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

@@ -1,2 +0,0 @@
-open_collective: xgboost
-custom: https://xgboost.ai/sponsors

.github/workflows/main.yml

@@ -1,316 +0,0 @@
-# This is a basic workflow to help you get started with Actions
-
-name: XGBoost-CI
-
-# Controls when the action will run. Triggers the workflow on push or pull request
-# events but only for the master branch
-on: [push, pull_request]
-
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
-jobs:
-  gtest-cpu:
-    name: Test Google C++ test (CPU)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [macos-10.15]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        brew install lz4 ninja libomp
-    - name: Build gtest binary
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DGOOGLE_TEST=ON -DUSE_OPENMP=ON -DUSE_DMLC_GTEST=ON -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON -GNinja
-        ninja -v
-    - name: Run gtest binary
-      run: |
-        cd build
-        # libomp internal error:
-        #   OMP: Error #131: Thread identifier invalid.
-        ./testxgboost  --gtest_filter="-HistIndexCreationWithExternalMemory.Test"
-        ctest -R TestXGBoostCLI --extra-verbose
-
-  gtest-cpu-nonomp:
-    name: Test Google C++ unittest (CPU Non-OMP)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -GNinja -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON -DUSE_OPENMP=OFF
-        ninja -v
-    - name: Run gtest binary
-      run: |
-        cd build
-        ctest --extra-verbose
-
-  python-sdist-test:
-    name: Test installing XGBoost Python source package
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-10.15, windows-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install osx system dependencies
-      if: matrix.os == 'macos-10.15'
-      run: |
-        brew install ninja libomp
-    - name: Install Ubuntu system dependencies
-      if: matrix.os == 'ubuntu-latest'
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py sdist
-        pip install -v ./dist/xgboost-*.tar.gz
-        cd ..
-        python -c 'import xgboost'
-
-  c-api-demo:
-    name: Test installing XGBoost lib + building the C API demo
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-        ninja -v install
-    - name: Build and run C API demo
-      shell: bash -l {0}
-      run: |
-        cd demo/c-api/
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v
-        cd ..
-        ./build/api-demo
-
-  test-with-jvm:
-    name: Test JVM on OS ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [windows-latest, ubuntu-latest]
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-        architecture: 'x64'
-
-    - uses: actions/setup-java@v1
-      with:
-        java-version: 1.8
-
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-
-    - name: Cache Maven packages
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2
-        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2
-
-    - name: Test XGBoost4J
-      run: |
-        cd jvm-packages
-        mvn test -B -pl :xgboost4j_2.12
-
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-
-    - name: Publish artifact xgboost4j.dll to S3
-      run: |
-        cd lib/
-        Rename-Item -Path xgboost4j.dll -NewName xgboost4j_${{ github.sha }}.dll
-        dir
-        python -m awscli s3 cp xgboost4j_${{ github.sha }}.dll s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-
-    - name: Test XGBoost4J-Spark
-      run: |
-        rm -rfv build/
-        cd jvm-packages
-        mvn -B test
-      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
-      env:
-        RABIT_MOCK: ON
-
-  lint:
-    runs-on: ubuntu-latest
-    name: Code linting for Python and C++
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools
-        python -m pip install pylint cpplint numpy scipy scikit-learn
-    - name: Run lint
-      run: |
-        make lint
-
-  mypy:
-    runs-on: ubuntu-latest
-    name: Type checking for Python
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools mypy dask[complete] distributed
-    - name: Run mypy
-      run: |
-        make mypy
-
-  doxygen:
-    runs-on: ubuntu-latest
-    name: Generate C/C++ API doc using Doxygen
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends doxygen graphviz ninja-build
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-    - name: Run Doxygen
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_C_DOC=ON -GNinja
-        ninja -v doc_doxygen
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Publish
-      run: |
-        cd build/
-        tar cvjf ${{ steps.extract_branch.outputs.branch }}.tar.bz2 doc_doxygen/
-        python -m awscli s3 cp ./${{ steps.extract_branch.outputs.branch }}.tar.bz2 s3://xgboost-docs/doxygen/ --acl public-read
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-  sphinx:
-    runs-on: ubuntu-latest
-    name: Build docs using Sphinx
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends graphviz
-        python -m pip install wheel setuptools
-        python -m pip install -r doc/requirements.txt
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Run Sphinx
-      run: |
-        make -C doc html
-      env:
-        SPHINX_GIT_BRANCH: ${{ steps.extract_branch.outputs.branch }}

.github/workflows/r_nold.yml

@@ -1,44 +0,0 @@
-# Run R tests with noLD R. Only triggered by a pull request review
-# See discussion at https://github.com/dmlc/xgboost/pull/6378
-
-name: XGBoost-R-noLD
-
-on:
-  pull_request_review_comment:
-    types: [created]
-
-env:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
-
-jobs:
-  test-R-noLD:
-    if: github.event.comment.body == '/gha run r-nold-test' && contains('OWNER,MEMBER,COLLABORATOR', github.event.comment.author_association)
-    timeout-minutes: 120
-    runs-on: ubuntu-latest
-    container: rhub/debian-gcc-devel-nold
-    steps:
-    - name: Install git and system packages
-      shell: bash
-      run: |
-        apt-get update && apt-get install -y git libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libxml2-dev
-
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - name: Install dependencies
-      shell: bash
-      run: |
-        cat > install_libs.R <<EOT
-          install.packages(${{ env.R_PACKAGES }},
-                           repos = 'http://cloud.r-project.org',
-                           dependencies = c('Depends', 'Imports', 'LinkingTo'))
-        EOT
-        /tmp/R-devel/bin/Rscript install_libs.R
-
-    - name: Run R tests
-      shell: bash
-      run: |
-        cd R-package && \
-        /tmp/R-devel/bin/R CMD INSTALL . && \
-        /tmp/R-devel/bin/R -q -e "library(testthat); setwd('tests'); source('testthat.R')"

.github/workflows/r_tests.yml

@@ -1,116 +0,0 @@
-name: XGBoost-R-Tests
-
-on: [push, pull_request]
-
-env:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
-
-jobs:
-  lintr:
-    runs-on: ${{ matrix.config.os }}
-    name: Run R linters on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-    strategy:
-      matrix:
-        config:
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Run lintr
-      run: |
-        cd R-package
-        R.exe CMD INSTALL .
-        Rscript.exe tests/helper_scripts/run_lint.R
-
-  test-with-R:
-    runs-on: ${{ matrix.config.os }}
-    name: Test R on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool='${{ matrix.config.build }}'
-
-  test-R-CRAN:
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {r: 'release'}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - uses: r-lib/actions/setup-tinytex@master
-
-    - name: Install system packages
-      run: |
-        sudo apt-get update && sudo apt-get install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev pandoc pandoc-citeproc
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Check R Package
-      run: |
-        # Print stacktrace upon success of failure
-        make Rcheck || tests/ci_build/print_r_stacktrace.sh fail
-        tests/ci_build/print_r_stacktrace.sh success

.gitignore

@@ -17,7 +17,7 @@
 *.tar.gz
 *conf
 *buffer
-*.model
+*model
 *pyc
 *.train
 *.test
@@ -51,7 +51,6 @@ Debug
 #.Rbuildignore
 R-package.Rproj
 *.cache*
-.mypy_cache/
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -66,12 +65,14 @@ nb-configuration*
 .pydevproject
 .settings/
 build
+config.mk
 /xgboost
 *.data
 build_plugin
+.idea
 recommonmark/
 tags
-TAGS
+*.iml
 *.class
 target
 *.swp
@@ -89,39 +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
-*.lib
-
-# Visual Studio Code
-/.vscode/
-
-# IntelliJ/CLion
-.idea
-*.iml
-/cmake-build-debug/
-
-# GDB
-.gdb_history
-
-# Python joblib.Memory used in pytest.
-cachedir/
-
-# Files from local Dask work
-dask-worker-space/
-
-# Jupyter notebook checkpoints
-.ipynb_checkpoints/
-
-# credentials and key material
-config
-credentials
-credentials.csv
-*.env
-*.pem
-*.pub
-*.rdp
-*_rsa

.gitmodules

@@ -1,10 +1,9 @@
 [submodule "dmlc-core"]
 	path = dmlc-core
 	url = https://github.com/dmlc/dmlc-core
-	branch = main
+[submodule "rabit"]
+	path = rabit
+	url = https://github.com/dmlc/rabit
 [submodule "cub"]
 	path = cub
 	url = https://github.com/NVlabs/cub
-[submodule "gputreeshap"]
-	path = gputreeshap
-	url = https://github.com/rapidsai/gputreeshap.git

.travis.yml

@@ -1,36 +1,80 @@
+# disable sudo for container build.
 sudo: required
 
-dist: bionic
+# Enabling test on Linux and OS X
+os:
+  - linux
+  - osx
 
+osx_image: xcode9.3
+
+# Use Build Matrix to do lint and build seperately
 env:
-  global:
-    - secure: "PR16i9F8QtNwn99C5NDp8nptAS+97xwDtXEJJfEiEVhxPaaRkOp0MPWhogCaK0Eclxk1TqkgWbdXFknwGycX620AzZWa/A1K3gAs+GrpzqhnPMuoBJ0Z9qxXTbSJvCyvMbYwVrjaxc/zWqdMU8waWz8A7iqKGKs/SqbQ3rO6v7c="
-    - secure: "dAGAjBokqm/0nVoLMofQni/fWIBcYSmdq4XvCBX1ZAMDsWnuOfz/4XCY6h2lEI1rVHZQ+UdZkc9PioOHGPZh5BnvE49/xVVWr9c4/61lrDOlkD01ZjSAeoV0fAZq+93V/wPl4QV+MM+Sem9hNNzFSbN5VsQLAiWCSapWsLdKzqA="
+  matrix:
+    # code lint
+    - TASK=lint
+    # r package test
+    - TASK=r_test
+    # python package test
+    - TASK=python_test
+    - TASK=python_lightweight_test
+    # java package test
+    - TASK=java_test
+    # cmake test
+    - TASK=cmake_test
+    # c++ test
+    - TASK=cpp_test
+    # distributed test
+    - TASK=distributed_test
+    # address sanitizer test
+    - TASK=sanitizer_test
 
-jobs:
-  include:
+matrix:
+  exclude:
     - os: osx
-      arch: amd64
-      osx_image: xcode10.2
-      env: TASK=python_test
+      env: TASK=lint
     - os: osx
-      arch: amd64
-      osx_image: xcode10.2
-      env: TASK=java_test
+      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
-# the dependencies from homebrew is installed manually from setup script due to outdated image from travis.
+# dependent apt packages
 addons:
-  homebrew:
-    update: false
   apt:
+    sources:
+      - llvm-toolchain-trusty-5.0
+      - ubuntu-toolchain-r-test
+      - george-edison55-precise-backports
     packages:
-      - snapd
+      - 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:
+      - gcc@7
+      - graphviz
+    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:
@@ -45,7 +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

@@ -1,338 +1,344 @@
-cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.4.2)
+cmake_minimum_required (VERSION 3.2)
+project(xgboost)
 include(cmake/Utils.cmake)
-list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
-cmake_policy(SET CMP0022 NEW)
-cmake_policy(SET CMP0079 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0063 NEW)
-cmake_policy(SET CMP0063 NEW)
+list(APPEND CMAKE_MODULE_PATH "${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
-## User 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)
-option(RABIT_BUILD_MPI "Build MPI" 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(FORCE_COLORED_OUTPUT "Force colored output from compilers, useful when ninja is used instead of make." OFF)
-option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC/Clang" OFF)
-option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
-option(GOOGLE_TEST "Build google tests" OFF)
-option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
-option(USE_DEVICE_DEBUG "Generate CUDA device debug info." 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(PLUGIN_RMM "Build with RAPIDS Memory Manager (RMM)" OFF)
-## TODO: 1. Add check if DPC++ compiler is used for building
-option(PLUGIN_UPDATER_ONEAPI "DPC++ updater" 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 (USE_DEVICE_DEBUG AND NOT (USE_CUDA))
-  message(SEND_ERROR "`USE_DEVICE_DEBUG` must be enabled with `USE_CUDA` flag.")
-endif (USE_DEVICE_DEBUG 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)
-if (PLUGIN_RMM AND NOT (USE_CUDA))
-  message(SEND_ERROR "`PLUGIN_RMM` must be enabled with `USE_CUDA` flag.")
-endif (PLUGIN_RMM AND NOT (USE_CUDA))
-if (PLUGIN_RMM AND NOT ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") OR (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with GCC or Clang compiler.")
-endif (PLUGIN_RMM AND NOT ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") OR (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")))
-if (PLUGIN_RMM AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with Linux.")
-endif (PLUGIN_RMM AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-if (ENABLE_ALL_WARNINGS)
-  if ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-    message(SEND_ERROR "ENABLE_ALL_WARNINGS is only available for Clang and GCC.")
-  endif ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-endif (ENABLE_ALL_WARNINGS)
-if (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
-  message(SEND_ERROR "Cannot build a static library libxgboost.a when R or JVM packages are enabled.")
-endif (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
-
-#-- 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: ${CMAKE_CUDA_HOST_COMPILER}")
-
-  enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.0)
-    message(FATAL_ERROR "CUDA version must be at least 10.0!")
-  endif()
-  set(GEN_CODE "")
-  format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
-  add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
-endif (USE_CUDA)
-
-if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
-    ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
-      (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-color=always")
+# Deprecation warning
+if(USE_AVX)
+  message(WARNING "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from xgboost.")
 endif()
 
-find_package(Threads REQUIRED)
+# 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()
 
-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)
+# 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)
 
 # dmlc-core
-msvc_use_static_runtime()
-add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-set_target_properties(dmlc PROPERTIES
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-if (MSVC)
-  target_compile_options(dmlc PRIVATE
-                         -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  if (TARGET dmlc_unit_tests)
-    target_compile_options(dmlc_unit_tests PRIVATE
-                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
-  endif (TARGET dmlc_unit_tests)
-endif (MSVC)
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(dmlc PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
+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
-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
+)
 
-# core xgboost
-add_subdirectory(${xgboost_SOURCE_DIR}/src)
-target_link_libraries(objxgboost PUBLIC dmlc)
+if(MINGW OR R_LIB)
+  # build a dummy rabit library
+  add_library(rabit STATIC ${RABIT_EMPTY_SOURCES})
+else()
+  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)
 
-# Plugin
-add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
+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)
-else (BUILD_STATIC_LIB)
-  add_library(xgboost SHARED)
-endif (BUILD_STATIC_LIB)
-target_link_libraries(xgboost PRIVATE objxgboost)
+  add_definitions(-DXGBOOST_USE_CUDA)
 
-if (USE_CUDA)
-  xgboost_set_cuda_flags(xgboost)
-endif (USE_CUDA)
+  include_directories(cub)
 
-#-- Hide all C++ symbols
-if (HIDE_CXX_SYMBOLS)
-  foreach(target objxgboost xgboost dmlc)
-    set_target_properties(${target} PROPERTIES CXX_VISIBILITY_PRESET hidden)
-  endforeach()
-endif (HIDE_CXX_SYMBOLS)
+  if(USE_NCCL)
+    find_package(Nccl REQUIRED)
+    cuda_include_directories(${NCCL_INCLUDE_DIR})
+    add_definitions(-DXGBOOST_USE_NCCL)
+  endif()
 
-target_include_directories(xgboost
-  INTERFACE
-  $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
+  set(GENCODE_FLAGS "")
+  format_gencode_flags("${GPU_COMPUTE_VER}" GENCODE_FLAGS)
+  message("cuda architecture flags: ${GENCODE_FLAGS}")
 
-# This creates its own shared library `xgboost4j'.
-if (JVM_BINDINGS)
-  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
-endif (JVM_BINDINGS)
-#-- End shared library
+  set(CUDA_NVCC_FLAGS "${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()
 
-#-- CLI for xgboost
-add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
-target_link_libraries(runxgboost PRIVATE objxgboost)
-if (USE_NVTX)
-  enable_nvtx(runxgboost)
-endif (USE_NVTX)
+  cuda_add_library(gpuxgboost ${CUDA_SOURCES} STATIC)
 
-target_include_directories(runxgboost
-  PRIVATE
-  ${xgboost_SOURCE_DIR}/include
-  ${xgboost_SOURCE_DIR}/dmlc-core/include
-  ${xgboost_SOURCE_DIR}/rabit/include)
-set_target_properties(
-  runxgboost PROPERTIES
-  OUTPUT_NAME xgboost
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON)
-#-- End CLI for xgboost
+  if(USE_NCCL)
+    link_directories(${NCCL_LIBRARY})
+    target_link_libraries(gpuxgboost ${NCCL_LIB_NAME})
+  endif()
+  list(APPEND LINK_LIBRARIES gpuxgboost)
 
-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)
+elseif (USE_CUDA AND GENERATE_COMPILATION_DATABASE)
+  # Enable CUDA language to generate a compilation database.
+  cmake_minimum_required(VERSION 3.8)
 
-#-- Installing XGBoost
-if (R_LIB)
-  include(cmake/RPackageInstallTargetSetup.cmake)
+  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 ${LINK_LIBRARIES})
+  # R uses no lib prefix in shared library names of its packages
   set_target_properties(xgboost PROPERTIES PREFIX "")
-  if (APPLE)
+  if(APPLE)
     set_target_properties(xgboost PROPERTIES SUFFIX ".so")
-  endif (APPLE)
-  setup_rpackage_install_target(xgboost "${CMAKE_CURRENT_BINARY_DIR}/R-package-install")
+  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 libraries. If `xgboost` is a static lib, specify `objxgboost` also, to avoid the
-# following error:
-#
-#  > install(EXPORT ...) includes target "xgboost" which requires target "objxgboost" that is not
-#  > in any export set.
-#
-# https://github.com/dmlc/xgboost/issues/6085
-if (BUILD_STATIC_LIB)
-  set(INSTALL_TARGETS xgboost runxgboost objxgboost dmlc)
-else (BUILD_STATIC_LIB)
-  set(INSTALL_TARGETS xgboost runxgboost)
-endif (BUILD_STATIC_LIB)
+  #Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
+  add_dependencies(xgboost runxgboost)
+endif()
 
-install(TARGETS ${INSTALL_TARGETS}
-  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)
+# JVM
+if(JVM_BINDINGS)
+    find_package(JNI QUIET REQUIRED)
 
-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)
+    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)
+
+# 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

@@ -2,44 +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 Group
-  - Yuan is a software engineer in Ant Group. 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.
-* [Egor Smirnov](https://github.com/SmirnovEgorRu), Intel
-  - Egor has led a major effort to improve the performance of XGBoost on multi-core CPUs.
-
+* [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
 ------------------
@@ -98,9 +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

@@ -3,455 +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'
-
-// Which CUDA version to use when building reference distribution wheel
-ref_cuda_ver = '10.0'
-
 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 {
-          def buildNumber = env.BUILD_NUMBER as int
-          if (buildNumber > 1) milestone(buildNumber - 1)
-          milestone(buildNumber)
-
-          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'
-      }
-    }
-    stage('Jenkins Linux: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'clang-tidy': { ClangTidy() },
-            'build-cpu': { BuildCPU() },
-            'build-cpu-arm64': { BuildCPUARM64() },
-            'build-cpu-rabit-mock': { BuildCPUMock() },
-            // Build reference, distribution-ready Python wheel with CUDA 10.0
-            // using CentOS 6 image
-            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            // The build-gpu-* builds below use Ubuntu image
-            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-gpu-cuda10.2': { BuildCUDA(cuda_version: '10.2', build_rmm: true) },
-            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0') },
-            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '10.0') },
-            'build-jvm-packages-gpu-cuda10.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '10.0') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
-            'build-jvm-doc': { BuildJVMDoc() }
-          ])
+        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() } ])
+                }
+            }
         }
-      }
     }
-    stage('Jenkins Linux: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-python-cpu': { TestPythonCPU() },
-            'test-python-cpu-arm64': { TestPythonCPUARM64() },
-            // artifact_cuda_version doesn't apply to RMM tests; RMM tests will always match CUDA version between artifact and host env
-            'test-python-gpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', test_rmm: true) },
-            'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '11.0') },
-            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', multi_gpu: true, test_rmm: true) },
-            'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2', test_rmm: true) },
-            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
-            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
-            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') }
-          ])
+}
+
+/**
+ * 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"
+                """
+            }
         }
+    }
+}
+
+/**
+ * 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: Deploy') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '3.0.0') }
-          ])
-        }
-      }
-    }
   }
-}
 
-// 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 GetCUDABuildContainerType(cuda_version) {
-  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos6' : 'gpu_build'
-}
-
-def ClangTidy() {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    echo "Running clang-tidy job..."
-    def container_type = "clang_tidy"
-    def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION_ARG=10.1"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
-    """
-    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 -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
-    """
-    // 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} bash -c "cd build && ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose"
-    """
-
-    stash name: 'xgboost_cli', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCPUARM64() {
-  node('linux && arm64') {
-    unstash name: 'srcs'
-    echo "Build CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    def wheel_tag = "manylinux2014_aarch64"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh --conda-env=aarch64_test -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOL=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl && python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}"
-    mv -v wheelhouse/*.whl python-package/dist/
-    # Make sure that libgomp.so is vendored in the wheel
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp || exit -1"
-    """
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_arm64_cpu", includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
-    stash name: 'xgboost_cli_arm64', 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 BuildCUDA(args) {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    echo "Build with CUDA ${args.cuda_version}"
-    def container_type = GetCUDABuildContainerType(args.cuda_version)
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    def wheel_tag = "manylinux2010_x86_64"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOLS=ON ${arch_flag}
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
-    """
-    if (args.cuda_version == ref_cuda_ver) {
-      sh """
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}
-      mv -v wheelhouse/*.whl python-package/dist/
-      # Make sure that libgomp.so is vendored in the wheel
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
-      """
-    }
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-    if (args.cuda_version == ref_cuda_ver && (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release'))) {
-      echo 'Uploading Python wheel...'
-      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_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    if (args.build_rmm) {
-      echo "Build with CUDA ${args.cuda_version} and RMM"
-      container_type = "rmm"
-      docker_binary = "docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-      sh """
-      rm -rf build/
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON -DUSE_NCCL=ON -DPLUGIN_RMM=ON ${arch_flag}
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
-      """
-      echo 'Stashing Python wheel...'
-      stash name: "xgboost_whl_rmm_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-      echo 'Stashing C++ test executable (testxgboost)...'
-      stash name: "xgboost_cpp_tests_rmm_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    }
-    deleteDir()
-  }
-}
-
-def BuildRPackageWithCUDA(args) {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    def container_type = 'gpu_build_r_centos6'
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=10.0"
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_r_pkg_with_cuda.sh ${commit_id}
-      """
-      echo 'Uploading R tarball...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_linux_*.tar.gz'
-    }
-    deleteDir()
-  }
-}
-
-def BuildJVMPackagesWithCUDA(args) {
-  node('linux && mgpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
-    def container_type = "jvm_gpu_build"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    // Use only 4 CPU cores
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
-    """
-    echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
-    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
-    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 ${BRANCH_NAME}
-    """
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading doc...'
-      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
-    }
-    deleteDir()
-  }
-}
-
-def TestPythonCPU() {
-  node('linux && cpu') {
-    unstash name: "xgboost_whl_cuda${ref_cuda_ver}"
-    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
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonCPUARM64() {
-  node('linux && arm64') {
-    unstash name: "xgboost_whl_arm64_cpu"
-    unstash name: 'srcs'
-    unstash name: 'xgboost_cli_arm64'
-    echo "Test Python CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-arm64
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonGPU(args) {
-  def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
-  node(nodeReq) {
-    unstash name: "xgboost_whl_cuda${artifact_cuda_version}"
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
-    unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.host_cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    def mgpu_indicator = (args.multi_gpu) ? 'mgpu' : 'gpu'
-    // Allocate extra space in /dev/shm to enable NCCL
-    def docker_extra_params = (args.multi_gpu) ? "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'" : ''
-    sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator}"
-    if (args.test_rmm) {
-      sh "rm -rfv build/ python-package/dist/"
-      unstash name: "xgboost_whl_rmm_cuda${args.host_cuda_version}"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator} --use-rmm-pool"
-    }
-    deleteDir()
-  }
-}
-
-def TestCppGPU(args) {
-  def nodeReq = 'linux && mgpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
-  node(nodeReq) {
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
-    unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.host_cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
-    if (args.test_rmm) {
-      sh "rm -rfv build/"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      echo "Test C++, CUDA ${args.host_cuda_version} with RMM"
-      container_type = "rmm"
-      docker_binary = "nvidia-docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "source activate gpu_test && build/testxgboost --use-rmm-pool --gtest_filter=-*DeathTest.*"
-      """
-    }
-    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 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...'
-      sh """
-      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.0 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

@@ -1,143 +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
-
-  // Setup common job properties
-  options {
-    timestamps()
-    timeout(time: 240, unit: 'MINUTES')
-    buildDiscarder(logRotator(numToKeepStr: '10'))
-    preserveStashes()
-  }
-
-  // Build stages
-  stages {
-    stage('Jenkins Win64: Initialize') {
-      agent { label 'job_initializer' }
-      steps {
-        script {
-          def buildNumber = env.BUILD_NUMBER as int
-          if (buildNumber > 1) milestone(buildNumber - 1)
-          milestone(buildNumber)
-          checkoutSrcs()
-          commit_id = "${GIT_COMMIT}"
-        }
-        sh 'python3 tests/jenkins_get_approval.py'
-        stash name: 'srcs'
-      }
-    }
-    stage('Jenkins Win64: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-win64-cuda10.1': { BuildWin64() }
-          ])
-        }
-      }
-    }
-    stage('Jenkins Win64: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-win64-cuda10.1': { TestWin64() },
-          ])
-        }
-      }
-    }
-  }
-}
-
-// 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 && cuda10_unified') {
-    unstash name: 'srcs'
-    echo "Building XGBoost for Windows AMD64 target..."
-    bat "nvcc --version"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    bat """
-    mkdir build
-    cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON ${arch_flag} -DCMAKE_UNITY_BUILD=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" ${commit_id} win_amd64
-    """
-    echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
-    bat """
-    cd python-package\\dist
-    COPY /B ..\\..\\tests\\ci_build\\insert_vcomp140.py
-    conda activate && python insert_vcomp140.py *.whl
-    """
-    echo 'Stashing Python wheel...'
-    stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
-    echo 'Stashing C++ test executable (testxgboost)...'
-    stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
-    stash name: 'xgboost_cli', includes: 'xgboost.exe'
-    deleteDir()
-  }
-}
-
-def TestWin64() {
-  node('win64 && cuda10_unified') {
-    unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    unstash name: 'xgboost_cli'
-    unstash name: 'xgboost_cpp_tests'
-    echo "Test Win64"
-    bat "nvcc --version"
-    echo "Running C++ tests..."
-    bat "build\\testxgboost.exe"
-    echo "Installing Python dependencies..."
-    def env_name = 'win64_' + UUID.randomUUID().toString().replaceAll('-', '')
-    bat "conda env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
-    echo "Installing Python wheel..."
-    bat """
-    conda activate ${env_name} && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "Running Python tests..."
-    bat "conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace tests\\python"
-    bat """
-    conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
-    """
-    bat "conda env remove --name ${env_name}"
-    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++14 -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
@@ -86,17 +195,8 @@ cover: check
 	)
 endif
 
-
-# dask is required to pass, others are not
-# If any of the dask tests failed, contributor won't see the other error.
-mypy:
-	cd python-package; \
-	mypy ./xgboost/dask.py ../tests/python/test_with_dask.py --follow-imports=silent; \
-	mypy ../tests/python-gpu/test_gpu_with_dask.py --follow-imports=silent; \
-	mypy . || true ;
-
 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; \
@@ -108,9 +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
@@ -131,30 +258,20 @@ 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
-	bash xgboost/remove_warning_suppression_pragma.sh
 	rm xgboost/remove_warning_suppression_pragma.sh
-	rm -rfv xgboost/tests/helper_scripts/
-
-R ?= R
 
 Rbuild: Rpack
-	$(R) CMD build xgboost
+	R CMD build --no-build-vignettes xgboost
 	rm -rf xgboost
 
 Rcheck: Rbuild
-	$(R) CMD check --as-cran xgboost*.tar.gz
+	R CMD check xgboost*.tar.gz
 
 -include build/*.d
 -include build/*/*.d
+-include build_plugin/*/*.d

R-package/CMakeLists.txt

@@ -1,44 +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})
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(xgboost-r PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
-target_compile_definitions(xgboost-r
-  PUBLIC
-  -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_include_directories(xgboost-r
-  PRIVATE
-  ${LIBR_INCLUDE_DIRS}
-  ${PROJECT_SOURCE_DIR}/include
-  ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include)
-target_link_libraries(xgboost-r PUBLIC ${LIBR_CORE_LIBRARY})
-if (USE_OPENMP)
-  find_package(OpenMP REQUIRED)
-  target_link_libraries(xgboost-r PUBLIC OpenMP::OpenMP_CXX OpenMP::OpenMP_C)
-endif (USE_OPENMP)
-set_target_properties(
-  xgboost-r PROPERTIES
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-
-# Get compilation and link flags of xgboost-r and propagate to objxgboost
-target_link_libraries(objxgboost PUBLIC xgboost-r)
-# Add all objects of xgboost-r to objxgboost
-target_sources(objxgboost INTERFACE $<TARGET_OBJECTS:xgboost-r>)
-
-set(LIBR_HOME "${LIBR_HOME}" PARENT_SCOPE)
-set(LIBR_EXECUTABLE "${LIBR_EXECUTABLE}" PARENT_SCOPE)

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.4.2.1
-Date: 2020-08-28
+Version: 0.82.0.1
+Date: 2019-03-11
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -52,10 +52,7 @@ Suggests:
     vcd (>= 1.3),
     testthat,
     lintr,
-    igraph (>= 1.0.1),
-    float,
-    crayon,
-    titanic
+    igraph (>= 1.0.1)
 Depends:
     R (>= 3.3.0)
 Imports:
@@ -63,6 +60,6 @@ Imports:
     methods,
     data.table (>= 1.9.6),
     magrittr (>= 1.5),
-    jsonlite (>= 1.0),
-RoxygenNote: 7.1.1
-SystemRequirements: GNU make, C++14
+    stringi (>= 0.5.2)
+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)
@@ -31,31 +30,23 @@ 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)
 export(xgb.gblinear.history)
-export(xgb.get.config)
 export(xgb.ggplot.deepness)
 export(xgb.ggplot.importance)
-export(xgb.ggplot.shap.summary)
 export(xgb.importance)
 export(xgb.load)
-export(xgb.load.raw)
 export(xgb.model.dt.tree)
 export(xgb.plot.deepness)
 export(xgb.plot.importance)
 export(xgb.plot.multi.trees)
 export(xgb.plot.shap)
-export(xgb.plot.shap.summary)
 export(xgb.plot.tree)
 export(xgb.save)
 export(xgb.save.raw)
-export(xgb.serialize)
-export(xgb.set.config)
 export(xgb.train)
-export(xgb.unserialize)
 export(xgboost)
 import(methods)
 importClassesFrom(Matrix,dgCMatrix)
@@ -80,11 +71,14 @@ importFrom(graphics,lines)
 importFrom(graphics,par)
 importFrom(graphics,points)
 importFrom(graphics,title)
-importFrom(jsonlite,fromJSON)
-importFrom(jsonlite,toJSON)
 importFrom(magrittr,"%>%")
 importFrom(stats,median)
 importFrom(stats,predict)
+importFrom(stringi,stri_detect_regex)
+importFrom(stringi,stri_match_first_regex)
+importFrom(stringi,stri_replace_all_regex)
+importFrom(stringi,stri_replace_first_regex)
+importFrom(stringi,stri_split_regex)
 importFrom(utils,head)
 importFrom(utils,object.size)
 importFrom(utils,str)

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 -
@@ -62,11 +62,11 @@ cb.print.evaluation <- function(period = 1, showsd = TRUE) {
   callback <- function(env = parent.frame()) {
     if (length(env$bst_evaluation) == 0 ||
         period == 0 ||
-        NVL(env$rank, 0) != 0)
+        NVL(env$rank, 0) != 0 )
       return()
     
     i <- env$iteration 
-    if ((i - 1) %% period == 0 ||
+    if ((i-1) %% period == 0 ||
         i == env$begin_iteration ||
         i == env$end_iteration) {
       stdev <- if (showsd) env$bst_evaluation_err else NULL
@@ -115,7 +115,7 @@ cb.evaluation.log <- function() {
       stop("bst_evaluation must have non-empty names")
     
     mnames <<- gsub('-', '_', names(env$bst_evaluation))
-    if (!is.null(env$bst_evaluation_err))
+    if(!is.null(env$bst_evaluation_err))
       mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
   }
   
@@ -123,12 +123,12 @@ cb.evaluation.log <- function() {
     env$evaluation_log <- as.data.table(t(simplify2array(env$evaluation_log)))
     setnames(env$evaluation_log, c('iter', mnames))
     
-    if (!is.null(env$bst_evaluation_err)) {
+    if(!is.null(env$bst_evaluation_err)) {
       # rearrange col order from _mean,_mean,...,_std,_std,...
       # to be _mean,_std,_mean,_std,...
       len <- length(mnames)
-      means <- mnames[seq_len(len / 2)]
-      stds <- mnames[(len / 2 + 1):len]
+      means <- mnames[seq_len(len/2)]
+      stds <- mnames[(len/2 + 1):len]
       cnames <- numeric(len)
       cnames[c(TRUE, FALSE)] <- means
       cnames[c(FALSE, TRUE)] <- stds
@@ -144,7 +144,7 @@ cb.evaluation.log <- function() {
       return(finalizer(env))
     
     ev <- env$bst_evaluation
-    if (!is.null(env$bst_evaluation_err))
+    if(!is.null(env$bst_evaluation_err))
       ev <- c(ev, env$bst_evaluation_err)
     env$evaluation_log <- c(env$evaluation_log, 
                             list(c(iter = env$iteration, ev)))
@@ -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} 
@@ -351,19 +351,13 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
   
   finalizer <- function(env) {
     if (!is.null(env$bst)) {
-      attr_best_score <- as.numeric(xgb.attr(env$bst$handle, 'best_score'))
-      if (best_score != attr_best_score) {
-        # If the difference is too big, throw an error
-        if (abs(best_score - attr_best_score) >= 1e-14) {
-          stop("Inconsistent 'best_score' values between the closure state: ", best_score,
-               " and the xgb.attr: ", attr_best_score)
-        }
-        # If the difference is due to floating-point truncation, update best_score
-        best_score <- attr_best_score
-      }
-      env$bst$best_iteration <- best_iteration
-      env$bst$best_ntreelimit <- best_ntreelimit
-      env$bst$best_score <- best_score
+      attr_best_score = as.numeric(xgb.attr(env$bst$handle, 'best_score'))
+      if (best_score != attr_best_score)
+        stop("Inconsistent 'best_score' values between the closure state: ", best_score,
+             " and the xgb.attr: ", attr_best_score)
+      env$bst$best_iteration = best_iteration
+      env$bst$best_ntreelimit = best_ntreelimit
+      env$bst$best_score = best_score
     } else {
       env$basket$best_iteration <- best_iteration
       env$basket$best_ntreelimit <- best_ntreelimit
@@ -378,9 +372,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
       return(finalizer(env))
     
     i <- env$iteration
-    score <- env$bst_evaluation[metric_idx]
+    score = env$bst_evaluation[metric_idx]
     
-    if ((maximize && score > best_score) ||
+    if (( maximize && score > best_score) ||
         (!maximize && score < best_score)) {
       
       best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
@@ -476,7 +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}.
 #' 
@@ -506,7 +500,7 @@ cb.cv.predict <- function(save_models = FALSE) {
     for (fd in env$bst_folds) {
       pr <- predict(fd$bst, fd$watchlist[[2]], ntreelimit = ntreelimit, reshape = TRUE)
       if (is.matrix(pred)) {
-        pred[fd$index, ] <- pr
+        pred[fd$index,] <- pr
       } else {
         pred[fd$index] <- pr
       }
@@ -619,7 +613,9 @@ cb.gblinear.history <- function(sparse=FALSE) {
 
   init <- function(env) {
     if (!is.null(env$bst)) { # xgb.train:
+      coef_path <- list()
     } else if (!is.null(env$bst_folds)) { # xgb.cv:
+      coef_path <- rep(list(), length(env$bst_folds))
     } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
   }
 
@@ -685,7 +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
@@ -709,11 +705,11 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   if (!is_cv) {
     # extract num_class & num_feat from the internal model
     dmp <- xgb.dump(model)
-    if (length(dmp) < 2 || dmp[2] != "bias:")
+    if(length(dmp) < 2 || dmp[2] != "bias:")
       stop("It does not appear to be a gblinear model")
-    dmp <- dmp[-c(1, 2)]
+    dmp <- dmp[-c(1,2)]
     n <- which(dmp == 'weight:')
-    if (length(n) != 1)
+    if(length(n) != 1)
       stop("It does not appear to be a gblinear model")
     num_class <- n - 1
     num_feat <- (length(dmp) - 4) / num_class
@@ -736,9 +732,9 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   if (!is.null(class_index) && num_class > 1) {
     coef_path <- if (is.list(coef_path)) {
       lapply(coef_path, 
-             function(x) x[, seq(1 + class_index, by = num_class, length.out = num_feat)])
+             function(x) x[, seq(1 + class_index, by=num_class, length.out=num_feat)])
     } else {
-      coef_path <- coef_path[, seq(1 + class_index, by = num_class, length.out = num_feat)]
+      coef_path <- coef_path[, seq(1 + class_index, by=num_class, length.out=num_feat)]
     }
   }
   coef_path

R-package/R/utils.R

@@ -20,12 +20,6 @@ NVL <- function(x, val) {
   stop("typeof(x) == ", typeof(x), " is not supported by NVL")
 }
 
-# List of classification and ranking objectives
-.CLASSIFICATION_OBJECTIVES <- function() {
-  return(c('binary:logistic', 'binary:logitraw', 'binary:hinge', 'multi:softmax',
-           'multi:softprob', 'rank:pairwise', 'rank:ndcg', 'rank:map'))
-}
-
 
 #
 # Low-level functions for boosting --------------------------------------------
@@ -34,7 +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
@@ -75,23 +69,23 @@ check.booster.params <- function(params, ...) {
   
   if (!is.null(params[['monotone_constraints']]) &&
       typeof(params[['monotone_constraints']]) != "character") {
-        vec2str <- paste(params[['monotone_constraints']], collapse = ',')
-        vec2str <- paste0('(', vec2str, ')')
-        params[['monotone_constraints']] <- vec2str
+        vec2str = paste(params[['monotone_constraints']], collapse = ',')
+        vec2str = paste0('(', vec2str, ')')
+        params[['monotone_constraints']] = vec2str
   }
   
   # interaction constraints parser (convert from list of column indices to string)
   if (!is.null(params[['interaction_constraints']]) && 
       typeof(params[['interaction_constraints']]) != "character"){
     # check input class
-    if (!identical(class(params[['interaction_constraints']]), 'list')) stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric', 'integer'))) {
+    if (class(params[['interaction_constraints']]) != 'list') stop('interaction_constraints should be class list')
+    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric','integer'))) {
       stop('interaction_constraints should be a list of numeric/integer vectors')
     }
 
     # recast parameter as string
-    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse = ','), ']'))
-    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse = ','), ']')
+    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse=','), ']'))
+    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse=','), ']')
   }
   return(params)
 }
@@ -151,8 +145,7 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
   if (is.null(obj)) {
     .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
   } else {
-    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE,
-                    ntreelimit = 0)
+    pred <- predict(booster_handle, dtrain)
     gpair <- obj(pred, dtrain)
     .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
   }
@@ -173,12 +166,13 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
   evnames <- names(watchlist)
   if (is.null(feval)) {
     msg <- .Call(XGBoosterEvalOneIter_R, booster_handle, as.integer(iter), watchlist, as.list(evnames))
-    mat <- matrix(strsplit(msg, '\\s+|:')[[1]][-1], nrow = 2)
-    res <- structure(as.numeric(mat[2, ]), names = mat[1, ])
+    msg <- stri_split_regex(msg, '(\\s+|:|\\s+)')[[1]][-1]
+    res <- as.numeric(msg[c(FALSE,TRUE)]) # even indices are the values
+    names(res) <- msg[c(TRUE,FALSE)]      # odds are the names
   } else {
     res <- sapply(seq_along(watchlist), function(j) {
       w <- watchlist[[j]]
-      preds <- predict(booster_handle, w, outputmargin = TRUE, ntreelimit = 0) # predict using all trees
+      preds <- predict(booster_handle, w) # predict using all trees
       eval_res <- feval(preds, w)
       out <- eval_res$value
       names(out) <- paste0(evnames[j], "-", eval_res$metric)
@@ -193,23 +187,13 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
 # Helper functions for cross validation ---------------------------------------
 #
 
-# Possibly convert the labels into factors, depending on the objective.
-# The labels are converted into factors only when the given objective refers to the classification
-# or ranking tasks.
-convert.labels <- function(labels, objective_name) {
-  if (objective_name %in% .CLASSIFICATION_OBJECTIVES()) {
-    return(as.factor(labels))
-  } else {
-    return(labels)
-  }
-}
-
 # Generates random (stratified if needed) CV folds
 generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
   
   # cannot do it for rank
-  objective <- params$objective
-  if (is.character(objective) && strtrim(objective, 5) == 'rank:') {
+  if (exists('objective', where = params) &&
+      is.character(params$objective) &&
+      strtrim(params$objective, 5) == 'rank:') {
     stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
          "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
   }
@@ -222,16 +206,18 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
     #  - For classification, need to convert y labels to factor before making the folds,
     #    and then do stratification by factor levels.
     #  - For regression, leave y numeric and do stratification by quantiles.
-    if (is.character(objective)) {
-      y <- convert.labels(y, params$objective)
-    } else {
-      # If no 'objective' given in params, it means that user either wants to
-      # use the default 'reg:squarederror' objective or has provided a custom
-      # obj function.  Here, assume classification setting when y has 5 or less
-      # unique values:
-      if (length(unique(y)) <= 5) {
+    if (exists('objective', where = params) &&
+        is.character(params$objective)) {
+      # If 'objective' provided in params, assume that y is a classification label
+      # unless objective is reg:linear
+      if (params$objective != 'reg:linear')
+        y <- factor(y)
+    } else {
+      # If no 'objective' given in params, it means that user either wants to use
+      # the default 'reg: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)
-      }
     }
     folds <- xgb.createFolds(y, nfold)
   } else {
@@ -320,68 +306,6 @@ xgb.createFolds <- function(y, k = 10)
 #' @name xgboost-deprecated
 NULL
 
-#' Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
-#' models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.
-#'
-#' It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
-#' \code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
-#' \code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
-#' the model is to be accessed in the future. If you train a model with the current version of
-#' XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
-#' accessible in later releases of XGBoost. To ensure that your model can be accessed in future
-#' releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
-#'
-#' @details
-#' Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-#' the JSON format by specifying the JSON extension. To read the model back, use
-#' \code{\link{xgb.load}}.
-#'
-#' Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-#' in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-#' re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-#' The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-#' as part of another R object.
-#'
-#' Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
-#' model but also internal configurations and parameters, and its format is not stable across
-#' multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
-#'
-#' For more details and explanation about model persistence and archival, consult the page
-#' \url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' # Save as a stand-alone file; load it with xgb.load()
-#' xgb.save(bst, 'xgb.model')
-#' bst2 <- xgb.load('xgb.model')
-#'
-#' # Save as a stand-alone file (JSON); load it with xgb.load()
-#' xgb.save(bst, 'xgb.model.json')
-#' bst2 <- xgb.load('xgb.model.json')
-#' if (file.exists('xgb.model.json')) file.remove('xgb.model.json')
-#'
-#' # Save as a raw byte vector; load it with xgb.load.raw()
-#' xgb_bytes <- xgb.save.raw(bst)
-#' bst2 <- xgb.load.raw(xgb_bytes)
-#'
-#' # Persist XGBoost model as part of another R object
-#' obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-#' # Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-#' # xgb.Booster directly. What's being persisted is the future-proof byte representation
-#' # as given by xgb.save.raw().
-#' saveRDS(obj, 'my_object.rds')
-#' # Read back the R object
-#' obj2 <- readRDS('my_object.rds')
-#' # Re-construct xgb.Booster object from the bytes
-#' bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-#' if (file.exists('my_object.rds')) file.remove('my_object.rds')
-#'
-#' @name a-compatibility-note-for-saveRDS-save
-NULL
-
 # Lookup table for the deprecated parameters bookkeeping
 depr_par_lut <- matrix(c(
   'print.every.n', 'print_every_n', 
@@ -390,8 +314,8 @@ depr_par_lut <- matrix(c(
   'with.stats', 'with_stats',
   'numberOfClusters', 'n_clusters',
   'features.keep', 'features_keep',
-  'plot.height', 'plot_height',
-  'plot.width', 'plot_width',
+  'plot.height','plot_height',
+  'plot.width','plot_width',
   'n_first_tree', 'trees',
   'dummy', 'DUMMY'
 ), ncol = 2, byrow = TRUE)
@@ -404,20 +328,20 @@ colnames(depr_par_lut) <- c('old', 'new')
 check.deprecation <- function(..., env = parent.frame()) {
   pars <- list(...)
   # exact and partial matches
-  all_match <- pmatch(names(pars), depr_par_lut[, 1])
+  all_match <- pmatch(names(pars), depr_par_lut[,1])
   # indices of matched pars' names
   idx_pars <- which(!is.na(all_match))
   if (length(idx_pars) == 0) return()
   # indices of matched LUT rows
   idx_lut <- all_match[idx_pars]
   # which of idx_lut were the exact matches?
-  ex_match <- depr_par_lut[idx_lut, 1] %in% names(pars)
+  ex_match <- depr_par_lut[idx_lut,1] %in% names(pars)
   for (i in seq_along(idx_pars)) {
     pars_par <- names(pars)[idx_pars[i]]
     old_par <- depr_par_lut[idx_lut[i], 1]
     new_par <- depr_par_lut[idx_lut[i], 2]
     if (!ex_match[i]) {
-      warning("'", pars_par, "' was partially matched to '", old_par, "'")
+      warning("'", pars_par, "' was partially matched to '", old_par,"'")
     }
     .Deprecated(new_par, old = old_par, package = 'xgboost')
     if (new_par != 'NULL') {

R-package/R/xgb.Booster.R

@@ -1,40 +1,24 @@
 # Construct an internal xgboost Booster and return a handle to it.
 # internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(),
-                               modelfile = NULL) {
+xgb.Booster.handle <- function(params = list(), cachelist = list(), modelfile = NULL) {
   if (typeof(cachelist) != "list" ||
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
   }
-  ## 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)
-      modelfile <- path.expand(modelfile)
       .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
@@ -64,16 +48,14 @@ is.null.handle <- function(handle) {
   return(FALSE)
 }
 
-# Return a verified to be valid handle out of either xgb.Booster.handle or
-# xgb.Booster internal utility function
+# Return a verified to be valid handle out of either xgb.Booster.handle or xgb.Booster
+# internal utility function
 xgb.get.handle <- function(object) {
-  if (inherits(object, "xgb.Booster")) {
-    handle <- object$handle
-  } else if (inherits(object, "xgb.Booster.handle")) {
-    handle <- object
-  } else {
+  handle <- switch(class(object)[1],
+    xgb.Booster = object$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")
   }
@@ -99,7 +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
@@ -112,10 +94,7 @@ xgb.get.handle <- function(object) {
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' saveRDS(bst, "xgb.model.rds")
 #'
-#' # Warning: The resulting RDS file is only compatible with the current XGBoost version.
-#' # Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 #' bst1 <- readRDS("xgb.model.rds")
-#' if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 #' # the handle is invalid:
 #' print(bst1$handle)
 #'
@@ -131,29 +110,9 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
   if (is.null.handle(object$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)
 }
 
@@ -177,8 +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
@@ -205,7 +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
@@ -328,7 +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"))
@@ -347,8 +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)
@@ -373,8 +329,8 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       matrix(ret, nrow = n_row, byrow = TRUE, dimnames = list(NULL, cnames))
     } else {
       arr <- array(ret, c(n_col1, n_group, n_row),
-                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2, 3, 1)) # [group, row, col]
-      lapply(seq_len(n_group), function(g) arr[g, , ])
+                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2,3,1)) # [group, row, col]
+      lapply(seq_len(n_group), function(g) arr[g,,])
     }
   } else if (predinteraction) {
     n_col1 <- ncol(newdata) + 1
@@ -383,11 +339,11 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
     ret <- if (n_ret == n_row) {
       matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
     } else if (n_group == 1) {
-      array(ret, c(n_col1, n_col1, n_row), dimnames = list(cnames, cnames, NULL)) %>% aperm(c(3, 1, 2))
+      array(ret, c(n_col1, n_col1, n_row), dimnames = list(cnames, cnames, NULL)) %>% aperm(c(3,1,2))
     } else {
       arr <- array(ret, c(n_col1, n_col1, n_group, n_row),
-                   dimnames = list(cnames, cnames, NULL, NULL)) %>% aperm(c(3, 4, 1, 2)) # [group, row, col1, col2]
-      lapply(seq_len(n_group), function(g) arr[g, , , ])
+                   dimnames = list(cnames, cnames, NULL, NULL)) %>% aperm(c(3,4,1,2)) # [group, row, col1, col2]
+      lapply(seq_len(n_group), function(g) arr[g,,,])
     }
   } else if (reshape && npred_per_case > 1) {
     ret <- matrix(ret, nrow = n_row, byrow = TRUE)
@@ -437,7 +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.
@@ -462,7 +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))
 #'
@@ -496,7 +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$handle)
   }
   object
 }
@@ -536,41 +491,11 @@ xgb.attributes <- function(object) {
     .Call(XGBoosterSetAttr_R, handle, names(a[i]), a[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$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$raw <- NULL  # force renew the raw buffer
-  object <- xgb.Booster.complete(object)
-  object
-}
-
 #' Accessors for model parameters.
 #'
 #' Only the setter for xgboost parameters is currently implemented.
@@ -607,7 +532,7 @@ xgb.config <- function(object) {
     .Call(XGBoosterSetParam_R, handle, names(p[i]), p[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
+    object$raw <- xgb.save.raw(object$handle)
   }
   object
 }
@@ -660,7 +585,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
 
   if (!is.null(x$params)) {
     cat('params (as set within xgb.train):\n')
-    cat('  ',
+    cat( '  ',
          paste(names(x$params),
                paste0('"', unlist(x$params), '"'),
                sep = ' = ', collapse = ', '), '\n', sep = '')
@@ -673,9 +598,9 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   if (length(attrs) > 0) {
     cat('xgb.attributes:\n')
     if (verbose) {
-        cat(paste(paste0('  ', names(attrs)),
-                  paste0('"', unlist(attrs), '"'),
-                  sep = ' = ', collapse = '\n'), '\n', sep = '')
+      cat( paste(paste0('  ',names(attrs)),
+                 paste0('"', unlist(attrs), '"'),
+                 sep = ' = ', collapse = '\n'), '\n', sep = '')
     } else {
       cat('  ', paste(names(attrs), collapse = ', '), '\n', sep = '')
     }
@@ -697,7 +622,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   #cat('ntree: ', xgb.ntree(x), '\n', sep='')
 
   for (n in setdiff(names(x), c('handle', 'raw', 'call', 'params', 'callbacks',
-                                'evaluation_log', 'niter', 'feature_names'))) {
+                                'evaluation_log','niter','feature_names'))) {
     if (is.atomic(x[[n]])) {
       cat(n, ':', x[[n]], '\n', sep = ' ')
     } else {

R-package/R/xgb.DMatrix.R

@@ -15,10 +15,10 @@
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' 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')
 #' @export
 xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
   cnames <- NULL
@@ -26,7 +26,6 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...)
     if (length(data) > 1)
       stop("'data' has class 'character' and length ", length(data),
            ".\n  'data' accepts either a numeric matrix or a single filename.")
-    data <- path.expand(data)
     handle <- .Call(XGDMatrixCreateFromFile_R, data, as.integer(silent))
   } else if (is.matrix(data)) {
     handle <- .Call(XGDMatrixCreateFromMat_R, data, missing)
@@ -65,7 +64,6 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
       warning("xgboost: label will be ignored.")
     }
     if (is.character(data)) {
-      data <- path.expand(data)
       dtrain <- xgb.DMatrix(data[1])
     } else if (inherits(data, "xgb.DMatrix")) {
       dtrain <- data
@@ -106,7 +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
@@ -172,7 +170,8 @@ dimnames.xgb.DMatrix <- function(x) {
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' 
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -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)
@@ -224,7 +222,8 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' 
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -243,19 +242,9 @@ 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")
     .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
     return(TRUE)
   }
@@ -277,10 +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
@@ -289,7 +278,8 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' 
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -311,17 +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"))
@@ -345,7 +330,8 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' 
 #' dtrain
 #' print(dtrain, verbose=TRUE)
@@ -354,10 +340,10 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #' @export
 print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
   cat('xgb.DMatrix  dim:', nrow(x), 'x', ncol(x), ' info: ')
-  infos <- character(0)
-  if (length(getinfo(x, 'label')) > 0) infos <- 'label'
-  if (length(getinfo(x, 'weight')) > 0) infos <- c(infos, 'weight')
-  if (length(getinfo(x, 'base_margin')) > 0) infos <- c(infos, 'base_margin')
+  infos <- c()
+  if(length(getinfo(x, 'label')) > 0) infos <- 'label'
+  if(length(getinfo(x, 'weight')) > 0) infos <- c(infos, 'weight')
+  if(length(getinfo(x, 'base_margin')) > 0) infos <- c(infos, 'base_margin')
   if (length(infos) == 0) infos <- 'NA'
   cat(infos)
   cnames <- colnames(x)

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

@@ -7,10 +7,10 @@
 #' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' 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')
 #' @export
 xgb.DMatrix.save <- function(dmatrix, fname) {
   if (typeof(fname) != "character")
@@ -18,7 +18,6 @@ xgb.DMatrix.save <- function(dmatrix, fname) {
   if (!inherits(dmatrix, "xgb.DMatrix"))
     stop("dmatrix must be xgb.DMatrix")
   
-  fname <- path.expand(fname)
   .Call(XGDMatrixSaveBinary_R, dmatrix, fname[1], 0L)
   return(TRUE)
 }

R-package/R/xgb.config.R

@@ -1,38 +0,0 @@
-#' Global configuration consists of a collection of parameters that can be applied in the global
-#' scope. See \url{https://xgboost.readthedocs.io/en/stable/parameter.html} for the full list of
-#' parameters supported in the global configuration. Use \code{xgb.set.config} to update the
-#' values of one or more global-scope parameters. Use \code{xgb.get.config} to fetch the current
-#' values of all global-scope parameters (listed in
-#' \url{https://xgboost.readthedocs.io/en/stable/parameter.html}).
-#'
-#' @rdname xgbConfig
-#' @title Set and get global configuration
-#' @name xgb.set.config, xgb.get.config
-#' @export xgb.set.config xgb.get.config
-#' @param ... List of parameters to be set, as keyword arguments
-#' @return
-#' \code{xgb.set.config} returns \code{TRUE} to signal success. \code{xgb.get.config} returns
-#' a list containing all global-scope parameters and their values.
-#'
-#' @examples
-#' # Set verbosity level to silent (0)
-#' xgb.set.config(verbosity = 0)
-#' # Now global verbosity level is 0
-#' config <- xgb.get.config()
-#' print(config$verbosity)
-#' # Set verbosity level to warning (1)
-#' xgb.set.config(verbosity = 1)
-#' # Now global verbosity level is 1
-#' config <- xgb.get.config()
-#' print(config$verbosity)
-xgb.set.config <- function(...) {
-  new_config <- list(...)
-  .Call(XGBSetGlobalConfig_R, jsonlite::toJSON(new_config, auto_unbox = TRUE))
-  return(TRUE)
-}
-
-#' @rdname xgbConfig
-xgb.get.config <- function() {
-  config <- .Call(XGBGetGlobalConfig_R)
-  return(jsonlite::fromJSON(config))
-}

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

@@ -48,8 +48,8 @@
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
+#' dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 #'
 #' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 #' nrounds = 4
@@ -83,5 +83,5 @@ xgb.create.features <- function(model, data, ...){
   check.deprecation(...)
   pred_with_leaf <- predict(model, data, predleaf = TRUE)
   cols <- lapply(as.data.frame(pred_with_leaf), factor)
-  cbind(data, sparse.model.matrix(~ . -1, cols)) # nolint
+  cbind(data, sparse.model.matrix( ~ . -1, cols))
 }

R-package/R/xgb.cv.R

@@ -2,15 +2,12 @@
 #' 
 #' The cross validation function of xgboost
 #' 
-#' @param params the list of parameters. The complete list of parameters is
-#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @param params the list of parameters. Commonly used ones are:
 #' \itemize{
 #'   \item \code{objective} objective function, common ones are
 #'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss.
-#'     \item \code{binary:logistic} logistic regression for classification.
-#'     \item See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
+#'     \item \code{reg:linear} linear regression
+#'     \item \code{binary:logistic} logistic regression for classification
 #'   }
 #'   \item \code{eta} step size of each boosting step
 #'   \item \code{max_depth} maximum depth of the tree
@@ -36,15 +33,13 @@
 #'   \item \code{error} binary classification error rate
 #'   \item \code{rmse} Rooted mean square error
 #'   \item \code{logloss} negative log-likelihood function
-#'   \item \code{mae} Mean absolute error
-#'   \item \code{mape} Mean absolute percentage error
 #'   \item \code{auc} Area under curve
 #'   \item \code{aucpr} Area under PR curve
 #'   \item \code{merror} Exact matching error, used to evaluate multi-class classification
 #' }
 #' @param obj customized objective function. Returns gradient and second order 
 #'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
+#' @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 
@@ -52,8 +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 
@@ -81,7 +74,7 @@
 #' 
 #' All observations are used for both training and validation.
 #' 
-#' Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
+#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
 #'
 #' @return 
 #' An object of class \code{xgb.cv.synchronous} with the following elements:
@@ -91,7 +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.
@@ -106,13 +99,13 @@
 #'         (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.
 #' }
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
 #'                   max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
@@ -121,7 +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(), ...) {
 
@@ -139,26 +132,19 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
   
   # Check the labels
-  if ((inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
-      (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
+  if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
+       (!inherits(data, 'xgb.DMatrix') && is.null(label)))
     stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
-  } else if (inherits(data, 'xgb.DMatrix')) {
-    if (!is.null(label))
-      warning("xgb.cv: label will be ignored, since data is of type xgb.DMatrix")
-    cv_label <- getinfo(data, 'label')
-  } else {
-    cv_label <- label
-  }
   
   # CV folds
-  if (!is.null(folds)) {
-    if (!is.list(folds) || length(folds) < 2)
+  if(!is.null(folds)) {
+    if(!is.list(folds) || length(folds) < 2)
       stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
     nfold <- length(folds)
   } else {
     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
@@ -167,7 +153,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
-  print_every_n <- max(as.integer(print_every_n), 1L)
+  print_every_n <- max( as.integer(print_every_n), 1L)
   if (!has.callbacks(callbacks, 'cb.print.evaluation') && verbose) {
     callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n, showsd = showsd))
   }
@@ -193,25 +179,20 @@ 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]])
+    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test=dtest), index = folds[[k]])
   })
   rm(dall)
   # a "basket" to collect some results from callbacks
   basket <- list()
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1) # nolint
-  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1) # nolint
+  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
+  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
 
   # those are fixed for CV (no training continuation)
   begin_iteration <- 1
@@ -228,7 +209,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
     })
     msg <- simplify2array(msg)
     bst_evaluation <- rowMeans(msg)
-    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2) # nolint
+    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
     
     for (f in cb$post_iter) f()
     
@@ -287,10 +268,10 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
     }
     if (!is.null(x$params)) {
       cat('params (as set within xgb.cv):\n')
-      cat('  ',
-          paste(names(x$params),
-                paste0('"', unlist(x$params), '"'),
-                sep = ' = ', collapse = ', '), '\n', sep = '')
+      cat( '  ', 
+           paste(names(x$params), 
+                 paste0('"', unlist(x$params), '"'),
+                 sep = ' = ', collapse = ', '), '\n', sep = '')
     }
     if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
       cat('callbacks:\n')

R-package/R/xgb.dump.R

@@ -56,17 +56,16 @@ xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
                       as.character(dump_format))
 
   if (is.null(fname)) 
-    model_dump <- gsub('\t', '', model_dump, fixed = TRUE)
+    model_dump <- stri_replace_all_regex(model_dump, '\t', '')
   
   if (dump_format == "text")
-    model_dump <- unlist(strsplit(model_dump, '\n', fixed = TRUE))
+    model_dump <- unlist(stri_split_regex(model_dump, '\n'))
   
   model_dump <- grep('^\\s*$', model_dump, invert = TRUE, value = TRUE)
   
   if (is.null(fname)) {
     return(model_dump)
   } else {
-    fname <- path.expand(fname)
     writeLines(model_dump, fname[1])
     return(TRUE)
   }

R-package/R/xgb.ggplot.R

@@ -74,7 +74,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     p <-
       ggplot2::ggplot(dt_depths[, max(Depth), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
+                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Max tree leaf depth")
     return(p)
@@ -83,7 +83,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     p <-
       ggplot2::ggplot(dt_depths[, median(as.numeric(Depth)), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
+                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median tree leaf depth")
     return(p)
@@ -92,98 +92,20 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     p <-
       ggplot2::ggplot(dt_depths[, median(abs(Weight)), Tree]) +
       ggplot2::geom_point(ggplot2::aes(x = Tree, y = V1),
-                          alpha = 0.4, size = 3, stroke = 0) +
+                          alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median absolute leaf weight")
     return(p)
   }
 }
 
-#' @rdname xgb.plot.shap.summary
-#' @export
-xgb.ggplot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
-                                    trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 10000  # 10,000 samples per feature.
-  )
-  p_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
-  # Reverse factor levels so that the first level is at the top of the plot
-  p_data[, "feature" := factor(feature, rev(levels(feature)))]
-  p <- ggplot2::ggplot(p_data, ggplot2::aes(x = feature, y = p_data$shap_value, colour = p_data$feature_value)) +
-    ggplot2::geom_jitter(alpha = 0.5, width = 0.1) +
-    ggplot2::scale_colour_viridis_c(limits = c(-3, 3), option = "plasma", direction = -1) +
-    ggplot2::geom_abline(slope = 0, intercept = 0, colour = "darkgrey") +
-    ggplot2::coord_flip()
-
-  p
-}
-
-#' Combine and melt feature values and SHAP contributions for sample
-#' observations.
-#'
-#' Conforms to data format required for ggplot functions.
-#'
-#' Internal utility function.
-#'
-#' @param data_list List containing 'data' and 'shap_contrib' returned by
-#'   \code{xgb.shap.data()}.
-#' @param normalize Whether to standardize feature values to have mean 0 and
-#'   standard deviation 1 (useful for comparing multiple features on the same
-#'   plot). Default \code{FALSE}.
-#'
-#' @return A data.table containing the observation ID, the feature name, the
-#'   feature value (normalized if specified), and the SHAP contribution value.
-prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-
-  data <- data.table::as.data.table(as.matrix(data))
-  if (normalize) {
-    data[, (names(data)) := lapply(.SD, normalize)]
-  }
-  data[, "id" := seq_len(nrow(data))]
-  data_m <- data.table::melt.data.table(data, id.vars = "id", variable.name = "feature", value.name = "feature_value")
-
-  shap_contrib <- data.table::as.data.table(as.matrix(shap_contrib))
-  shap_contrib[, "id" := seq_len(nrow(shap_contrib))]
-  shap_contrib_m <- data.table::melt.data.table(shap_contrib, id.vars = "id", variable.name = "feature", value.name = "shap_value")
-
-  p_data <- data.table::merge.data.table(data_m, shap_contrib_m, by = c("id", "feature"))
-
-  p_data
-}
-
-#' Scale feature value to have mean 0, standard deviation 1
-#'
-#' This is used to compare multiple features on the same plot.
-#' Internal utility function
-#'
-#' @param x Numeric vector
-#'
-#' @return Numeric vector with mean 0 and sd 1.
-normalize <- function(x) {
-  loc <- mean(x, na.rm = TRUE)
-  scale <- stats::sd(x, na.rm = TRUE)
-
-  (x - loc) / scale
-}
-
 # Plot multiple ggplot graph aligned by rows and columns.
 # ... the plots
 # cols number of columns
 # internal utility function
 multiplot <- function(..., cols = 1) {
   plots <- list(...)
-  num_plots <- length(plots)
+  num_plots = length(plots)
   
   layout <- matrix(seq(1, cols * ceiling(num_plots / cols)),
                    ncol = cols, nrow = ceiling(num_plots / cols))
@@ -209,5 +131,5 @@ multiplot <- function(..., cols = 1) {
 
 globalVariables(c(
   "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight", "feature"
+  "element_blank", "element_text", "V1", "Weight"
 ))

R-package/R/xgb.importance.R

@@ -99,13 +99,13 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
   model_text_dump <- xgb.dump(model = model, with_stats = TRUE)
   
   # linear model
-  if (model_text_dump[2] == "bias:"){
+  if(model_text_dump[2] == "bias:"){
     weights <- which(model_text_dump == "weight:") %>%
                {model_text_dump[(. + 1):length(model_text_dump)]} %>%
                as.numeric
     
     num_class <- NVL(model$params$num_class, 1)
-    if (is.null(feature_names))
+    if(is.null(feature_names)) 
       feature_names <- seq(to = length(weights) / num_class) - 1
     if (length(feature_names) * num_class != length(weights))
       stop("feature_names length does not match the number of features used in the model")
@@ -117,17 +117,18 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
                  Weight = weights,
                  Class = seq_len(num_class) - 1)[order(Class, -abs(Weight))]
     }
-  } else { # tree model
-      result <- xgb.model.dt.tree(feature_names = feature_names,
-                                  text = model_text_dump,
-                                  trees = trees)[
-          Feature != "Leaf", .(Gain = sum(Quality),
-                               Cover = sum(Cover),
-                               Frequency = .N), by = Feature][
-        , `:=`(Gain = Gain / sum(Gain),
-               Cover = Cover / sum(Cover),
-               Frequency = Frequency / sum(Frequency))][
-          order(Gain, decreasing = TRUE)]
+  } else { 
+  # tree model
+    result <- xgb.model.dt.tree(feature_names = feature_names,
+                                text = model_text_dump,
+                                trees = trees)[
+      Feature != "Leaf", .(Gain = sum(Quality), 
+                           Cover = sum(Cover), 
+                           Frequency = .N), by = Feature][
+      ,`:=`(Gain = Gain / sum(Gain), 
+            Cover = Cover / sum(Cover),
+            Frequency = Frequency / sum(Frequency))][
+      order(Gain, decreasing = TRUE)]
   }
   result
 }

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

@@ -87,11 +87,11 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   }
   
   if (length(text) < 2 ||
-      sum(grepl('yes=(\\d+),no=(\\d+)', text)) < 1) {
+      sum(stri_detect_regex(text, 'yes=(\\d+),no=(\\d+)')) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
   
-  position <- which(grepl("booster", text, fixed = TRUE))
+  position <- which(!is.na(stri_match_first_regex(text, "booster")))
   
   add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
   
@@ -108,9 +108,9 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   }
   td <- td[Tree %in% trees & !grepl('^booster', t)]
   
-  td[, Node := as.integer(sub("^([0-9]+):.*", "\\1", t))]
+  td[, Node := stri_match_first_regex(t, "(\\d+):")[,2] %>% as.integer ]
   if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := grepl("leaf", t, fixed = TRUE)]
+  td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
 
   # parse branch lines
   branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
@@ -118,17 +118,16 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
   td[isLeaf == FALSE, 
      (branch_cols) := {
-       matches <- regmatches(t, regexec(branch_rx, t))
-       # skip some indices with spurious capture groups from anynumber_regex
-       xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
-       xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-       as.data.table(xtr)
+      # skip some indices with spurious capture groups from anynumber_regex
+      xtr <- stri_match_first_regex(t, branch_rx)[, c(2,3,5,6,7,8,10), drop = FALSE]
+      xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
+      lapply(seq_len(ncol(xtr)), function(i) xtr[,i])
     }]
   # assign feature_names when available
   if (!is.null(feature_names)) {
     if (length(feature_names) <= max(as.numeric(td$Feature), na.rm = TRUE))
       stop("feature_names has less elements than there are features used in the model")
-    td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1]]
+    td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1] ]
   }
   
   # parse leaf lines
@@ -136,9 +135,8 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   leaf_cols <- c("Feature", "Quality", "Cover")
   td[isLeaf == TRUE,
      (leaf_cols) := {
-       matches <- regmatches(t, regexec(leaf_rx, t))
-       xtr <- do.call(rbind, matches)[, c(2, 4)]
-       c("Leaf", as.data.table(xtr))
+      xtr <- stri_match_first_regex(t, leaf_rx)[, c(2,4)]
+      c("Leaf", lapply(seq_len(ncol(xtr)), function(i) xtr[,i]))
     }]
   
   # convert some columns to numeric
@@ -158,4 +156,4 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
 # Avoid error messages during CRAN check.
 # The reason is that these variables are never declared
 # They are mainly column names inferred by Data.table...
-globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf", ".SD", ".SDcols"))
+globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf",".SD", ".SDcols"))

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

@@ -89,9 +89,9 @@ xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.d
   if (plot) {
     if (which == "2x1") {
       op <- par(no.readonly = TRUE)
-      par(mfrow = c(2, 1),
-          oma = c(3, 1, 3, 1) + 0.1,
-          mar = c(1, 4, 1, 0) + 0.1)
+      par(mfrow = c(2,1),
+          oma = c(3,1,3,1) + 0.1,
+          mar = c(1,4,1,0) + 0.1)
 
       dt_summaries[, barplot(N, border = NA, ylab = 'Number of leafs', ...)]
 
@@ -130,7 +130,7 @@ get.leaf.depth <- function(dt_tree) {
   dt_edges[is.na(Leaf), Leaf := FALSE]
 
   dt_edges[, {
-    graph <- igraph::graph_from_data_frame(.SD[, .(ID, To)])
+    graph <- igraph::graph_from_data_frame(.SD[,.(ID, To)])
     # min(ID) in a tree is a root node
     paths_tmp <- igraph::shortest_paths(graph, from = min(ID), to = To[Leaf == TRUE])
     # list of paths to each leaf in a tree

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

@@ -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})
@@ -92,27 +92,28 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
     importance_matrix <- head(importance_matrix, top_n)
   }
   if (rel_to_first) {
-    importance_matrix[, Importance := Importance / max(abs(Importance))]
+    importance_matrix[, Importance := Importance/max(abs(Importance))]
   }
   if (is.null(cex)) {
-    cex <- 2.5 / log2(1 + nrow(importance_matrix))
+    cex <- 2.5/log2(1 + nrow(importance_matrix))
   }
   
   if (plot) {
-    original_mar <- par()$mar
-
-    # reset margins so this function doesn't have side effects
-    on.exit({par(mar = original_mar)})
-
-    mar <- original_mar
+    op <- par(no.readonly = TRUE)
+    mar <- op$mar
     if (!is.null(left_margin))
       mar[2] <- left_margin
     par(mar = mar)
     
     # reverse the order of rows to have the highest ranked at the top
-    importance_matrix[rev(seq_len(nrow(importance_matrix))),
+    importance_matrix[nrow(importance_matrix):1,
                       barplot(Importance, horiz = TRUE, border = NA, cex.names = cex,
                               names.arg = Feature, las = 1, ...)]
+    grid(NULL, NA)
+    # redraw over the grid
+    importance_matrix[nrow(importance_matrix):1,
+                      barplot(Importance, horiz = TRUE, border = NA, add = TRUE)]
+    par(op)
   }
   
   invisible(importance_matrix)

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

@@ -67,12 +67,12 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
 
   # first number of the path represents the tree, then the following numbers are related to the path to follow
   # root init
-  root.nodes <- tree.matrix[Node == 0, ID]
+  root.nodes <- tree.matrix[stri_detect_regex(ID, "\\d+-0"), ID]
   tree.matrix[ID %in% root.nodes, abs.node.position := root.nodes]
 
   precedent.nodes <- root.nodes
 
-  while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
+  while(tree.matrix[,sum(is.na(abs.node.position))] > 0) {
     yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
     no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
     yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
@@ -86,34 +86,37 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
   tree.matrix[!is.na(Yes), Yes := paste0(abs.node.position, "_0")]
   tree.matrix[!is.na(No), No := paste0(abs.node.position, "_1")]
   
-  for (nm in c("abs.node.position", "Yes", "No"))
-    data.table::set(tree.matrix, j = nm, value = sub("^\\d+-", "", tree.matrix[[nm]]))
+  remove.tree <- . %>% stri_replace_first_regex(pattern = "^\\d+-", replacement = "")
+  
+  tree.matrix[,`:=`(abs.node.position = remove.tree(abs.node.position),
+                    Yes = remove.tree(Yes),
+                    No = remove.tree(No))]
   
   nodes.dt <- tree.matrix[
         , .(Quality = sum(Quality))
         , by = .(abs.node.position, Feature)
       ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
                           " (",
-                          format(Quality[1:min(length(Quality), features_keep)], digits = 5),
+                          format(Quality[1:min(length(Quality), features_keep)], digits=5),
                           ")") %>%
                    paste0(collapse = "\n"))
         , by = abs.node.position]
   
   edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
-    list(tree.matrix[Feature != "Leaf", .(abs.node.position, No)]) %>%
+    list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>%
     rbindlist() %>%
     setnames(c("From", "To")) %>%
     .[, .N, .(From, To)] %>%
-    .[, N := NULL]
+    .[, N:=NULL]
   
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
-    label = nodes.dt[, Text]
+    label = nodes.dt[,Text]
   )
   
   edges <- DiagrammeR::create_edge_df(
-    from = match(edges.dt[, From], nodes.dt[, abs.node.position]),
-    to = match(edges.dt[, To], nodes.dt[, abs.node.position]),
+    from = match(edges.dt[,From], nodes.dt[,abs.node.position]),
+    to = match(edges.dt[,To], nodes.dt[,abs.node.position]),
     rel = "leading_to")
   
   graph <- DiagrammeR::create_graph(

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}.
@@ -81,7 +81,6 @@
 #' xgb.plot.shap(agaricus.test$data, model = bst, features = "odor=none")
 #' contr <- predict(bst, agaricus.test$data, predcontrib = TRUE)
 #' xgb.plot.shap(agaricus.test$data, contr, model = bst, top_n = 12, n_col = 3)
-#' xgb.ggplot.shap.summary(agaricus.test$data, contr, model = bst, top_n = 12)  # Summary plot
 #'
 #' # multiclass example - plots for each class separately:
 #' nclass <- 3
@@ -100,7 +99,6 @@
 #'               n_col = 2, col = col, pch = 16, pch_NA = 17)
 #' xgb.plot.shap(x, model = mbst, trees = trees0 + 2, target_class = 2, top_n = 4,
 #'               n_col = 2, col = col, pch = 16, pch_NA = 17)
-#' xgb.ggplot.shap.summary(x, model = mbst, target_class = 0, top_n = 4)  # Summary plot
 #' 
 #' @rdname xgb.plot.shap
 #' @export
@@ -111,33 +109,69 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
                           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, ...) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 100000
-  )
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-  features <- colnames(data)
+  
+  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
+    stop("data: must be either matrix or dgCMatrix")
+
+  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
+
+  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
+
+  if (!is.null(shap_contrib) &&
+      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
+    stop("shap_contrib is not compatible with the provided data")
+  
+  nsample <- if (is.null(subsample)) min(100000, nrow(data)) else as.integer(subsample * nrow(data))
+  idx <- sample(1:nrow(data), nsample)
+  data <- data[idx,]
+
+  if (is.null(shap_contrib)) {
+    shap_contrib <- predict(model, data, predcontrib = TRUE, approxcontrib = approxcontrib)
+  } else {
+    shap_contrib <- shap_contrib[idx,]
+  }
 
   which <- match.arg(which)
   if (which == "2d")
     stop("2D plots are not implemented yet")
 
+  if (is.null(features)) {
+    imp <- xgb.importance(model = model, trees = trees)
+    top_n <- as.integer(top_n[1])
+    if (top_n < 1 && top_n > 100)
+      stop("top_n: must be an integer within [1, 100]")
+    features <- imp$Feature[1:min(top_n, NROW(imp))]
+  }
+  
+  if (is.character(features)) {
+    if (is.null(colnames(data)))
+      stop("Either provide `data` with column names or provide `features` as column indices")
+    features <- match(features, colnames(data))
+  }
+  
   if (n_col > length(features)) n_col <- length(features)
+
+  if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
+    shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]]
+                    else Reduce("+", lapply(shap_contrib, abs))
+  }
+
+  shap_contrib <- shap_contrib[, features, drop = FALSE]
+  data <- data[, features, drop = FALSE]
+  cols <- colnames(data)
+  if (is.null(cols)) cols <- colnames(shap_contrib)
+  if (is.null(cols)) cols <- paste0('X', 1:ncol(data))
+  colnames(data) <- cols
+  colnames(shap_contrib) <- cols
+  
   if (plot && which == "1d") {
     op <- par(mfrow = c(ceiling(length(features) / n_col), n_col),
-              oma = c(0, 0, 0, 0) + 0.2,
-              mar = c(3.5, 3.5, 0, 0) + 0.1,
+              oma = c(0,0,0,0) + 0.2,
+              mar = c(3.5,3.5,0,0) + 0.1,
               mgp = c(1.7, 0.6, 0))
-    for (f in features) {
+    for (f in cols) {
       ord <- order(data[, f])
       x <- data[, f][ord]
       y <- shap_contrib[, f][ord]
@@ -158,7 +192,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       grid()
       if (plot_loess) {
         # compress x to 3 digits, and mean-aggredate y
-        zz <- data.table(x = signif(x, 3), y)[, .(.N, y = mean(y)), x]
+        zz <- data.table(x = signif(x, 3), y)[, .(.N, y=mean(y)), x]
         if (nrow(zz) <= 5) {
           lines(zz$x, zz$y, col = col_loess)
         } else {
@@ -182,108 +216,3 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
   }
   invisible(list(data = data, shap_contrib = shap_contrib))
 }
-
-#' SHAP contribution dependency summary plot
-#'
-#' Compare SHAP contributions of different features.
-#'
-#' A point plot (each point representing one sample from \code{data}) is
-#' produced for each feature, with the points plotted on the SHAP value axis.
-#' Each point (observation) is coloured based on its feature value. The plot
-#' hence allows us to see which features have a negative / positive contribution
-#' on the model prediction, and whether the contribution is different for larger
-#' or smaller values of the feature. We effectively try to replicate the
-#' \code{summary_plot} function from https://github.com/slundberg/shap.
-#'
-#' @inheritParams xgb.plot.shap
-#'
-#' @return A \code{ggplot2} object.
-#' @export
-#'
-#' @examples # See \code{\link{xgb.plot.shap}}.
-#' @seealso \code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-#'   \url{https://github.com/slundberg/shap}
-xgb.plot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
-                                  trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
-  # Only ggplot implementation is available.
-  xgb.ggplot.shap.summary(data, shap_contrib, features, top_n, model, trees, target_class, approxcontrib, subsample)
-}
-
-#' Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-#' Internal utility function.
-#'
-#' @inheritParams xgb.plot.shap
-#' @keywords internal
-#'
-#' @return A list containing: 'data', a matrix containing sample observations
-#'   and their feature values; 'shap_contrib', a matrix containing the SHAP contribution
-#'   values for these observations.
-xgb.shap.data <- function(data, shap_contrib = NULL, features = NULL, top_n = 1, model = NULL,
-                          trees = NULL, target_class = NULL, approxcontrib = FALSE,
-                          subsample = NULL, max_observations = 100000) {
-  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
-    stop("data: must be either matrix or dgCMatrix")
-
-  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
-
-  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
-
-  if (!is.null(shap_contrib) &&
-      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
-    stop("shap_contrib is not compatible with the provided data")
-
-  if (is.character(features) && is.null(colnames(data)))
-    stop("either provide `data` with column names or provide `features` as column indices")
-
-  if (is.null(model$feature_names) && model$nfeatures != ncol(data))
-    stop("if model has no feature_names, columns in `data` must match features in model")
-
-  if (!is.null(subsample)) {
-    idx <- sample(x = seq_len(nrow(data)), size = as.integer(subsample * nrow(data)), replace = FALSE)
-  } else {
-    idx <- seq_len(min(nrow(data), max_observations))
-  }
-  data <- data[idx, ]
-  if (is.null(colnames(data))) {
-    colnames(data) <- paste0("X", seq_len(ncol(data)))
-  }
-
-  if (!is.null(shap_contrib)) {
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-    shap_contrib <- shap_contrib[idx, ]
-    if (is.null(colnames(shap_contrib))) {
-      colnames(shap_contrib) <- paste0("X", seq_len(ncol(data)))
-    }
-  } else {
-    shap_contrib <- predict(model, newdata = data, predcontrib = TRUE, approxcontrib = approxcontrib)
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-  }
-
-  if (is.null(features)) {
-    if (!is.null(model$feature_names)) {
-      imp <- xgb.importance(model = model, trees = trees)
-    } else {
-      imp <- xgb.importance(model = model, trees = trees, feature_names = colnames(data))
-    }
-    top_n <- top_n[1]
-    if (top_n < 1 | top_n > 100) stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[1:min(top_n, NROW(imp))]
-  }
-  if (is.character(features)) {
-    features <- match(features, colnames(data))
-  }
-
-  shap_contrib <- shap_contrib[, features, drop = FALSE]
-  data <- data[, features, drop = FALSE]
-
-  list(
-    data = data,
-    shap_contrib = shap_contrib
-  )
-}

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

@@ -80,12 +80,12 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
   
   dt <- xgb.model.dt.tree(feature_names = feature_names, model = model, trees = trees)
 
-  dt[, label := paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
+  dt[, label:= paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
   if (show_node_id)
     dt[, label := paste0(ID, ": ", label)]
   dt[Node == 0, label := paste0("Tree ", Tree, "\n", label)]
-  dt[, shape := "rectangle"][Feature == "Leaf", shape := "oval"]
-  dt[, filledcolor := "Beige"][Feature == "Leaf", filledcolor := "Khaki"]
+  dt[, shape:= "rectangle"][Feature == "Leaf", shape:= "oval"]
+  dt[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"]
   # in order to draw the first tree on top:
   dt <- dt[order(-Tree)]
   

R-package/R/xgb.save.R

@@ -13,11 +13,7 @@
 #' 
 #' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
 #' or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
-#' corresponding R-methods would need to be used to load it. Moreover, persisting the model with
-#' \code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
-#' future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-#' how to persist models in a future-proof way, i.e. to make the model accessible in future
-#' releases of XGBoost.
+#' corresponding R-methods would need to be used to load it.
 #' 
 #' @seealso 
 #' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}. 
@@ -31,7 +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$data)
 #' @export
 xgb.save <- function(model, fname) {
@@ -42,7 +37,6 @@ xgb.save <- function(model, fname) {
          if (inherits(model, "xgb.DMatrix")) " Use xgb.DMatrix.save to save an xgb.DMatrix object." else "")
   }
   model <- xgb.Booster.complete(model, saveraw = FALSE)
-  fname <- path.expand(fname)
   .Call(XGBoosterSaveModel_R, model$handle, fname[1])
   return(TRUE)
 }

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

@@ -3,9 +3,9 @@
 #' \code{xgb.train} is an advanced interface for training an xgboost model.
 #' The \code{xgboost} function is a simpler wrapper for \code{xgb.train}.
 #'
-#' @param params the list of parameters. The complete list of parameters is
-#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @param params the list of parameters. 
+#'        The complete list of parameters is available at \url{http://xgboost.readthedocs.io/en/latest/parameter.html}.
+#'        Below is a shorter summary:
 #' 
 #' 1. General Parameters
 #' 
@@ -15,7 +15,7 @@
 #'  
 #' 2. Booster Parameters
 #' 
-#' 2.1. Parameters for Tree Booster
+#' 2.1. Parameter for Tree Booster
 #' 
 #' \itemize{
 #'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
@@ -24,14 +24,12 @@
 #'   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
 #'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1 
 #'   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
-#'   \item \code{lambda} L2 regularization term on weights. Default: 1
-#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
 #'   \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. Parameters for Linear Booster
+#' 2.2. Parameter for Linear Booster
 #'  
 #' \itemize{
 #'   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -44,24 +42,14 @@
 #' \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:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
+#'     \item \code{reg:linear} linear regression (Default).
 #'     \item \code{reg:logistic} logistic regression.
-#'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
-#'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
-#'     \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
-#'     \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
-#'     \item \code{aft_loss_distribution}: Probabilty Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+#'     \item \code{num_class} set the number of classes. To use only with multiclass objectives.
 #'     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
 #'     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
 #'     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
-#'     \item \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
-#'     \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
-#'     \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
-#'     \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
 #'   }
 #'   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
 #'   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
@@ -80,7 +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.
@@ -130,20 +118,18 @@
 #' 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{https://en.wikipedia.org/wiki/Root_mean_square_error}
-#'      \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
-#'      \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
+#'      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
+#'      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
+#'      \item \code{mlogloss} multiclass logloss. \url{http://wiki.fast.ai/index.php/Log_Loss}
 #'      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
 #'            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
 #'            Different threshold (e.g., 0.) could be specified as "error@0."
 #'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'      \item \code{mae} Mean absolute error
-#'      \item \code{mape} Mean absolute percentage error
-#'      \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+#'      \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
 #'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
+#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
 #'   }
 #' 
 #' The following callbacks are automatically created when certain parameters are set:
@@ -161,14 +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, 
@@ -177,7 +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.
 #' }
 #' 
@@ -195,12 +181,12 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' 
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+#' dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 #' watchlist <- list(train = dtrain, eval = dtest)
 #' 
 #' ## A simple xgb.train example:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
+#' 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)
 #' 
@@ -221,12 +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)
 #' 
@@ -236,7 +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,
@@ -281,8 +267,8 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   }
 
   # evaluation printing callback
-  params <- c(params)
-  print_every_n <- max(as.integer(print_every_n), 1L)
+  params <- c(params, list(silent = ifelse(verbose > 1, 0, 1)))
+  print_every_n <- max( as.integer(print_every_n), 1L)
   if (!has.callbacks(callbacks, 'cb.print.evaluation') &&
       verbose) {
     callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n))
@@ -305,13 +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'
@@ -332,9 +313,12 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
       niter_init <- xgb.ntree(bst) %/% (num_parallel_tree * num_class)
     }
   }
-  if (is_update && nrounds > niter_init)
+  if(is_update && nrounds > niter_init)
     stop("nrounds cannot be larger than ", niter_init, " (nrounds of xgb_model)")
 
+  # TODO: distributed code
+  rank <- 0
+  
   niter_skip <- ifelse(is_update, 0, niter_init)
   begin_iteration <- niter_skip + 1
   end_iteration <- niter_skip + nrounds
@@ -346,6 +330,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     
     xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
     
+    bst_evaluation <- numeric(0)
     if (length(watchlist) > 0)
       bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
     
@@ -360,7 +345,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   bst <- xgb.Booster.complete(bst, saveraw = TRUE)
   
   # store the total number of boosting iterations
-  bst$niter <- end_iteration
+  bst$niter = end_iteration
 
   # store the evaluation results
   if (length(evaluation_log) > 0 &&

R-package/R/xgb.unserialize.R

@@ -1,31 +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)
-  tryCatch(
-    .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer),
-    error = function(e) {
-      error_msg <- conditionMessage(e)
-      m <- regexec("(src[\\\\/]learner.cc:[0-9]+): Check failed: (header == serialisation_header_)",
-                   error_msg, perl = TRUE)
-      groups <- regmatches(error_msg, m)[[1]]
-      if (length(groups) == 3) {
-        warning(paste("The model had been generated by XGBoost version 1.0.0 or earlier and was ",
-                      "loaded from a RDS file. We strongly ADVISE AGAINST using saveRDS() ",
-                      "function, to ensure that your model can be read in current and upcoming ",
-                      "XGBoost releases. Please use xgb.save() instead to preserve models for the ",
-                      "long term. For more details and explanation, see ",
-                      "https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html",
-                      sep = ""))
-        .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
-      } else {
-        stop(e)
-      }
-    })
-  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
@@ -91,8 +91,11 @@ NULL
 #' @importFrom data.table setkeyv
 #' @importFrom data.table setnames
 #' @importFrom magrittr %>%
-#' @importFrom jsonlite fromJSON
-#' @importFrom jsonlite toJSON
+#' @importFrom stringi stri_detect_regex
+#' @importFrom stringi stri_match_first_regex
+#' @importFrom stringi stri_replace_first_regex
+#' @importFrom stringi stri_replace_all_regex
+#' @importFrom stringi stri_split_regex
 #' @importFrom utils object.size str tail
 #' @importFrom stats predict
 #' @importFrom stats median

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

@@ -1,24 +1,9 @@
 ### configure.ac					-*- Autoconf -*-
 
-AC_PREREQ(2.69)
+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"
@@ -28,27 +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 ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  AC_LANG_CONFTEST(
+  [AC_LANG_PROGRAM([[#include <omp.h>]], [[ return omp_get_num_threads (); ]])])
+  PKG_CFLAGS="${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 '         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/README.md

@@ -17,4 +17,4 @@ Benchmarks
 Notes
 ====
 * Contribution of examples, benchmarks is more than welcomed!
-* If you like to share how you use xgboost to solve your problem, send a pull request :)
+* If you like to share how you use xgboost to solve your problem, send a pull request:)

R-package/demo/basic_walkthrough.R

@@ -3,8 +3,8 @@ require(methods)
 
 # we load in the agaricus dataset
 # In this example, we are aiming to predict whether a mushroom is edible
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
 # the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
@@ -58,31 +58,31 @@ xgb.save(bst, "xgboost.model")
 bst2 <- xgb.load("xgboost.model")
 pred2 <- predict(bst2, test$data)
 # pred2 should be identical to pred
-print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
+print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
 
 # save model to R's raw vector
-raw <- xgb.save.raw(bst)
+raw = xgb.save.raw(bst)
 # load binary model to R
 bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))
+print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix
-dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-dtest <- xgb.DMatrix(data = test$data, label = test$label)
+dtrain <- xgb.DMatrix(data = train$data, label=train$label)
+dtest <- xgb.DMatrix(data = test$data, label=test$label)
 #---------------Using watchlist----------------
 # watchlist is a list of xgb.DMatrix, each of them is tagged with name
-watchlist <- list(train = dtrain, test = dtest)
+watchlist <- list(train=dtrain, test=dtest)
 # to train with watchlist, use xgb.train, which contains more advanced features
 # watchlist allows us to monitor the evaluation result on all data in the list 
 print("Train xgboost using xgb.train with watchlist")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  nthread = 2, objective = "binary:logistic")
 # we can change evaluation metrics, or use multiple evaluation metrics
 print("train xgboost using xgb.train with watchlist, watch logloss and error")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  eval_metric = "error", eval_metric = "logloss",
                  nthread = 2, objective = "binary:logistic")
 
@@ -90,17 +90,17 @@ bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist =
 xgb.DMatrix.save(dtrain, "dtrain.buffer")
 # to load it in, simply call xgb.DMatrix
 dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+bst <- xgb.train(data=dtrain2, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  nthread = 2, objective = "binary:logistic")
 # information can be extracted from xgb.DMatrix using getinfo
-label <- getinfo(dtest, "label")
+label = getinfo(dtest, "label")
 pred <- predict(bst, dtest)
-err <- as.numeric(sum(as.integer(pred > 0.5) != label)) / length(label)
+err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
 print(paste("test-error=", err))
 
 # You can dump the tree you learned using xgb.dump into a text file
-dump_path <- file.path(tempdir(), 'dump.raw.txt')
-xgb.dump(bst, dump_path, with_stats = TRUE)
+dump_path = file.path(tempdir(), 'dump.raw.txt')
+xgb.dump(bst, dump_path, with_stats = T)
 
 # Finally, you can check which features are the most important.
 print("Most important features (look at column Gain):")

R-package/demo/boost_from_prediction.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
@@ -11,12 +11,12 @@ watchlist <- list(eval = dtest, train = dtrain)
 #
 print('start running example to start from a initial prediction')
 # train xgboost for 1 round
-param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
+param <- list(max_depth=2, eta=1, nthread = 2, silent=1, objective='binary:logistic')
 bst <- xgb.train(param, dtrain, 1, watchlist)
 # Note: we need the margin value instead of transformed prediction in set_base_margin
 # do predict with output_margin=TRUE, will always give you margin values before logistic transformation
-ptrain <- predict(bst, dtrain, outputmargin = TRUE)
-ptest  <- predict(bst, dtest, outputmargin = TRUE)
+ptrain <- predict(bst, dtrain, outputmargin=TRUE)
+ptest  <- predict(bst, dtest, outputmargin=TRUE)
 # set the base_margin property of dtrain and dtest
 # base margin is the base prediction we will boost from
 setinfo(dtrain, "base_margin", ptrain)

R-package/demo/caret_wrapper.R

@@ -9,17 +9,17 @@ require(e1071)
 # Load Arthritis dataset in memory.
 data(Arthritis)
 # Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = FALSE)
+df <- data.table(Arthritis, keep.rownames = F)
 
 # Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 # For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
+df[,AgeDiscret:= as.factor(round(Age/10,0))]
 
 # Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[, ID := NULL]
+df[,ID:=NULL]
 
 #-------------Basic Training using XGBoost in caret Library-----------------
 # Set up control parameters for caret::train

R-package/demo/create_sparse_matrix.R

@@ -19,7 +19,7 @@ if (!require(vcd)) {
 data(Arthritis)
 
 # create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = FALSE)
+df <- data.table(Arthritis, keep.rownames = F)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
@@ -32,17 +32,17 @@ str(df)
 # Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 
 # For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
+df[,AgeDiscret:= as.factor(round(Age/10,0))]
 
 # Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[, ID := NULL]
+df[,ID:=NULL]
 
 # List the different values for the column Treatment: Placebo, Treated.
 cat("Values of the categorical feature Treatment\n")
-print(levels(df[, Treatment]))
+print(levels(df[,Treatment]))
 
 # Next step, we will transform the categorical data to dummy variables.
 # This method is also called one hot encoding.
@@ -52,7 +52,7 @@ print(levels(df[, Treatment]))
 #
 # Formulae Improved~.-1 used below means transform all categorical features but column Improved to binary values.
 # Column Improved is excluded because it will be our output column, the one we want to predict.
-sparse_matrix <- sparse.model.matrix(Improved ~ . - 1, data = df)
+sparse_matrix = sparse.model.matrix(Improved~.-1, data = df)
 
 cat("Encoding of the sparse Matrix\n")
 print(sparse_matrix)
@@ -61,7 +61,7 @@ print(sparse_matrix)
 # 1. Set, for all rows, field in Y column to 0; 
 # 2. set Y to 1 when Improved == Marked; 
 # 3. Return Y column
-output_vector <- df[, Y := 0][Improved == "Marked", Y := 1][, Y]
+output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
 
 # Following is the same process as other demo
 cat("Learning...\n")

R-package/demo/cross_validation.R

@@ -1,25 +1,25 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 nrounds <- 2
-param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
+param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
 
 cat('running cross validation\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold = 5, metrics = {'error'})
+xgb.cv(param, dtrain, nrounds, nfold=5, metrics={'error'})
 
 cat('running cross validation, disable standard deviation display\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold = 5,
-       metrics = 'error', showsd = FALSE)
+xgb.cv(param, dtrain, nrounds, nfold=5,
+       metrics='error', showsd = FALSE)
 
 ###
 # you can also do cross validation with cutomized loss function
@@ -29,18 +29,18 @@ print ('running cross validation, with cutomsized loss function')
 
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1,
+param <- list(max_depth=2, eta=1, silent=1,
               objective = logregobj, eval_metric = evalerror)
 # train with customized objective
 xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)

R-package/demo/custom_objective.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
@@ -15,7 +15,7 @@ num_round <- 2
 # this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -29,12 +29,12 @@ logregobj <- function(preds, dtrain) {
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
-              objective = logregobj, eval_metric = evalerror)
+param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
+              objective=logregobj, eval_metric=evalerror)
 print ('start training with user customized objective')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
@@ -52,13 +52,13 @@ attr(dtrain, 'label') <- getinfo(dtrain, 'label')
 logregobjattr <- function(preds, dtrain) {
   # now you can access the attribute in customized function
   labels <- attr(dtrain, 'label')
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
-param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
-              objective = logregobjattr, eval_metric = evalerror)
+param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
+              objective=logregobjattr, eval_metric=evalerror)
 print ('start training with user customized objective, with additional attributes in DMatrix')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train

R-package/demo/early_stopping.R

@@ -1,20 +1,20 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-param <- list(max_depth = 2, eta = 1, nthread = 2, verbosity = 0)
+param <- list(max_depth=2, eta=1, nthread=2, verbosity=0)
 watchlist <- list(eval = dtest)
 num_round <- 20
 # user define objective function, given prediction, return gradient and second order gradient
 # this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -27,7 +27,7 @@ logregobj <- function(preds, dtrain) {
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 print ('start training with early Stopping setting')

R-package/demo/generalized_linear_model.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
@@ -30,4 +30,5 @@ num_round <- 2
 bst <- xgb.train(param, dtrain, num_round, watchlist)
 ypred <- predict(bst, dtest)
 labels <- getinfo(dtest, 'label')
-cat('error of preds=', mean(as.numeric(ypred > 0.5) != labels), '\n')
+cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
+

R-package/demo/gpu_accelerated.R

@@ -21,8 +21,8 @@ m <- X[, sel] %*% betas - 1 + rnorm(N)
 y <- rbinom(N, 1, plogis(m))
 
 tr <- sample.int(N, N * 0.75)
-dtrain <- xgb.DMatrix(X[tr, ], label = y[tr])
-dtest <- xgb.DMatrix(X[-tr, ], label = y[-tr])
+dtrain <- xgb.DMatrix(X[tr,], label = y[tr])
+dtest <- xgb.DMatrix(X[-tr,], label = y[-tr])
 wl <- list(train = dtrain, test = dtest)
 
 # An example of running 'gpu_hist' algorithm
@@ -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/interaction_constraints.R

@@ -4,39 +4,34 @@ library(data.table)
 set.seed(1024)
 
 # Function to obtain a list of interactions fitted in trees, requires input of maximum depth
-treeInteractions <- function(input_tree, input_max_depth) {
-  ID_merge <- i.id <- i.feature <- NULL  # Suppress warning "no visible binding for global variable"
-
-  trees <- data.table::copy(input_tree)  # copy tree input to prevent overwriting
+treeInteractions <- function(input_tree, input_max_depth){
+  trees <- copy(input_tree)  # copy tree input to prevent overwriting
   if (input_max_depth < 2) return(list())  # no interactions if max depth < 2
   if (nrow(input_tree) == 1) return(list())
 
   # Attach parent nodes
-  for (i in 2:input_max_depth) {
-    if (i == 2) trees[, ID_merge := ID] else trees[, ID_merge := get(paste0('parent_', i - 2))]
-    parents_left <- trees[!is.na(Split), list(i.id = ID, i.feature = Feature, ID_merge = Yes)]
-    parents_right <- trees[!is.na(Split), list(i.id = ID, i.feature = Feature, ID_merge = No)]
+  for (i in 2:input_max_depth){
+    if (i == 2) trees[, ID_merge:=ID] else trees[, ID_merge:=get(paste0('parent_',i-2))]
+    parents_left <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=Yes)]
+    parents_right <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=No)]
 
-    data.table::setorderv(trees, 'ID_merge')
-    data.table::setorderv(parents_left, 'ID_merge')
-    data.table::setorderv(parents_right, 'ID_merge')
+    setorderv(trees, 'ID_merge')
+    setorderv(parents_left, 'ID_merge')
+    setorderv(parents_right, 'ID_merge')
 
-    trees <- merge(trees, parents_left, by = 'ID_merge', all.x = TRUE)
-    trees[!is.na(i.id), c(paste0('parent_', i - 1), paste0('parent_feat_', i - 1))
-          := list(i.id, i.feature)]
-    trees[, c('i.id', 'i.feature') := NULL]
+    trees <- merge(trees, parents_left, by='ID_merge', all.x=T)
+    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
+    trees[, c('i.id','i.feature'):=NULL]
 
-    trees <- merge(trees, parents_right, by = 'ID_merge', all.x = TRUE)
-    trees[!is.na(i.id), c(paste0('parent_', i - 1), paste0('parent_feat_', i - 1))
-          := list(i.id, i.feature)]
-    trees[, c('i.id', 'i.feature') := NULL]
+    trees <- merge(trees, parents_right, by='ID_merge', all.x=T)
+    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
+    trees[, c('i.id','i.feature'):=NULL]
   }
 
   # Extract nodes with interactions
   interaction_trees <- trees[!is.na(Split) & !is.na(parent_1), 
-                             c('Feature', paste0('parent_feat_', 1:(input_max_depth - 1))),
-                             with = FALSE]
-  interaction_trees_split <- split(interaction_trees, seq_len(nrow(interaction_trees)))
+                             c('Feature',paste0('parent_feat_',1:(input_max_depth-1))), with=F]
+  interaction_trees_split <- split(interaction_trees, 1:nrow(interaction_trees))
   interaction_list <- lapply(interaction_trees_split, as.character)
 
   # Remove NAs (no parent interaction)
@@ -52,59 +47,56 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
 # Generate sample data
 x <- list()
-for (i in 1:10) {
-  x[[i]] <- i * rnorm(1000, 10)
+for (i in 1:10){
+  x[[i]] = i*rnorm(1000, 10)
 }
 x <- as.data.table(x)
 
-y <- -1 * x[, rowSums(.SD)] + x[['V1']] * x[['V2']] + x[['V3']] * x[['V4']] * x[['V5']]
-     + rnorm(1000, 0.001) + 3 * sin(x[['V7']])
+y = -1*x[, rowSums(.SD)] + x[['V1']]*x[['V2']] + x[['V3']]*x[['V4']]*x[['V5']] + rnorm(1000, 0.001) + 3*sin(x[['V7']])
 
-train <- as.matrix(x)
+train = as.matrix(x)
 
 # Interaction constraint list (column names form)
-interaction_list <- list(c('V1', 'V2'), c('V3', 'V4', 'V5'))
+interaction_list <- list(c('V1','V2'),c('V3','V4','V5'))
 
 # Convert interaction constraint list into feature index form
 cols2ids <- function(object, col_names) {
   LUT <- seq_along(col_names) - 1
   names(LUT) <- col_names
-  rapply(object, function(x) LUT[x], classes = "character", how = "replace")
+  rapply(object, function(x) LUT[x], classes="character", how="replace")
 }
-interaction_list_fid <- cols2ids(interaction_list, colnames(train))
+interaction_list_fid = cols2ids(interaction_list, colnames(train))
 
 # Fit model with interaction constraints
-bst <- xgboost(data = train, label = y, max_depth = 4,
-               eta = 0.1, nthread = 2, nrounds = 1000,
-               interaction_constraints = interaction_list_fid)
+bst = xgboost(data = train, label = y, max_depth = 4,
+              eta = 0.1, nthread = 2, nrounds = 1000,
+              interaction_constraints = interaction_list_fid)
 
 bst_tree <- xgb.model.dt.tree(colnames(train), bst)
-bst_interactions <- treeInteractions(bst_tree, 4)
-  # interactions constrained to combinations of V1*V2 and V3*V4*V5
+bst_interactions <- treeInteractions(bst_tree, 4)  # interactions constrained to combinations of V1*V2 and V3*V4*V5
 
 # Fit model without interaction constraints
-bst2 <- xgboost(data = train, label = y, max_depth = 4,
-                eta = 0.1, nthread = 2, nrounds = 1000)
+bst2 = xgboost(data = train, label = y, max_depth = 4,
+               eta = 0.1, nthread = 2, nrounds = 1000)
 
 bst2_tree <- xgb.model.dt.tree(colnames(train), bst2)
 bst2_interactions <- treeInteractions(bst2_tree, 4)  # much more interactions
 
 # Fit model with both interaction and monotonicity constraints
-bst3 <- xgboost(data = train, label = y, max_depth = 4,
-                eta = 0.1, nthread = 2, nrounds = 1000,
-                interaction_constraints = interaction_list_fid,
-                monotone_constraints = c(-1, 0, 0, 0, 0, 0, 0, 0, 0, 0))
+bst3 = xgboost(data = train, label = y, max_depth = 4,
+               eta = 0.1, nthread = 2, nrounds = 1000,
+               interaction_constraints = interaction_list_fid,
+               monotone_constraints = c(-1,0,0,0,0,0,0,0,0,0))
 
 bst3_tree <- xgb.model.dt.tree(colnames(train), bst3)
-bst3_interactions <- treeInteractions(bst3_tree, 4)
-  # interactions still constrained to combinations of V1*V2 and V3*V4*V5
+bst3_interactions <- treeInteractions(bst3_tree, 4)  # interactions still constrained to combinations of V1*V2 and V3*V4*V5
 
 # Show monotonic constraints still apply by checking scores after incrementing V1
 x1 <- sort(unique(x[['V1']]))
-for (i in seq_along(x1)){
-  testdata <- copy(x[, - ('V1')])
+for (i in 1:length(x1)){
+  testdata <- copy(x[, -c('V1')])
   testdata[['V1']] <- x1[i]
-  testdata <- testdata[, paste0('V', 1:10), with = FALSE]
+  testdata <- testdata[, paste0('V',1:10), with=F]
   pred <- predict(bst3, as.matrix(testdata))
   
   # Should not print out anything due to monotonic constraints

R-package/demo/poisson_regression.R

@@ -1,6 +1,7 @@
 data(mtcars)
 head(mtcars)
-bst <- xgboost(data = as.matrix(mtcars[, -11]), label = mtcars[, 11],
-               objective = 'count:poisson', nrounds = 5)
-pred <- predict(bst, as.matrix(mtcars[, -11]))
-sqrt(mean((pred - mtcars[, 11]) ^ 2))
+bst = xgboost(data=as.matrix(mtcars[,-11]),label=mtcars[,11],
+              objective='count:poisson',nrounds=5)
+pred = predict(bst,as.matrix(mtcars[,-11]))
+sqrt(mean((pred-mtcars[,11])^2))
+

R-package/demo/predict_first_ntree.R

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

R-package/demo/predict_leaf_indices.R

@@ -5,40 +5,39 @@ require(Matrix)
 set.seed(1982)
 
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 
-param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic')
-nrounds <- 4
+param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
+nrounds = 4
 
 # training the model for two rounds
-bst <- xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
+bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy without new features
-accuracy.before <- (sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label)
-                    / length(agaricus.test$label))
+accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
 
 # by default, we predict using all the trees
-pred_with_leaf <- predict(bst, dtest, predleaf = TRUE)
+
+pred_with_leaf = predict(bst, dtest, predleaf = TRUE)
 head(pred_with_leaf)
 
 create.new.tree.features <- function(model, original.features){
   pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
   cols <- list()
-  for (i in 1:model$niter) {
+  for(i in 1:model$niter){
     # max is not the real max but it s not important for the purpose of adding features
-    leaf.id <- sort(unique(pred_with_leaf[, i]))
-    cols[[i]] <- factor(x = pred_with_leaf[, i], level = leaf.id)
+    leaf.id <- sort(unique(pred_with_leaf[,i]))
+    cols[[i]] <- factor(x = pred_with_leaf[,i], level = leaf.id)
   }
-  cbind(original.features, sparse.model.matrix(~ . - 1, as.data.frame(cols)))
+  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
 }
 
 # Convert previous features to one hot encoding
 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)
@@ -47,9 +46,7 @@ watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy with new features
-accuracy.after <- (sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label)
-                   / length(agaricus.test$label))
+accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
 
 # Here the accuracy was already good and is now perfect.
-cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
-          accuracy.after, "!\n"))
+cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now", accuracy.after, "!\n"))

R-package/demo/runall.R

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

R-package/demo/tweedie_regression.R

@@ -8,12 +8,12 @@ data(AutoClaim)
 dt <- data.table(AutoClaim)
 
 # exclude these columns from the model matrix
-exclude <- c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
+exclude <-  c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
 
 # retains the missing values
 # NOTE: this dataset is comes ready out of the box
 options(na.action = 'na.pass')
-x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = FALSE])
+x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = F])
 options(na.action = 'na.omit')
 
 # response
@@ -46,4 +46,4 @@ var_imp <- xgb.importance(attr(x, 'Dimnames')[[2]], model = bst)
 
 preds <- predict(bst, d_train)
 
-rmse <- sqrt(sum(mean((y - preds) ^ 2)))
+rmse <- sqrt(sum(mean((y - preds)^2)))

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

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

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

@@ -1,64 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/utils.R
-\name{a-compatibility-note-for-saveRDS-save}
-\alias{a-compatibility-note-for-saveRDS-save}
-\title{Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
-models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.}
-\description{
-It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
-\code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
-\code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
-the model is to be accessed in the future. If you train a model with the current version of
-XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
-accessible in later releases of XGBoost. To ensure that your model can be accessed in future
-releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
-}
-\details{
-Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-the JSON format by specifying the JSON extension. To read the model back, use
-\code{\link{xgb.load}}.
-
-Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-as part of another R object.
-
-Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
-model but also internal configurations and parameters, and its format is not stable across
-multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
-
-For more details and explanation about model persistence and archival, consult the page
-\url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-
-# Save as a stand-alone file; load it with xgb.load()
-xgb.save(bst, 'xgb.model')
-bst2 <- xgb.load('xgb.model')
-
-# Save as a stand-alone file (JSON); load it with xgb.load()
-xgb.save(bst, 'xgb.model.json')
-bst2 <- xgb.load('xgb.model.json')
-if (file.exists('xgb.model.json')) file.remove('xgb.model.json')
-
-# Save as a raw byte vector; load it with xgb.load.raw()
-xgb_bytes <- xgb.save.raw(bst)
-bst2 <- xgb.load.raw(xgb_bytes)
-
-# Persist XGBoost model as part of another R object
-obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-# Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-# xgb.Booster directly. What's being persisted is the future-proof byte representation
-# as given by xgb.save.raw().
-saveRDS(obj, 'my_object.rds')
-# Read back the R object
-obj2 <- readRDS('my_object.rds')
-# Re-construct xgb.Booster object from the bytes
-bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-if (file.exists('my_object.rds')) file.remove('my_object.rds')
-
-}

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/normalize.Rd

@@ -1,18 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R
-\name{normalize}
-\alias{normalize}
-\title{Scale feature value to have mean 0, standard deviation 1}
-\usage{
-normalize(x)
-}
-\arguments{
-\item{x}{Numeric vector}
-}
-\value{
-Numeric vector with mean 0 and sd 1.
-}
-\description{
-This is used to compare multiple features on the same plot.
-Internal utility function
-}

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/prepare.ggplot.shap.data.Rd

@@ -1,27 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R
-\name{prepare.ggplot.shap.data}
-\alias{prepare.ggplot.shap.data}
-\title{Combine and melt feature values and SHAP contributions for sample
-observations.}
-\usage{
-prepare.ggplot.shap.data(data_list, normalize = FALSE)
-}
-\arguments{
-\item{data_list}{List containing 'data' and 'shap_contrib' returned by
-\code{xgb.shap.data()}.}
-
-\item{normalize}{Whether to standardize feature values to have mean 0 and
-standard deviation 1 (useful for comparing multiple features on the same
-plot). Default \code{FALSE}.}
-}
-\value{
-A data.table containing the observation ID, the feature name, the
-  feature value (normalized if specified), and the SHAP contribution value.
-}
-\description{
-Conforms to data format required for ggplot functions.
-}
-\details{
-Internal utility function.
-}

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{
@@ -38,10 +38,7 @@ bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_dep
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 saveRDS(bst, "xgb.model.rds")
 
-# Warning: The resulting RDS file is only compatible with the current XGBoost version.
-# Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 bst1 <- readRDS("xgb.model.rds")
-if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 # the handle is invalid:
 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

@@ -4,39 +4,20 @@
 \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. The complete list of parameters is
-  available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-  is a shorter summary:
+\item{params}{the list of parameters. Commonly used ones are:
 \itemize{
   \item \code{objective} objective function, common ones are
   \itemize{
-    \item \code{reg:squarederror} Regression with squared loss.
-    \item \code{binary:logistic} logistic regression for classification.
-    \item See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
+    \item \code{reg:linear} linear regression
+    \item \code{binary:logistic} logistic regression for classification
   }
   \item \code{eta} step size of each boosting step
   \item \code{max_depth} maximum depth of the tree
@@ -70,8 +51,6 @@ from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callb
   \item \code{error} binary classification error rate
   \item \code{rmse} Rooted mean square error
   \item \code{logloss} negative log-likelihood function
-  \item \code{mae} Mean absolute error
-  \item \code{mape} Mean absolute percentage error
   \item \code{auc} Area under curve
   \item \code{aucpr} Area under PR curve
   \item \code{merror} Exact matching error, used to evaluate multi-class classification
@@ -80,7 +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.}
 
@@ -91,9 +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}.
@@ -125,7 +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.
@@ -140,7 +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.
 }
 }
@@ -156,7 +132,7 @@ The cross-validation process is then repeated \code{nrounds} times, with each of
 
 All observations are used for both training and validation.
 
-Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
+Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
 }
 \examples{
 data(agaricus.train, package='xgboost')

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.}
 
@@ -131,7 +111,6 @@ bst <- xgboost(agaricus.train$data, agaricus.train$label, nrounds = 50,
 xgb.plot.shap(agaricus.test$data, model = bst, features = "odor=none")
 contr <- predict(bst, agaricus.test$data, predcontrib = TRUE)
 xgb.plot.shap(agaricus.test$data, contr, model = bst, top_n = 12, n_col = 3)
-xgb.ggplot.shap.summary(agaricus.test$data, contr, model = bst, top_n = 12)  # Summary plot
 
 # multiclass example - plots for each class separately:
 nclass <- 3
@@ -150,7 +129,6 @@ xgb.plot.shap(x, model = mbst, trees = trees0 + 1, target_class = 1, top_n = 4,
               n_col = 2, col = col, pch = 16, pch_NA = 17)
 xgb.plot.shap(x, model = mbst, trees = trees0 + 2, target_class = 2, top_n = 4,
               n_col = 2, col = col, pch = 16, pch_NA = 17)
-xgb.ggplot.shap.summary(x, model = mbst, target_class = 0, top_n = 4)  # Summary plot
 
 }
 \references{

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

@@ -1,78 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R, R/xgb.plot.shap.R
-\name{xgb.ggplot.shap.summary}
-\alias{xgb.ggplot.shap.summary}
-\alias{xgb.plot.shap.summary}
-\title{SHAP contribution dependency summary plot}
-\usage{
-xgb.ggplot.shap.summary(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 10,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL
-)
-
-xgb.plot.shap.summary(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 10,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL
-)
-}
-\arguments{
-\item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
-
-\item{shap_contrib}{a matrix of SHAP contributions that was computed earlier for the above
-\code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.}
-
-\item{features}{a vector of either column indices or of feature names to plot. When it is NULL,
-feature importance is calculated, and \code{top_n} high ranked features are taken.}
-
-\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.}
-
-\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-or \code{features} is missing.}
-
-\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.}
-
-\item{target_class}{is only relevant for multiclass models. When it is set to a 0-based class index,
-only SHAP contributions for that specific class are used.
-If it is not set, SHAP importances are averaged over all classes.}
-
-\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.}
-
-\item{subsample}{a random fraction of data points to use for plotting. When it is NULL,
-it is set so that up to 100K data points are used.}
-}
-\value{
-A \code{ggplot2} object.
-}
-\description{
-Compare SHAP contributions of different features.
-}
-\details{
-A point plot (each point representing one sample from \code{data}) is
-produced for each feature, with the points plotted on the SHAP value axis.
-Each point (observation) is coloured based on its feature value. The plot
-hence allows us to see which features have a negative / positive contribution
-on the model prediction, and whether the contribution is different for larger
-or smaller values of the feature. We effectively try to replicate the
-\code{summary_plot} function from https://github.com/slundberg/shap.
-}
-\examples{
-# See \code{\link{xgb.plot.shap}}.
-}
-\seealso{
-\code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-  \url{https://github.com/slundberg/shap}
-}

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

@@ -22,11 +22,7 @@ of \code{\link{xgb.train}}.
 
 Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
 or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
-corresponding R-methods would need to be used to load it. Moreover, persisting the model with
-\code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
-future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-how to persist models in a future-proof way, i.e. to make the model accessible in future
-releases of XGBoost.
+corresponding R-methods would need to be used to load it.
 }
 \examples{
 data(agaricus.train, package='xgboost')
@@ -37,7 +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.shap.data.Rd

@@ -1,55 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.plot.shap.R
-\name{xgb.shap.data}
-\alias{xgb.shap.data}
-\title{Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-Internal utility function.}
-\usage{
-xgb.shap.data(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 1,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL,
-  max_observations = 1e+05
-)
-}
-\arguments{
-\item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
-
-\item{shap_contrib}{a matrix of SHAP contributions that was computed earlier for the above
-\code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.}
-
-\item{features}{a vector of either column indices or of feature names to plot. When it is NULL,
-feature importance is calculated, and \code{top_n} high ranked features are taken.}
-
-\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.}
-
-\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-or \code{features} is missing.}
-
-\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.}
-
-\item{target_class}{is only relevant for multiclass models. When it is set to a 0-based class index,
-only SHAP contributions for that specific class are used.
-If it is not set, SHAP importances are averaged over all classes.}
-
-\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.}
-
-\item{subsample}{a random fraction of data points to use for plotting. When it is NULL,
-it is set so that up to 100K data points are used.}
-}
-\value{
-A list containing: 'data', a matrix containing sample observations
-  and their feature values; 'shap_contrib', a matrix containing the SHAP contribution
-  values for these observations.
-}
-\description{
-Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-Internal utility function.
-}
-\keyword{internal}