude:
-    - os: linux
-      env: TASK=python_test
-    - os: linux
-      env: TASK=java_test
-    - os: linux
+    - os: osx
+      env: TASK=lint
+    - os: osx
       env: TASK=cmake_test
+    - os: linux
+      env: TASK=r_test
+    - os: osx
+      env: TASK=python_lightweight_test
+    - os: osx
+      env: TASK=cpp_test
+    - os: osx
+      env: TASK=distributed_test
+    - os: osx
+      env: TASK=sanitizer_test
 
-# dependent brew packages
+# dependent apt packages
 addons:
+  apt:
+    sources:
+      - llvm-toolchain-trusty-5.0
+      - ubuntu-toolchain-r-test
+      - george-edison55-precise-backports
+    packages:
+      - clang
+      - clang-tidy-5.0
+      - cmake-data
+      - doxygen
+      - wget
+      - libcurl4-openssl-dev
+      - unzip
+      - graphviz
+      - gcc-4.8
+      - g++-4.8
+      - gcc-7
+      - g++-7
   homebrew:
     packages:
-      - cmake
-      - libomp
+      - gcc@7
       - graphviz
-      - openssl
-      - libgit2
-      - wget
-      - r
     update: true
 
 before_install:
-  - source tests/travis/travis_setup_env.sh
-  - if [ "${TASK}" != "python_sdist_test" ]; then export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package; fi
+  - source dmlc-core/scripts/travis/travis_setup_env.sh
+  - export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package
   - echo "MAVEN_OPTS='-Xmx2g -XX:MaxPermSize=1024m -XX:ReservedCodeCacheSize=512m -Dorg.slf4j.simpleLogger.defaultLogLevel=error'" > ~/.mavenrc
 
 install:
@@ -64,7 +89,7 @@ cache:
     - ${HOME}/.cache/pip
 
 before_cache:
-  - tests/travis/travis_before_cache.sh
+  - dmlc-core/scripts/travis/travis_before_cache.sh
 
 after_failure:
   - tests/travis/travis_after_failure.sh

CMakeLists.txt

@@ -1,286 +1,344 @@
-cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.1.1)
+cmake_minimum_required (VERSION 3.2)
+project(xgboost)
 include(cmake/Utils.cmake)
-list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
-cmake_policy(SET CMP0022 NEW)
-cmake_policy(SET CMP0079 NEW)
-cmake_policy(SET CMP0063 NEW)
+list(APPEND CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/cmake/modules")
+find_package(OpenMP)
 
-if ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
-  cmake_policy(SET CMP0077 NEW)
-endif ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
-
-message(STATUS "CMake version ${CMAKE_VERSION}")
-
-if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 5.0)
-  message(FATAL_ERROR "GCC version must be at least 5.0!")
-endif()
-
-include(${xgboost_SOURCE_DIR}/cmake/FindPrefetchIntrinsics.cmake)
-find_prefetch_intrinsics()
-include(${xgboost_SOURCE_DIR}/cmake/Version.cmake)
-write_version()
 set_default_configuration_release()
+msvc_use_static_runtime()
+
+# Options
+## GPUs
+option(USE_CUDA  "Build with GPU acceleration" OFF)
+option(USE_NCCL  "Build with multiple GPUs support" OFF)
+set(GPU_COMPUTE_VER "" CACHE STRING
+  "Space separated list of compute versions to be built against, e.g. '35 61'")
 
-#-- Options
-option(BUILD_C_DOC "Build documentation for C APIs using Doxygen." OFF)
-option(USE_OPENMP "Build with OpenMP support." ON)
-option(BUILD_STATIC_LIB "Build static library" OFF)
 ## Bindings
 option(JVM_BINDINGS "Build JVM bindings" OFF)
 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(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)
-set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
-option(RABIT_MOCK "Build rabit with mock" OFF)
-option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
-## CUDA
-option(USE_CUDA  "Build with GPU acceleration" OFF)
-option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
-option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
-set(GPU_COMPUTE_VER "" CACHE STRING
-  "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
-## Copied From dmlc
-option(USE_HDFS "Build with HDFS support" OFF)
-option(USE_AZURE "Build with AZURE support" OFF)
-option(USE_S3 "Build with S3 support" OFF)
-## Sanitizers
+
+## Devs
 option(USE_SANITIZER "Use santizer flags" OFF)
 option(SANITIZER_PATH "Path to sanitizes.")
 set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
   "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
-address, leak, undefined and thread.")
-## Plugins
+address, leak and thread.")
+option(GOOGLE_TEST "Build google tests" OFF)
+
+# 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)))
-  message(SEND_ERROR "Do not enable `USE_DEBUG_OUTPUT' with release build.")
-endif (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
-if (USE_NCCL AND NOT (USE_CUDA))
-  message(SEND_ERROR "`USE_NCCL` must be enabled with `USE_CUDA` flag.")
-endif (USE_NCCL AND NOT (USE_CUDA))
-if (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_NCCL=ON to enable BUILD_WITH_SHARED_NCCL.")
-endif (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-if (JVM_BINDINGS AND R_LIB)
-  message(SEND_ERROR "`R_LIB' is not compatible with `JVM_BINDINGS' as they both have customized configurations.")
-endif (JVM_BINDINGS AND R_LIB)
-if (R_LIB AND GOOGLE_TEST)
-  message(WARNING "Some C++ unittests will fail with `R_LIB` enabled,
- as R package redirects some functions to R runtime implementation.")
-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)
+# Deprecation warning
+if(USE_AVX)
+  message(WARNING "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from xgboost.")
+endif()
 
-#-- Sanitizer
-if (USE_SANITIZER)
+# Compiler flags
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+if(OpenMP_CXX_FOUND OR OPENMP_FOUND)
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
+endif()
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+if(MSVC)
+  # Multithreaded compilation
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /MP")
+else()
+  # Correct error for GCC 5 and cuda
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D_MWAITXINTRIN_H_INCLUDED -D_FORCE_INLINES")
+  # Performance
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -funroll-loops")
+endif()
+if(WIN32 AND MINGW)
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -static-libstdc++")
+endif()
+
+# Check existence of software pre-fetching
+include(CheckCXXSourceCompiles)
+check_cxx_source_compiles("
+#include <xmmintrin.h>
+int main() {
+  char data = 0;
+  const char* address = &data;
+  _mm_prefetch(address, _MM_HINT_NTA);
+  return 0;
+}
+" XGBOOST_MM_PREFETCH_PRESENT)
+check_cxx_source_compiles("
+int main() {
+  char data = 0;
+  const char* address = &data;
+  __builtin_prefetch(address, 0, 0);
+  return 0;
+}
+" XGBOOST_BUILTIN_PREFETCH_PRESENT)
+
+# Sanitizer
+if(USE_SANITIZER)
   include(cmake/Sanitizer.cmake)
   enable_sanitizers("${ENABLED_SANITIZERS}")
-endif (USE_SANITIZER)
-
-if (USE_CUDA)
-  SET(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
-  # `export CXX=' is ignored by CMake CUDA.
-  set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
-  message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
-
-  enable_language(CUDA)
-  set(GEN_CODE "")
-  format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
-  message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
-endif (USE_CUDA)
-
-find_package(Threads REQUIRED)
-
-if (USE_OPENMP)
-  if (APPLE)
-    # Require CMake 3.16+ on Mac OSX, as previous versions of CMake had trouble locating
-    # OpenMP on Mac. See https://github.com/dmlc/xgboost/pull/5146#issuecomment-568312706
-    cmake_minimum_required(VERSION 3.16)
-  endif (APPLE)
-  find_package(OpenMP REQUIRED)
-endif (USE_OPENMP)
+endif(USE_SANITIZER)
 
 # dmlc-core
-msvc_use_static_runtime()
-add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-set_target_properties(dmlc PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-list(APPEND LINKED_LIBRARIES_PRIVATE dmlc)
+add_subdirectory(dmlc-core)
+set(LINK_LIBRARIES dmlc rabit)
+
+# enable custom logging
+add_definitions(-DDMLC_LOG_CUSTOMIZE=1)
+
+# compiled code customizations for R package
+if(R_LIB)
+  add_definitions(
+    -DXGBOOST_STRICT_R_MODE=1
+    -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
+    -DDMLC_LOG_BEFORE_THROW=0
+    -DDMLC_DISABLE_STDIN=1
+    -DDMLC_LOG_CUSTOMIZE=1
+    -DRABIT_CUSTOMIZE_MSG_
+    -DRABIT_STRICT_CXX98_
+  )
+endif()
+
+# Gather source files
+include_directories (
+    ${PROJECT_SOURCE_DIR}/include
+    ${PROJECT_SOURCE_DIR}/dmlc-core/include
+    ${PROJECT_SOURCE_DIR}/rabit/include
+)
+
+# Generate configurable header
+set(CMAKE_LOCAL "${PROJECT_SOURCE_DIR}/cmake")
+set(INCLUDE_ROOT "${PROJECT_SOURCE_DIR}/include")
+message(STATUS "${CMAKE_LOCAL}/build_config.h.in -> ${INCLUDE_ROOT}/xgboost/build_config.h")
+configure_file("${CMAKE_LOCAL}/build_config.h.in" "${INCLUDE_ROOT}/xgboost/build_config.h")
+
+file(GLOB_RECURSE SOURCES
+    src/*.cc
+    src/*.h
+    include/*.h
+)
+
+# Only add main function for executable target
+list(REMOVE_ITEM SOURCES ${PROJECT_SOURCE_DIR}/src/cli_main.cc)
+
+file(GLOB_RECURSE CUDA_SOURCES
+    src/*.cu
+    src/*.cuh
+)
+
+# Add plugins to source files
+if(PLUGIN_LZ4)
+  list(APPEND SOURCES plugin/lz4/sparse_page_lz4_format.cc)
+  link_libraries(lz4)
+endif()
+if(PLUGIN_DENSE_PARSER)
+  list(APPEND SOURCES plugin/dense_parser/dense_libsvm.cc)
+endif()
 
 # rabit
-set(RABIT_BUILD_DMLC OFF)
-set(DMLC_ROOT ${xgboost_SOURCE_DIR}/dmlc-core)
-set(RABIT_WITH_R_LIB ${R_LIB})
-add_subdirectory(rabit)
+# TODO: Use CMakeLists.txt from rabit.
+set(RABIT_SOURCES
+    rabit/src/allreduce_base.cc
+    rabit/src/allreduce_robust.cc
+    rabit/src/engine.cc
+    rabit/src/c_api.cc
+)
+set(RABIT_EMPTY_SOURCES
+    rabit/src/engine_empty.cc
+    rabit/src/c_api.cc
+)
 
-if (RABIT_MOCK)
-  list(APPEND LINKED_LIBRARIES_PRIVATE rabit_mock_static)
+if(MINGW OR R_LIB)
+  # build a dummy rabit library
+  add_library(rabit STATIC ${RABIT_EMPTY_SOURCES})
 else()
-  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)
-  # from dmlc is correctly applied to rabit.
-  if (TARGET ${lib})
-    target_link_libraries(${lib} dmlc ${CMAKE_THREAD_LIBS_INIT})
-    if (HIDE_CXX_SYMBOLS)  # Hide all C++ symbols from Rabit
-      set_target_properties(${lib} PROPERTIES CXX_VISIBILITY_PRESET hidden)
-    endif (HIDE_CXX_SYMBOLS)
-  endif (TARGET ${lib})
-endforeach()
+  add_library(rabit STATIC ${RABIT_SOURCES})
+endif()
 
-# Exports some R specific definitions and objects
-if (R_LIB)
-  add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
-endif (R_LIB)
+if (GENERATE_COMPILATION_DATABASE)
+  set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+endif (GENERATE_COMPILATION_DATABASE)
 
-# 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>")
+if(USE_CUDA AND (NOT GENERATE_COMPILATION_DATABASE))
+  find_package(CUDA 8.0 REQUIRED)
+  cmake_minimum_required(VERSION 3.5)
 
-#-- library
-if (BUILD_STATIC_LIB)
-  add_library(xgboost STATIC ${XGBOOST_OBJ_SOURCES})
-else (BUILD_STATIC_LIB)
-  add_library(xgboost SHARED ${XGBOOST_OBJ_SOURCES})
-endif (BUILD_STATIC_LIB)
+  add_definitions(-DXGBOOST_USE_CUDA)
 
-#-- Hide all C++ symbols
-if (HIDE_CXX_SYMBOLS)
-  set_target_properties(objxgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
-  set_target_properties(xgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
-endif (HIDE_CXX_SYMBOLS)
+  include_directories(cub)
 
-target_include_directories(xgboost
-  INTERFACE
-  $<INSTALL_INTERFACE:${CMAKE_INSTALL_PREFIX}/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
-target_link_libraries(xgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
+  if(USE_NCCL)
+    find_package(Nccl REQUIRED)
+    cuda_include_directories(${NCCL_INCLUDE_DIR})
+    add_definitions(-DXGBOOST_USE_NCCL)
+  endif()
 
-# This creates its own shared library `xgboost4j'.
-if (JVM_BINDINGS)
-  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
-endif (JVM_BINDINGS)
-#-- End shared library
+  set(GENCODE_FLAGS "")
+  format_gencode_flags("${GPU_COMPUTE_VER}" GENCODE_FLAGS)
+  message("cuda architecture flags: ${GENCODE_FLAGS}")
 
-#-- CLI for xgboost
-add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc ${XGBOOST_OBJ_SOURCES})
+  set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};--expt-extended-lambda;--expt-relaxed-constexpr;${GENCODE_FLAGS};-lineinfo;")
+  if(NOT MSVC)
+    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};-Xcompiler -fPIC; -Xcompiler -Werror; -std=c++11")
+  endif()
 
-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 11
-  CXX_STANDARD_REQUIRED ON)
-#-- End CLI for xgboost
+  cuda_add_library(gpuxgboost ${CUDA_SOURCES} STATIC)
 
-set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
-set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
-# Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
-add_dependencies(xgboost runxgboost)
+  if(USE_NCCL)
+    link_directories(${NCCL_LIBRARY})
+    target_link_libraries(gpuxgboost ${NCCL_LIB_NAME})
+  endif()
+  list(APPEND LINK_LIBRARIES gpuxgboost)
 
-#-- Installing XGBoost
-if (R_LIB)
+elseif (USE_CUDA AND GENERATE_COMPILATION_DATABASE)
+  # Enable CUDA language to generate a compilation database.
+  cmake_minimum_required(VERSION 3.8)
+
+  find_package(CUDA 8.0 REQUIRED)
+  enable_language(CUDA)
+  set(CMAKE_CUDA_COMPILER clang++)
+  set(CUDA_SEPARABLE_COMPILATION ON)
+  if (NOT CLANG_CUDA_GENCODE)
+    set(CLANG_CUDA_GENCODE "--cuda-gpu-arch=sm_35")
+  endif (NOT CLANG_CUDA_GENCODE)
+  set(CMAKE_CUDA_FLAGS " -Wno-deprecated  ${CLANG_CUDA_GENCODE} -fPIC ${GENCODE} -std=c++11 -x cuda")
+  message(STATUS "CMAKE_CUDA_FLAGS: ${CMAKE_CUDA_FLAGS}")
+
+  add_library(gpuxgboost STATIC ${CUDA_SOURCES})
+
+  if(USE_NCCL)
+    find_package(Nccl REQUIRED)
+    target_include_directories(gpuxgboost PUBLIC ${NCCL_INCLUDE_DIR})
+    target_compile_definitions(gpuxgboost PUBLIC -DXGBOOST_USE_NCCL)
+    target_link_libraries(gpuxgboost PUBLIC ${NCCL_LIB_NAME})
+  endif()
+
+  target_compile_definitions(gpuxgboost PUBLIC -DXGBOOST_USE_CUDA)
+  # A hack for CMake to make arguments valid for clang++
+  string(REPLACE "-x cu" "-x cuda" CMAKE_CUDA_COMPILE_PTX_COMPILATION
+    ${CMAKE_CUDA_COMPILE_PTX_COMPILATION})
+  string(REPLACE "-x cu" "-x cuda" CMAKE_CUDA_COMPILE_WHOLE_COMPILATION
+    ${CMAKE_CUDA_COMPILE_WHOLE_COMPILATION})
+  string(REPLACE "-x cu" "-x cuda" CMAKE_CUDA_COMPILE_SEPARABLE_COMPILATION
+    ${CMAKE_CUDA_COMPILE_SEPARABLE_COMPILATION})
+  target_include_directories(gpuxgboost PUBLIC cub)
+endif()
+
+
+# flags and sources for R-package
+if(R_LIB)
+  file(GLOB_RECURSE R_SOURCES
+    R-package/src/*.h
+    R-package/src/*.c
+    R-package/src/*.cc
+  )
+  list(APPEND SOURCES ${R_SOURCES})
+endif()
+
+add_library(objxgboost OBJECT ${SOURCES})
+
+# building shared library for R package
+if(R_LIB)
+  find_package(LibR REQUIRED)
+
+  list(APPEND LINK_LIBRARIES "${LIBR_CORE_LIBRARY}")
+  MESSAGE(STATUS "LIBR_CORE_LIBRARY " ${LIBR_CORE_LIBRARY})
+
+  # Shared library target for the R package
+  add_library(xgboost SHARED $<TARGET_OBJECTS:objxgboost>)
+  include_directories(xgboost
+    "${LIBR_INCLUDE_DIRS}"
+    "${PROJECT_SOURCE_DIR}"
+  )
+
+  target_link_libraries(xgboost ${LINK_LIBRARIES})
+  # R uses no lib prefix in shared library names of its packages
   set_target_properties(xgboost PROPERTIES PREFIX "")
-  if (APPLE)
+  if(APPLE)
     set_target_properties(xgboost PROPERTIES SUFFIX ".so")
-  endif (APPLE)
+  endif()
+
   setup_rpackage_install_target(xgboost ${CMAKE_CURRENT_BINARY_DIR})
+  # use a dummy location for any other remaining installs
   set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
-endif (R_LIB)
-if (MINGW)
-  set_target_properties(xgboost PROPERTIES PREFIX "")
-endif (MINGW)
 
-if (BUILD_C_DOC)
-  include(cmake/Doc.cmake)
-  run_doxygen()
-endif (BUILD_C_DOC)
+  # main targets: shared library & exe
+else()
+  # Executable
+  add_executable(runxgboost $<TARGET_OBJECTS:objxgboost> src/cli_main.cc)
+  set_target_properties(runxgboost PROPERTIES
+    OUTPUT_NAME xgboost
+  )
+  set_output_directory(runxgboost ${PROJECT_SOURCE_DIR})
+  target_link_libraries(runxgboost ${LINK_LIBRARIES})
 
-include(GNUInstallDirs)
-# Install all headers.  Please note that currently the C++ headers does not form an "API".
-install(DIRECTORY ${xgboost_SOURCE_DIR}/include/xgboost
-  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
+  # Shared library
+  add_library(xgboost SHARED $<TARGET_OBJECTS:objxgboost>)
+  target_link_libraries(xgboost ${LINK_LIBRARIES})
+  set_output_directory(xgboost ${PROJECT_SOURCE_DIR}/lib)
+  if(MINGW)
+    # remove the 'lib' prefix to conform to windows convention for shared library names
+    set_target_properties(xgboost PROPERTIES PREFIX "")
+  endif()
 
-install(TARGETS xgboost runxgboost
-  EXPORT XGBoostTargets
-  ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
-  INCLUDES DESTINATION ${LIBLEGACY_INCLUDE_DIRS})
-install(EXPORT XGBoostTargets
-  FILE XGBoostTargets.cmake
-  NAMESPACE xgboost::
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
+  #Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
+  add_dependencies(xgboost runxgboost)
+endif()
 
-include(CMakePackageConfigHelpers)
-configure_package_config_file(
-  ${CMAKE_CURRENT_LIST_DIR}/cmake/xgboost-config.cmake.in
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
-  INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-write_basic_package_version_file(
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  VERSION ${XGBOOST_VERSION}
-  COMPATIBILITY AnyNewerVersion)
-install(
-  FILES
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
+# JVM
+if(JVM_BINDINGS)
+    find_package(JNI QUIET REQUIRED)
 
-#-- Test
-if (GOOGLE_TEST)
+    add_library(xgboost4j SHARED
+      $<TARGET_OBJECTS:objxgboost>
+      jvm-packages/xgboost4j/src/native/xgboost4j.cpp)
+    target_include_directories(xgboost4j
+      PRIVATE ${JNI_INCLUDE_DIRS}
+      PRIVATE jvm-packages/xgboost4j/src/native)
+    target_link_libraries(xgboost4j
+      ${LINK_LIBRARIES}
+      ${JAVA_JVM_LIBRARY})
+    set_output_directory(xgboost4j ${PROJECT_SOURCE_DIR}/lib)
+endif()
+
+
+# Test
+if(GOOGLE_TEST)
   enable_testing()
-  # Unittests.
-  add_subdirectory(${xgboost_SOURCE_DIR}/tests/cpp)
-  add_test(
-    NAME TestXGBoostLib
-    COMMAND testxgboost
-    WORKING_DIRECTORY ${xgboost_BINARY_DIR})
+  find_package(GTest REQUIRED)
 
-  # CLI tests
-  configure_file(
-    ${xgboost_SOURCE_DIR}/tests/cli/machine.conf.in
-    ${xgboost_BINARY_DIR}/tests/cli/machine.conf
-    @ONLY)
-  add_test(
-    NAME TestXGBoostCLI
-    COMMAND runxgboost ${xgboost_BINARY_DIR}/tests/cli/machine.conf
-    WORKING_DIRECTORY ${xgboost_BINARY_DIR})
-  set_tests_properties(TestXGBoostCLI
-    PROPERTIES
-    PASS_REGULAR_EXPRESSION ".*test-rmse:0.087.*")
-endif (GOOGLE_TEST)
+  file(GLOB_RECURSE TEST_SOURCES "tests/cpp/*.cc")
+  auto_source_group("${TEST_SOURCES}")
 
-# For MSVC: Call msvc_use_static_runtime() once again to completely
-# replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
-# for issues caused by mixing of /MD and /MT flags
-msvc_use_static_runtime()
+  if(USE_CUDA AND (NOT GENERATE_COMPILATION_DATABASE))
+    file(GLOB_RECURSE CUDA_TEST_SOURCES "tests/cpp/*.cu")
+    cuda_include_directories(${GTEST_INCLUDE_DIRS})
+    cuda_compile(CUDA_TEST_OBJS ${CUDA_TEST_SOURCES})
+  elseif (USE_CUDA AND GENERATE_COMPILATION_DATABASE)
+    file(GLOB_RECURSE CUDA_TEST_SOURCES "tests/cpp/*.cu")
+  else()
+    set(CUDA_TEST_OBJS "")
+  endif()
 
-# Add xgboost.pc
-if (ADD_PKGCONFIG)
-  configure_file(${xgboost_SOURCE_DIR}/cmake/xgboost.pc.in ${xgboost_BINARY_DIR}/xgboost.pc @ONLY)
+  if (USE_CUDA AND GENERATE_COMPILATION_DATABASE)
+    add_executable(testxgboost ${TEST_SOURCES} ${CUDA_TEST_SOURCES}
+      $<TARGET_OBJECTS:objxgboost>)
+    target_include_directories(testxgboost PRIVATE cub)
+  else ()
+    add_executable(testxgboost ${TEST_SOURCES} ${CUDA_TEST_OBJS}
+      $<TARGET_OBJECTS:objxgboost>)
+  endif ()
 
-  install(
-    FILES ${xgboost_BINARY_DIR}/xgboost.pc
-    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
-endif (ADD_PKGCONFIG)
+  set_output_directory(testxgboost ${PROJECT_SOURCE_DIR})
+  target_include_directories(testxgboost
+    PRIVATE ${GTEST_INCLUDE_DIRS})
+  target_link_libraries(testxgboost ${GTEST_LIBRARIES} ${LINK_LIBRARIES})
+
+  add_test(TestXGBoost testxgboost)
+endif()
+
+
+# Group sources
+auto_source_group("${SOURCES}")

CONTRIBUTORS.md

@@ -2,42 +2,34 @@ Contributors of DMLC/XGBoost
 ============================
 XGBoost has been developed and used by a group of active community. Everyone is more than welcomed to is a great way to make the project better and more accessible to more users.
 
-Project Management Committee(PMC) 
-----------
-The Project Management Committee(PMC) consists group of active committers that moderate the discussion, manage the project release, and proposes new committer/PMC members. 
-
-* [Tianqi Chen](https://github.com/tqchen), University of Washington
-  - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
-* [Michael Benesty](https://github.com/pommedeterresautee)
-  - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Ant Financial
-  - Yuan is a software engineer in Ant Financial. He contributed mostly in R and Python packages.
-* [Nan Zhu](https://github.com/CodingCat), Uber
-  - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
-* [Jiaming Yuan](https://github.com/trivialfis)
-  - Jiaming contributed to the GPU algorithms. He has also introduced new abstractions to improve the quality of the C++ codebase.
-* [Hyunsu Cho](http://hyunsu-cho.io/), NVIDIA
-  - Hyunsu is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater.
-* [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
-  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
-* [Hongliang Liu](https://github.com/phunterlau)
-
-
 Committers
 ----------
 Committers are people who have made substantial contribution to the project and granted write access to the project.
-
+* [Tianqi Chen](https://github.com/tqchen), University of Washington
+  - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [Tong He](https://github.com/hetong007), Amazon AI
   - Tong is an applied scientist in Amazon AI. He is the maintainer of XGBoost R package.
 * [Vadim Khotilovich](https://github.com/khotilov)
   - Vadim contributes many improvements in R and core packages.
 * [Bing Xu](https://github.com/antinucleon)
   - Bing is the original creator of XGBoost Python package and currently the maintainer of [XGBoost.jl](https://github.com/antinucleon/XGBoost.jl).
+* [Michael Benesty](https://github.com/pommedeterresautee)
+  - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
+* [Yuan Tang](https://github.com/terrytangyuan), Ant Financial
+  - Yuan is a software engineer in Ant Financial. He contributed mostly in R and Python packages.
+* [Nan Zhu](https://github.com/CodingCat), Uber
+  - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
 * [Sergei Lebedev](https://github.com/superbobry), Criteo
   - Sergei is a software engineer in Criteo. He contributed mostly in JVM packages.
+* [Hongliang Liu](https://github.com/phunterlau)
 * [Scott Lundberg](http://scottlundberg.com/), University of Washington
   - Scott is a Ph.D. student at University of Washington. He is the creator of SHAP, a unified approach to explain the output of machine learning models such as decision tree ensembles. He also helps maintain the XGBoost Julia package.
-
+* [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
+  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
+* [Hyunsu Cho](http://hyunsu-cho.io/), Amazon AI
+  - Hyunsu is an applied scientist in Amazon AI. He is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater. 
+* [Jiaming](https://github.com/trivialfis)
+  - Jiaming contributed to the GPU algorithms. He has also introduced new abstractions to improve the quality of the C++ codebase.
 
 Become a Committer
 ------------------
@@ -96,9 +88,3 @@ List of Contributors
 * [Chen Qin](https://github.com/chenqin)
 * [Sam Wilkinson](https://samwilkinson.io)
 * [Matthew Jones](https://github.com/mt-jones)
-* [Jiaxiang Li](https://github.com/JiaxiangBU)
-* [Bryan Woods](https://github.com/bryan-woods)
-  - Bryan added support for cross-validation for the ranking objective
-* [Haoda Fu](https://github.com/fuhaoda)
-* [Evan Kepner](https://github.com/EvanKepner)
-  - Evan Kepner added support for os.PathLike file paths in Python

Jenkinsfile

@@ -3,420 +3,125 @@
 // Jenkins pipeline
 // See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
 
-// Command to run command inside a docker container
-dockerRun = 'tests/ci_build/ci_build.sh'
-
 import groovy.transform.Field
 
+/* Unrestricted tasks: tasks that do NOT generate artifacts */
+
+// Command to run command inside a docker container
+def dockerRun = 'tests/ci_build/ci_build.sh'
+// Utility functions
 @Field
-def commit_id   // necessary to pass a variable from one stage to another
+def utils
+
+def buildMatrix = [
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "9.2", "multiGpu": true],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "9.2" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": false, "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+]
 
 pipeline {
-  // Each stage specify its own agent
-  agent none
+    // Each stage specify its own agent
+    agent none
 
-  environment {
-    DOCKER_CACHE_ECR_ID = '492475357299'
-    DOCKER_CACHE_ECR_REGION = 'us-west-2'
-  }
+    // Setup common job properties
+    options {
+        ansiColor('xterm')
+        timestamps()
+        timeout(time: 120, unit: 'MINUTES')
+        buildDiscarder(logRotator(numToKeepStr: '10'))
+    }
 
-  // Setup common job properties
-  options {
-    ansiColor('xterm')
-    timestamps()
-    timeout(time: 240, unit: 'MINUTES')
-    buildDiscarder(logRotator(numToKeepStr: '10'))
-    preserveStashes()
-  }
-
-  // Build stages
-  stages {
-    stage('Jenkins Linux: Initialize') {
-      agent { label 'job_initializer' }
-      steps {
-        script {
-          checkoutSrcs()
-          commit_id = "${GIT_COMMIT}"
+    // Build stages
+    stages {
+        stage('Jenkins: Get sources') {
+            agent {
+                label 'unrestricted'
+            }
+            steps {
+                script {
+                    utils = load('tests/ci_build/jenkins_tools.Groovy')
+                    utils.checkoutSrcs()
+                }
+                stash name: 'srcs', excludes: '.git/'
+                milestone label: 'Sources ready', ordinal: 1
+            }
         }
-        sh 'python3 tests/jenkins_get_approval.py'
-        stash name: 'srcs'
-        milestone ordinal: 1
-      }
-    }
-    stage('Jenkins Linux: Formatting Check') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'clang-tidy': { ClangTidy() },
-            'sphinx-doc': { SphinxDoc() },
-            'doxygen': { Doxygen() }
-          ])
+        stage('Jenkins: Build & Test') {
+            steps {
+                script {
+                    parallel (buildMatrix.findAll{it['enabled']}.collectEntries{ c ->
+                        def buildName = utils.getBuildName(c)
+                        utils.buildFactory(buildName, c, false, this.&buildPlatformCmake)
+                    } + [ "clang-tidy" : { buildClangTidyJob() } ])
+                }
+            }
         }
-        milestone ordinal: 2
-      }
     }
-    stage('Jenkins Linux: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-cpu': { BuildCPU() },
-            'build-cpu-rabit-mock': { BuildCPUMock() },
-            'build-cpu-non-omp': { BuildCPUNonOmp() },
-            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
-            'build-jvm-doc': { BuildJVMDoc() }
-          ])
+}
+
+/**
+ * Build platform and test it via cmake.
+ */
+def buildPlatformCmake(buildName, conf, nodeReq, dockerTarget) {
+    def opts = utils.cmakeOptions(conf)
+    // Destination dir for artifacts
+    def distDir = "dist/${buildName}"
+    def dockerArgs = ""
+    if (conf["withGpu"]) {
+        dockerArgs = "--build-arg CUDA_VERSION=" + conf["cudaVersion"]
+    }
+    def test_suite = conf["withGpu"] ? (conf["multiGpu"] ? "mgpu" : "gpu") : "cpu"
+    // Build node - this is returned result
+    retry(1) {
+        node(nodeReq) {
+            unstash name: 'srcs'
+            echo """
+            |===== XGBoost CMake build =====
+            |  dockerTarget: ${dockerTarget}
+            |  cmakeOpts   : ${opts}
+            |=========================
+            """.stripMargin('|')
+            // Invoke command inside docker
+            sh """
+            ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/build_via_cmake.sh ${opts}
+            ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/test_${test_suite}.sh
+            """
+            if (!conf["multiGpu"]) {
+                sh """
+                ${dockerRun} ${dockerTarget} ${dockerArgs} bash -c "cd python-package; rm -f dist/*; python setup.py bdist_wheel --universal"
+                rm -rf "${distDir}"; mkdir -p "${distDir}/py"
+                cp xgboost "${distDir}"
+                cp -r python-package/dist "${distDir}/py"
+                # Test the wheel for compatibility on a barebones CPU container
+                ${dockerRun} release ${dockerArgs} bash -c " \
+                    pip install --user python-package/dist/xgboost-*-none-any.whl && \
+		    pytest -v --fulltrace -s tests/python"
+                # Test the wheel for compatibility on CUDA 10.0 container
+                ${dockerRun} gpu --build-arg CUDA_VERSION=10.0 bash -c " \
+                    pip install --user python-package/dist/xgboost-*-none-any.whl && \
+		    pytest -v -s --fulltrace -m '(not mgpu) and (not slow)' tests/python-gpu"
+                """
+            }
         }
-        milestone ordinal: 3
+    }
+}
+
+/**
+ * Run a clang-tidy job on a GPU machine
+ */
+def buildClangTidyJob() {
+    def nodeReq = "linux && gpu && unrestricted"
+    node(nodeReq) {
+        unstash name: 'srcs'
+        echo "Running clang-tidy job..."
+        // Invoke command inside docker
+        // Install Google Test and Python yaml
+        dockerTarget = "clang_tidy"
+        dockerArgs = "--build-arg CUDA_VERSION=9.2"
+        sh """
+        ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/clang_tidy.sh
+        """
       }
-    }
-    stage('Jenkins Linux: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-python-cpu': { TestPythonCPU() },
-            '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) }
-          ])
-        }
-        milestone ordinal: 4
-      }
-    }
-    stage('Jenkins Linux: Deploy') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '2.4.3') }
-          ])
-        }
-        milestone ordinal: 5
-      }
-    }
   }
-}
 
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def ClangTidy() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running clang-tidy job..."
-    def container_type = "clang_tidy"
-    def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION=10.1"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
-    """
-    deleteDir()
-  }
-}
-
-def Lint() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running lint..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} make lint
-    """
-    deleteDir()
-  }
-}
-
-def SphinxDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running sphinx-doc..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
-    sh """#!/bin/bash
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} make -C doc html
-    """
-    deleteDir()
-  }
-}
-
-def Doxygen() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running doxygen..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
-    """
-    echo 'Uploading doc...'
-    s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
-    deleteDir()
-  }
-}
-
-def BuildCPU() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} rm -fv dmlc-core/include/dmlc/build_config_default.h
-      # 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
-    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
-    """
-    // Sanitizer test
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
-      -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
-    """
-
-    stash name: 'xgboost_cli', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCPUMock() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU with rabit mock"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_mock_cmake.sh
-    """
-    echo 'Stashing rabit C++ test executable (xgboost)...'
-    stash name: 'xgboost_rabit_tests', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCPUNonOmp() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU without OpenMP"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_OPENMP=OFF
-    """
-    echo "Running Non-OpenMP C++ test..."
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
-    """
-    deleteDir()
-  }
-}
-
-def BuildCUDA(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build with CUDA ${args.cuda_version}"
-    def container_type = "gpu_build"
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -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} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
-    """
-    // Stash wheel for CUDA 10.0 target
-    if (args.cuda_version == '10.0') {
-      echo 'Stashing Python wheel...'
-      stash name: 'xgboost_whl_cuda10', includes: 'python-package/dist/*.whl'
-      path = ("${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'
-    }
-    deleteDir()
-  }
-}
-
-def BuildJVMPackages(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}"
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    // Use only 4 CPU cores
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
-    """
-    echo 'Stashing XGBoost4J JAR...'
-    stash name: 'xgboost4j_jar', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
-    deleteDir()
-  }
-}
-
-def BuildJVMDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Building JVM doc..."
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
-    """
-    echo 'Uploading doc...'
-    s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
-    deleteDir()
-  }
-}
-
-def TestPythonCPU() {
-  node('linux && cpu') {
-    unstash name: 'xgboost_whl_cuda10'
-    unstash name: 'srcs'
-    unstash name: 'xgboost_cli'
-    echo "Test Python CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-py35
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  node(nodeReq) {
-    unstash name: 'xgboost_whl_cuda10'
-    unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
-      """
-    } else {
-      echo "Using a single GPU"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
-      """
-    }
-    deleteDir()
-  }
-}
-
-def TestCppRabit() {
-  node(nodeReq) {
-    unstash name: 'xgboost_rabit_tests'
-    unstash name: 'srcs'
-    echo "Test C++, rabit mock on"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/runxgb.sh xgboost tests/ci_build/approx.conf.in
-    """
-    deleteDir()
-  }
-}
-
-def TestCppGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  node(nodeReq) {
-    unstash name: 'xgboost_cpp_tests'
-    unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=*.MGPU_*"
-    } else {
-      echo "Using a single GPU"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=-*.MGPU_*"
-    }
-    deleteDir()
-  }
-}
-
-def CrossTestJVMwithJDK(args) {
-  node('linux && cpu') {
-    unstash name: 'xgboost4j_jar'
-    unstash name: 'srcs'
-    if (args.spark_version != null) {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
-    } else {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
-    }
-    def container_type = "jvm_cross"
-    def docker_binary = "docker"
-    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
-    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
-    // Run integration tests only when spark_version is given
-    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
-    """
-    deleteDir()
-  }
-}
-
-def TestR(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Test R package"
-    def container_type = "rproject"
-    def docker_binary = "docker"
-    def use_r35_flag = (args.use_r35) ? "1" : "0"
-    def docker_args = "--build-arg USE_R35=${use_r35_flag}"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_test_rpkg.sh || tests/ci_build/print_r_stacktrace.sh
-    """
-    deleteDir()
-  }
-}
-
-def DeployJVMPackages(args) {
-  node('linux && cpu') {
-    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} ${container_type} ${docker_binary} tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
-      """
-    }
-    deleteDir()
-  }
-}

Jenkinsfile-restricted

@@ -0,0 +1,123 @@
+#!/usr/bin/groovy
+// -*- mode: groovy -*-
+// Jenkins pipeline
+// See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
+
+import groovy.transform.Field
+
+/* Restricted tasks: tasks generating artifacts, such as binary wheels and
+                     documentation */
+
+// Command to run command inside a docker container
+def dockerRun = 'tests/ci_build/ci_build.sh'
+// Utility functions
+@Field
+def utils
+@Field
+def commit_id
+@Field
+def branch_name
+
+def buildMatrix = [
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "9.2" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": false, "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+]
+
+pipeline {
+    // Each stage specify its own agent
+    agent none
+
+    // Setup common job properties
+    options {
+        ansiColor('xterm')
+        timestamps()
+        timeout(time: 120, unit: 'MINUTES')
+        buildDiscarder(logRotator(numToKeepStr: '10'))
+    }
+
+    // Build stages
+    stages {
+        stage('Jenkins: Get sources') {
+            agent {
+                label 'restricted'
+            }
+            steps {
+                script {
+                    utils = load('tests/ci_build/jenkins_tools.Groovy')
+                    utils.checkoutSrcs()
+                    commit_id = "${GIT_COMMIT}"
+                    branch_name = "${GIT_LOCAL_BRANCH}"
+                }
+                stash name: 'srcs', excludes: '.git/'
+                milestone label: 'Sources ready', ordinal: 1
+            }
+        }
+        stage('Jenkins: Build doc') {
+            steps {
+                script {
+                    retry(1) {
+                        node('linux && cpu && restricted') {
+                            unstash name: 'srcs'
+                            echo 'Building doc...'
+                            dir ('jvm-packages') {
+                                sh "bash ./build_doc.sh ${commit_id}"
+                                archiveArtifacts artifacts: "${commit_id}.tar.bz2", allowEmptyArchive: true
+                                echo 'Deploying doc...'
+                                withAWS(credentials:'xgboost-doc-bucket') {
+                                    s3Upload file: "${commit_id}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${branch_name}.tar.bz2"
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+
+        stage('Jenkins: Build artifacts') {
+            steps {
+                script {
+                    parallel (buildMatrix.findAll{it['enabled']}.collectEntries{ c ->
+                        def buildName = utils.getBuildName(c)
+                        utils.buildFactory(buildName, c, true, this.&buildPlatformCmake)
+                    })
+                }
+            }
+        }
+    }
+}
+
+/**
+ * Build platform and test it via cmake.
+ */
+def buildPlatformCmake(buildName, conf, nodeReq, dockerTarget) {
+    def opts = utils.cmakeOptions(conf)
+    // Destination dir for artifacts
+    def distDir = "dist/${buildName}"
+    def dockerArgs = ""
+    if(conf["withGpu"]){
+        dockerArgs = "--build-arg CUDA_VERSION=" + conf["cudaVersion"]
+    }
+    // Build node - this is returned result
+    retry(1) {
+        node(nodeReq) {
+            unstash name: 'srcs'
+            echo """
+            |===== XGBoost CMake build =====
+            |  dockerTarget: ${dockerTarget}
+            |  cmakeOpts   : ${opts}
+            |=========================
+            """.stripMargin('|')
+            // Invoke command inside docker
+            sh """
+            ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/build_via_cmake.sh ${opts}
+            ${dockerRun} ${dockerTarget} ${dockerArgs} bash -c "cd python-package; rm -f dist/*; python setup.py bdist_wheel --universal"
+            rm -rf "${distDir}"; mkdir -p "${distDir}/py"
+            cp xgboost "${distDir}"
+            cp -r lib "${distDir}"
+            cp -r python-package/dist "${distDir}/py"
+            """
+            archiveArtifacts artifacts: "${distDir}/**/*.*", allowEmptyArchive: true
+        }
+    }
+}

Jenkinsfile-win64

@@ -1,150 +0,0 @@
-#!/usr/bin/groovy
-// -*- mode: groovy -*-
-
-/* Jenkins pipeline for Windows AMD64 target */
-
-import groovy.transform.Field
-
-@Field
-def commit_id   // necessary to pass a variable from one stage to another
-
-pipeline {
-  agent none
-  // Build stages
-  stages {
-    stage('Jenkins Win64: Initialize') {
-      agent { label 'job_initializer' }
-      steps {
-        script {
-          checkoutSrcs()
-          commit_id = "${GIT_COMMIT}"
-        }
-        sh 'python3 tests/jenkins_get_approval.py'
-        stash name: 'srcs'
-        milestone ordinal: 1
-      }
-    }
-    stage('Jenkins Win64: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-win64-cuda10.0': { BuildWin64() }
-          ])
-        }
-        milestone ordinal: 2
-      }
-    }
-    stage('Jenkins Win64: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-win64-cpu': { TestWin64CPU() },
-            'test-win64-gpu-cuda10.1': { TestWin64GPU(cuda_target: 'cuda10_1') }
-          ])
-        }
-        milestone ordinal: 3
-      }
-    }
-  }
-}
-
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def BuildWin64() {
-  node('win64 && build && cuda10') {
-    unstash name: 'srcs'
-    echo "Building XGBoost for Windows AMD64 target..."
-    bat "nvcc --version"
-    bat """
-    mkdir build
-    cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
-    """
-    bat """
-    cd build
-    "C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Community\\MSBuild\\15.0\\Bin\\MSBuild.exe" xgboost.sln /m /p:Configuration=Release /nodeReuse:false
-    """
-    bat """
-    cd python-package
-    conda activate && python setup.py bdist_wheel --universal && for /R %%i in (dist\\*.whl) DO python ../tests/ci_build/rename_whl.py "%%i" ${commit_id} win_amd64
-    """
-    echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
-    bat """
-    cd python-package\\dist
-    COPY /B ..\\..\\tests\\ci_build\\insert_vcomp140.py
-    conda activate && python insert_vcomp140.py *.whl
-    """
-    echo 'Stashing Python wheel...'
-    stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    path = ("${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'
-    deleteDir()
-  }
-}
-
-def TestWin64CPU() {
-  node('win64 && cpu') {
-    unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    unstash name: 'xgboost_cli'
-    echo "Test Win64 CPU"
-    echo "Installing Python wheel..."
-    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
-    bat """
-    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "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 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 && python -m pip uninstall -y cupy-cuda100 cupy-cuda101 cupy-cuda102
-    """
-    echo "Running Python tests..."
-    bat """
-    conda activate && python -m pytest -v -s --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
-    """
-    bat "conda activate && python -m pip uninstall -y xgboost"
-    deleteDir()
-  }
-}

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright (c) 2019 by Contributors
+   Copyright (c) 2018 by Contributors
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,3 +1,11 @@
+ifndef config
+ifneq ("$(wildcard ./config.mk)","")
+	config = config.mk
+else
+	config = make/config.mk
+endif
+endif
+
 ifndef DMLC_CORE
 	DMLC_CORE = dmlc-core
 endif
@@ -22,8 +30,23 @@ ifndef MAKE_OK
 endif
 $(warning MAKE [$(MAKE)] - $(if $(MAKE_OK),checked OK,PROBLEM))
 
+ifeq ($(OS), Windows_NT)
+	UNAME="Windows"
+else
+	UNAME=$(shell uname)
+endif
+
+include $(config)
+ifeq ($(USE_OPENMP), 0)
+	export NO_OPENMP = 1
+endif
 include $(DMLC_CORE)/make/dmlc.mk
 
+# include the plugins
+ifdef XGB_PLUGINS
+include $(XGB_PLUGINS)
+endif
+
 # set compiler defaults for OSX versus *nix
 # let people override either
 OS := $(shell uname)
@@ -44,40 +67,126 @@ export CXX = g++
 endif
 endif
 
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
+export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS) $(PLUGIN_LDFLAGS)
+export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS) $(PLUGIN_CFLAGS)
 CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
+#java include path
+export JAVAINCFLAGS = -I${JAVA_HOME}/include -I./java
 
 ifeq ($(TEST_COVER), 1)
 	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
 else
 	CFLAGS += -O3 -funroll-loops
+ifeq ($(USE_SSE), 1)
+	CFLAGS += -msse2
+endif
 endif
 
 ifndef LINT_LANG
 	LINT_LANG= "all"
 endif
 
+ifeq ($(UNAME), Windows)
+	XGBOOST_DYLIB = lib/xgboost.dll
+	JAVAINCFLAGS += -I${JAVA_HOME}/include/win32
+else
+ifeq ($(UNAME), Darwin)
+	XGBOOST_DYLIB = lib/libxgboost.dylib
+	CFLAGS += -fPIC
+else
+	XGBOOST_DYLIB = lib/libxgboost.so
+	CFLAGS += -fPIC
+endif
+endif
+
+ifeq ($(UNAME), Linux)
+	LDFLAGS += -lrt
+	JAVAINCFLAGS += -I${JAVA_HOME}/include/linux
+endif
+
+ifeq ($(UNAME), Darwin)
+	JAVAINCFLAGS += -I${JAVA_HOME}/include/darwin
+endif
+
+OPENMP_FLAGS =
+ifeq ($(USE_OPENMP), 1)
+	OPENMP_FLAGS = -fopenmp
+else
+	OPENMP_FLAGS = -DDISABLE_OPENMP
+endif
+CFLAGS += $(OPENMP_FLAGS)
+
 # specify tensor path
-.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck
+.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck java pylint
+
+all: lib/libxgboost.a $(XGBOOST_DYLIB) xgboost
+
+$(DMLC_CORE)/libdmlc.a: $(wildcard $(DMLC_CORE)/src/*.cc $(DMLC_CORE)/src/*/*.cc)
+	+ cd $(DMLC_CORE); "$(MAKE)" libdmlc.a config=$(ROOTDIR)/$(config); cd $(ROOTDIR)
+
+$(RABIT)/lib/$(LIB_RABIT): $(wildcard $(RABIT)/src/*.cc)
+	+ cd $(RABIT); "$(MAKE)" lib/$(LIB_RABIT) USE_SSE=$(USE_SSE); cd $(ROOTDIR)
+
+jvm: jvm-packages/lib/libxgboost4j.so
+
+SRC = $(wildcard src/*.cc src/*/*.cc)
+ALL_OBJ = $(patsubst src/%.cc, build/%.o, $(SRC)) $(PLUGIN_OBJS)
+AMALGA_OBJ = amalgamation/xgboost-all0.o
+LIB_DEP = $(DMLC_CORE)/libdmlc.a $(RABIT)/lib/$(LIB_RABIT)
+ALL_DEP = $(filter-out build/cli_main.o, $(ALL_OBJ)) $(LIB_DEP)
+CLI_OBJ = build/cli_main.o
+include tests/cpp/xgboost_test.mk
 
 build/%.o: src/%.cc
 	@mkdir -p $(@D)
 	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.d
 	$(CXX) -c $(CFLAGS) $< -o $@
 
+build_plugin/%.o: plugin/%.cc
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) -MM -MT build_plugin/$*.o $< >build_plugin/$*.d
+	$(CXX) -c $(CFLAGS) $< -o $@
+
 # The should be equivalent to $(ALL_OBJ)  except for build/cli_main.o
 amalgamation/xgboost-all0.o: amalgamation/xgboost-all0.cc
 	$(CXX) -c $(CFLAGS) $< -o $@
 
+# Equivalent to lib/libxgboost_all.so
+lib/libxgboost_all.so: $(AMALGA_OBJ) $(LIB_DEP)
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %.a, $^) $(LDFLAGS)
+
+lib/libxgboost.a: $(ALL_DEP)
+	@mkdir -p $(@D)
+	ar crv $@ $(filter %.o, $?)
+
+lib/xgboost.dll lib/libxgboost.so lib/libxgboost.dylib: $(ALL_DEP)
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %a,  $^) $(LDFLAGS)
+
+jvm-packages/lib/libxgboost4j.so: jvm-packages/xgboost4j/src/native/xgboost4j.cpp $(ALL_DEP)
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) $(JAVAINCFLAGS) -shared -o $@ $(filter %.cpp %.o %.a, $^) $(LDFLAGS)
+
+
+xgboost: $(CLI_OBJ) $(ALL_DEP)
+	$(CXX) $(CFLAGS) -o $@  $(filter %.o %.a, $^)  $(LDFLAGS)
+
 rcpplint:
-	python3 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
+	python2 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
 
 lint: rcpplint
-	python3 dmlc-core/scripts/lint.py --exclude_path python-package/xgboost/dmlc-core \
-	  python-package/xgboost/include python-package/xgboost/lib \
-	  python-package/xgboost/make python-package/xgboost/rabit \
-	  python-package/xgboost/src --pylint-rc ${PWD}/python-package/.pylintrc xgboost \
-	  ${LINT_LANG} include src python-package
+	python2 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} include src plugin python-package
+
+pylint:
+	flake8 --ignore E501 python-package
+	flake8 --ignore E501 tests/python
+
+test: $(ALL_TEST)
+	$(ALL_TEST)
+
+check: test
+	./tests/cpp/xgboost_test
 
 ifeq ($(TEST_COVER), 1)
 cover: check
@@ -87,7 +196,7 @@ cover: check
 endif
 
 clean:
-	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
+	$(RM) -rf build build_plugin lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
 	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
 	if [ -d "R-package/src" ]; then \
 		cd R-package/src; \
@@ -99,9 +208,36 @@ clean_all: clean
 	cd $(DMLC_CORE); "$(MAKE)" clean; cd $(ROOTDIR)
 	cd $(RABIT); "$(MAKE)" clean; cd $(ROOTDIR)
 
+doxygen:
+	doxygen doc/Doxyfile
+
+# create standalone python tar file.
+pypack: ${XGBOOST_DYLIB}
+	cp ${XGBOOST_DYLIB} python-package/xgboost
+	cd python-package; tar cf xgboost.tar xgboost; cd ..
+
 # create pip source dist (sdist) pack for PyPI
 pippack: clean_all
-	cd python-package; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
+	rm -rf xgboost-python
+# remove symlinked directories in python-package/xgboost
+	rm -rf python-package/xgboost/lib
+	rm -rf python-package/xgboost/dmlc-core
+	rm -rf python-package/xgboost/include
+	rm -rf python-package/xgboost/make
+	rm -rf python-package/xgboost/rabit
+	rm -rf python-package/xgboost/src
+	cp -r python-package xgboost-python
+	cp -r Makefile xgboost-python/xgboost/
+	cp -r make xgboost-python/xgboost/
+	cp -r src xgboost-python/xgboost/
+	cp -r tests xgboost-python/xgboost/
+	cp -r include xgboost-python/xgboost/
+	cp -r dmlc-core xgboost-python/xgboost/
+	cp -r rabit xgboost-python/xgboost/
+# Use setup_pip.py instead of setup.py
+	mv xgboost-python/setup_pip.py xgboost-python/setup.py
+# Build sdist tarball
+	cd xgboost-python; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
 
 # Script to make a clean installable R package.
 Rpack: clean_all
@@ -122,17 +258,10 @@ Rpack: clean_all
 	cp -r dmlc-core/include xgboost/src/dmlc-core/include
 	cp -r dmlc-core/src xgboost/src/dmlc-core/src
 	cp ./LICENSE xgboost
-# Modify PKGROOT in Makevars.in
-	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
-# Configure Makevars.win (Windows-specific Makevars, likely using MinGW)
+	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' | sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.in
 	cp xgboost/src/Makevars.in xgboost/src/Makevars.win
-	cat xgboost/src/Makevars.in| sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.win
 	sed -i -e 's/@OPENMP_CXXFLAGS@/$$\(SHLIB_OPENMP_CXXFLAGS\)/g' xgboost/src/Makevars.win
 	sed -i -e 's/-pthread/$$\(SHLIB_PTHREAD_FLAGS\)/g' xgboost/src/Makevars.win
-	sed -i -e 's/@ENDIAN_FLAG@/-DDMLC_CMAKE_LITTLE_ENDIAN=1/g' xgboost/src/Makevars.win
-	sed -i -e 's/@BACKTRACE_LIB@//g' xgboost/src/Makevars.win
-	sed -i -e 's/@OPENMP_LIB@//g' xgboost/src/Makevars.win
-	rm -f xgboost/src/Makevars.win-e   # OSX sed create this extra file; remove it
 	bash R-package/remove_warning_suppression_pragma.sh
 	rm xgboost/remove_warning_suppression_pragma.sh
 
@@ -145,3 +274,4 @@ Rcheck: Rbuild
 
 -include build/*.d
 -include build/*/*.d
+-include build_plugin/*/*.d

NEWS.md

@@ -3,450 +3,6 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
-## v1.0.0 (2020.02.19)
-This release marks a major milestone for the XGBoost project.
-
-### Apache-style governance, contribution policy, and semantic versioning (#4646, #4659)
-* Starting with 1.0.0 release, the XGBoost Project is adopting Apache-style governance. The full community guideline is [available in the doc website](https://xgboost.readthedocs.io/en/release_1.0.0/contrib/community.html). Note that we now have Project Management Committee (PMC) who would steward the project on the long-term basis. The PMC is also entrusted to run and fund the project's continuous integration (CI) infrastructure (https://xgboost-ci.net).
-* We also adopt the [semantic versioning](https://semver.org/). See [our release versioning policy](https://xgboost.readthedocs.io/en/release_1.0.0/contrib/release.html).
-
-### Better performance scaling for multi-core CPUs (#4502, #4529, #4716, #4851, #5008, #5107, #5138, #5156)
-* Poor performance scaling of the `hist` algorithm for multi-core CPUs has been under investigation (#3810). Previous effort #4529 was replaced with a series of pull requests (#5107, #5138, #5156) aimed at achieving the same performance benefits while keeping the C++ codebase legible. The latest performance benchmark results show [up to 5x speedup on Intel CPUs with many cores](https://github.com/dmlc/xgboost/pull/5156#issuecomment-580024413). Note: #5244, which concludes the effort, will become part of the upcoming release 1.1.0.
-
-### Improved installation experience on Mac OSX (#4672, #5074, #5080, #5146, #5240)
-* It used to be quite complicated to install XGBoost on Mac OSX. XGBoost uses OpenMP to distribute work among multiple CPU cores, and Mac's default C++ compiler (Apple Clang) does not come with OpenMP. Existing work-around (using another C++ compiler) was complex and prone to fail with cryptic diagnosis (#4933, #4949, #4969).
-* Now it only takes two commands to install XGBoost: `brew install libomp` followed by `pip install xgboost`. The installed XGBoost will use all CPU cores.
-* Even better, XGBoost is now available from Homebrew: `brew install xgboost`. See Homebrew/homebrew-core#50467.
-* Previously, if you installed the XGBoost R package using the command `install.packages('xgboost')`, it could only use a single CPU core and you would experience slow training performance. With 1.0.0 release, the R package will use all CPU cores out of box.
-
-### Distributed XGBoost now available on Kubernetes (#4621, #4939)
-* Check out the [tutorial for setting up distributed XGBoost on a Kubernetes cluster](https://xgboost.readthedocs.io/en/release_1.0.0/tutorials/kubernetes.html).
-
-### Ruby binding for XGBoost (#4856)
-
-### New Native Dask interface for multi-GPU and multi-node scaling (#4473, #4507, #4617, #4819, #4907, #4914, #4941, #4942, #4951, #4973, #5048, #5077, #5144, #5270)
-* XGBoost now integrates seamlessly with [Dask](https://dask.org/), a lightweight distributed framework for data processing. Together with the first-class support for cuDF data frames (see below), it is now easier than ever to create end-to-end data pipeline running on one or more NVIDIA GPUs.
-* Multi-GPU training with Dask is now up to 20% faster than the previous release (#4914, #4951).
-
-### First-class support for cuDF data frames and cuPy arrays (#4737, #4745, #4794, #4850, #4891, #4902, #4918, #4927, #4928, #5053, #5189, #5194, #5206, #5219, #5225)
-* [cuDF](https://github.com/rapidsai/cudf) is a data frame library for loading and processing tabular data on NVIDIA GPUs. It provides a Pandas-like API.
-* [cuPy](https://github.com/cupy/cupy) implements a NumPy-compatible multi-dimensional array on NVIDIA GPUs.
-* Now users can keep the data on the GPU memory throughout the end-to-end data pipeline, obviating the need for copying data between the main memory and GPU memory.
-* XGBoost can accept any data structure that exposes `__array_interface__` signature, opening way to support other columar formats that are compatible with Apache Arrow.
-
-### [Feature interaction constraint](https://xgboost.readthedocs.io/en/release_1.0.0/tutorials/feature_interaction_constraint.html) is now available with `approx` and `gpu_hist` algorithms (#4534, #4587, #4596, #5034).
-
-### Learning to rank is now GPU accelerated (#4873, #5004, #5129)
-* Supported ranking objectives: NDGC, Map, Pairwise.
-* [Up to 2x improved training performance on GPUs](https://devblogs.nvidia.com/learning-to-rank-with-xgboost-and-gpu/).
-
-### Enable `gamma` parameter for GPU training (#4874, #4953)
-* The `gamma` parameter specifies the minimum loss reduction required to add a new split in a tree. A larger value for `gamma` has the effect of pre-pruning the tree, by making harder to add splits.
-
-### External memory for GPU training (#4486, #4526, #4747, #4833, #4879, #5014)
-* It is now possible to use NVIDIA GPUs even when the size of training data exceeds the available GPU memory. Note that the external memory support for GPU is still experimental. #5093 will further improve performance and will become part of the upcoming release 1.1.0.
-* RFC for enabling external memory with GPU algorithms: #4357
-
-### Improve Scikit-Learn interface (#4558, #4842, #4929, #5049, #5151, #5130, #5227)
-* Many users of XGBoost enjoy the convenience and breadth of Scikit-Learn ecosystem. In this release, we revise the Scikit-Learn API of XGBoost (`XGBRegressor`, `XGBClassifier`, and `XGBRanker`) to achieve feature parity with the traditional XGBoost interface (`xgboost.train()`).
-* Insert check to validate data shapes.
-* Produce an error message if `eval_set` is not a tuple. An error message is better than silently crashing.
-* Allow using `numpy.RandomState` object.
-* Add `n_jobs` as an alias of `nthread`.
-* Roadmap: #5152
-
-### XGBoost4J-Spark: Redesigning checkpointing mechanism
-* RFC is available at #4786
-* Clean up checkpoint file after a successful training job (#4754): The current implementation in XGBoost4J-Spark does not clean up the checkpoint file after a successful training job. If the user runs another job with the same checkpointing directory, she will get a wrong model because the second job will re-use the checkpoint file left over from the first job. To prevent this scenario, we propose to always clean up the checkpoint file after every successful training job.
-* Avoid Multiple Jobs for Checkpointing (#5082): The current method for checkpoint is to collect the booster produced at the last iteration of each checkpoint internal to Driver and persist it in HDFS. The major issue with this approach is that it needs to re-perform the data preparation for training if the user did not choose to cache the training dataset. To avoid re-performing data prep, we build external-memory checkpointing in the XGBoost4J layer as well.
-* Enable deterministic repartitioning when checkpoint is enabled (#4807): Distributed algorithm for gradient boosting assumes a fixed partition of the training data between multiple iterations. In previous versions, there was no guarantee that data partition would stay the same, especially when a worker goes down and some data had to recovered from previous checkpoint. In this release, we make data partition deterministic by using the data hash value of each data row in computing the partition.
-
-### XGBoost4J-Spark: handle errors thrown by the native code (#4560)
-* All core logic of XGBoost is written in C++, so XGBoost4J-Spark internally uses the C++ code via Java Native Interface (JNI). #4560 adds a proper error handling for any errors or exceptions arising from the C++ code, so that the XGBoost Spark application can be torn down in an orderly fashion.
-
-### XGBoost4J-Spark: Refine method to count the number of alive cores  (#4858)
-* The `SparkParallelismTracker` class ensures that sufficient number of executor cores are alive. To that end, it is important to query the number of alive cores reliably.
-
-### XGBoost4J: Add `BigDenseMatrix` to store more than `Integer.MAX_VALUE` elements (#4383)
-
-### Robust model serialization with JSON (#4632, #4708, #4739, #4868, #4936, #4945, #4974, #5086, #5087, #5089, #5091, #5094, #5110, #5111, #5112, #5120, #5137, #5218, #5222, #5236, #5245, #5248, #5281)
-* In this release, we introduce an experimental support of using [JSON](https://www.json.org/json-en.html) for serializing (saving/loading) XGBoost models and related hyperparameters for training. We would like to eventually replace the old binary format with JSON, since it is an open format and parsers are available in many programming languages and platforms. See [the documentation for model I/O using JSON](https://xgboost.readthedocs.io/en/release_1.0.0/tutorials/saving_model.html). #3980 explains why JSON was chosen over other alternatives.
-* To maximize interoperability and compatibility of the serialized models, we now split serialization into two parts (#4855):
-  1. Model, e.g. decision trees and strictly related metadata like `num_features`.
-  2. Internal configuration, consisting of training parameters and other configurable parameters. For example, `max_delta_step`, `tree_method`, `objective`, `predictor`, `gpu_id`.
-
-  Previously, users often ran into issues where the model file produced by one machine could not load or run on another machine. For example, models trained using a machine with an NVIDIA GPU could not run on another machine without a GPU (#5291, #5234). The reason is that the old binary format saved some internal configuration that were not universally applicable to all machines, e.g. `predictor='gpu_predictor'`.
-
-  Now, model saving function (`Booster.save_model()` in Python) will save only the model, without internal configuration. This will guarantee that your model file would be used anywhere. Internal configuration will be serialized in limited circumstances such as:
-  * Multiple nodes in a distributed system exchange model details over the network.
-  * Model checkpointing, to recover from possible crashes.
-
-  This work proved to be useful for parameter validation as well (see below).
-* Starting with 1.0.0 release, we will use semantic versioning to indicate whether the model produced by one version of XGBoost would be compatible with another version of XGBoost. Any change in the major version indicates a breaking change in the serialization format.
-* We now provide a robust method to save and load scikit-learn related attributes (#5245). Previously, we used Python pickle to save Python attributes related to `XGBClassifier`, `XGBRegressor`, and `XGBRanker` objects. The attributes are necessary to properly interact with scikit-learn. See #4639 for more details. The use of pickling hampered interoperability, as a pickle from one machine may not necessarily work on another machine. Starting with this release, we use an alternative method to serialize the scikit-learn related attributes. The use of Python pickle is now discouraged (#5236, #5281).
-
-### Parameter validation: detection of unused or incorrect parameters (#4553, #4577, #4738, #4801, #4961, #5101, #5157, #5167, #5256)
-* 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. Currently, parameter validation is available to R users and Python XGBoost API users. We are working to extend its support to scikit-learn users.
-* Configuration steps now have well-defined semantics (#4542, #4738), so we know exactly where and how the internal configurable parameters are changed.
-* The user can now use `save_config()` function to inspect all (used) training parameters. This is helpful for debugging model performance.
-
-### Allow individual workers to recover from faults (#4808, #4966)
-* Status quo: if a worker fails, all workers are shut down and restarted, and learning resumes from the last checkpoint. This involves requesting resources from the scheduler (e.g. Spark) and shuffling all the data again from scratch. Both of these operations can be quite costly and block training for extended periods of time, especially if the training data is big and the number of worker nodes is in the hundreds.
-* The proposed solution is to recover the single node that failed, instead of shutting down all workers. The rest of the clusters wait until the single failed worker is bootstrapped and catches up with the rest.
-* See roadmap at #4753. Note that this is work in progress. In particular, the feature is not yet available from XGBoost4J-Spark.
-
-### Accurate prediction for DART models
-* Use DART tree weights when computing SHAPs (#5050)
-* Don't drop trees during DART prediction by default (#5115)
-* Fix DART prediction in R (#5204)
-
-### Make external memory more robust
-* Fix issues with training with external memory on cpu (#4487)
-* Fix crash with approx tree method on cpu (#4510)
-* Fix external memory race in `exact` (#4980). Note: `dmlc::ThreadedIter` is not actually thread-safe. We would like to re-design it in the long term.
-
-### Major refactoring of the `DMatrix` class (#4686, #4744, #4748, #5044, #5092, #5108, #5188, #5198)
-* Goal 1: improve performance and reduce memory consumption. Right now, if the user trains a model with a NumPy array as training data, the array gets copies 2-3 times before training begins. We'd like to reduce duplication of the data matrix.
-* Goal 2: Expose a common interface to external data, unify the way DMatrix objects are constructed and simplify the process of adding new external data sources. This work is essential for ingesting cuPy arrays.
-* Goal 3: Handle missing values consistently.
-* RFC: #4354, Roadmap: #5143
-* This work is also relevant to external memory support on GPUs.
-
-### Breaking: XGBoost Python package now requires Python 3.5 or newer (#5021, #5274)
-* Python 3.4 has reached its end-of-life on March 16, 2019, so we now require Python 3.5 or newer.
-
-### Breaking: GPU algorithm now requires CUDA 9.0 and higher (#4527, #4580)
-
-### Breaking: `n_gpus` parameter removed; multi-GPU training now requires a distributed framework (#4579, #4749, #4773, #4810, #4867, #4908)
-* #4531 proposed removing support for single-process multi-GPU training. Contributors would focus on multi-GPU support through distributed frameworks such as Dask and Spark, where the framework would be expected to assign a worker process for each GPU independently. By delegating GPU management and data movement to the distributed framework, we can greatly simplify the core XGBoost codebase, make multi-GPU training more robust, and reduce burden for future development.
-
-### Breaking: Some deprecated features have been removed
-* ``gpu_exact`` training method (#4527, #4742, #4777). Use ``gpu_hist`` instead.
-* ``learning_rates`` parameter in Python (#5155). Use the callback API instead.
-* ``num_roots`` (#5059, #5165), since the current training code always uses a single root node.
-* GPU-specific objectives (#4690), such as `gpu:reg:linear`. Use objectives without `gpu:` prefix; GPU will be used automatically if your machine has one.
-
-### Breaking: the C API function `XGBoosterPredict()` now asks for an extra parameter `training`.
-
-### Breaking: We now use CMake exclusively to build XGBoost. `Makefile` is being sunset.
-* Exception: the R package uses Autotools, as the CRAN ecosystem did not yet adopt CMake widely.
-
-### Performance improvements
-* Smarter choice of histogram construction for distributed `gpu_hist` (#4519)
-* Optimizations for quantization on device (#4572)
-* Introduce caching memory allocator to avoid latency associated with GPU memory allocation (#4554, #4615)
-* Optimize the initialization stage of the CPU `hist` algorithm for sparse datasets (#4625)
-* Prevent unnecessary data copies from GPU memory to the host (#4795)
-* Improve operation efficiency for single prediction (#5016)
-* Group builder modified for incremental building, to speed up building large `DMatrix` (#5098)
-
-### Bug-fixes
-* Eliminate `FutureWarning: Series.base is deprecated` (#4337)
-* Ensure pandas DataFrame column names are treated as strings in type error message (#4481)
-* [jvm-packages] Add back `reg:linear` for scala, as it is only deprecated and not meant to be removed yet (#4490)
-* Fix library loading for Cygwin users (#4499)
-* Fix prediction from loaded pickle (#4516)
-* Enforce exclusion between `pred_interactions=True` and `pred_interactions=True` (#4522)
-* Do not return dangling reference to local `std::string` (#4543)
-* Set the appropriate device before freeing device memory (#4566)
-* Mark `SparsePageDmatrix` destructor default. (#4568)
-* Choose the appropriate tree method only when the tree method is 'auto' (#4571)
-* Fix `benchmark_tree.py` (#4593)
-* [jvm-packages] Fix silly bug in feature scoring (#4604)
-* Fix GPU predictor when the test data matrix has different number of features than the training data matrix used to train the model (#4613)
-* Fix external memory for get column batches. (#4622)
-* [R] Use built-in label when xgb.DMatrix is given to xgb.cv() (#4631)
-* Fix early stopping in the Python package (#4638)
-* Fix AUC error in distributed mode caused by imbalanced dataset (#4645, #4798)
-* [jvm-packages] Expose `setMissing` method in `XGBoostClassificationModel` / `XGBoostRegressionModel` (#4643)
-* Remove initializing stringstream reference. (#4788)
-* [R] `xgb.get.handle` now checks all class listed of `object` (#4800)
-* Do not use `gpu_predictor` unless data comes from GPU (#4836)
-* Fix data loading (#4862)
-* Workaround `isnan` across different environments. (#4883)
-* [jvm-packages] Handle Long-type parameter (#4885)
-* Don't `set_params` at the end of `set_state` (#4947). Ensure that the model does not change after pickling and unpickling multiple times.
-* C++ exceptions should not crash OpenMP loops (#4960)
-* Fix `usegpu` flag in DART. (#4984)
-* Run training with empty `DMatrix` (#4990, #5159)
-* Ensure that no two processes can use the same GPU (#4990)
-* Fix repeated split and 0 cover nodes (#5010)
-* Reset histogram hit counter between multiple data batches (#5035)
-* Fix `feature_name` crated from int64index dataframe. (#5081)
-* Don't use 0 for "fresh leaf" (#5084)
-* Throw error when user attempts to use multi-GPU training and XGBoost has not been compiled with NCCL (#5170)
-* Fix metric name loading (#5122)
-* Quick fix for memory leak in CPU `hist` algorithm (#5153)
-* Fix wrapping GPU ID and prevent data copying (#5160)
-* Fix signature of Span constructor (#5166)
-* Lazy initialization of device vector, so that XGBoost compiled with CUDA can run on a machine without any GPU (#5173)
-* Model loading should not change system locale (#5314)
-* Distributed training jobs would sometimes hang; revert Rabit to fix this regression (dmlc/rabit#132, #5237)
-
-### API changes
-* Add support for cross-validation using query ID (#4474)
-* Enable feature importance property for DART model (#4525)
-* Add `rmsle` metric and `reg:squaredlogerror` objective (#4541)
-* All objective and evaluation metrics are now exposed to JVM packages (#4560)
-* `dump_model()` and `get_dump()` now support exporting in GraphViz language (#4602)
-* Support metrics `ndcg-` and `map-` (#4635)
-* [jvm-packages] Allow chaining prediction (transform) in XGBoost4J-Spark (#4667)
-* [jvm-packages] Add option to bypass missing value check in the Spark layer (#4805). Only use this option if you know what you are doing.
-* [jvm-packages] Add public group getter (#4838)
-* `XGDMatrixSetGroup` C API is now deprecated (#4864). Use `XGDMatrixSetUIntInfo` instead.
-* [R] Added new `train_folds` parameter to `xgb.cv()` (#5114)
-* Ingest meta information from Pandas DataFrame, such as data weights (#5216)
-
-### Maintenance: Refactor code for legibility and maintainability
-* De-duplicate GPU parameters (#4454)
-* Simplify INI-style config reader using C++11 STL (#4478, #4521)
-* Refactor histogram building code for `gpu_hist` (#4528)
-* Overload device memory allocator, to enable instrumentation for compiling memory usage statistics (#4532)
-* Refactor out row partitioning logic from `gpu_hist` (#4554)
-* Remove an unused variable (#4588)
-* Implement tree model dump with code generator, to de-duplicate code for generating dumps in 3 different formats (#4602)
-* Remove `RowSet` class which is no longer being used (#4697)
-* Remove some unused functions as reported by cppcheck (#4743)
-* Mimic CUDA assert output in Span check (#4762)
-* [jvm-packages] Refactor `XGBoost.scala` to put all params processing in one place (#4815)
-* Add some comments for GPU row partitioner (#4832)
-* Span: use `size_t' for index_type,  add `front' and `back'. (#4935)
-* Remove dead code in `exact` algorithm (#5034, #5105)
-* Unify integer types used for row and column indices (#5034)
-* Extract feature interaction constraint from `SplitEvaluator` class. (#5034)
-* [Breaking] De-duplicate paramters and docstrings in the constructors of Scikit-Learn models (#5130)
-* Remove benchmark code from GPU tests (#5141)
-* Clean up Python 2 compatibility code. (#5161)
-* Extensible binary serialization format for `DMatrix::MetaInfo` (#5187). This will be useful for implementing censored labels for survival analysis applications.
-* Cleanup clang-tidy warnings. (#5247)
-
-### Maintenance: testing, continuous integration, build system
-* Use `yaml.safe_load` instead of `yaml.load`. (#4537)
-* Ensure GCC is at least 5.x (#4538)
-* Remove all mention of `reg:linear` from tests (#4544)
-* [jvm-packages] Upgrade to Scala 2.12 (#4574)
-* [jvm-packages] Update kryo dependency to 2.22 (#4575)
-* [CI] Specify account ID when logging into ECR Docker registry (#4584)
-* Use Sphinx 2.1+ to compile documentation (#4609)
-* Make Pandas optional for running Python unit tests (#4620)
-* Fix spark tests on machines with many cores (#4634)
-* [jvm-packages] Update local dev build process (#4640)
-* Add optional dependencies to setup.py (#4655)
-* [jvm-packages] Fix maven warnings (#4664)
-* Remove extraneous files from the R package, to comply with CRAN policy (#4699)
-* Remove VC-2013 support, since it is not C++11 compliant (#4701)
-* [CI] Fix broken installation of Pandas (#4704, #4722)
-* [jvm-packages] Clean up temporary files afer running tests (#4706)
-* Specify version macro in CMake. (#4730)
-* Include dmlc-tracker into XGBoost Python package (#4731)
-* [CI] Use long key ID for Ubuntu repository fingerprints. (#4783)
-* Remove plugin, cuda related code in automake & autoconf files (#4789)
-* Skip related tests when scikit-learn is not installed. (#4791)
-* Ignore vscode and clion files (#4866)
-* Use bundled Google Test by default (#4900)
-* [CI] Raise timeout threshold in Jenkins (#4938)
-* Copy CMake parameter from dmlc-core. (#4948)
-* Set correct file permission. (#4964)
-* [CI] Update lint configuration to support latest pylint convention (#4971)
-* [CI] Upload nightly builds to S3 (#4976, #4979)
-* Add asan.so.5 to cmake script. (#4999)
-* [CI] Fix Travis tests. (#5062)
-* [CI] Locate vcomp140.dll from System32 directory (#5078)
-* Implement training observer to dump internal states of objects (#5088). This will be useful for debugging.
-* Fix visual studio output library directories (#5119)
-* [jvm-packages] Comply with scala style convention + fix broken unit test (#5134)
-* [CI] Repair download URL for Maven 3.6.1 (#5139)
-* Don't use modernize-use-trailing-return-type in clang-tidy. (#5169)
-* Explicitly use UTF-8 codepage when using MSVC (#5197)
-* Add CMake option to run Undefined Behavior Sanitizer (UBSan) (#5211)
-* Make some GPU tests deterministic (#5229)
-* [R] Robust endian detection in CRAN xgboost build (#5232)
-* Support FreeBSD (#5233)
-* Make `pip install xgboost*.tar.gz` work by fixing build-python.sh (#5241)
-* Fix compilation error due to 64-bit integer narrowing to `size_t` (#5250)
-* Remove use of `std::cout` from R package, to comply with CRAN policy (#5261)
-* Update DMLC-Core submodule (#4674, #4688, #4726, #4924)
-* Update Rabit submodule (#4560, #4667, #4718, #4808, #4966, #5237)
-
-### Usability Improvements, Documentation
-* Add Random Forest API to Python API doc (#4500)
-* Fix Python demo and doc. (#4545)
-* Remove doc about not supporting cuda 10.1 (#4578)
-* Address some sphinx warnings and errors, add doc for building doc. (#4589)
-* Add instruction to run formatting checks locally (#4591)
-* Fix docstring for `XGBModel.predict()` (#4592)
-* Doc and demo for customized metric and objective (#4598, #4608)
-* Add to documentation how to run tests locally (#4610)
-* Empty evaluation list in early stopping should produce meaningful error message (#4633)
-* Fixed year to 2019 in conf.py, helpers.h and LICENSE (#4661)
-* Minor updates to links and grammar (#4673)
-* Remove `silent` in doc (#4689)
-* Remove old Python trouble shooting doc (#4729)
-* Add `os.PathLike` support for file paths to DMatrix and Booster Python classes (#4757)
-* Update XGBoost4J-Spark doc (#4804)
-* Regular formatting for evaluation metrics (#4803)
-* [jvm-packages] Refine documentation for handling missing values in XGBoost4J-Spark (#4805)
-* Monitor for distributed envorinment (#4829). This is useful for identifying performance bottleneck.
-* Add check for length of weights and produce a good error message (#4872)
-* Fix DMatrix doc (#4884)
-* Export C++ headers in CMake installation (#4897)
-* Update license year in README.md to 2019 (#4940)
-* Fix incorrectly displayed Note in the doc (#4943)
-* Follow PEP 257 Docstring Conventions (#4959)
-* Document minimum version required for Google Test (#5001)
-* Add better error message for invalid feature names (#5024)
-* Some guidelines on device memory usage (#5038)
-* [doc] Some notes for external memory. (#5065)
-* Update document for `tree_method` (#5106)
-* Update demo for ranking. (#5154)
-* Add new lines for Spark XGBoost missing values section (#5180)
-* Fix simple typo: utilty -> utility (#5182)
-* Update R doc by roxygen2 (#5201)
-* [R] Direct user to use `set.seed()` instead of setting `seed` parameter (#5125)
-* Add Optuna badge to `README.md` (#5208)
-* Fix compilation error in `c-api-demo.c` (#5215)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), Crissman Loomis (@Crissman), Cyprien Ricque (@Cyprien-Ricque), Evan Kepner (@EvanKepner), K.O. (@Hi-king), KaiJin Ji (@KerryJi), Peter Badida (@KeyWeeUsr), Kodi Arfer (@Kodiologist), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Jacob Kim (@TheJacobKim), Vibhu Jawa (@VibhuJawa), Marcos (@astrowonk), Andy Adinets (@canonizer), Chen Qin (@chenqin), Christopher Cowden (@cowden), @cpfarrell, @david-cortes, Liangcai Li (@firestarman), @fuhaoda, Philip Hyunsu Cho (@hcho3), @here-nagini, Tong He (@hetong007), Michal Kurka (@michalkurka), Honza Sterba (@honzasterba), @iblumin, @koertkuipers, mattn (@mattn), Mingjie Tang (@merlintang), OrdoAbChao (@mglowacki100), Matthew Jones (@mt-jones), mitama (@nigimitama), Nathan Moore (@nmoorenz), Daniel Stahl (@phillyfan1138), Michaël Benesty (@pommedeterresautee), Rong Ou (@rongou), Sebastian (@sfahnens), Xu Xiao (@sperlingxx), @sriramch, Sean Owen (@srowen), Stephanie Yang (@stpyang), Yuan Tang (@terrytangyuan), Mathew Wicks (@thesuperzapper), Tim Gates (@timgates42), TinkleG (@tinkle1129), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Matvey Turkov (@turk0v), Bobby Wang (@wbo4958), yage (@yage99), @yellowdolphin
-
-**Reviewers**: Nan Zhu (@CodingCat), Crissman Loomis (@Crissman), Cyprien Ricque (@Cyprien-Ricque), Evan Kepner (@EvanKepner), John Zedlewski (@JohnZed), KOLANICH (@KOLANICH), KaiJin Ji (@KerryJi), Kodi Arfer (@Kodiologist), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Nikita Titov (@StrikerRUS), Jacob Kim (@TheJacobKim), Vibhu Jawa (@VibhuJawa), Andrew Kane (@ankane), Arno Candel (@arnocandel), Marcos (@astrowonk), Bryan Woods (@bryan-woods), Andy Adinets (@canonizer), Chen Qin (@chenqin), Thomas Franke (@coding-komek), Peter  (@codingforfun), @cpfarrell, Joshua Patterson (@datametrician), @fuhaoda, Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), Honza Sterba (@honzasterba), @iblumin, @jakirkham, Vadim Khotilovich (@khotilov), Keith Kraus (@kkraus14), @koertkuipers, @melonki, Mingjie Tang (@merlintang), OrdoAbChao (@mglowacki100), Daniel Mahler (@mhlr), Matthew Rocklin (@mrocklin), Matthew Jones (@mt-jones), Michaël Benesty (@pommedeterresautee), PSEUDOTENSOR / Jonathan McKinney (@pseudotensor), Rong Ou (@rongou), Vladimir (@sh1ng), Scott Lundberg (@slundberg), Xu Xiao (@sperlingxx), @sriramch, Pasha Stetsenko (@st-pasha), Stephanie Yang (@stpyang), Yuan Tang (@terrytangyuan), Mathew Wicks (@thesuperzapper), Theodore Vasiloudis (@thvasilo), TinkleG (@tinkle1129), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), yage (@yage99), @yellowdolphin, Yin Lou (@yinlou)
-
-## v0.90 (2019.05.18)
-
-### XGBoost Python package drops Python 2.x (#4379, #4381)
-Python 2.x is reaching its end-of-life at the end of this year. [Many scientific Python packages are now moving to drop Python 2.x](https://python3statement.org/).
-
-### XGBoost4J-Spark now requires Spark 2.4.x (#4377)
-* Spark 2.3 is reaching its end-of-life soon. See discussion at #4389.
-* **Consistent handling of missing values** (#4309, #4349, #4411): Many users had reported issue with inconsistent predictions between XGBoost4J-Spark and the Python XGBoost package. The issue was caused by Spark mis-handling non-zero missing values (NaN, -1, 999 etc). We now alert the user whenever Spark doesn't handle missing values correctly (#4309, #4349). See [the tutorial for dealing with missing values in XGBoost4J-Spark](https://xgboost.readthedocs.io/en/release_0.90/jvm/xgboost4j_spark_tutorial.html#dealing-with-missing-values). This fix also depends on the availability of Spark 2.4.x.
-
-### Roadmap: better performance scaling for multi-core CPUs (#4310)
-* Poor performance scaling of the `hist` algorithm for multi-core CPUs has been under investigation (#3810). #4310 optimizes quantile sketches and other pre-processing tasks. Special thanks to @SmirnovEgorRu.
-
-### Roadmap: Harden distributed training (#4250)
-* Make distributed training in XGBoost more robust by hardening [Rabit](https://github.com/dmlc/rabit), which implements [the AllReduce primitive](https://en.wikipedia.org/wiki/Reduce_%28parallel_pattern%29). In particular, improve test coverage on mechanisms for fault tolerance and recovery. Special thanks to @chenqin.
-
-### New feature: Multi-class metric functions for GPUs (#4368)
-* Metrics for multi-class classification have been ported to GPU: `merror`, `mlogloss`. Special thanks to @trivialfis.
-* With supported metrics, XGBoost will select the correct devices based on your system and `n_gpus` parameter.
-
-### New feature: Scikit-learn-like random forest API (#4148, #4255, #4258)
-* XGBoost Python package now offers `XGBRFClassifier` and `XGBRFRegressor` API to train random forests. See [the tutorial](https://xgboost.readthedocs.io/en/release_0.90/tutorials/rf.html). Special thanks to @canonizer
-
-### New feature: use external memory in GPU predictor (#4284, #4396, #4438, #4457)
-* It is now possible to make predictions on GPU when the input is read from external memory. This is useful when you want to make predictions with big dataset that does not fit into the GPU memory. Special thanks to @rongou, @canonizer, @sriramch.
-
-  ```python
-  dtest = xgboost.DMatrix('test_data.libsvm#dtest.cache')
-  bst.set_param('predictor', 'gpu_predictor')
-  bst.predict(dtest)
-  ```
-
-* Coming soon: GPU training (`gpu_hist`) with external memory
-
-### New feature: XGBoost can now handle comments in LIBSVM files (#4430)
-* Special thanks to @trivialfis and @hcho3
-
-### New feature: Embed XGBoost in your C/C++ applications using CMake (#4323, #4333, #4453)
-* It is now easier than ever to embed XGBoost in your C/C++ applications. In your CMakeLists.txt, add `xgboost::xgboost` as a linked library:
-
-  ```cmake
-  find_package(xgboost REQUIRED)
-  add_executable(api-demo c-api-demo.c)
-  target_link_libraries(api-demo xgboost::xgboost)
-  ```
-
-  [XGBoost C API documentation is available.](https://xgboost.readthedocs.io/en/release_0.90/dev) Special thanks to @trivialfis
-
-### Performance improvements
-* Use feature interaction constraints to narrow split search space (#4341, #4428)
-* Additional optimizations for `gpu_hist` (#4248, #4283)
-* Reduce OpenMP thread launches in `gpu_hist` (#4343)
-* Additional optimizations for multi-node multi-GPU random forests. (#4238)
-* Allocate unique prediction buffer for each input matrix, to avoid re-sizing GPU array (#4275)
-* Remove various synchronisations from CUDA API calls (#4205)
-* XGBoost4J-Spark
-  - Allow the user to control whether to cache partitioned training data, to potentially reduce execution time (#4268)
-
-### Bug-fixes
-* Fix node reuse in `hist` (#4404)
-* Fix GPU histogram allocation (#4347)
-* Fix matrix attributes not sliced (#4311)
-* Revise AUC and AUCPR metrics now work with weighted ranking task (#4216, #4436)
-* Fix timer invocation for InitDataOnce() in `gpu_hist` (#4206)
-* Fix R-devel errors (#4251)
-* Make gradient update in GPU linear updater thread-safe (#4259)
-* Prevent out-of-range access in column matrix (#4231)
-* Don't store DMatrix handle in Python object until it's initialized, to improve exception safety (#4317)
-* XGBoost4J-Spark
-  - Fix non-deterministic order within a zipped partition on prediction (#4388)
-  - Remove race condition on tracker shutdown (#4224)
-  - Allow set the parameter `maxLeaves`. (#4226)
-  - Allow partial evaluation of dataframe before prediction (#4407)
-  - Automatically set `maximize_evaluation_metrics` if not explicitly given (#4446)
-
-### API changes
-* Deprecate `reg:linear` in favor of `reg:squarederror`. (#4267, #4427)
-* Add attribute getter and setter to the Booster object in XGBoost4J (#4336)
-
-### Maintenance: Refactor C++ code for legibility and maintainability
-* Fix clang-tidy warnings. (#4149)
-* Remove deprecated C APIs. (#4266)
-* Use Monitor class to time functions in `hist`. (#4273)
-* Retire DVec class in favour of c++20 style span for device memory. (#4293)
-* Improve HostDeviceVector exception safety (#4301)
-
-### Maintenance: testing, continuous integration, build system
-* **Major refactor of CMakeLists.txt** (#4323, #4333, #4453): adopt modern CMake and export XGBoost as a target
-* **Major improvement in Jenkins CI pipeline** (#4234)
-  - Migrate all Linux tests to Jenkins (#4401)
-  - Builds and tests are now de-coupled, to test an artifact against multiple versions of CUDA, JDK, and other dependencies (#4401)
-  - Add Windows GPU to Jenkins CI pipeline (#4463, #4469)
-* Support CUDA 10.1 (#4223, #4232, #4265, #4468)
-* Python wheels are now built with CUDA 9.0, so that JIT is not required on Volta architecture (#4459)
-* Integrate with NVTX CUDA profiler (#4205)
-* Add a test for cpu predictor using external memory (#4308)
-* Refactor tests to get rid of duplication (#4358)
-* Remove test dependency on `craigcitro/r-travis`, since it's deprecated (#4353)
-* Add files from local R build to `.gitignore` (#4346)
-* Make XGBoost4J compatible with Java 9+ by revising NativeLibLoader (#4351)
-* Jenkins build for CUDA 10.0 (#4281)
-* Remove remaining `silent` and `debug_verbose` in Python tests (#4299)
-* Use all cores to build XGBoost4J lib on linux (#4304)
-* Upgrade Jenkins Linux build environment to GCC 5.3.1, CMake 3.6.0 (#4306)
-* Make CMakeLists.txt compatible with CMake 3.3 (#4420)
-* Add OpenMP option in CMakeLists.txt (#4339)
-* Get rid of a few trivial compiler warnings (#4312)
-* Add external Docker build cache, to speed up builds on Jenkins CI (#4331, #4334, #4458)
-* Fix Windows tests (#4403)
-* Fix a broken python test (#4395)
-* Use a fixed seed to split data in XGBoost4J-Spark tests, for reproducibility (#4417)
-* Add additional Python tests to test training under constraints (#4426)
-* Enable building with shared NCCL. (#4447)
-
-### Usability Improvements, Documentation
-* Document limitation of one-split-at-a-time Greedy tree learning heuristic (#4233)
-* Update build doc: PyPI wheel now support multi-GPU (#4219)
-* Fix docs for `num_parallel_tree` (#4221)
-* Fix document about `colsample_by*` parameter (#4340)
-* Make the train and test input with same colnames. (#4329)
-* Update R contribute link. (#4236)
-* Fix travis R tests (#4277)
-* Log version number in crash log in XGBoost4J-Spark (#4271, #4303)
-* Allow supression of Rabit output in Booster::train in XGBoost4J (#4262)
-* Add tutorial on handling missing values in XGBoost4J-Spark (#4425)
-* Fix typos (#4345, #4393, #4432, #4435)
-* Added language classifier in setup.py (#4327)
-* Added Travis CI badge (#4344)
-* Add BentoML to use case section (#4400)
-* Remove subtly sexist remark (#4418)
-* Add R vignette about parsing JSON dumps (#4439)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Andy Adinets (@canonizer), Jonas (@elcombato), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), James Lamb (@jameslamb), Jean-Francois Zinque (@jeffzi), Yang Yang (@jokerkeny), Mayank Suman (@mayanksuman), jess (@monkeywithacupcake), Hajime Morrita (@omo), Ravi Kalia (@project-delphi), @ras44, Rong Ou (@rongou), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Jiaming Yuan (@trivialfis), Christopher Suchanek (@wsuchy), Bozhao (@yubozhao)
-
-**Reviewers**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Laurae (@Laurae2), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), @alois-bissuel, Andy Adinets (@canonizer), Chen Qin (@chenqin), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), @jakirkham, James Lamb (@jameslamb), Julien Schueller (@jschueller), Mayank Suman (@mayanksuman), Hajime Morrita (@omo), Rong Ou (@rongou), Sara Robinson (@sararob), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Sean Owen (@srowen), Sergei Lebedev (@superbobry), Yuan (Terry) Tang (@terrytangyuan), Theodore Vasiloudis (@thvasilo), Matthew Tovbin (@tovbinm), Jiaming Yuan (@trivialfis), Xin Yin (@xydrolase)
-
 ## v0.82 (2019.03.03)
 This release is packed with many new features and bug fixes.
 

R-package/CMakeLists.txt

@@ -1,38 +0,0 @@
-find_package(LibR REQUIRED)
-message(STATUS "LIBR_CORE_LIBRARY " ${LIBR_CORE_LIBRARY})
-
-file(GLOB_RECURSE R_SOURCES
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.cc
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
-# Use object library to expose symbols
-add_library(xgboost-r OBJECT ${R_SOURCES})
-
-set(R_DEFINITIONS
-  -DXGBOOST_STRICT_R_MODE=1
-  -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
-  -DDMLC_LOG_BEFORE_THROW=0
-  -DDMLC_DISABLE_STDIN=1
-  -DDMLC_LOG_CUSTOMIZE=1
-  -DRABIT_CUSTOMIZE_MSG_
-  -DRABIT_STRICT_CXX98_)
-target_compile_definitions(xgboost-r
-  PRIVATE ${R_DEFINITIONS})
-target_include_directories(xgboost-r
-  PRIVATE
-  ${LIBR_INCLUDE_DIRS}
-  ${PROJECT_SOURCE_DIR}/include
-  ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include)
-set_target_properties(
-  xgboost-r PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-
-set(XGBOOST_DEFINITIONS "${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)
-
-if (USE_OPENMP)
-  target_link_libraries(xgboost-r PRIVATE OpenMP::OpenMP_CXX)
-endif ()

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.1.1.1
-Date: 2020-02-21
+Version: 0.82.0.1
+Date: 2019-03-11
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -52,9 +52,7 @@ Suggests:
     vcd (>= 1.3),
     testthat,
     lintr,
-    igraph (>= 1.0.1),
-    jsonlite,
-    float
+    igraph (>= 1.0.1)
 Depends:
     R (>= 3.3.0)
 Imports:
@@ -63,5 +61,5 @@ Imports:
     data.table (>= 1.9.6),
     magrittr (>= 1.5),
     stringi (>= 0.5.2)
-RoxygenNote: 7.1.0
+RoxygenNote: 6.1.0
 SystemRequirements: GNU make, C++11

R-package/NAMESPACE

@@ -14,7 +14,6 @@ S3method(setinfo,xgb.DMatrix)
 S3method(slice,xgb.DMatrix)
 export("xgb.attr<-")
 export("xgb.attributes<-")
-export("xgb.config<-")
 export("xgb.parameters<-")
 export(cb.cv.predict)
 export(cb.early.stop)
@@ -31,7 +30,6 @@ export(xgb.DMatrix)
 export(xgb.DMatrix.save)
 export(xgb.attr)
 export(xgb.attributes)
-export(xgb.config)
 export(xgb.create.features)
 export(xgb.cv)
 export(xgb.dump)
@@ -40,7 +38,6 @@ export(xgb.ggplot.deepness)
 export(xgb.ggplot.importance)
 export(xgb.importance)
 export(xgb.load)
-export(xgb.load.raw)
 export(xgb.model.dt.tree)
 export(xgb.plot.deepness)
 export(xgb.plot.importance)
@@ -49,9 +46,7 @@ export(xgb.plot.shap)
 export(xgb.plot.tree)
 export(xgb.save)
 export(xgb.save.raw)
-export(xgb.serialize)
 export(xgb.train)
-export(xgb.unserialize)
 export(xgboost)
 import(methods)
 importClassesFrom(Matrix,dgCMatrix)

R-package/R/callbacks.R

@@ -14,7 +14,7 @@
 #' WARNING: side-effects!!! Be aware that these callback functions access and modify things in 
 #' the environment from which they are called from, which is a fairly uncommon thing to do in R.
 #' 
-#' To write a custom callback closure, make sure you first understand the main concepts about R environments.
+#' To write a custom callback closure, make sure you first understand the main concepts about R envoronments.
 #' Check either R documentation on \code{\link[base]{environment}} or the 
 #' \href{http://adv-r.had.co.nz/Environments.html}{Environments chapter} from the "Advanced R" 
 #' book by Hadley Wickham. Further, the best option is to read the code of some of the existing callbacks -
@@ -154,7 +154,7 @@ cb.evaluation.log <- function() {
   callback
 }
 
-#' Callback closure for resetting the booster's parameters at each iteration.
+#' Callback closure for restetting the booster's parameters at each iteration.
 #' 
 #' @param new_params a list where each element corresponds to a parameter that needs to be reset.
 #'        Each element's value must be either a vector of values of length \code{nrounds} 
@@ -470,7 +470,7 @@ cb.save.model <- function(save_period = 0, save_name = "xgboost.model") {
 #' to the order of rows in the original dataset. Note that when a custom \code{folds} list is 
 #' provided in \code{xgb.cv}, the predictions would only be returned properly when this list is a 
 #' non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be 
-#' meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
+#' meaningful when user-profided folds have overlapping indices as in, e.g., random sampling splits.
 #' When some of the indices in the training dataset are not included into user-provided \code{folds},
 #' their prediction value would be \code{NA}.
 #' 
@@ -681,7 +681,7 @@ cb.gblinear.history <- function(sparse=FALSE) {
 #'        using the \code{cb.gblinear.history()} callback.
 #' @param class_index zero-based class index to extract the coefficients for only that
 #'        specific class in a multinomial multiclass model. When it is NULL, all the
-#'        coefficients are returned. Has no effect in non-multiclass models.
+#'        coeffients are returned. Has no effect in non-multiclass models.
 #'
 #' @return 
 #' For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns

R-package/R/utils.R

@@ -28,7 +28,7 @@ NVL <- function(x, val) {
 # Merges booster params with whatever is provided in ...
 # plus runs some checks
 check.booster.params <- function(params, ...) {
-  if (!identical(class(params), "list"))
+  if (typeof(params) != "list") 
     stop("params must be a list")
   
   # in R interface, allow for '.' instead of '_' in parameter names
@@ -78,7 +78,7 @@ check.booster.params <- function(params, ...) {
   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 (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')
     }
@@ -145,7 +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)
+    pred <- predict(booster_handle, dtrain)
     gpair <- obj(pred, dtrain)
     .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
   }
@@ -209,14 +209,13 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
     if (exists('objective', where = params) &&
         is.character(params$objective)) {
       # If 'objective' provided in params, assume that y is a classification label
-      # unless objective is reg:squarederror
-      if (params$objective != 'reg:squarederror')
+      # unless objective is reg:linear
+      if (params$objective != 'reg:linear')
         y <- factor(y)
     } else {
-      # If no 'objective' given in params, it means that user either wants to
-      # use the default 'reg:squarederror' objective or has provided a custom
-      # obj function.  Here, assume classification setting when y has 5 or less
-      # unique values:
+      # If no 'objective' given in params, it means that user either wants to use
+      # the default 'reg:linear' objective or has provided a custom obj function.
+      # Here, assume classification setting when y has 5 or less unique values:
       if (length(unique(y)) <= 5)
         y <- factor(y)
     }

R-package/R/xgb.Booster.R

@@ -5,34 +5,20 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(), modelfile =
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
   }
-  ## Load existing model, dispatch for on disk model file and in memory buffer
+
+  handle <- .Call(XGBoosterCreate_R, cachelist)
   if (!is.null(modelfile)) {
     if (typeof(modelfile) == "character") {
-      ## A filename
-      handle <- .Call(XGBoosterCreate_R, cachelist)
       .Call(XGBoosterLoadModel_R, handle, modelfile[1])
-      class(handle) <- "xgb.Booster.handle"
-      if (length(params) > 0) {
-        xgb.parameters(handle) <- params
-      }
-      return(handle)
     } else if (typeof(modelfile) == "raw") {
-      ## A memory buffer
-      bst <- xgb.unserialize(modelfile)
-      xgb.parameters(bst) <- params
-      return (bst)
+      .Call(XGBoosterLoadModelFromRaw_R, handle, modelfile)
     } else if (inherits(modelfile, "xgb.Booster")) {
-      ## A booster object
       bst <- xgb.Booster.complete(modelfile, saveraw = TRUE)
-      bst <- xgb.unserialize(bst$raw)
-      xgb.parameters(bst) <- params
-      return (bst)
+      .Call(XGBoosterLoadModelFromRaw_R, handle, bst$raw)
     } else {
       stop("modelfile must be either character filename, or raw booster dump, or xgb.Booster object")
     }
   }
-  ## Create new model
-  handle <- .Call(XGBoosterCreate_R, cachelist)
   class(handle) <- "xgb.Booster.handle"
   if (length(params) > 0) {
     xgb.parameters(handle) <- params
@@ -65,13 +51,11 @@ is.null.handle <- function(handle) {
 # 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$handle
-  } else if (inherits(object, "xgb.Booster.handle")) {
-    handle <- object
-  } else {
+  handle <- switch(class(object)[1],
+    xgb.Booster = object$handle,
+    xgb.Booster.handle = object,
     stop("argument must be of either xgb.Booster or xgb.Booster.handle class")
-  }
+  )
   if (is.null.handle(handle)) {
     stop("invalid xgb.Booster.handle")
   }
@@ -97,7 +81,7 @@ xgb.get.handle <- function(object) {
 #' its handle (pointer) to an internal xgboost model would be invalid. The majority of xgboost methods
 #' should still work for such a model object since those methods would be using
 #' \code{xgb.Booster.complete} internally. However, one might find it to be more efficient to call the
-#' \code{xgb.Booster.complete} function explicitly once after loading a model as an R-object.
+#' \code{xgb.Booster.complete} function explicitely once after loading a model as an R-object.
 #' That would prevent further repeated implicit reconstruction of an internal booster model.
 #'
 #' @return
@@ -111,7 +95,6 @@ xgb.get.handle <- function(object) {
 #' saveRDS(bst, "xgb.model.rds")
 #'
 #' bst1 <- readRDS("xgb.model.rds")
-#' if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 #' # the handle is invalid:
 #' print(bst1$handle)
 #'
@@ -127,29 +110,9 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
   if (is.null.handle(object$handle)) {
     object$handle <- xgb.Booster.handle(modelfile = object$raw)
   } else {
-    if (is.null(object$raw) && saveraw) {
-      object$raw <- xgb.serialize(object$handle)
-    }
+    if (is.null(object$raw) && saveraw)
+      object$raw <- xgb.save.raw(object$handle)
   }
-
-  attrs <- xgb.attributes(object)
-  if (!is.null(attrs$best_ntreelimit)) {
-    object$best_ntreelimit <- as.integer(attrs$best_ntreelimit)
-  }
-  if (!is.null(attrs$best_iteration)) {
-    ## Convert from 0 based back to 1 based.
-    object$best_iteration <- as.integer(attrs$best_iteration) + 1
-  }
-  if (!is.null(attrs$best_score)) {
-    object$best_score <- as.numeric(attrs$best_score)
-  }
-  if (!is.null(attrs$best_msg)) {
-    object$best_msg <- attrs$best_msg
-  }
-  if (!is.null(attrs$niter)) {
-    object$niter <- as.integer(attrs$niter)
-  }
-
   return(object)
 }
 
@@ -173,8 +136,6 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' @param reshape whether to reshape the vector of predictions to a matrix form when there are several
 #'        prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
 #'        or predinteraction flags is TRUE.
-#' @param training whether is the prediction result used for training.  For dart booster,
-#'        training predicting will perform dropout.
 #' @param ... Parameters passed to \code{predict.xgb.Booster}
 #'
 #' @details
@@ -201,7 +162,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #'
 #' With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
 #' are computed. Note that this operation might be rather expensive in terms of compute and memory.
-#' Since it quadratically depends on the number of features, it is recommended to perform selection
+#' Since it quadratically depends on the number of features, it is recommended to perfom selection
 #' of the most important features first. See below about the format of the returned results.
 #'
 #' @return
@@ -324,7 +285,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' @export
 predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE, ntreelimit = NULL,
                                 predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, training = FALSE, ...) {
+                                reshape = FALSE, ...) {
 
   object <- xgb.Booster.complete(object, saveraw = FALSE)
   if (!inherits(newdata, "xgb.DMatrix"))
@@ -343,8 +304,7 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
   option <- 0L + 1L * as.logical(outputmargin) + 2L * as.logical(predleaf) + 4L * as.logical(predcontrib) +
     8L * as.logical(approxcontrib) + 16L * as.logical(predinteraction)
 
-  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1],
-               as.integer(ntreelimit), as.integer(training))
+  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1], as.integer(ntreelimit))
 
   n_ret <- length(ret)
   n_row <- nrow(newdata)
@@ -433,7 +393,7 @@ predict.xgb.Booster.handle <- function(object, ...) {
 #' That would only matter if attributes need to be set many times.
 #' Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
 #' the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-#' and it would be user's responsibility to call \code{xgb.serialize} to update it.
+#' and it would be user's responsibility to call \code{xgb.save.raw} to update it.
 #'
 #' The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
 #' but it doesn't delete the other existing attributes.
@@ -458,7 +418,6 @@ predict.xgb.Booster.handle <- function(object, ...) {
 #'
 #' xgb.save(bst, 'xgb.model')
 #' bst1 <- xgb.load('xgb.model')
-#' if (file.exists('xgb.model')) file.remove('xgb.model')
 #' print(xgb.attr(bst1, "my_attribute"))
 #' print(xgb.attributes(bst1))
 #'
@@ -492,7 +451,7 @@ xgb.attr <- function(object, name) {
   }
   .Call(XGBoosterSetAttr_R, handle, as.character(name[1]), value)
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
+    object$raw <- xgb.save.raw(object$handle)
   }
   object
 }
@@ -532,41 +491,11 @@ xgb.attributes <- function(object) {
     .Call(XGBoosterSetAttr_R, handle, names(a[i]), a[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
+    object$raw <- xgb.save.raw(object$handle)
   }
   object
 }
 
-#' Accessors for model parameters as JSON string.
-#'
-#' @param object Object of class \code{xgb.Booster}
-#' @param value A JSON string.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' config <- xgb.config(bst)
-#'
-#' @rdname xgb.config
-#' @export
-xgb.config <- function(object) {
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterSaveJsonConfig_R, handle);
-}
-
-#' @rdname xgb.config
-#' @export
-`xgb.config<-` <- function(object, value) {
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterLoadJsonConfig_R, handle, value)
-  object$raw <- NULL  # force renew the raw buffer
-  object <- xgb.Booster.complete(object)
-  object
-}
-
 #' Accessors for model parameters.
 #'
 #' Only the setter for xgboost parameters is currently implemented.
@@ -603,7 +532,7 @@ xgb.config <- function(object) {
     .Call(XGBoosterSetParam_R, handle, names(p[i]), p[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
+    object$raw <- xgb.save.raw(object$handle)
   }
   object
 }

R-package/R/xgb.DMatrix.R

@@ -19,7 +19,6 @@
 #' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
 xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
   cnames <- NULL
@@ -105,7 +104,7 @@ dim.xgb.DMatrix <- function(x) {
 #' Handling of column names of \code{xgb.DMatrix}
 #' 
 #' Only column names are supported for \code{xgb.DMatrix}, thus setting of 
-#' row names would have no effect and returned row names would be NULL.
+#' row names would have no effect and returnten row names would be NULL.
 #' 
 #' @param x object of class \code{xgb.DMatrix}
 #' @param value a list of two elements: the first one is ignored
@@ -188,10 +187,9 @@ getinfo <- function(object, ...) UseMethod("getinfo")
 getinfo.xgb.DMatrix <- function(object, name, ...) {
   if (typeof(name) != "character" ||
       length(name) != 1 ||
-      !name %in% c('label', 'weight', 'base_margin', 'nrow',
-                   'label_lower_bound', 'label_upper_bound')) {
+      !name %in% c('label', 'weight', 'base_margin', 'nrow')) {
     stop("getinfo: name must be one of the following\n",
-         "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound'")
+         "    'label', 'weight', 'base_margin', 'nrow'")
   }
   if (name != "nrow"){
     ret <- .Call(XGDMatrixGetInfo_R, object, name)
@@ -244,18 +242,6 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
     .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
     return(TRUE)
   }
-  if (name == "label_lower_bound") {
-    if (length(info) != nrow(object))
-      stop("The length of lower-bound labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "label_upper_bound") {
-    if (length(info) != nrow(object))
-      stop("The length of upper-bound labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
   if (name == "weight") {
     if (length(info) != nrow(object))
       stop("The length of weights must equal to the number of rows in the input data")
@@ -280,10 +266,10 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 
 
 #' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
+#' orginal xgb.DMatrix object
 #'
 #' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
+#' orginal xgb.DMatrix object
 #' 
 #' @param object Object of class "xgb.DMatrix"
 #' @param idxset a integer vector of indices of rows needed
@@ -315,17 +301,12 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 
   attr_list <- attributes(object)
   nr <- nrow(object)
-  len <- sapply(attr_list, NROW)
+  len <- sapply(attr_list, length)
   ind <- which(len == nr)
   if (length(ind) > 0) {
     nms <- names(attr_list)[ind]
     for (i in seq_along(ind)) {
-      obj_attr <- attr(object, nms[i])
-      if (NCOL(obj_attr) > 1) {
-        attr(ret, nms[i]) <- obj_attr[idxset,]
-      } else {
-        attr(ret, nms[i]) <- obj_attr[idxset]
-      }
+      attr(ret, nms[i]) <- attr(object, nms[i])[idxset]
     }
   }
   return(structure(ret, class = "xgb.DMatrix"))

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

@@ -11,7 +11,6 @@
 #' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
 xgb.DMatrix.save <- function(dmatrix, fname) {
   if (typeof(fname) != "character")

R-package/R/xgb.cv.R

@@ -6,7 +6,7 @@
 #' \itemize{
 #'   \item \code{objective} objective function, common ones are
 #'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss
+#'     \item \code{reg:linear} linear regression
 #'     \item \code{binary:logistic} logistic regression for classification
 #'   }
 #'   \item \code{eta} step size of each boosting step
@@ -39,7 +39,7 @@
 #' }
 #' @param obj customized objective function. Returns gradient and second order 
 #'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
+#' @param feval custimized evaluation function. Returns 
 #'        \code{list(metric='metric-name', value='metric-value')} with given 
 #'        prediction and dtrain.
 #' @param stratified a \code{boolean} indicating whether sampling of folds should be stratified 
@@ -47,8 +47,6 @@
 #' @param folds \code{list} provides a possibility to use a list of pre-defined CV folds
 #'        (each element must be a vector of test fold's indices). When folds are supplied, 
 #'        the \code{nfold} and \code{stratified} parameters are ignored.
-#' @param train_folds \code{list} list specifying which indicies to use for training. If \code{NULL}
-#'        (the default) all indices not specified in \code{folds} will be used for training.
 #' @param verbose \code{boolean}, print the statistics during the process
 #' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
 #'        Default is 1 which means all messages are printed. This parameter is passed to the 
@@ -86,7 +84,7 @@
 #'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
 #'   \item \code{callbacks} callback functions that were either automatically assigned or 
 #'         explicitly passed.
-#'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
+#'   \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
 #'         first column corresponding to iteration number and the rest corresponding to the 
 #'         CV-based evaluation means and standard deviations for the training and test CV-sets.
 #'         It is created by the \code{\link{cb.evaluation.log}} callback.
@@ -101,7 +99,7 @@
 #'         (only available with early stopping).
 #'   \item \code{pred} CV prediction values available when \code{prediction} is set. 
 #'         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-#'   \item \code{models} a list of the CV folds' models. It is only available with the explicit
+#'   \item \code{models} a liost of the CV folds' models. It is only available with the explicit 
 #'         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
 #' }
 #'
@@ -116,7 +114,7 @@
 #' @export
 xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NA,
                    prediction = FALSE, showsd = TRUE, metrics=list(),
-                   obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, train_folds = NULL,
+                   obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, 
                    verbose = TRUE, print_every_n=1L,
                    early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...) {
 
@@ -135,15 +133,8 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   
   # Check the labels
   if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
-       (!inherits(data, 'xgb.DMatrix') && is.null(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')
-  } else {
-    cv_label = label
-  }
   
   # CV folds
   if(!is.null(folds)) {
@@ -153,7 +144,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   } else {
     if (nfold <= 1)
       stop("'nfold' must be > 1")
-    folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, params)
+    folds <- generate.cv.folds(nfold, nrow(data), stratified, label, params)
   }
   
   # Potential TODO: sequential CV
@@ -188,15 +179,10 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   
   # create the booster-folds
-  # train_folds
   dall <- xgb.get.DMatrix(data, label, 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))
-       dtrain <- slice(dall, unlist(folds[-k]))
-    else
-       dtrain <- slice(dall, train_folds[[k]])
+    dtrain <- slice(dall, unlist(folds[-k]))
     handle <- xgb.Booster.handle(params, list(dtrain, dtest))
     list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test=dtest), index = folds[[k]])
   })

R-package/R/xgb.load.R

@@ -28,7 +28,6 @@
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' xgb.save(bst, 'xgb.model')
 #' bst <- xgb.load('xgb.model')
-#' if (file.exists('xgb.model')) file.remove('xgb.model')
 #' pred <- predict(bst, test$data)
 #' @export
 xgb.load <- function(modelfile) {

R-package/R/xgb.load.raw.R

@@ -1,14 +0,0 @@
-#' Load serialised xgboost model from R's raw vector
-#'
-#' User can generate raw memory buffer by calling xgb.save.raw
-#'
-#' @param buffer the buffer returned by xgb.save.raw
-#'
-#' @export
-xgb.load.raw <- function(buffer) {
-  cachelist <- list()
-  handle <- .Call(XGBoosterCreate_R, cachelist)
-  .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
-  class(handle) <- "xgb.Booster.handle"
-  return (handle)
-}

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

@@ -30,8 +30,8 @@
 #' Setting \code{rel_to_first = TRUE} allows to see the picture from the perspective of 
 #' "what is feature's importance contribution relative to the most important feature?"
 #' 
-#' The ggplot-backend method also performs 1-D clustering of the importance values,
-#' with bar colors corresponding to different clusters that have somewhat similar importance values.
+#' The ggplot-backend method also performs 1-D custering of the importance values, 
+#' with bar colors coresponding to different clusters that have somewhat similar importance values.
 #' 
 #' @return
 #' The \code{xgb.plot.importance} function creates a \code{barplot} (when \code{plot=TRUE})

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

@@ -31,7 +31,7 @@
 #' @param plot_loess whether to plot loess-smoothed curves. The smoothing is only done for features with
 #'          more than 5 distinct values.
 #' @param col_loess a color to use for the loess curves.
-#' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
+#' @param span_loess the \code{span} paramerer in \code{\link[stats]{loess}}'s call.
 #' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
 #' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
 #' @param ... other parameters passed to \code{plot}.

R-package/R/xgb.save.R

@@ -27,7 +27,6 @@
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' xgb.save(bst, 'xgb.model')
 #' bst <- xgb.load('xgb.model')
-#' if (file.exists('xgb.model')) file.remove('xgb.model')
 #' pred <- predict(bst, test$data)
 #' @export
 xgb.save <- function(model, fname) {

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

@@ -1,5 +1,5 @@
 #' Save xgboost model to R's raw vector,
-#' user can call xgb.load.raw to load the model back from raw vector
+#' user can call xgb.load to load the model back from raw vector
 #' 
 #' Save xgboost model from xgboost or xgb.train
 #' 
@@ -13,11 +13,11 @@
 #' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' raw <- xgb.save.raw(bst)
-#' bst <- xgb.load.raw(raw)
+#' bst <- xgb.load(raw)
 #' pred <- predict(bst, test$data)
 #'
 #' @export
 xgb.save.raw <- function(model) {
-  handle <- xgb.get.handle(model)
-  .Call(XGBoosterModelToRaw_R, handle)
+  model <- xgb.get.handle(model)
+  .Call(XGBoosterModelToRaw_R, model)
 }

R-package/R/xgb.serialize.R

@@ -1,21 +0,0 @@
-#' Serialize the booster instance into R's raw vector.  The serialization method differs
-#' from \code{\link{xgb.save.raw}} as the latter one saves only the model but not
-#' parameters.  This serialization format is not stable across different xgboost versions.
-#'
-#' @param booster the booster instance
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#' train <- agaricus.train
-#' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' raw <- xgb.serialize(bst)
-#' bst <- xgb.unserialize(raw)
-#'
-#' @export
-xgb.serialize <- function(booster) {
-  handle <- xgb.get.handle(booster)
-  .Call(XGBoosterSerializeToBuffer_R, handle)
-}

R-package/R/xgb.train.R

@@ -42,7 +42,7 @@
 #' \itemize{
 #' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
 #'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss (Default).
+#'     \item \code{reg:linear} linear regression (Default).
 #'     \item \code{reg:logistic} logistic regression.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
@@ -68,7 +68,7 @@
 #'        the performance of each round's model on mat1 and mat2.
 #' @param obj customized objective function. Returns gradient and second order 
 #'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
+#' @param feval custimized evaluation function. Returns 
 #'        \code{list(metric='metric-name', value='metric-value')} with given 
 #'        prediction and dtrain.
 #' @param verbose If 0, xgboost will stay silent. If 1, it will print information about performance.
@@ -118,7 +118,7 @@
 #' when the \code{eval_metric} parameter is not provided.
 #' User may set one or several \code{eval_metric} parameters. 
 #' Note that when using a customized metric, only this single metric can be used.
-#' The following is the list of built-in metrics for which Xgboost provides optimized implementation:
+#' The folloiwing is the list of built-in metrics for which Xgboost provides optimized implementation:
 #'   \itemize{
 #'      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
 #'      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
@@ -147,14 +147,14 @@
 #'   \item \code{handle} a handle (pointer) to the xgboost model in memory.
 #'   \item \code{raw} a cached memory dump of the xgboost model saved as R's \code{raw} type.
 #'   \item \code{niter} number of boosting iterations.
-#'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
+#'   \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
 #'         first column corresponding to iteration number and the rest corresponding to evaluation
 #'         metrics' values. It is created by the \code{\link{cb.evaluation.log}} callback.
 #'   \item \code{call} a function call.
 #'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not 
 #'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
 #'   \item \code{callbacks} callback functions that were either automatically assigned or 
-#'         explicitly passed.
+#'         explicitely passed.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
 #'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration, 
@@ -163,7 +163,7 @@
 #'   \item \code{best_score} the best evaluation metric value during early stopping.
 #'         (only available with early stopping).
 #'   \item \code{feature_names} names of the training dataset features
-#'         (only when column names were defined in training data).
+#'         (only when comun names were defined in training data).
 #'   \item \code{nfeatures} number of features in training data.
 #' }
 #' 
@@ -186,7 +186,7 @@
 #' watchlist <- list(train = dtrain, eval = dtest)
 #' 
 #' ## A simple xgb.train example:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+#' param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2, 
 #'               objective = "binary:logistic", eval_metric = "auc")
 #' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 #' 
@@ -207,12 +207,12 @@
 #' 
 #' # These functions could be used by passing them either:
 #' #  as 'objective' and 'eval_metric' parameters in the params list:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+#' param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2, 
 #'               objective = logregobj, eval_metric = evalerror)
 #' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 #' 
 #' #  or through the ... arguments:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2)
+#' param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2)
 #' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
 #'                  objective = logregobj, eval_metric = evalerror)
 #' 
@@ -222,7 +222,7 @@
 #' 
 #' 
 #' ## An xgb.train example of using variable learning rates at each iteration:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+#' param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
 #'               objective = "binary:logistic", eval_metric = "auc")
 #' my_etas <- list(eta = c(0.5, 0.1))
 #' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
@@ -267,7 +267,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   }
 
   # evaluation printing callback
-  params <- c(params)
+  params <- c(params, list(silent = ifelse(verbose > 1, 0, 1)))
   print_every_n <- max( as.integer(print_every_n), 1L)
   if (!has.callbacks(callbacks, 'cb.print.evaluation') &&
       verbose) {
@@ -291,13 +291,8 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds, 
                                                  maximize = maximize, verbose = verbose))
   }
-
   # Sort the callbacks into categories
   cb <- categorize.callbacks(callbacks)
-  params['validate_parameters'] <- TRUE
-  if (!is.null(params[['seed']])) {
-    warning("xgb.train: `seed` is ignored in R package.  Use `set.seed()` instead.")
-  }
 
   # The tree updating process would need slightly different handling
   is_update <- NVL(params[['process_type']], '.') == 'update'

R-package/R/xgb.unserialize.R

@@ -1,12 +0,0 @@
-#' Load the instance back from \code{\link{xgb.serialize}}
-#'
-#' @param buffer the buffer containing booster instance saved by \code{\link{xgb.serialize}}
-#'
-#' @export
-xgb.unserialize <- function(buffer) {
-  cachelist <- list()
-  handle <- .Call(XGBoosterCreate_R, cachelist)
-  .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer)
-  class(handle) <- "xgb.Booster.handle"
-  return (handle)
-}

R-package/R/xgboost.R

@@ -18,7 +18,7 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
                    early_stopping_rounds = early_stopping_rounds, maximize = maximize,
                    save_period = save_period, save_name = save_name,
                    xgb_model = xgb_model, callbacks = callbacks, ...)
-  return (bst)
+  return(bst)
 }
 
 #' Training part from Mushroom Data Set

R-package/README.md

@@ -30,4 +30,4 @@ Examples
 Development
 -----------
 
-* See the [R Package section](https://xgboost.readthedocs.io/en/latest/contribute.html#r-package) of the contributors guide.
+* See the [R Package section](https://xgboost.readthedocs.io/en/latest/how_to/contribute.html#r-package) of the contributors guide.

R-package/cleanup

@@ -1,4 +1,3 @@
 #!/bin/sh
 
 rm -f src/Makevars
-rm -f CMakeLists.txt

R-package/configure.ac

@@ -4,21 +4,6 @@ AC_PREREQ(2.62)
 
 AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
-# Use this line to set CC variable to a C compiler
-AC_PROG_CC
-
-### Check whether backtrace() is part of libc or the external lib libexecinfo
-AC_MSG_CHECKING([Backtrace lib])
-AC_MSG_RESULT([])
-AC_CHECK_LIB([execinfo], [backtrace], [BACKTRACE_LIB=-lexecinfo], [BACKTRACE_LIB=''])
-
-### Endian detection
-AC_MSG_CHECKING([endian])
-AC_MSG_RESULT([])
-AC_RUN_IFELSE([AC_LANG_PROGRAM([[#include <stdint.h>]], [[const uint16_t endianness = 256; return !!(*(const uint8_t *)&endianness);]])],
-  [ENDIAN_FLAG="-DDMLC_CMAKE_LITTLE_ENDIAN=1"],
-  [ENDIAN_FLAG="-DDMLC_CMAKE_LITTLE_ENDIAN=0"])
-
 OPENMP_CXXFLAGS=""
 
 if test `uname -s` = "Linux"
@@ -28,28 +13,19 @@ fi
 
 if test `uname -s` = "Darwin"
 then
-  OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='-lomp'
+  OPENMP_CXXFLAGS="\$(SHLIB_OPENMP_CXXFLAGS)"
   ac_pkg_openmp=no
   AC_MSG_CHECKING([whether OpenMP will work in a package])
-  AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
-  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  AC_LANG_CONFTEST(
+  [AC_LANG_PROGRAM([[#include <omp.h>]], [[ return omp_get_num_threads (); ]])])
+  PKG_CFLAGS="${OPENMP_CFLAGS}" PKG_LIBS="${OPENMP_CFLAGS}" "$RBIN" CMD SHLIB conftest.c 1>&AS_MESSAGE_LOG_FD 2>&AS_MESSAGE_LOG_FD && "$RBIN" --vanilla -q -e "dyn.load(paste('conftest',.Platform\$dynlib.ext,sep=''))" 1>&AS_MESSAGE_LOG_FD 2>&AS_MESSAGE_LOG_FD && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''
-    OPENMP_LIB=''
-    echo '*****************************************************************************************'
-    echo 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
-    echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
-    echo '             brew install libomp'
-    echo '*****************************************************************************************'
   fi
 fi
 
 AC_SUBST(OPENMP_CXXFLAGS)
-AC_SUBST(OPENMP_LIB)
-AC_SUBST(ENDIAN_FLAG)
-AC_SUBST(BACKTRACE_LIB)
 AC_CONFIG_FILES([src/Makevars])
 AC_OUTPUT
 

R-package/demo/gpu_accelerated.R

@@ -30,7 +30,7 @@ wl <- list(train = dtrain, test = dtest)
 # - similar to the 'hist'
 # - the fastest option for moderately large datasets
 # - current limitations: max_depth < 16, does not implement guided loss
-# You can use tree_method = 'gpu_hist' for another GPU accelerated algorithm,
+# You can use tree_method = 'gpu_exact' for another GPU accelerated algorithm,
 # which is slower, more memory-hungry, but does not use binning.
 param <- list(objective = 'reg:logistic', eval_metric = 'auc', subsample = 0.5, nthread = 4,
               max_bin = 64, tree_method = 'gpu_hist')

R-package/demo/predict_leaf_indices.R

@@ -38,7 +38,6 @@ create.new.tree.features <- function(model, original.features){
 # Convert previous features to one hot encoding
 new.features.train <- create.new.tree.features(bst, agaricus.train$data)
 new.features.test <- create.new.tree.features(bst, agaricus.test$data)
-colnames(new.features.test) <- colnames(new.features.train)
 
 # learning with new features
 new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)

R-package/man/agaricus.test.Rd

@@ -4,10 +4,8 @@
 \name{agaricus.test}
 \alias{agaricus.test}
 \title{Test part from Mushroom Data Set}
-\format{
-A list containing a label vector, and a dgCMatrix object with 1611
-rows and 126 variables
-}
+\format{A list containing a label vector, and a dgCMatrix object with 1611 
+rows and 126 variables}
 \usage{
 data(agaricus.test)
 }

R-package/man/agaricus.train.Rd

@@ -4,10 +4,8 @@
 \name{agaricus.train}
 \alias{agaricus.train}
 \title{Training part from Mushroom Data Set}
-\format{
-A list containing a label vector, and a dgCMatrix object with 6513
-rows and 127 variables
-}
+\format{A list containing a label vector, and a dgCMatrix object with 6513 
+rows and 127 variables}
 \usage{
 data(agaricus.train)
 }

R-package/man/callbacks.Rd

@@ -18,7 +18,7 @@ the boosting is completed.
 WARNING: side-effects!!! Be aware that these callback functions access and modify things in 
 the environment from which they are called from, which is a fairly uncommon thing to do in R.
 
-To write a custom callback closure, make sure you first understand the main concepts about R environments.
+To write a custom callback closure, make sure you first understand the main concepts about R envoronments.
 Check either R documentation on \code{\link[base]{environment}} or the 
 \href{http://adv-r.had.co.nz/Environments.html}{Environments chapter} from the "Advanced R" 
 book by Hadley Wickham. Further, the best option is to read the code of some of the existing callbacks -

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

@@ -15,7 +15,7 @@ depending on the number of prediction outputs per data row. The order of predict
 to the order of rows in the original dataset. Note that when a custom \code{folds} list is 
 provided in \code{xgb.cv}, the predictions would only be returned properly when this list is a 
 non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be 
-meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
+meaningful when user-profided folds have overlapping indices as in, e.g., random sampling splits.
 When some of the indices in the training dataset are not included into user-provided \code{folds},
 their prediction value would be \code{NA}.
 }

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

@@ -4,12 +4,8 @@
 \alias{cb.early.stop}
 \title{Callback closure to activate the early stopping.}
 \usage{
-cb.early.stop(
-  stopping_rounds,
-  maximize = FALSE,
-  metric_name = NULL,
-  verbose = TRUE
-)
+cb.early.stop(stopping_rounds, maximize = FALSE, metric_name = NULL,
+  verbose = TRUE)
 }
 \arguments{
 \item{stopping_rounds}{The number of rounds with no improvement in 

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

@@ -2,7 +2,7 @@
 % Please edit documentation in R/callbacks.R
 \name{cb.reset.parameters}
 \alias{cb.reset.parameters}
-\title{Callback closure for resetting the booster's parameters at each iteration.}
+\title{Callback closure for restetting the booster's parameters at each iteration.}
 \usage{
 cb.reset.parameters(new_params)
 }
@@ -15,7 +15,7 @@ which returns a new parameter value by using the current iteration number
 and the total number of boosting rounds.}
 }
 \description{
-Callback closure for resetting the booster's parameters at each iteration.
+Callback closure for restetting the booster's parameters at each iteration.
 }
 \details{
 This is a "pre-iteration" callback function used to reset booster's parameters

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

@@ -17,7 +17,7 @@ and the second one is column names}
 }
 \description{
 Only column names are supported for \code{xgb.DMatrix}, thus setting of 
-row names would have no effect and returned row names would be NULL.
+row names would have no effect and returnten row names would be NULL.
 }
 \details{
 Generic \code{dimnames} methods are used by \code{colnames}.

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

@@ -5,20 +5,10 @@
 \alias{predict.xgb.Booster.handle}
 \title{Predict method for eXtreme Gradient Boosting model}
 \usage{
-\method{predict}{xgb.Booster}(
-  object,
-  newdata,
-  missing = NA,
-  outputmargin = FALSE,
-  ntreelimit = NULL,
-  predleaf = FALSE,
-  predcontrib = FALSE,
-  approxcontrib = FALSE,
-  predinteraction = FALSE,
-  reshape = FALSE,
-  training = FALSE,
-  ...
-)
+\method{predict}{xgb.Booster}(object, newdata, missing = NA,
+  outputmargin = FALSE, ntreelimit = NULL, predleaf = FALSE,
+  predcontrib = FALSE, approxcontrib = FALSE,
+  predinteraction = FALSE, reshape = FALSE, ...)
 
 \method{predict}{xgb.Booster.handle}(object, ...)
 }
@@ -49,9 +39,6 @@ It will use all the trees by default (\code{NULL} value).}
 prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
 or predinteraction flags is TRUE.}
 
-\item{training}{whether is the prediction result used for training.  For dart booster,
-training predicting will perform dropout.}
-
 \item{...}{Parameters passed to \code{predict.xgb.Booster}}
 }
 \value{
@@ -104,7 +91,7 @@ in \url{http://blog.datadive.net/interpreting-random-forests/}.
 
 With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
 are computed. Note that this operation might be rather expensive in terms of compute and memory.
-Since it quadratically depends on the number of features, it is recommended to perform selection
+Since it quadratically depends on the number of features, it is recommended to perfom selection
 of the most important features first. See below about the format of the returned results.
 }
 \examples{

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

@@ -5,7 +5,7 @@
 \alias{slice.xgb.DMatrix}
 \alias{[.xgb.DMatrix}
 \title{Get a new DMatrix containing the specified rows of
-original xgb.DMatrix object}
+orginal xgb.DMatrix object}
 \usage{
 slice(object, ...)
 
@@ -24,7 +24,7 @@ slice(object, ...)
 }
 \description{
 Get a new DMatrix containing the specified rows of
-original xgb.DMatrix object
+orginal xgb.DMatrix object
 }
 \examples{
 data(agaricus.train, package='xgboost')

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

@@ -28,7 +28,7 @@ E.g., when an \code{xgb.Booster} model is saved as an R object and then is loade
 its handle (pointer) to an internal xgboost model would be invalid. The majority of xgboost methods
 should still work for such a model object since those methods would be using
 \code{xgb.Booster.complete} internally. However, one might find it to be more efficient to call the
-\code{xgb.Booster.complete} function explicitly once after loading a model as an R-object.
+\code{xgb.Booster.complete} function explicitely once after loading a model as an R-object.
 That would prevent further repeated implicit reconstruction of an internal booster model.
 }
 \examples{
@@ -39,7 +39,6 @@ bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_dep
 saveRDS(bst, "xgb.model.rds")
 
 bst1 <- readRDS("xgb.model.rds")
-if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 # the handle is invalid:
 print(bst1$handle)
 

R-package/man/xgb.DMatrix.Rd

@@ -31,5 +31,4 @@ train <- agaricus.train
 dtrain <- xgb.DMatrix(train$data, label=train$label)
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 }

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

@@ -20,5 +20,4 @@ train <- agaricus.train
 dtrain <- xgb.DMatrix(train$data, label=train$label)
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 }

R-package/man/xgb.attr.Rd

@@ -55,7 +55,7 @@ than for \code{xgb.Booster}, since only just a handle (pointer) would need to be
 That would only matter if attributes need to be set many times.
 Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
 the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-and it would be user's responsibility to call \code{xgb.serialize} to update it.
+and it would be user's responsibility to call \code{xgb.save.raw} to update it.
 
 The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
 but it doesn't delete the other existing attributes.
@@ -73,7 +73,6 @@ xgb.attributes(bst) <- list(a = 123, b = "abc")
 
 xgb.save(bst, 'xgb.model')
 bst1 <- xgb.load('xgb.model')
-if (file.exists('xgb.model')) file.remove('xgb.model')
 print(xgb.attr(bst1, "my_attribute"))
 print(xgb.attributes(bst1))
 

R-package/man/xgb.config.Rd

@@ -1,28 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{xgb.config}
-\alias{xgb.config}
-\alias{xgb.config<-}
-\title{Accessors for model parameters as JSON string.}
-\usage{
-xgb.config(object)
-
-xgb.config(object) <- value
-}
-\arguments{
-\item{object}{Object of class \code{xgb.Booster}}
-
-\item{value}{A JSON string.}
-}
-\description{
-Accessors for model parameters as JSON string.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-config <- xgb.config(bst)
-
-}

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

@@ -87,6 +87,6 @@ accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == 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"))
+          accuracy.after, "!\\n"))
 
 }

R-package/man/xgb.cv.Rd

@@ -4,35 +4,19 @@
 \alias{xgb.cv}
 \title{Cross Validation}
 \usage{
-xgb.cv(
-  params = list(),
-  data,
-  nrounds,
-  nfold,
-  label = NULL,
-  missing = NA,
-  prediction = FALSE,
-  showsd = TRUE,
-  metrics = list(),
-  obj = NULL,
-  feval = NULL,
-  stratified = TRUE,
-  folds = NULL,
-  train_folds = NULL,
-  verbose = TRUE,
-  print_every_n = 1L,
-  early_stopping_rounds = NULL,
-  maximize = NULL,
-  callbacks = list(),
-  ...
-)
+xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
+  missing = NA, prediction = FALSE, showsd = TRUE,
+  metrics = list(), obj = NULL, feval = NULL, stratified = TRUE,
+  folds = NULL, verbose = TRUE, print_every_n = 1L,
+  early_stopping_rounds = NULL, maximize = NULL, callbacks = list(),
+  ...)
 }
 \arguments{
 \item{params}{the list of parameters. Commonly used ones are:
 \itemize{
   \item \code{objective} objective function, common ones are
   \itemize{
-    \item \code{reg:squarederror} Regression with squared loss
+    \item \code{reg:linear} linear regression
     \item \code{binary:logistic} logistic regression for classification
   }
   \item \code{eta} step size of each boosting step
@@ -75,7 +59,7 @@ from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callb
 \item{obj}{customized objective function. Returns gradient and second order 
 gradient with given prediction and dtrain.}
 
-\item{feval}{customized evaluation function. Returns
+\item{feval}{custimized evaluation function. Returns 
 \code{list(metric='metric-name', value='metric-value')} with given 
 prediction and dtrain.}
 
@@ -86,9 +70,6 @@ by the values of outcome labels.}
 (each element must be a vector of test fold's indices). When folds are supplied, 
 the \code{nfold} and \code{stratified} parameters are ignored.}
 
-\item{train_folds}{\code{list} list specifying which indicies to use for training. If \code{NULL}
-(the default) all indices not specified in \code{folds} will be used for training.}
-
 \item{verbose}{\code{boolean}, print the statistics during the process}
 
 \item{print_every_n}{Print each n-th iteration evaluation messages when \code{verbose>0}.
@@ -120,7 +101,7 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
   \item \code{callbacks} callback functions that were either automatically assigned or 
         explicitly passed.
-  \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
+  \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
         first column corresponding to iteration number and the rest corresponding to the 
         CV-based evaluation means and standard deviations for the training and test CV-sets.
         It is created by the \code{\link{cb.evaluation.log}} callback.
@@ -135,7 +116,7 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
         (only available with early stopping).
   \item \code{pred} CV prediction values available when \code{prediction} is set. 
         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-  \item \code{models} a list of the CV folds' models. It is only available with the explicit
+  \item \code{models} a liost of the CV folds' models. It is only available with the explicit 
         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
 }
 }

R-package/man/xgb.dump.Rd

@@ -4,14 +4,8 @@
 \alias{xgb.dump}
 \title{Dump an xgboost model in text format.}
 \usage{
-xgb.dump(
-  model,
-  fname = NULL,
-  fmap = "",
-  with_stats = FALSE,
-  dump_format = c("text", "json"),
-  ...
-)
+xgb.dump(model, fname = NULL, fmap = "", with_stats = FALSE,
+  dump_format = c("text", "json"), ...)
 }
 \arguments{
 \item{model}{the model object.}

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

@@ -12,7 +12,7 @@ using the \code{cb.gblinear.history()} callback.}
 
 \item{class_index}{zero-based class index to extract the coefficients for only that
 specific class in a multinomial multiclass model. When it is NULL, all the
-coefficients are returned. Has no effect in non-multiclass models.}
+coeffients are returned. Has no effect in non-multiclass models.}
 }
 \value{
 For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns

R-package/man/xgb.importance.Rd

@@ -4,14 +4,8 @@
 \alias{xgb.importance}
 \title{Importance of features in a model.}
 \usage{
-xgb.importance(
-  feature_names = NULL,
-  model = NULL,
-  trees = NULL,
-  data = NULL,
-  label = NULL,
-  target = NULL
-)
+xgb.importance(feature_names = NULL, model = NULL, trees = NULL,
+  data = NULL, label = NULL, target = NULL)
 }
 \arguments{
 \item{feature_names}{character vector of feature names. If the model already

R-package/man/xgb.load.Rd

@@ -33,7 +33,6 @@ 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')
-if (file.exists('xgb.model')) file.remove('xgb.model')
 pred <- predict(bst, test$data)
 }
 \seealso{

R-package/man/xgb.load.raw.Rd

@@ -1,14 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.load.raw.R
-\name{xgb.load.raw}
-\alias{xgb.load.raw}
-\title{Load serialised xgboost model from R's raw vector}
-\usage{
-xgb.load.raw(buffer)
-}
-\arguments{
-\item{buffer}{the buffer returned by xgb.save.raw}
-}
-\description{
-User can generate raw memory buffer by calling xgb.save.raw
-}

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

@@ -4,14 +4,8 @@
 \alias{xgb.model.dt.tree}
 \title{Parse a boosted tree model text dump}
 \usage{
-xgb.model.dt.tree(
-  feature_names = NULL,
-  model = NULL,
-  text = NULL,
-  trees = NULL,
-  use_int_id = FALSE,
-  ...
-)
+xgb.model.dt.tree(feature_names = NULL, model = NULL, text = NULL,
+  trees = NULL, use_int_id = FALSE, ...)
 }
 \arguments{
 \item{feature_names}{character vector of feature names. If the model already

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

@@ -5,17 +5,11 @@
 \alias{xgb.plot.deepness}
 \title{Plot model trees deepness}
 \usage{
-xgb.ggplot.deepness(
-  model = NULL,
-  which = c("2x1", "max.depth", "med.depth", "med.weight")
-)
+xgb.ggplot.deepness(model = NULL, which = c("2x1", "max.depth",
+  "med.depth", "med.weight"))
 
-xgb.plot.deepness(
-  model = NULL,
-  which = c("2x1", "max.depth", "med.depth", "med.weight"),
-  plot = TRUE,
-  ...
-)
+xgb.plot.deepness(model = NULL, which = c("2x1", "max.depth",
+  "med.depth", "med.weight"), plot = TRUE, ...)
 }
 \arguments{
 \item{model}{either an \code{xgb.Booster} model generated by the \code{xgb.train} function

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

@@ -5,25 +5,12 @@
 \alias{xgb.plot.importance}
 \title{Plot feature importance as a bar graph}
 \usage{
-xgb.ggplot.importance(
-  importance_matrix = NULL,
-  top_n = NULL,
-  measure = NULL,
-  rel_to_first = FALSE,
-  n_clusters = c(1:10),
-  ...
-)
+xgb.ggplot.importance(importance_matrix = NULL, top_n = NULL,
+  measure = NULL, rel_to_first = FALSE, n_clusters = c(1:10), ...)
 
-xgb.plot.importance(
-  importance_matrix = NULL,
-  top_n = NULL,
-  measure = NULL,
-  rel_to_first = FALSE,
-  left_margin = 10,
-  cex = NULL,
-  plot = TRUE,
-  ...
-)
+xgb.plot.importance(importance_matrix = NULL, top_n = NULL,
+  measure = NULL, rel_to_first = FALSE, left_margin = 10,
+  cex = NULL, plot = TRUE, ...)
 }
 \arguments{
 \item{importance_matrix}{a \code{data.table} returned by \code{\link{xgb.importance}}.}
@@ -72,8 +59,8 @@ For linear models, \code{rel_to_first = FALSE} would show actual values of the c
 Setting \code{rel_to_first = TRUE} allows to see the picture from the perspective of 
 "what is feature's importance contribution relative to the most important feature?"
 
-The ggplot-backend method also performs 1-D clustering of the importance values,
-with bar colors corresponding to different clusters that have somewhat similar importance values.
+The ggplot-backend method also performs 1-D custering of the importance values, 
+with bar colors coresponding to different clusters that have somewhat similar importance values.
 }
 \examples{
 data(agaricus.train)

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

@@ -4,15 +4,8 @@
 \alias{xgb.plot.multi.trees}
 \title{Project all trees on one tree and plot it}
 \usage{
-xgb.plot.multi.trees(
-  model,
-  feature_names = NULL,
-  features_keep = 5,
-  plot_width = NULL,
-  plot_height = NULL,
-  render = TRUE,
-  ...
-)
+xgb.plot.multi.trees(model, feature_names = NULL, features_keep = 5,
+  plot_width = NULL, plot_height = NULL, render = TRUE, ...)
 }
 \arguments{
 \item{model}{produced by the \code{xgb.train} function.}

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

@@ -4,33 +4,13 @@
 \alias{xgb.plot.shap}
 \title{SHAP contribution dependency plots}
 \usage{
-xgb.plot.shap(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 1,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL,
-  n_col = 1,
-  col = rgb(0, 0, 1, 0.2),
-  pch = ".",
-  discrete_n_uniq = 5,
-  discrete_jitter = 0.01,
-  ylab = "SHAP",
-  plot_NA = TRUE,
-  col_NA = rgb(0.7, 0, 1, 0.6),
-  pch_NA = ".",
-  pos_NA = 1.07,
-  plot_loess = TRUE,
-  col_loess = 2,
-  span_loess = 0.5,
-  which = c("1d", "2d"),
-  plot = TRUE,
-  ...
-)
+xgb.plot.shap(data, shap_contrib = NULL, features = NULL, top_n = 1,
+  model = NULL, trees = NULL, target_class = NULL,
+  approxcontrib = FALSE, subsample = NULL, n_col = 1, col = rgb(0,
+  0, 1, 0.2), pch = ".", discrete_n_uniq = 5, discrete_jitter = 0.01,
+  ylab = "SHAP", plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6),
+  pch_NA = ".", pos_NA = 1.07, plot_loess = TRUE, col_loess = 2,
+  span_loess = 0.5, which = c("1d", "2d"), plot = TRUE, ...)
 }
 \arguments{
 \item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
@@ -83,7 +63,7 @@ more than 5 distinct values.}
 
 \item{col_loess}{a color to use for the loess curves.}
 
-\item{span_loess}{the \code{span} parameter in \code{\link[stats]{loess}}'s call.}
+\item{span_loess}{the \code{span} paramerer in \code{\link[stats]{loess}}'s call.}
 
 \item{which}{whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.}
 

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

@@ -4,16 +4,9 @@
 \alias{xgb.plot.tree}
 \title{Plot a boosted tree model}
 \usage{
-xgb.plot.tree(
-  feature_names = NULL,
-  model = NULL,
-  trees = NULL,
-  plot_width = NULL,
-  plot_height = NULL,
-  render = TRUE,
-  show_node_id = FALSE,
-  ...
-)
+xgb.plot.tree(feature_names = NULL, model = NULL, trees = NULL,
+  plot_width = NULL, plot_height = NULL, render = TRUE,
+  show_node_id = FALSE, ...)
 }
 \arguments{
 \item{feature_names}{names of each feature as a \code{character} vector.}

R-package/man/xgb.save.Rd

@@ -33,7 +33,6 @@ 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')
-if (file.exists('xgb.model')) file.remove('xgb.model')
 pred <- predict(bst, test$data)
 }
 \seealso{

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

@@ -3,7 +3,7 @@
 \name{xgb.save.raw}
 \alias{xgb.save.raw}
 \title{Save xgboost model to R's raw vector,
-user can call xgb.load.raw to load the model back from raw vector}
+user can call xgb.load to load the model back from raw vector}
 \usage{
 xgb.save.raw(model)
 }
@@ -21,7 +21,7 @@ test <- agaricus.test
 bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 raw <- xgb.save.raw(bst)
-bst <- xgb.load.raw(raw)
+bst <- xgb.load(raw)
 pred <- predict(bst, test$data)
 
 }

R-package/man/xgb.serialize.Rd

@@ -1,29 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.serialize.R
-\name{xgb.serialize}
-\alias{xgb.serialize}
-\title{Serialize the booster instance into R's raw vector.  The serialization method differs
-from \code{\link{xgb.save.raw}} as the latter one saves only the model but not
-parameters.  This serialization format is not stable across different xgboost versions.}
-\usage{
-xgb.serialize(booster)
-}
-\arguments{
-\item{booster}{the booster instance}
-}
-\description{
-Serialize the booster instance into R's raw vector.  The serialization method differs
-from \code{\link{xgb.save.raw}} as the latter one saves only the model but not
-parameters.  This serialization format is not stable across different xgboost versions.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-raw <- xgb.serialize(bst)
-bst <- xgb.unserialize(raw)
-
-}

R-package/man/xgb.train.Rd

@@ -5,41 +5,17 @@
 \alias{xgboost}
 \title{eXtreme Gradient Boosting Training}
 \usage{
-xgb.train(
-  params = list(),
-  data,
-  nrounds,
-  watchlist = list(),
-  obj = NULL,
-  feval = NULL,
-  verbose = 1,
-  print_every_n = 1L,
-  early_stopping_rounds = NULL,
-  maximize = NULL,
-  save_period = NULL,
-  save_name = "xgboost.model",
-  xgb_model = NULL,
-  callbacks = list(),
-  ...
-)
+xgb.train(params = list(), data, nrounds, watchlist = list(),
+  obj = NULL, feval = NULL, verbose = 1, print_every_n = 1L,
+  early_stopping_rounds = NULL, maximize = NULL, save_period = NULL,
+  save_name = "xgboost.model", xgb_model = NULL, callbacks = list(),
+  ...)
 
-xgboost(
-  data = NULL,
-  label = NULL,
-  missing = NA,
-  weight = NULL,
-  params = list(),
-  nrounds,
-  verbose = 1,
-  print_every_n = 1L,
-  early_stopping_rounds = NULL,
-  maximize = NULL,
-  save_period = NULL,
-  save_name = "xgboost.model",
-  xgb_model = NULL,
-  callbacks = list(),
-  ...
-)
+xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
+  params = list(), nrounds, verbose = 1, print_every_n = 1L,
+  early_stopping_rounds = NULL, maximize = NULL, save_period = NULL,
+  save_name = "xgboost.model", xgb_model = NULL, callbacks = list(),
+  ...)
 }
 \arguments{
 \item{params}{the list of parameters. 
@@ -65,7 +41,6 @@ xgboost(
   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
-  \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 }
 
 2.2. Parameter for Linear Booster
@@ -81,7 +56,7 @@ xgboost(
 \itemize{
 \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
   \itemize{
-    \item \code{reg:squarederror} Regression with squared loss (Default).
+    \item \code{reg:linear} linear regression (Default).
     \item \code{reg:logistic} logistic regression.
     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
@@ -111,7 +86,7 @@ the performance of each round's model on mat1 and mat2.}
 \item{obj}{customized objective function. Returns gradient and second order 
 gradient with given prediction and dtrain.}
 
-\item{feval}{customized evaluation function. Returns
+\item{feval}{custimized evaluation function. Returns 
 \code{list(metric='metric-name', value='metric-value')} with given 
 prediction and dtrain.}
 
@@ -165,14 +140,14 @@ An object of class \code{xgb.Booster} with the following elements:
   \item \code{handle} a handle (pointer) to the xgboost model in memory.
   \item \code{raw} a cached memory dump of the xgboost model saved as R's \code{raw} type.
   \item \code{niter} number of boosting iterations.
-  \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
+  \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
         first column corresponding to iteration number and the rest corresponding to evaluation
         metrics' values. It is created by the \code{\link{cb.evaluation.log}} callback.
   \item \code{call} a function call.
   \item \code{params} parameters that were passed to the xgboost library. Note that it does not 
         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
   \item \code{callbacks} callback functions that were either automatically assigned or 
-        explicitly passed.
+        explicitely passed.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration, 
@@ -181,7 +156,7 @@ An object of class \code{xgb.Booster} with the following elements:
   \item \code{best_score} the best evaluation metric value during early stopping.
         (only available with early stopping).
   \item \code{feature_names} names of the training dataset features
-        (only when column names were defined in training data).
+        (only when comun names were defined in training data).
   \item \code{nfeatures} number of features in training data.
 }
 }
@@ -203,7 +178,7 @@ The evaluation metric is chosen automatically by Xgboost (according to the objec
 when the \code{eval_metric} parameter is not provided.
 User may set one or several \code{eval_metric} parameters. 
 Note that when using a customized metric, only this single metric can be used.
-The following is the list of built-in metrics for which Xgboost provides optimized implementation:
+The folloiwing is the list of built-in metrics for which Xgboost provides optimized implementation:
   \itemize{
      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
@@ -235,7 +210,7 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:
-param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2, 
               objective = "binary:logistic", eval_metric = "auc")
 bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 
@@ -256,12 +231,12 @@ evalerror <- function(preds, dtrain) {
 
 # These functions could be used by passing them either:
 #  as 'objective' and 'eval_metric' parameters in the params list:
-param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2, 
               objective = logregobj, eval_metric = evalerror)
 bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 
 #  or through the ... arguments:
-param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2)
+param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2)
 bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
                  objective = logregobj, eval_metric = evalerror)
 
@@ -271,7 +246,7 @@ bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
 
 
 ## An xgb.train example of using variable learning rates at each iteration:
-param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
               objective = "binary:logistic", eval_metric = "auc")
 my_etas <- list(eta = c(0.5, 0.1))
 bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,

R-package/man/xgb.unserialize.Rd

@@ -1,14 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.unserialize.R
-\name{xgb.unserialize}
-\alias{xgb.unserialize}
-\title{Load the instance back from \code{\link{xgb.serialize}}}
-\usage{
-xgb.unserialize(buffer)
-}
-\arguments{
-\item{buffer}{the buffer containing booster instance saved by \code{\link{xgb.serialize}}}
-}
-\description{
-Load the instance back from \code{\link{xgb.serialize}}
-}

R-package/src/Makevars.in

@@ -17,8 +17,8 @@ endif
 $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
-PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ @ENDIAN_FLAG@ -pthread
-PKG_LIBS = @OPENMP_CXXFLAGS@ @OPENMP_LIB@ @ENDIAN_FLAG@ @BACKTRACE_LIB@ -pthread
+PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ -pthread
+PKG_LIBS = @OPENMP_CXXFLAGS@ -pthread
 OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o\
          $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o\
          $(PKGROOT)/rabit/src/engine_empty.o $(PKGROOT)/rabit/src/c_api.o

R-package/src/init.c

@@ -23,12 +23,8 @@ extern SEXP XGBoosterGetAttrNames_R(SEXP);
 extern SEXP XGBoosterGetAttr_R(SEXP, SEXP);
 extern SEXP XGBoosterLoadModelFromRaw_R(SEXP, SEXP);
 extern SEXP XGBoosterLoadModel_R(SEXP, SEXP);
-extern SEXP XGBoosterSaveJsonConfig_R(SEXP handle);
-extern SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value);
-extern SEXP XGBoosterSerializeToBuffer_R(SEXP handle);
-extern SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw);
 extern SEXP XGBoosterModelToRaw_R(SEXP);
-extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSaveModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSetAttr_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSetParam_R(SEXP, SEXP, SEXP);
@@ -53,12 +49,8 @@ static const R_CallMethodDef CallEntries[] = {
   {"XGBoosterGetAttr_R",          (DL_FUNC) &XGBoosterGetAttr_R,          2},
   {"XGBoosterLoadModelFromRaw_R", (DL_FUNC) &XGBoosterLoadModelFromRaw_R, 2},
   {"XGBoosterLoadModel_R",        (DL_FUNC) &XGBoosterLoadModel_R,        2},
-  {"XGBoosterSaveJsonConfig_R",   (DL_FUNC) &XGBoosterSaveJsonConfig_R,   1},
-  {"XGBoosterLoadJsonConfig_R",   (DL_FUNC) &XGBoosterLoadJsonConfig_R,   2},
-  {"XGBoosterSerializeToBuffer_R",     (DL_FUNC) &XGBoosterSerializeToBuffer_R,     1},
-  {"XGBoosterUnserializeFromBuffer_R", (DL_FUNC) &XGBoosterUnserializeFromBuffer_R, 2},
   {"XGBoosterModelToRaw_R",       (DL_FUNC) &XGBoosterModelToRaw_R,       1},
-  {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          5},
+  {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          4},
   {"XGBoosterSaveModel_R",        (DL_FUNC) &XGBoosterSaveModel_R,        2},
   {"XGBoosterSetAttr_R",          (DL_FUNC) &XGBoosterSetAttr_R,          3},
   {"XGBoosterSetParam_R",         (DL_FUNC) &XGBoosterSetParam_R,         3},

R-package/src/xgboost_R.cc

@@ -136,10 +136,9 @@ SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
     idxvec[i] = INTEGER(idxset)[i] - 1;
   }
   DMatrixHandle res;
-  CHECK_CALL(XGDMatrixSliceDMatrixEx(R_ExternalPtrAddr(handle),
-                                     BeginPtr(idxvec), len,
-                                     &res,
-                                     0));
+  CHECK_CALL(XGDMatrixSliceDMatrix(R_ExternalPtrAddr(handle),
+                                   BeginPtr(idxvec), len,
+                                   &res));
   ret = PROTECT(R_MakeExternalPtr(res, R_NilValue, R_NilValue));
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
@@ -166,9 +165,7 @@ SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
     for (int i = 0; i < len; ++i) {
       vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
     }
-    CHECK_CALL(XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle),
-                                    CHAR(asChar(field)),
-                                    BeginPtr(vec), len));
+    CHECK_CALL(XGDMatrixSetGroup(R_ExternalPtrAddr(handle), BeginPtr(vec), len));
   } else {
     std::vector<float> vec(len);
     #pragma omp parallel for schedule(static)
@@ -176,8 +173,8 @@ SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
       vec[i] = REAL(array)[i];
     }
     CHECK_CALL(XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle),
-                                     CHAR(asChar(field)),
-                                     BeginPtr(vec), len));
+                                   CHAR(asChar(field)),
+                                   BeginPtr(vec), len));
   }
   R_API_END();
   return R_NilValue;
@@ -295,26 +292,24 @@ SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
     vec_sptr.push_back(vec_names[i].c_str());
   }
   CHECK_CALL(XGBoosterEvalOneIter(R_ExternalPtrAddr(handle),
-                                  asInteger(iter),
-                                  BeginPtr(vec_dmats),
-                                  BeginPtr(vec_sptr),
-                                  len, &ret));
+                                asInteger(iter),
+                                BeginPtr(vec_dmats),
+                                BeginPtr(vec_sptr),
+                                len, &ret));
   R_API_END();
   return mkString(ret);
 }
 
-SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
-                        SEXP ntree_limit, SEXP training) {
+SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask, SEXP ntree_limit) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong olen;
   const float *res;
   CHECK_CALL(XGBoosterPredict(R_ExternalPtrAddr(handle),
-                              R_ExternalPtrAddr(dmat),
-                              asInteger(option_mask),
-                              asInteger(ntree_limit),
-                              asInteger(training),
-                              &olen, &res));
+                            R_ExternalPtrAddr(dmat),
+                            asInteger(option_mask),
+                            asInteger(ntree_limit),
+                            &olen, &res));
   ret = PROTECT(allocVector(REALSXP, olen));
   for (size_t i = 0; i < olen; ++i) {
     REAL(ret)[i] = res[i];
@@ -338,6 +333,15 @@ SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
   return R_NilValue;
 }
 
+SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
+  R_API_BEGIN();
+  CHECK_CALL(XGBoosterLoadModelFromBuffer(R_ExternalPtrAddr(handle),
+                                          RAW(raw),
+                                          length(raw)));
+  R_API_END();
+  return R_NilValue;
+}
+
 SEXP XGBoosterModelToRaw_R(SEXP handle) {
   SEXP ret;
   R_API_BEGIN();
@@ -353,57 +357,6 @@ SEXP XGBoosterModelToRaw_R(SEXP handle) {
   return ret;
 }
 
-SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
-  R_API_BEGIN();
-  CHECK_CALL(XGBoosterLoadModelFromBuffer(R_ExternalPtrAddr(handle),
-                                          RAW(raw),
-                                          length(raw)));
-  R_API_END();
-  return R_NilValue;
-}
-
-SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
-  const char* ret;
-  R_API_BEGIN();
-  bst_ulong len {0};
-  CHECK_CALL(XGBoosterSaveJsonConfig(R_ExternalPtrAddr(handle),
-                                     &len,
-                                     &ret));
-  R_API_END();
-  return mkString(ret);
-}
-
-SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
-  R_API_BEGIN();
-  XGBoosterLoadJsonConfig(R_ExternalPtrAddr(handle), CHAR(asChar(value)));
-  R_API_END();
-  return R_NilValue;
-}
-
-SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
-  SEXP ret;
-  R_API_BEGIN();
-  bst_ulong out_len;
-  const char *raw;
-  CHECK_CALL(XGBoosterSerializeToBuffer(R_ExternalPtrAddr(handle), &out_len, &raw));
-  ret = PROTECT(allocVector(RAWSXP, out_len));
-  if (out_len != 0) {
-    memcpy(RAW(ret), raw, out_len);
-  }
-  R_API_END();
-  UNPROTECT(1);
-  return ret;
-}
-
-SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
-  R_API_BEGIN();
-  XGBoosterUnserializeFromBuffer(R_ExternalPtrAddr(handle),
-                                 RAW(raw),
-                                 length(raw));
-  R_API_END();
-  return R_NilValue;
-}
-
 SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_format) {
   SEXP out;
   R_API_BEGIN();

R-package/src/xgboost_R.h

@@ -1,6 +1,6 @@
 /*!
  * Copyright 2014 (c) by Contributors
- * \file xgboost_R.h
+ * \file xgboost_wrapper_R.h
  * \author Tianqi Chen
  * \brief R wrapper of xgboost
  */
@@ -148,10 +148,8 @@ XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evn
  * \param dmat data matrix
  * \param option_mask output_margin:1 predict_leaf:2
  * \param ntree_limit limit number of trees used in prediction
- * \param training Whether the prediction value is used for training.
  */
-XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
-                                SEXP ntree_limit, SEXP training);
+XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask, SEXP ntree_limit);
 /*!
  * \brief load model from existing file
  * \param handle handle
@@ -179,39 +177,9 @@ XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw);
  * \brief save model into R's raw array
  * \param handle handle
  * \return raw array
- */
+   */
 XGB_DLL SEXP XGBoosterModelToRaw_R(SEXP handle);
 
-/*!
- * \brief Save internal parameters as a JSON string
- * \param handle handle
- * \return JSON string
- */
-
-XGB_DLL SEXP XGBoosterSaveJsonConfig_R(SEXP handle);
-/*!
- * \brief Load the JSON string returnd by XGBoosterSaveJsonConfig_R
- * \param handle handle
- * \param value JSON string
- * \return R_NilValue
- */
-XGB_DLL SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value);
-
-/*!
-  * \brief Memory snapshot based serialization method.  Saves everything states
-  *        into buffer.
-  * \param handle handle to booster
-  */
-XGB_DLL SEXP XGBoosterSerializeToBuffer_R(SEXP handle);
-
-/*!
- * \brief Memory snapshot based serialization method.  Loads the buffer returned
- *        from `XGBoosterSerializeToBuffer'.
- * \param handle handle to booster
- * \return raw byte array
- */
-XGB_DLL SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw);
-
 /*!
  * \brief dump model into a string
  * \param handle handle

R-package/src/xgboost_custom.cc

@@ -3,7 +3,7 @@
 // to change behavior of libxgboost
 
 #include <xgboost/logging.h>
-#include "../../src/common/random.h"
+#include "src/common/random.h"
 #include "./xgboost_R.h"
 
 // redirect the messages to R's console.

R-package/tests/testthat/test_basic.R

@@ -35,87 +35,6 @@ test_that("train and predict binary classification", {
   expect_lt(abs(err_pred1 - err_log), 10e-6)
 })
 
-test_that("parameter validation works", {
-  p <- list(foo = "bar")
-  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"]) +
-    rnorm(10)
-  dtrain <- xgb.DMatrix(data=d, info = list(label=y))
-
-  correct <- function() {
-    params <- list(max_depth = 2, booster = "dart",
-                   rate_drop = 0.5, one_drop = TRUE,
-                   objective = "reg:squarederror")
-    xgb.train(params = params, data = dtrain, nrounds = nrounds)
-  }
-  expect_silent(correct())
-  incorrect <- function() {
-    params <- list(max_depth = 2, booster = "dart",
-                   rate_drop = 0.5, one_drop = TRUE,
-                   objective = "reg:squarederror",
-                   foo = "bar", bar = "foo")
-    output <- capture.output(
-      xgb.train(params = params, data = dtrain, nrounds = nrounds))
-    print(output)
-  }
-  expect_output(incorrect(), "bar, foo")
-})
-
-
-test_that("dart prediction works", {
-  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"]) +
-    rnorm(100)
-
-  set.seed(1994)
-  booster_by_xgboost <- xgboost(data = d, label = y, max_depth = 2, booster = "dart",
-                                rate_drop = 0.5, one_drop = TRUE,
-                                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)))
-
-  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)))
-
-  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"
-                                 ),
-                                data = dtrain,
-                                nrounds = nrounds
-                                )
-  pred_by_train_0 <- predict(booster_by_train, newdata = dtrain, ntreelimit = 0)
-  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)))
-})
-
 test_that("train and predict softprob", {
   lb <- as.numeric(iris$Species) - 1
   set.seed(11)
@@ -252,21 +171,6 @@ test_that("training continuation works", {
   expect_equal(dim(bst2$evaluation_log), c(2, 2))
 })
 
-test_that("model serialization works", {
-  out_path <- "model_serialization"
-  dtrain <- xgb.DMatrix(train$data, label = train$label)
-  watchlist = list(train=dtrain)
-  param <- list(objective = "binary:logistic")
-  booster <- xgb.train(param, dtrain, nrounds = 4, watchlist)
-  raw <- xgb.serialize(booster)
-  saveRDS(raw, out_path)
-  raw <- readRDS(out_path)
-
-  loaded <- xgb.unserialize(raw)
-  raw_from_loaded <- xgb.serialize(loaded)
-  expect_equal(raw, raw_from_loaded)
-  file.remove(out_path)
-})
 
 test_that("xgb.cv works", {
   set.seed(11)
@@ -287,20 +191,6 @@ test_that("xgb.cv works", {
   expect_false(is.null(cv$call))
 })
 
-test_that("xgb.cv works with stratified folds", {
-  dtrain <- xgb.DMatrix(train$data, label = train$label)
-  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)
-  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)
-  # Stratified folds should result in a different evaluation logs
-  expect_true(all(cv$evaluation_log[, test_error_mean] != cv2$evaluation_log[, test_error_mean]))
-})
-
 test_that("train and predict with non-strict classes", {
   # standard dense matrix input
   train_dense <- as.matrix(train$data)
@@ -357,28 +247,18 @@ test_that("colsample_bytree works", {
   test_y <- as.numeric(rowSums(test_x) > 0)
   colnames(train_x) <- paste0("Feature_", sprintf("%03d", 1:100))
   colnames(test_x) <- paste0("Feature_", sprintf("%03d", 1:100))
-  dtrain <- xgb.DMatrix(train_x, label = train_y)
+   dtrain <- xgb.DMatrix(train_x, label = train_y)
   dtest <- xgb.DMatrix(test_x, label = test_y)
   watchlist <- list(train = dtrain, eval = dtest)
-  ## Use colsample_bytree = 0.01, so that roughly one out of 100 features is chosen for
-  ## each tree
-  param <- list(max_depth = 2, eta = 0, nthread = 2,
+   # Use colsample_bytree = 0.01, so that roughly one out of 100 features is
+  # chosen for each tree
+  param <- list(max_depth = 2, eta = 0, silent = 1, nthread = 2,
                 colsample_bytree = 0.01, objective = "binary:logistic",
                 eval_metric = "auc")
-  set.seed(2)
+   set.seed(2)
   bst <- xgb.train(param, dtrain, nrounds = 100, watchlist, verbose = 0)
   xgb.importance(model = bst)
   # If colsample_bytree works properly, a variety of features should be used
   # in the 100 trees
   expect_gte(nrow(xgb.importance(model = bst)), 30)
 })
-
-test_that("Configuration works", {
-  bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-                 eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic",
-                 eval_metric = 'error', eval_metric = 'auc', eval_metric = "logloss")
-  config <- xgb.config(bst)
-  xgb.config(bst) <- config
-  reloaded_config <- xgb.config(bst)
-  expect_equal(config, reloaded_config);
-})

R-package/tests/testthat/test_callbacks.R

@@ -184,9 +184,6 @@ test_that("cb.save.model works as expected", {
   expect_equal(xgb.ntree(b1), 1)
   b2 <- xgb.load('xgboost_02.model')
   expect_equal(xgb.ntree(b2), 2)
-
-  xgb.config(b2) <- xgb.config(bst)
-  expect_equal(xgb.config(bst), xgb.config(b2))
   expect_equal(bst$raw, b2$raw)
 
   # save_period = 0 saves the last iteration's model
@@ -194,7 +191,6 @@ test_that("cb.save.model works as expected", {
                    save_period = 0)
   expect_true(file.exists('xgboost.model'))
   b2 <- xgb.load('xgboost.model')
-  xgb.config(b2) <- xgb.config(bst)
   expect_equal(bst$raw, b2$raw)
   
   for (f in files) if (file.exists(f)) file.remove(f)
@@ -222,15 +218,6 @@ test_that("early stopping xgb.train works", {
                       early_stopping_rounds = 3, maximize = FALSE, verbose = 0)
   )
   expect_equal(bst$evaluation_log, bst0$evaluation_log)
-
-  xgb.save(bst, "model.bin")
-  loaded <- xgb.load("model.bin")
-
-  expect_false(is.null(loaded$best_iteration))
-  expect_equal(loaded$best_iteration, bst$best_ntreelimit)
-  expect_equal(loaded$best_ntreelimit, bst$best_ntreelimit)
-
-  file.remove("model.bin")
 })
 
 test_that("early stopping using a specific metric works", {
@@ -249,7 +236,7 @@ test_that("early stopping using a specific metric works", {
   expect_equal(length(pred), 1611)
   logloss_pred <- sum(-ltest * log(pred) - (1 - ltest) * log(1 - pred)) / length(ltest)
   logloss_log <- bst$evaluation_log[bst$best_iteration, test_logloss]
-  expect_equal(logloss_log, logloss_pred, tolerance = 1e-5)
+  expect_equal(logloss_log, logloss_pred, tolerance = 5e-6)
 })
 
 test_that("early stopping xgb.cv works", {
@@ -298,8 +285,7 @@ test_that("prediction in early-stopping xgb.cv works", {
   set.seed(11)
   expect_output(
     cv <- xgb.cv(param, dtrain, nfold = 5, eta = 0.1, nrounds = 20,
-                 early_stopping_rounds = 5, maximize = FALSE, stratified = FALSE,
-                 prediction = TRUE)
+                 early_stopping_rounds = 5, maximize = FALSE, prediction = TRUE)
   , "Stopping. Best iteration")
   
   expect_false(is.null(cv$best_iteration))

R-package/tests/testthat/test_custom_objective.R

@@ -31,6 +31,7 @@ num_round <- 2
 test_that("custom objective works", {
   bst <- xgb.train(param, dtrain, num_round, watchlist)
   expect_equal(class(bst), "xgb.Booster")
+  expect_equal(length(bst$raw), 1094)
   expect_false(is.null(bst$evaluation_log))
   expect_false(is.null(bst$evaluation_log$eval_error))
   expect_lt(bst$evaluation_log[num_round, eval_error], 0.03)
@@ -57,21 +58,5 @@ test_that("custom objective using DMatrix attr works", {
   param$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$Species) - 1
-  dtrain <- xgb.DMatrix(data = data, label = label)
-  nclasses <- 3
-
-  fake_softprob <- function(preds, dtrain) {
-    expect_true(all(matrix(preds) == 0.5))
-    grad <- rnorm(dim(as.matrix(preds))[1])
-    expect_equal(dim(data)[1] * nclasses, dim(as.matrix(preds))[1])
-    hess <- rnorm(dim(as.matrix(preds))[1])
-    return (list(grad = grad, hess = hess))
-  }
-  param$objective = fake_softprob
-  bst <- xgb.train(param, dtrain, 1, num_class=nclasses)
+  expect_equal(length(bst$raw), 1094)
 })

R-package/tests/testthat/test_dmatrix.R

@@ -50,12 +50,6 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
   labels <- getinfo(dtest, 'label')
   expect_equal(test_label, getinfo(dtest, 'label'))
   
-  expect_true(setinfo(dtest, 'label_lower_bound', test_label))
-  expect_equal(test_label, getinfo(dtest, 'label_lower_bound'))
-
-  expect_true(setinfo(dtest, 'label_upper_bound', test_label))
-  expect_equal(test_label, getinfo(dtest, 'label_upper_bound'))
-
   expect_true(length(getinfo(dtest, 'weight')) == 0)
   expect_true(length(getinfo(dtest, 'base_margin')) == 0)
 
@@ -65,7 +59,7 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
   expect_error(setinfo(dtest, 'group', test_label))
   
   # providing character values will give a warning
-  expect_warning(setinfo(dtest, 'weight', rep('a', nrow(test_data))))
+  expect_warning( setinfo(dtest, 'weight', rep('a', nrow(test_data))) )
   
   # any other label should error
   expect_error(setinfo(dtest, 'asdf', test_label))

R-package/tests/testthat/test_glm.R

@@ -40,7 +40,7 @@ test_that("gblinear works", {
   expect_lt(bst$evaluation_log$eval_error[2], ERR_UL)
 
   bst <- xgb.train(param, dtrain, n, watchlist, verbose = VERB, feature_selector = 'thrifty',
-                   top_k = 50, callbacks = list(cb.gblinear.history(sparse = TRUE)))
+                   top_n = 50, callbacks = list(cb.gblinear.history(sparse = TRUE)))
   expect_lt(bst$evaluation_log$eval_error[n], ERR_UL)
   h <- xgb.gblinear.history(bst)
   expect_equal(dim(h), c(n, ncol(dtrain) + 1))

R-package/tests/testthat/test_helpers.R

@@ -7,8 +7,8 @@ require(vcd, quietly = TRUE)
 
 float_tolerance = 5e-6
 
-# disable some tests for 32-bit environment
-flag_32bit = .Machine$sizeof.pointer != 8
+# disable some tests for Win32
+win32_flag = .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
 
 set.seed(1982)
 data(Arthritis)
@@ -44,7 +44,7 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 
 
 test_that("xgb.dump works", {
-  if (!flag_32bit)
+  if (!win32_flag)
     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 = T))
@@ -54,7 +54,7 @@ test_that("xgb.dump works", {
   # JSON format
   dmp <- xgb.dump(bst.Tree, dump_format = "json")
   expect_length(dmp, 1)
-  if (!flag_32bit)
+  if (!win32_flag)
     expect_length(grep('nodeid', strsplit(dmp, '\n')[[1]]), 188)
 })
 
@@ -142,44 +142,6 @@ test_that("predict feature contributions works", {
   }
 })
 
-test_that("SHAPs sum to predictions, with or without DART", {
-  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"]) +
-    rnorm(100)
-  nrounds <- 30
-
-  for (booster in list("gbtree", "dart")) {
-    fit <- xgboost(
-      params = c(
-        list(
-          booster = booster,
-          objective = "reg:squarederror",
-          eval_metric = "rmse"),
-        if (booster == "dart")
-          list(rate_drop = .01, one_drop = T)),
-      data = d,
-      label = y,
-      nrounds = nrounds)
-
-    pr <- function(...)
-      predict(fit, newdata = d, ...)
-    pred <- pr()
-    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)
-  }
-})
-
 test_that("xgb-attribute functionality", {
   val <- "my attribute value"
   list.val <- list(my_attr=val, a=123, b='ok')
@@ -201,7 +163,6 @@ test_that("xgb-attribute functionality", {
   # serializing:
   xgb.save(bst.Tree, 'xgb.model')
   bst <- xgb.load('xgb.model')
-  if (file.exists('xgb.model')) file.remove('xgb.model')
   expect_equal(xgb.attr(bst, "my_attr"), val)
   expect_equal(xgb.attributes(bst), list.ch)
   # deletion:
@@ -238,12 +199,10 @@ if (grepl('Windows', Sys.info()[['sysname']]) ||
 test_that("xgb.Booster serializing as R object works", {
   saveRDS(bst.Tree, 'xgb.model.rds')
   bst <- readRDS('xgb.model.rds')
-  if (file.exists('xgb.model.rds')) file.remove('xgb.model.rds')
   dtrain <- xgb.DMatrix(sparse_matrix, label = label)
   expect_equal(predict(bst.Tree, dtrain), predict(bst, dtrain), tolerance = float_tolerance)
   expect_equal(xgb.dump(bst.Tree), xgb.dump(bst))
   xgb.save(bst, 'xgb.model')
-  if (file.exists('xgb.model')) file.remove('xgb.model')
   nil_ptr <- new("externalptr")
   class(nil_ptr) <- "xgb.Booster.handle"
   expect_true(identical(bst$handle, nil_ptr))
@@ -256,7 +215,7 @@ test_that("xgb.model.dt.tree works with and without feature names", {
   names.dt.trees <- c("Tree", "Node", "ID", "Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
   dt.tree <- xgb.model.dt.tree(feature_names = feature.names, model = bst.Tree)
   expect_equal(names.dt.trees, names(dt.tree))
-  if (!flag_32bit)
+  if (!win32_flag)
     expect_equal(dim(dt.tree), c(188, 10))
   expect_output(str(dt.tree), 'Feature.*\\"Age\\"')
 
@@ -283,7 +242,7 @@ test_that("xgb.model.dt.tree throws error for gblinear", {
 
 test_that("xgb.importance works with and without feature names", {
   importance.Tree <- xgb.importance(feature_names = feature.names, model = bst.Tree)
-  if (!flag_32bit)
+  if (!win32_flag)
     expect_equal(dim(importance.Tree), c(7, 4))
   expect_equal(colnames(importance.Tree), c("Feature", "Gain", "Cover", "Frequency"))
   expect_output(str(importance.Tree), 'Feature.*\\"Age\\"')

R-package/tests/testthat/test_interaction_constraints.R

@@ -17,39 +17,22 @@ test_that("interaction constraints for regression", {
   
   # 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)
-    return(predict(bst, tmat))
-  })
+	preds <- lapply(c(1,2,3), function(x){
+		tmat <- matrix(c(x1,x2,rep(x,1000)), ncol=3)
+		return(predict(bst, tmat))
+	})
 
   # Check incrementing x3 has the same effect on all observations
   #   since x3 is constrained to be independent of x1 and x2
   #   and all observations start off from the same x3 value
-  diff1 <- preds[[2]] - preds[[1]]
-  test1 <- all(abs(diff1 - diff1[1]) < 1e-4)
+	diff1 <- preds[[2]] - preds[[1]]
+	test1 <- all(abs(diff1 - diff1[1]) < 1e-4)
 	
-  diff2 <- preds[[3]] - preds[[2]]
-  test2 <- all(abs(diff2 - diff2[1]) < 1e-4)
+	diff2 <- preds[[3]] - preds[[2]]
+	test2 <- all(abs(diff2 - diff2[1]) < 1e-4)
 	
   expect_true({
     test1 & test2
   }, "Interaction Contraint Satisfied")
-})
-
-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
-
-  d <- matrix(rexp(rows, rate=.1), nrow=rows, ncol=cols)
-  y <- rnorm(rows)
-
-  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)
-  expect_equal(xgb.save.raw(with_inc), xgb.save.raw(without_inc))
+  
 })

R-package/tests/testthat/test_interactions.R

@@ -98,7 +98,7 @@ test_that("SHAP contribution values are not NAN", {
   fit <- xgboost(
     verbose = 0,
     params = list(
-      objective = "reg:squarederror",
+      objective = "reg:linear",
       eval_metric = "rmse"),
     data = as.matrix(subset(d, fold == 2)[, ivs]),
     label = subset(d, fold == 2)$y,

R-package/vignettes/discoverYourData.Rmd

@@ -138,7 +138,7 @@ levels(df[,Treatment])
 
 Next step, we will transform the categorical data to dummy variables.
 Several encoding methods exist, e.g., [one-hot encoding](http://en.wikipedia.org/wiki/One-hot) is a common approach.
-We will use the [dummy contrast coding](http://www.ats.ucla.edu/stat/r/library/contrast_coding.htm#dummy) which is popular because it produces "full rank" encoding (also see [this blog post by Max Kuhn](http://appliedpredictivemodeling.com/blog/2013/10/23/the-basics-of-encoding-categorical-data-for-predictive-models)).
+We will use the [dummy contrast coding](http://www.ats.ucla.edu/stat/r/library/contrast_coding.htm#dummy) which is popular because it producess "full rank" encoding (also see [this blog post by Max Kuhn](http://appliedpredictivemodeling.com/blog/2013/10/23/the-basics-of-encoding-categorical-data-for-predictive-models)).
 
 The purpose is to transform each value of each *categorical* feature into a *binary* feature `{0, 1}`.
 
@@ -268,7 +268,7 @@ c2 <- chisq.test(df$Age, output_vector)
 print(c2)
 ```
 
-Pearson correlation between Age and illness disappearing is **`r round(c2$statistic, 2 )`**.
+Pearson correlation between Age and illness disapearing is **`r round(c2$statistic, 2 )`**.
 
 ```{r, warning=FALSE, message=FALSE}
 c2 <- chisq.test(df$AgeDiscret, output_vector)

R-package/vignettes/xgboostPresentation.Rmd

@@ -313,7 +313,7 @@ Until now, all the learnings we have performed were based on boosting trees. **X
 bst <- xgb.train(data=dtrain, booster = "gblinear", max_depth=2, nthread = 2, nrounds=2, watchlist=watchlist, eval_metric = "error", eval_metric = "logloss", objective = "binary:logistic")
 ```
 
-In this specific case, *linear boosting* gets slightly better performance metrics than decision trees based algorithm.
+In this specific case, *linear boosting* gets sligtly better performance metrics than decision trees based algorithm.
 
 In simple cases, it will happen because there is nothing better than a linear algorithm to catch a linear link. However, decision trees are much better to catch a non linear link between predictors and outcome. Because there is no silver bullet, we advise you to check both algorithms with your own datasets to have an idea of what to use.
 
@@ -410,7 +410,7 @@ In some very specific cases, like when you want to pilot **XGBoost** from `caret
 
 ```{r saveLoadRBinVectorModel, message=F, warning=F}
 # save model to R's raw vector
-rawVec <- xgb.serialize(bst)
+rawVec <- xgb.save.raw(bst)
 
 # print class
 print(class(rawVec))

R-package/vignettes/xgboostfromJSON.Rmd

@@ -1,189 +0,0 @@
----
-title: "XGBoost from JSON"
-output:
-  rmarkdown::html_vignette:
-    number_sections: yes
-    toc: yes
-author: Roland Stevenson
-vignette: >
-  %\VignetteIndexEntry{XGBoost from JSON}
-  %\VignetteEngine{knitr::rmarkdown}
-  \usepackage[utf8]{inputenc}
----
-
-XGBoost from JSON
-=================
-
-## Introduction
-
-The purpose of this Vignette is to show you how to correctly load and work with an **Xgboost** model that has been dumped to JSON.  **Xgboost** internally converts all data to [32-bit floats](https://en.wikipedia.org/wiki/Single-precision_floating-point_format), and the values dumped to JSON are decimal representations of these values.  When working with a model that has been parsed from a JSON file, care must be taken to correctly treat:
-
-- the input data, which should be converted to 32-bit floats
-- any 32-bit floats that were stored in JSON as decimal representations
-- any calculations must be done with 32-bit mathematical operators
-
-## Setup
-
-For the purpose of this tutorial we will load the xgboost, jsonlite, and float packages.  We'll also set `digits=22` in our options in case we want to inspect many digits of our results.
-
-```{r}
-require(xgboost)
-require(jsonlite)
-require(float)
-options(digits=22)
-```
-
-We will create a toy binary logistic model based on the example first provided [here](https://github.com/dmlc/xgboost/issues/3960), so that we can easily understand the structure of the dumped JSON model object.  This will allow us to understand where discrepancies can occur and how they should be handled.
-
-```{r}
-dates <- c(20180130, 20180130, 20180130,
-           20180130, 20180130, 20180130,
-           20180131, 20180131, 20180131,
-           20180131, 20180131, 20180131,
-           20180131, 20180131, 20180131,
-           20180134, 20180134, 20180134)
-
-labels <- c(1, 1, 1,
-            1, 1, 1,
-            0, 0, 0,
-            0, 0, 0,
-            0, 0, 0,
-            0, 0, 0)
-
-data <- data.frame(dates = dates, labels=labels)
-
-bst <- xgboost(
-  data = as.matrix(data$dates), 
-  label = labels,
-  nthread = 2,
-  nrounds = 1,
-  objective = "binary:logistic",
-  missing = NA,
-  max_depth = 1
-)
-```
-
-## Comparing results
-We will now dump the model to JSON and attempt to illustrate a variety of issues that can arise, and how to properly deal with them.
-
-First let's dump the model to JSON:
-
-```{r}
-bst_json <- xgb.dump(bst, with_stats = FALSE, dump_format='json')
-bst_from_json <- fromJSON(bst_json, simplifyDataFrame = FALSE)
-node <- bst_from_json[[1]]
-cat(bst_json)
-```
-
-The tree JSON shown by the above code-chunk tells us that if the data is less than 20180132, the tree will output the value in the first leaf.  Otherwise it will output the value in the second leaf.  Let's try to reproduce this manually with the data we have and confirm that it matches the model predictions we've already calculated.
-
-```{r}
-bst_preds_logodds <- predict(bst,as.matrix(data$dates), outputmargin = TRUE)
-
-# calculate the logodds values using the JSON representation
-bst_from_json_logodds <- ifelse(data$dates<node$split_condition,
-                                node$children[[1]]$leaf,
-                                node$children[[2]]$leaf)
-
-bst_preds_logodds
-bst_from_json_logodds
-
-# test that values are equal
-bst_preds_logodds == bst_from_json_logodds
-
-```
-None are equal.  What happened?
-
-At this stage two things happened:
-
-- input data was not converted to 32-bit floats
-- the JSON variables were not converted to 32-bit floats
-
-### Lesson 1: All data is 32-bit floats
-
-> When working with imported JSON, all data must be converted to 32-bit floats
-
-To explain this, let's repeat the comparison and round to two decimals:
-
-```{r}
-round(bst_preds_logodds,2) == round(bst_from_json_logodds,2)
-```
-
-If we round to two decimals, we see that only the elements related to data values of `20180131` don't agree.  If we convert the data to floats, they agree:
-
-```{r}
-# now convert the dates to floats first
-bst_from_json_logodds <- ifelse(fl(data$dates)<node$split_condition,
-                                node$children[[1]]$leaf,
-                                node$children[[2]]$leaf)
-
-# test that values are equal
-round(bst_preds_logodds,2) == round(bst_from_json_logodds,2)
-```
-
-What's the lesson?  If we are going to work with an imported JSON model, any data must be converted to floats first.  In this case, since '20180131' cannot be represented as a 32-bit float, it is rounded up to 20180132, as shown here:
-
-```{r}
-fl(20180131)
-```
-
-
-### Lesson 2: JSON parameters are 32-bit floats
-
-> All JSON parameters stored as floats must be converted to floats.
-
-Let's now say we do care about numbers past the first two decimals.
-
-```{r}
-# test that values are equal
-bst_preds_logodds == bst_from_json_logodds
-```
-
-None are exactly equal.  What happened?  Although we've converted the data to 32-bit floats, we also need to convert the JSON parameters to 32-bit floats.  Let's do this:
-
-```{r}
-# now convert the dates to floats first
-bst_from_json_logodds <- ifelse(fl(data$dates)<fl(node$split_condition),
-                                as.numeric(fl(node$children[[1]]$leaf)),
-                                as.numeric(fl(node$children[[2]]$leaf)))
-
-# test that values are equal
-bst_preds_logodds == bst_from_json_logodds
-```
-All equal.  What's the lesson?  If we are going to work with an imported JSON model, any JSON parameters that were stored as floats must also be converted to floats first.
-
-### Lesson 3: Use 32-bit math
-
-> Always use 32-bit numbers and operators
-
-We were able to get the log-odds to agree, so now let's manually calculate the sigmoid of the log-odds.  This should agree with the xgboost predictions.
-
-
-```{r}
-bst_preds <- predict(bst,as.matrix(data$dates))
-
-# calculate the predictions casting doubles to floats
-bst_from_json_preds <- ifelse(fl(data$dates)<fl(node$split_condition),
-                              as.numeric(1/(1+exp(-1*fl(node$children[[1]]$leaf)))),
-                              as.numeric(1/(1+exp(-1*fl(node$children[[2]]$leaf))))
-)
-
-# test that values are equal
-bst_preds == bst_from_json_preds
-```
-
-None are exactly equal again.  What is going on here?  Well, since we are using the value `1` in the calcuations, we have introduced a double into the calculation.  Because of this, all float values are promoted to 64-bit doubles and the 64-bit version of the exponentiation operator `exp` is also used.  On the other hand, xgboost uses the 32-bit version of the exponentation operator in its [sigmoid function](https://github.com/dmlc/xgboost/blob/54980b8959680a0da06a3fc0ec776e47c8cbb0a1/src/common/math.h#L25-L27).
-
-How do we fix this?  We have to ensure we use the correct datatypes everywhere and the correct operators.  If we use only floats, the float library that we have loaded will ensure the 32-bit float exponention operator is applied. 
-```{r}
-# calculate the predictions casting doubles to floats
-bst_from_json_preds <- ifelse(fl(data$dates)<fl(node$split_condition),
-                              as.numeric(fl(1)/(fl(1)+exp(fl(-1)*fl(node$children[[1]]$leaf)))),
-                              as.numeric(fl(1)/(fl(1)+exp(fl(-1)*fl(node$children[[2]]$leaf))))
-)
-
-# test that values are equal
-bst_preds == bst_from_json_preds
-```
-
-All equal.  What's the lesson?  We have to ensure that all calculations are done with 32-bit floating point operators if we want to reproduce the results that we see with xgboost.

README.md

@@ -1,13 +1,12 @@
 <img src=https://raw.githubusercontent.com/dmlc/dmlc.github.io/master/img/logo-m/xgboost.png width=135/>  eXtreme Gradient Boosting
 ===========
 [![Build Status](https://xgboost-ci.net/job/xgboost/job/master/badge/icon?style=plastic)](https://xgboost-ci.net/blue/organizations/jenkins/xgboost/activity)
-[![Build Status](https://img.shields.io/travis/dmlc/xgboost.svg?label=build&logo=travis&branch=master)](https://travis-ci.org/dmlc/xgboost)
+[![Build Status](https://travis-ci.org/dmlc/xgboost.svg?branch=master)](https://travis-ci.org/dmlc/xgboost)
 [![Build Status](https://ci.appveyor.com/api/projects/status/5ypa8vaed6kpmli8?svg=true)](https://ci.appveyor.com/project/tqchen/xgboost)
 [![Documentation Status](https://readthedocs.org/projects/xgboost/badge/?version=latest)](https://xgboost.readthedocs.org)
 [![GitHub license](http://dmlc.github.io/img/apache2.svg)](./LICENSE)
 [![CRAN Status Badge](http://www.r-pkg.org/badges/version/xgboost)](http://cran.r-project.org/web/packages/xgboost)
 [![PyPI version](https://badge.fury.io/py/xgboost.svg)](https://pypi.python.org/pypi/xgboost/)
-[![Optuna](https://img.shields.io/badge/Optuna-integrated-blue)](https://optuna.org)
 
 [Community](https://xgboost.ai/community) |
 [Documentation](https://xgboost.readthedocs.org) |
@@ -18,50 +17,18 @@
 XGBoost is an optimized distributed gradient boosting library designed to be highly ***efficient***, ***flexible*** and ***portable***.
 It implements machine learning algorithms under the [Gradient Boosting](https://en.wikipedia.org/wiki/Gradient_boosting) framework.
 XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way.
-The same code runs on major distributed environment (Kubernetes, Hadoop, SGE, MPI, Dask) and can solve problems beyond billions of examples.
+The same code runs on major distributed environment (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.
 
 License
 -------
-© Contributors, 2019. Licensed under an [Apache-2](https://github.com/dmlc/xgboost/blob/master/LICENSE) license.
+© Contributors, 2016. Licensed under an [Apache-2](https://github.com/dmlc/xgboost/blob/master/LICENSE) license.
 
 Contribute to XGBoost
 ---------------------
 XGBoost has been developed and used by a group of active community members. Your help is very valuable to make the package better for everyone.
-Checkout the [Community Page](https://xgboost.ai/community).
+Checkout the [Community Page](https://xgboost.ai/community)
 
 Reference
 ---------
 - Tianqi Chen and Carlos Guestrin. [XGBoost: A Scalable Tree Boosting System](http://arxiv.org/abs/1603.02754). In 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016
 - XGBoost originates from research project at University of Washington.
-
-Sponsors
---------
-Become a sponsor and get a logo here. See details at [Sponsoring the XGBoost Project](https://xgboost.ai/sponsors). The funds are used to defray the cost of continuous integration and testing infrastructure (https://xgboost-ci.net).
-
-## Open Source Collective sponsors
-[![Backers on Open Collective](https://opencollective.com/xgboost/backers/badge.svg)](#backers) [![Sponsors on Open Collective](https://opencollective.com/xgboost/sponsors/badge.svg)](#sponsors)
-
-### Sponsors
-[[Become a sponsor](https://opencollective.com/xgboost#sponsor)]
-
-<!--<a href="https://opencollective.com/xgboost/sponsor/0/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/0/avatar.svg"></a>-->
-<a href="https://www.nvidia.com/en-us/" target="_blank"><img src="https://raw.githubusercontent.com/xgboost-ai/xgboost-ai.github.io/master/images/sponsors/nvidia.jpg" alt="NVIDIA" width="72" height="72"></a>
-<a href="https://opencollective.com/xgboost/sponsor/1/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/1/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/2/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/2/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/3/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/3/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/4/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/4/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/5/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/5/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/6/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/6/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/7/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/7/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/8/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/8/avatar.svg"></a>
-<a href="https://opencollective.com/xgboost/sponsor/9/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/9/avatar.svg"></a>
-
-### Backers
-[[Become a backer](https://opencollective.com/xgboost#backer)]
-
-<a href="https://opencollective.com/xgboost#backers" target="_blank"><img src="https://opencollective.com/xgboost/backers.svg?width=890"></a>
-
-## Other sponsors
-The sponsors in this list are donating cloud hours in lieu of cash donation.
-
-<a href="https://aws.amazon.com/" target="_blank"><img src="https://raw.githubusercontent.com/xgboost-ai/xgboost-ai.github.io/master/images/sponsors/aws.png" alt="Amazon Web Services" width="72" height="72"></a>

amalgamation/xgboost-all0.cc

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2015-2019 by Contributors.
+ * Copyright 2015 by Contributors.
  * \brief XGBoost Amalgamation.
  *  This offers an alternative way to compile the entire library from this single file.
  *
@@ -14,7 +14,6 @@
 #include "../src/metric/elementwise_metric.cc"
 #include "../src/metric/multiclass_metric.cc"
 #include "../src/metric/rank_metric.cc"
-#include "../src/metric/survival_metric.cc"
 
 // objectives
 #include "../src/objective/objective.cc"
@@ -22,32 +21,29 @@
 #include "../src/objective/multiclass_obj.cc"
 #include "../src/objective/rank_obj.cc"
 #include "../src/objective/hinge.cc"
-#include "../src/objective/aft_obj.cc"
 
 // gbms
 #include "../src/gbm/gbm.cc"
 #include "../src/gbm/gbtree.cc"
-#include "../src/gbm/gbtree_model.cc"
 #include "../src/gbm/gblinear.cc"
-#include "../src/gbm/gblinear_model.cc"
 
 // data
 #include "../src/data/data.cc"
+#include "../src/data/simple_csr_source.cc"
 #include "../src/data/simple_dmatrix.cc"
 #include "../src/data/sparse_page_raw_format.cc"
-#include "../src/data/ellpack_page.cc"
-#include "../src/data/ellpack_page_source.cc"
 
 // prediction
 #include "../src/predictor/predictor.cc"
 #include "../src/predictor/cpu_predictor.cc"
 
 #if DMLC_ENABLE_STD_THREAD
+#include "../src/data/sparse_page_source.cc"
 #include "../src/data/sparse_page_dmatrix.cc"
+#include "../src/data/sparse_page_writer.cc"
 #endif
 
-// trees
-#include "../src/tree/param.cc"
+// tress
 #include "../src/tree/split_evaluator.cc"
 #include "../src/tree/tree_model.cc"
 #include "../src/tree/tree_updater.cc"
@@ -58,7 +54,6 @@
 #include "../src/tree/updater_sync.cc"
 #include "../src/tree/updater_histmaker.cc"
 #include "../src/tree/updater_skmaker.cc"
-#include "../src/tree/constraints.cc"
 
 // linear
 #include "../src/linear/linear_updater.cc"
@@ -69,14 +64,8 @@
 #include "../src/learner.cc"
 #include "../src/logging.cc"
 #include "../src/common/common.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
 #include "../src/c_api/c_api.cc"

appveyor.yml

@@ -2,6 +2,10 @@ environment:
     R_ARCH: x64
     USE_RTOOLS: true
     matrix:
+        - target: msvc
+          ver: 2013
+          generator: "Visual Studio 12 2013 Win64"
+          configuration: Release
         - target: msvc
           ver: 2015
           generator: "Visual Studio 14 2015 Win64"
@@ -32,21 +36,15 @@ install:
     - set PATH=C:\msys64\mingw64\bin;C:\msys64\usr\bin;%PATH%
     - gcc -v
     - ls -l C:\
-    # Miniconda3
-    - call C:\Miniconda3-x64\Scripts\activate.bat
-    - conda info
+    # Miniconda2
+    - set PATH=;C:\Miniconda-x64;C:\Miniconda-x64\Scripts;%PATH%
     - where python
     - python --version
     # do python build for mingw and one of the msvc jobs
     - set DO_PYTHON=off
     - if /i "%target%" == "mingw" set DO_PYTHON=on
     - if /i "%target%_%ver%_%configuration%" == "msvc_2015_Release" set DO_PYTHON=on
-    - 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
-      )
-    - set PATH=C:\Miniconda3-x64\Library\bin\graphviz;%PATH%
+    - if /i "%DO_PYTHON%" == "on" conda install -y numpy scipy pandas matplotlib pytest scikit-learn graphviz python-graphviz
     # R: based on https://github.com/krlmlr/r-appveyor
     - ps: |
         if($env:target -eq 'rmingw' -or $env:target -eq 'rmsvc') {
@@ -54,10 +52,10 @@ install:
           Invoke-WebRequest https://raw.githubusercontent.com/krlmlr/r-appveyor/master/scripts/appveyor-tool.ps1 -OutFile "$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"
+          $BINARY_DEPS = "c('XML','igraph')"
+          cmd.exe /c "R.exe -q -e ""install.packages($BINARY_DEPS, repos='$CRAN', type='win.binary')"" 2>&1"
         }
 
 build_script:
@@ -94,7 +92,7 @@ build_script:
         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
+    - if /i "%target%" == "jvm" cd jvm-packages && mvn test -pl :xgboost4j
 
 test_script:
     - cd %APPVEYOR_BUILD_FOLDER%
@@ -102,7 +100,6 @@ test_script:
     # 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

build.sh

@@ -0,0 +1,51 @@
+#!/bin/bash
+# This is a simple script to make xgboost in MAC and Linux
+# Basically, it first try to make with OpenMP, if fails, disable OpenMP and make it again.
+# This will automatically make xgboost for MAC users who don't have OpenMP support.
+# In most cases, type make will give what you want.
+
+# See additional instruction in doc/build.md
+set -e
+
+if make; then
+    echo "Successfully build multi-thread xgboost"
+else
+
+    not_ready=0
+
+    if [[ ! -e ./rabit/Makefile ]]; then
+        echo ""
+        echo "Please init the rabit submodule:"
+        echo "git submodule update --init --recursive -- rabit"
+        not_ready=1
+    fi
+    
+    if [[ ! -e ./dmlc-core/Makefile ]]; then
+        echo ""
+        echo "Please init the dmlc-core submodule:"
+        echo "git submodule update --init --recursive -- dmlc-core"
+        not_ready=1
+    fi
+
+    if [[ "${not_ready}" == "1" ]]; then
+        echo ""
+        echo "Please fix the errors above and retry the build, or reclone the repository with:"
+        echo "git clone --recursive https://github.com/dmlc/xgboost.git"
+        echo ""
+        exit 1
+    fi
+
+
+    echo "-----------------------------"
+    echo "Building multi-thread xgboost failed"
+    echo "Start to build single-thread xgboost"
+    make clean_all
+    make config=make/minimum.mk
+    if [ $? -eq 0 ] ;then
+      echo "Successfully build single-thread xgboost"
+      echo "If you want multi-threaded version"
+      echo "See additional instructions in doc/build.md"
+    else
+      echo "Failed to build single-thread xgboost"
+    fi
+fi

cmake/Doc.cmake

@@ -1,16 +0,0 @@
-function (run_doxygen)
-  find_package(Doxygen REQUIRED)
-
-  if (NOT DOXYGEN_DOT_FOUND)
-    message(FATAL_ERROR "Command `dot` not found.  Please install graphviz.")
-  endif (NOT DOXYGEN_DOT_FOUND)
-
-  configure_file(
-    ${xgboost_SOURCE_DIR}/doc/Doxyfile.in
-    ${CMAKE_CURRENT_BINARY_DIR}/Doxyfile @ONLY)
-  add_custom_target( doc_doxygen ALL
-    COMMAND ${DOXYGEN_EXECUTABLE} ${CMAKE_CURRENT_BINARY_DIR}/Doxyfile
-    WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
-    COMMENT "Generate C APIs documentation."
-    VERBATIM)
-endfunction (run_doxygen)

cmake/FindPrefetchIntrinsics.cmake

@@ -1,22 +0,0 @@
-function (find_prefetch_intrinsics)
-  include(CheckCXXSourceCompiles)
-  check_cxx_source_compiles("
-  #include <xmmintrin.h>
-  int main() {
-    char data = 0;
-    const char* address = &data;
-    _mm_prefetch(address, _MM_HINT_NTA);
-    return 0;
-  }
-  " XGBOOST_MM_PREFETCH_PRESENT)
-  check_cxx_source_compiles("
-  int main() {
-    char data = 0;
-    const char* address = &data;
-    __builtin_prefetch(address, 0, 0);
-    return 0;
-  }
-  " XGBOOST_BUILTIN_PREFETCH_PRESENT)
-  set(XGBOOST_MM_PREFETCH_PRESENT ${XGBOOST_MM_PREFETCH_PRESENT} PARENT_SCOPE)
-  set(XGBOOST_BUILTIN_PREFETCH_PRESENT ${XGBOOST_BUILTIN_PREFETCH_PRESENT} PARENT_SCOPE)
-endfunction (find_prefetch_intrinsics)

cmake/Python_version.in

@@ -1 +0,0 @@
-@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@

cmake/Sanitizer.cmake

@@ -4,29 +4,24 @@
 #  enable_sanitizers("address;leak")
 
 # Add flags
-macro(enable_sanitizer sanitizer)
-  if(${sanitizer} MATCHES "address")
+macro(enable_sanitizer santizer)
+  if(${santizer} MATCHES "address")
     find_package(ASan REQUIRED)
     set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=address")
     link_libraries(${ASan_LIBRARY})
 
-  elseif(${sanitizer} MATCHES "thread")
+  elseif(${santizer} MATCHES "thread")
     find_package(TSan REQUIRED)
     set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=thread")
     link_libraries(${TSan_LIBRARY})
 
-  elseif(${sanitizer} MATCHES "leak")
+  elseif(${santizer} MATCHES "leak")
     find_package(LSan REQUIRED)
     set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=leak")
     link_libraries(${LSan_LIBRARY})
 
-  elseif(${sanitizer} MATCHES "undefined")
-    find_package(UBSan REQUIRED)
-    set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=undefined -fno-sanitize-recover=undefined")
-    link_libraries(${UBSan_LIBRARY})
-
   else()
-    message(FATAL_ERROR "Santizer ${sanitizer} not supported.")
+    message(FATAL_ERROR "Santizer ${santizer} not supported.")
   endif()
 endmacro()
 

cmake/Utils.cmake

@@ -1,3 +1,4 @@
+
 # Automatically set source group based on folder
 function(auto_source_group SOURCES)
 
@@ -17,10 +18,6 @@ endfunction(auto_source_group)
 function(msvc_use_static_runtime)
   if(MSVC)
       set(variables
-          CMAKE_C_FLAGS_DEBUG
-          CMAKE_C_FLAGS_MINSIZEREL
-          CMAKE_C_FLAGS_RELEASE
-          CMAKE_C_FLAGS_RELWITHDEBINFO
           CMAKE_CXX_FLAGS_DEBUG
           CMAKE_CXX_FLAGS_MINSIZEREL
           CMAKE_CXX_FLAGS_RELEASE
@@ -32,23 +29,6 @@ function(msvc_use_static_runtime)
               set(${variable} "${${variable}}"  PARENT_SCOPE)
           endif()
       endforeach()
-      set(variables
-          CMAKE_CUDA_FLAGS
-          CMAKE_CUDA_FLAGS_DEBUG
-          CMAKE_CUDA_FLAGS_MINSIZEREL
-          CMAKE_CUDA_FLAGS_RELEASE
-          CMAKE_CUDA_FLAGS_RELWITHDEBINFO
-      )
-      foreach(variable ${variables})
-          if(${variable} MATCHES "-MD")
-              string(REGEX REPLACE "-MD" "-MT" ${variable} "${${variable}}")
-              set(${variable} "${${variable}}"  PARENT_SCOPE)
-          endif()
-          if(${variable} MATCHES "/MD")
-              string(REGEX REPLACE "/MD" "/MT" ${variable} "${${variable}}")
-              set(${variable} "${${variable}}"  PARENT_SCOPE)
-          endif()
-      endforeach()
   endif()
 endfunction(msvc_use_static_runtime)
 
@@ -58,18 +38,9 @@ function(set_output_directory target dir)
 		RUNTIME_OUTPUT_DIRECTORY ${dir}
 		RUNTIME_OUTPUT_DIRECTORY_DEBUG ${dir}
 		RUNTIME_OUTPUT_DIRECTORY_RELEASE ${dir}
-		RUNTIME_OUTPUT_DIRECTORY_RELWITHDEBINFO ${dir}
-		RUNTIME_OUTPUT_DIRECTORY_MINSIZEREL ${dir}
 		LIBRARY_OUTPUT_DIRECTORY ${dir} 
 		LIBRARY_OUTPUT_DIRECTORY_DEBUG ${dir} 
 		LIBRARY_OUTPUT_DIRECTORY_RELEASE ${dir} 
-		LIBRARY_OUTPUT_DIRECTORY_RELWITHDEBINFO ${dir}
-		LIBRARY_OUTPUT_DIRECTORY_MINSIZEREL ${dir}
-		ARCHIVE_OUTPUT_DIRECTORY ${dir}
-		ARCHIVE_OUTPUT_DIRECTORY_DEBUG ${dir}
-		ARCHIVE_OUTPUT_DIRECTORY_RELEASE ${dir}
-		ARCHIVE_OUTPUT_DIRECTORY_RELWITHDEBINFO ${dir}
-		ARCHIVE_OUTPUT_DIRECTORY_MINSIZEREL ${dir}
 	)
 endfunction(set_output_directory)
 
@@ -86,14 +57,9 @@ endfunction(set_default_configuration_release)
 # Generate nvcc compiler flags given a list of architectures
 # Also generates PTX for the most recent architecture for forwards compatibility
 function(format_gencode_flags flags out)
-  if(CMAKE_CUDA_COMPILER_VERSION MATCHES "^([0-9]+\\.[0-9]+)")
-    set(CUDA_VERSION "${CMAKE_MATCH_1}")
-  endif()
   # Set up architecture flags
   if(NOT flags) 
-    if(CUDA_VERSION VERSION_GREATER_EQUAL "10.0")
-      set(flags "35;50;52;60;61;70;75")
-    elseif(CUDA_VERSION VERSION_GREATER_EQUAL "9.0")
+    if((CUDA_VERSION_MAJOR EQUAL 9) OR (CUDA_VERSION_MAJOR GREATER 9))
       set(flags "35;50;52;60;61;70")
     else()
       set(flags "35;50;52;60;61")
@@ -101,11 +67,11 @@ function(format_gencode_flags flags out)
   endif()
   # Generate SASS
   foreach(ver ${flags})
-    set(${out} "${${out}}--generate-code=arch=compute_${ver},code=sm_${ver};")
+    set(${out} "${${out}}-gencode arch=compute_${ver},code=sm_${ver};")
   endforeach()
   # Generate PTX for last architecture
   list(GET flags -1 ver)
-  set(${out} "${${out}}--generate-code=arch=compute_${ver},code=compute_${ver};")
+  set(${out} "${${out}}-gencode arch=compute_${ver},code=compute_${ver};")
   
   set(${out} "${${out}}" PARENT_SCOPE)
 endfunction(format_gencode_flags flags)
@@ -114,13 +80,9 @@ endfunction(format_gencode_flags flags)
 # if necessary, installs the main R package dependencies;
 # runs R CMD INSTALL.
 function(setup_rpackage_install_target rlib_target build_dir)
-  # backup cmake_install.cmake
-  install(CODE "file(COPY \"${build_dir}/R-package/cmake_install.cmake\"
-DESTINATION \"${build_dir}/bak\")")
-
   install(CODE "file(REMOVE_RECURSE \"${build_dir}/R-package\")")
   install(
-    DIRECTORY "${xgboost_SOURCE_DIR}/R-package"
+    DIRECTORY "${PROJECT_SOURCE_DIR}/R-package"
     DESTINATION "${build_dir}"
     REGEX "src/*" EXCLUDE
     REGEX "R-package/configure" EXCLUDE
@@ -136,8 +98,4 @@ DESTINATION \"${build_dir}/bak\")")
   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/Version.cmake

@@ -1,9 +0,0 @@
-function (write_version)
-  message(STATUS "xgboost VERSION: ${xgboost_VERSION}")
-  configure_file(
-    ${xgboost_SOURCE_DIR}/cmake/version_config.h.in
-    ${xgboost_SOURCE_DIR}/include/xgboost/version_config.h @ONLY)
-  configure_file(
-    ${xgboost_SOURCE_DIR}/cmake/Python_version.in
-    ${xgboost_SOURCE_DIR}/python-package/xgboost/VERSION @ONLY)
-endfunction (write_version)

cmake/build_config.h.in

@@ -0,0 +1,11 @@
+/*!
+ * Copyright 2019 by Contributors
+ * \file build_config.h
+ */
+#ifndef XGBOOST_BUILD_CONFIG_H_
+#define XGBOOST_BUILD_CONFIG_H_
+
+#cmakedefine XGBOOST_MM_PREFETCH_PRESENT
+#cmakedefine XGBOOST_BUILTIN_PREFETCH_PRESENT
+
+#endif  // XGBOOST_BUILD_CONFIG_H_

cmake/modules/FindASan.cmake

@@ -1,7 +1,7 @@
 set(ASan_LIB_NAME ASan)
 
 find_library(ASan_LIBRARY
-  NAMES libasan.so libasan.so.5 libasan.so.4 libasan.so.3 libasan.so.2 libasan.so.1 libasan.so.0
+  NAMES libasan.so libasan.so.4 libasan.so.3 libasan.so.2 libasan.so.1 libasan.so.0
   PATHS ${SANITIZER_PATH} /usr/lib64 /usr/lib /usr/local/lib64 /usr/local/lib ${CMAKE_PREFIX_PATH}/lib)
 
 include(FindPackageHandleStandardArgs)

cmake/modules/FindLibR.cmake

@@ -50,10 +50,10 @@ function(create_rlib_for_msvc)
       \nDo you have Rtools installed with its MinGW's bin/ in PATH?")
   endif()  
   # extract symbols from R.dll into R.def and R.lib import library
-  execute_process(COMMAND ${GENDEF_EXE}
+  execute_process(COMMAND gendef
     "-" "${LIBR_LIB_DIR}/R.dll"
     OUTPUT_FILE "${CMAKE_CURRENT_BINARY_DIR}/R.def")
-  execute_process(COMMAND ${DLLTOOL_EXE}
+  execute_process(COMMAND dlltool
     "--input-def" "${CMAKE_CURRENT_BINARY_DIR}/R.def"
     "--output-lib" "${CMAKE_CURRENT_BINARY_DIR}/R.lib")
 endfunction(create_rlib_for_msvc)
@@ -103,12 +103,12 @@ else()
     )
     # ask R for the include dir
     execute_process(
-      COMMAND ${LIBR_EXECUTABLE} "--slave" "--vanilla" "-e" "cat(R.home('include'))"
+      COMMAND ${LIBR_EXECUTABLE} "--slave" "--no-save" "-e" "cat(R.home('include'))"
       OUTPUT_VARIABLE LIBR_INCLUDE_DIRS
     )
     # ask R for the lib dir
     execute_process(
-      COMMAND ${LIBR_EXECUTABLE} "--slave" "--vanilla" "-e" "cat(R.home('lib'))"
+      COMMAND ${LIBR_EXECUTABLE} "--slave" "--no-save" "-e" "cat(R.home('lib'))"
       OUTPUT_VARIABLE LIBR_LIB_DIR
     )
 

cmake/modules/FindNVML.cmake

@@ -1,23 +0,0 @@
-if (NVML_LIBRARY)
-  unset(NVML_LIBRARY CACHE)
-endif(NVML_LIBRARY)
-
-set(NVML_LIB_NAME nvml)
-
-find_path(NVML_INCLUDE_DIR
-  NAMES nvml.h
-  PATHS ${CUDA_HOME}/include ${CUDA_INCLUDE} /usr/local/cuda/include)
-
-find_library(NVML_LIBRARY
-  NAMES nvidia-ml)
-
-message(STATUS "Using nvml library: ${NVML_LIBRARY}")
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NVML DEFAULT_MSG
-                                  NVML_INCLUDE_DIR NVML_LIBRARY)
-
-mark_as_advanced(
-  NVML_INCLUDE_DIR
-  NVML_LIBRARY
-)

cmake/modules/FindNccl.cmake

@@ -32,28 +32,20 @@
 #
 # This module assumes that the user has already called find_package(CUDA)
 
-if (NCCL_LIBRARY)
-  # Don't cache NCCL_LIBRARY to enable switching between static and shared.
-  unset(NCCL_LIBRARY CACHE)
-endif()
 
-if (BUILD_WITH_SHARED_NCCL)
-  # libnccl.so
-  set(NCCL_LIB_NAME nccl)
-else ()
-  # libnccl_static.a
-  set(NCCL_LIB_NAME nccl_static)
-endif (BUILD_WITH_SHARED_NCCL)
+set(NCCL_LIB_NAME nccl_static)
 
 find_path(NCCL_INCLUDE_DIR
   NAMES nccl.h
-  PATHS $ENV{NCCL_ROOT}/include ${NCCL_ROOT}/include)
+  PATHS $ENV{NCCL_ROOT}/include ${NCCL_ROOT}/include ${CUDA_INCLUDE_DIRS} /usr/include)
 
 find_library(NCCL_LIBRARY
   NAMES ${NCCL_LIB_NAME}
-  PATHS $ENV{NCCL_ROOT}/lib/ ${NCCL_ROOT}/lib)
+  PATHS $ENV{NCCL_ROOT}/lib ${NCCL_ROOT}/lib ${CUDA_INCLUDE_DIRS}/../lib /usr/lib)
 
-message(STATUS "Using nccl library: ${NCCL_LIBRARY}")
+if (NCCL_INCLUDE_DIR AND NCCL_LIBRARY)
+  get_filename_component(NCCL_LIBRARY ${NCCL_LIBRARY} PATH)
+endif ()
 
 include(FindPackageHandleStandardArgs)
 find_package_handle_standard_args(Nccl DEFAULT_MSG
@@ -62,4 +54,5 @@ find_package_handle_standard_args(Nccl DEFAULT_MSG
 mark_as_advanced(
   NCCL_INCLUDE_DIR
   NCCL_LIBRARY
+  NCCL_LIB_NAME
 )