Fix typo. (#8192)

* Fix loading DMatrix binary in distributed env. (#8149)

- Try to load DMatrix binary before trying to parse text input.
- Remove some unmaintained code.

* Fix.

.clang-tidy

@@ -1,4 +1,4 @@
-Checks: 'modernize-*,-modernize-use-nodiscard,-modernize-concat-nested-namespaces,-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,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,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  }

.gitattributes

@@ -1,18 +0,0 @@
-* text=auto
-
-*.c   text eol=lf
-*.h   text eol=lf
-*.cc  text eol=lf
-*.cuh text eol=lf
-*.cu  text eol=lf
-*.py  text eol=lf
-*.txt text eol=lf
-*.R   text eol=lf
-*.scala text eol=lf
-*.java  text eol=lf
-
-*.sh text eol=lf
-
-*.rst text eol=lf
-*.md  text eol=lf
-*.csv text eol=lf

.github/dependabot.yml

@@ -1,31 +0,0 @@
-# To get started with Dependabot version updates, you'll need to specify which
-# package ecosystems to update and where the package manifests are located.
-# Please see the documentation for all configuration options:
-# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
-
-version: 2
-updates:
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages"
-    schedule:
-      interval: "daily"
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages/xgboost4j"
-    schedule:
-      interval: "daily"
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages/xgboost4j-gpu"
-    schedule:
-      interval: "daily"
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages/xgboost4j-example"
-    schedule:
-      interval: "daily"
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages/xgboost4j-spark"
-    schedule:
-      interval: "daily"
-  - package-ecosystem: "maven"
-    directory: "/jvm-packages/xgboost4j-spark-gpu"
-    schedule:
-      interval: "daily"

.github/workflows/jvm_tests.yml

@@ -2,9 +2,6 @@ name: XGBoost-JVM-Tests
 
 on: [push, pull_request]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 jobs:
   test-with-jvm:
     name: Test JVM on OS ${{ matrix.os }}
@@ -12,19 +9,19 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [windows-latest, ubuntu-latest, macos-11]
+        os: [windows-latest, ubuntu-latest, macos-10.15]
 
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+    - uses: actions/setup-python@v2
       with:
         python-version: '3.8'
         architecture: 'x64'
 
-    - uses: actions/setup-java@d202f5dbf7256730fb690ec59f6381650114feb2 # v3.6.0
+    - uses: actions/setup-java@v1
       with:
         java-version: 1.8
 
@@ -34,13 +31,13 @@ jobs:
         python -m pip install awscli
 
     - name: Cache Maven packages
-      uses: actions/cache@6998d139ddd3e68c71e9e398d8e40b71a2f39812 # v3.2.5
+      uses: actions/cache@v2
       with:
         path: ~/.m2
         key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
+        restore-keys: ${{ runner.os }}-m2
 
-    - name: Test XGBoost4J (Core)
+    - name: Test XGBoost4J
       run: |
         cd jvm-packages
         mvn test -B -pl :xgboost4j_2.12
@@ -51,14 +48,14 @@ jobs:
       id: extract_branch
       if: |
         (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        (matrix.os == 'windows-latest' || matrix.os == 'macos-11')
+        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/${{ steps.extract_branch.outputs.branch }}/libxgboost4j/ --acl public-read
+        python -m awscli s3 cp xgboost4j_${{ 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'
@@ -66,21 +63,8 @@ jobs:
         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: Publish artifact libxgboost4j.dylib to S3
-      run: |
-        cd lib/
-        mv -v libxgboost4j.dylib libxgboost4j_${{ github.sha }}.dylib
-        ls
-        python -m awscli s3 cp libxgboost4j_${{ github.sha }}.dylib s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/libxgboost4j/ --acl public-read
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'macos-11'
-      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 (Core, Spark, Examples)
+    - name: Test XGBoost4J-Spark
       run: |
         rm -rfv build/
         cd jvm-packages
@@ -88,13 +72,3 @@ jobs:
       if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
       env:
         RABIT_MOCK: ON
-
-
-    - name: Build and Test XGBoost4J with scala 2.13
-      run: |
-        rm -rfv build/
-        cd jvm-packages
-        mvn -B clean install test -Pdefault,scala-2.13
-      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
-      env:
-        RABIT_MOCK: ON

.github/workflows/main.yml

@@ -6,9 +6,6 @@ name: XGBoost-CI
 # events but only for the master branch
 on: [push, pull_request]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 # A workflow run is made up of one or more jobs that can run sequentially or in parallel
 jobs:
   gtest-cpu:
@@ -17,9 +14,9 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-11]
+        os: [macos-10.15]
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - name: Install system packages
@@ -45,7 +42,7 @@ jobs:
       matrix:
         os: [ubuntu-latest]
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - name: Install system packages
@@ -66,30 +63,30 @@ jobs:
   c-api-demo:
     name: Test installing XGBoost lib + building the C API demo
     runs-on: ${{ matrix.os }}
-    defaults:
-      run:
-        shell: bash -l {0}
     strategy:
       fail-fast: false
       matrix:
         os: ["ubuntu-latest"]
         python-version: ["3.8"]
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+    - name: Install system packages
+      run: |
+        sudo apt-get install -y --no-install-recommends ninja-build
+    - uses: conda-incubator/setup-miniconda@v2
       with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: cpp_test
-        environment-file: tests/ci_build/conda_env/cpp_test.yml
+        auto-update-conda: true
+        python-version: ${{ matrix.python-version }}
+        activate-environment: test
     - name: Display Conda env
+      shell: bash -l {0}
       run: |
         conda info
         conda list
-
     - name: Build and install XGBoost static library
+      shell: bash -l {0}
       run: |
         mkdir build
         cd build
@@ -97,6 +94,7 @@ jobs:
         ninja -v install
         cd -
     - name: Build and run C API demo with static
+      shell: bash -l {0}
       run: |
         pushd .
         cd demo/c-api/
@@ -108,14 +106,15 @@ jobs:
         cd ..
         rm -rf ./build
         popd
-
     - name: Build and install XGBoost shared library
+      shell: bash -l {0}
       run: |
         cd build
         cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
         ninja -v install
         cd -
     - name: Build and run C API demo with shared
+      shell: bash -l {0}
       run: |
         pushd .
         cd demo/c-api/
@@ -128,31 +127,103 @@ jobs:
         ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
         ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
 
-  cpp-lint:
+  lint:
     runs-on: ubuntu-latest
-    name: Code linting for C++
+    name: Code linting for Python and C++
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
-    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+    - uses: actions/setup-python@v2
       with:
-        python-version: "3.8"
+        python-version: '3.7'
         architecture: 'x64'
     - name: Install Python packages
       run: |
-        python -m pip install wheel setuptools cpplint pylint
+        python -m pip install wheel setuptools
+        python -m pip install pylint cpplint numpy scipy scikit-learn
     - name: Run lint
       run: |
-        python3 dmlc-core/scripts/lint.py xgboost cpp R-package/src
+        make lint
 
-        python3 dmlc-core/scripts/lint.py --exclude_path \
-            python-package/xgboost/dmlc-core \
-            python-package/xgboost/include \
-            python-package/xgboost/lib \
-            python-package/xgboost/rabit \
-            python-package/xgboost/src \
-            --pylint-rc python-package/.pylintrc \
-            xgboost \
-            cpp \
-            include src python-package
+  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 pandas 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/python_tests.yml

@@ -2,139 +2,121 @@ name: XGBoost-Python-Tests
 
 on: [push, pull_request]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-defaults:
-  run:
-    shell: bash -l {0}
-
 jobs:
-  python-mypy-lint:
-    runs-on: ubuntu-latest
-    name: Type and format checks for the Python package
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: python_lint
-        environment-file: tests/ci_build/conda_env/python_lint.yml
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-    - name: Run mypy
-      run: |
-        python tests/ci_build/lint_python.py --format=0 --type-check=1 --pylint=0
-    - name: Run formatter
-      run: |
-        python tests/ci_build/lint_python.py --format=1 --type-check=0 --pylint=0
-    - name: Run pylint
-      run: |
-        python tests/ci_build/lint_python.py --format=0 --type-check=0 --pylint=1
-
-  python-sdist-test-on-Linux:
-    # Mismatched glibcxx version between system and conda forge.
-    runs-on: ${{ matrix.os }}
-    name: Test installing XGBoost Python source package on ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: sdist_test
-        environment-file: tests/ci_build/conda_env/sdist_test.yml
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      run: |
-        cd python-package
-        python --version
-        python -m build --sdist
-        pip install -v ./dist/xgboost-*.tar.gz --config-settings use_openmp=False
-        cd ..
-        python -c 'import xgboost'
-
   python-sdist-test:
-    # Use system toolchain instead of conda toolchain for macos and windows.
-    # MacOS has linker error if clang++ from conda-forge is used
     runs-on: ${{ matrix.os }}
     name: Test installing XGBoost Python source package on ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-11, windows-latest]
+        os: [ubuntu-latest, macos-10.15, windows-latest]
         python-version: ["3.8"]
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - name: Install osx system dependencies
-      if: matrix.os == 'macos-11'
+      if: matrix.os == 'macos-10.15'
       run: |
         brew install ninja libomp
-    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
+    - 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: Install build
-      run: |
-        conda install -c conda-forge python-build
     - 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 -m build --sdist
+        python setup.py sdist
         pip install -v ./dist/xgboost-*.tar.gz
         cd ..
         python -c 'import xgboost'
 
-  python-tests-on-macos:
+  python-tests-on-win:
     name: Test XGBoost Python package on ${{ matrix.config.os }}
     runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 60
     strategy:
       matrix:
         config:
-          - {os: macos-11}
+          - {os: windows-latest, python-version: '3.8'}
 
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+    - uses: conda-incubator/setup-miniconda@v2
       with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: macos_test
+        auto-update-conda: true
+        python-version: ${{ matrix.config.python-version }}
+        activate-environment: win64_env
+        environment-file: tests/ci_build/conda_env/win64_cpu_test.yml
+
+    - name: Display Conda env
+      shell: bash -l {0}
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on Windows
+      shell: bash -l {0}
+      run: |
+        mkdir build_msvc
+        cd build_msvc
+        cmake .. -G"Visual Studio 17 2022" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
+        cmake --build . --config Release --parallel $(nproc)
+
+    - name: Install Python package
+      shell: bash -l {0}
+      run: |
+        cd python-package
+        python --version
+        python setup.py bdist_wheel --universal
+        pip install ./dist/*.whl
+
+    - name: Test Python package
+      shell: bash -l {0}
+      run: |
+        pytest -s -v ./tests/python
+
+  python-tests-on-macos:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    strategy:
+      matrix:
+        config:
+          - {os: macos-10.15, python-version "3.8" }
+
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+
+    - uses: conda-incubator/setup-miniconda@v2
+      with:
+        auto-update-conda: true
+        python-version: ${{ matrix.config.python-version }}
+        activate-environment: macos_test
         environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
 
     - name: Display Conda env
+      shell: bash -l {0}
       run: |
         conda info
         conda list
 
     - name: Build XGBoost on macos
+      shell: bash -l {0}
       run: |
         brew install ninja
 
@@ -143,156 +125,18 @@ jobs:
         # Set prefix, to use OpenMP library from Conda env
         # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
         # to learn why we don't use libomp from Homebrew.
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        cmake .. -GNinja -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
         ninja
 
     - name: Install Python package
+      shell: bash -l {0}
       run: |
         cd python-package
         python --version
-        pip install -v .
-
-    - name: Test Python package
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/python
-
-    - name: Test Dask Interface
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_dask
-
-  python-tests-on-win:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 60
-    strategy:
-      matrix:
-        config:
-          - {os: windows-latest, python-version: '3.8'}
-
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.config.python-version }}
-        activate-environment: win64_env
-        environment-file: tests/ci_build/conda_env/win64_cpu_test.yml
-
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on Windows
-      run: |
-        mkdir build_msvc
-        cd build_msvc
-        cmake .. -G"Visual Studio 17 2022" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
-        cmake --build . --config Release --parallel $(nproc)
-
-    - name: Install Python package
-      run: |
-        cd python-package
-        python --version
-        pip wheel -v . --wheel-dir dist/
+        python setup.py bdist_wheel --universal
         pip install ./dist/*.whl
 
     - name: Test Python package
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/python
-
-  python-tests-on-ubuntu:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 90
-    strategy:
-      matrix:
-        config:
-          - {os: ubuntu-latest, python-version: "3.8"}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: linux_cpu_test
-        environment-file: tests/ci_build/conda_env/linux_cpu_test.yml
-
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on Ubuntu
-      run: |
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja
-
-    - name: Install Python package
-      run: |
-        cd python-package
-        python --version
-        pip install -v .
-
-    - name: Test Python package
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/python
-
-    - name: Test Dask Interface
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_dask
-
-    - name: Test PySpark Interface
       shell: bash -l {0}
       run: |
-        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_spark
-
-  python-system-installation-on-ubuntu:
-    name: Test XGBoost Python package System Installation on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          submodules: 'true'
-
-      - name: Set up Python 3.8
-        uses: actions/setup-python@v4
-        with:
-          python-version: 3.8
-
-      - name: Install ninja
-        run: |
-          sudo apt-get update && sudo apt-get install -y ninja-build
-
-      - name: Build XGBoost on Ubuntu
-        run: |
-          mkdir build
-          cd build
-          cmake .. -GNinja
-          ninja
-
-      - name: Copy lib to system lib
-        run: |
-          cp lib/* "$(python -c 'import sys; print(sys.base_prefix)')/lib"
-
-      - name: Install XGBoost in Virtual Environment
-        run: |
-          cd python-package
-          pip install virtualenv
-          virtualenv venv
-          source venv/bin/activate && \
-            pip install -v . --config-settings use_system_libxgboost=True && \
-            python -c 'import xgboost'
+        pytest -s -v ./tests/python

.github/workflows/python_wheels.yml

@@ -2,9 +2,6 @@ name: XGBoost-Python-Wheels
 
 on: [push, pull_request]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 jobs:
   python-wheels:
     name: Build wheel for ${{ matrix.platform_id }}
@@ -17,13 +14,13 @@ jobs:
         - os: macos-latest
           platform_id: macosx_arm64
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - name: Setup Python
-      uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+      uses: actions/setup-python@v2
       with:
-        python-version: "3.8"
+        python-version: '3.9'
     - name: Build wheels
       run: bash tests/ci_build/build_python_wheels.sh ${{ matrix.platform_id }} ${{ github.sha }}
     - name: Extract branch name

.github/workflows/r_nold.yml

@@ -1,4 +1,4 @@
-# Run expensive R tests with the help of rhub. Only triggered by a pull request review
+# 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
@@ -7,30 +7,34 @@ on:
   pull_request_review_comment:
     types: [created]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
+env:
+  R_PACKAGES: c('XML', 'igraph', 'data.table', '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:
-      image: rhub/debian-gcc-devel-nold
+    container: rhub/debian-gcc-devel-nold
     steps:
     - name: Install git and system packages
       shell: bash
       run: |
-        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
+        apt-get update && apt-get install -y git libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libxml2-dev
 
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
     - name: Install dependencies
-      shell: bash -l {0}
+      shell: bash
       run: |
-        /tmp/R-devel/bin/Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
+        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

.github/workflows/r_tests.yml

@@ -3,11 +3,9 @@ name: XGBoost-R-Tests
 on: [push, pull_request]
 
 env:
+  R_PACKAGES: c('XML', 'data.table', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
   GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 jobs:
   lintr:
     runs-on: ${{ matrix.config.os }}
@@ -15,38 +13,46 @@ jobs:
     strategy:
       matrix:
         config:
-          - {os: ubuntu-latest, r: 'release'}
+          - {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@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@11a22a908006c25fe054c4ef0ac0436b1de3edbe # v2.6.4
+    - uses: r-lib/actions/setup-r@master
       with:
         r-version: ${{ matrix.config.r }}
 
     - name: Cache R packages
-      uses: actions/cache@937d24475381cd9c75ae6db12cb4e79714b926ed # v3.0.11
+      uses: actions/cache@v2
       with:
         path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
 
     - name: Install dependencies
       shell: Rscript {0}
       run: |
-        source("./R-package/tests/helper_scripts/install_deps.R")
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+    - name: Install igraph on Windows
+      shell: Rscript {0}
+      if: matrix.config.os == 'windows-latest'
+      run: |
+        install.packages('igraph', type='binary')
 
     - name: Run lintr
       run: |
-        MAKEFLAGS="-j$(nproc)" R CMD INSTALL R-package/
-        Rscript tests/ci_build/lint_r.R $(pwd)
+        cd R-package
+        R.exe CMD INSTALL .
+        Rscript.exe tests/helper_scripts/run_lint.R
 
-  test-R-on-Windows:
+  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:
@@ -54,82 +60,90 @@ jobs:
       matrix:
         config:
           - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-latest, r: '4.2.0', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@11a22a908006c25fe054c4ef0ac0436b1de3edbe # v2.6.4
+    - uses: r-lib/actions/setup-r@master
       with:
         r-version: ${{ matrix.config.r }}
 
     - name: Cache R packages
-      uses: actions/cache@937d24475381cd9c75ae6db12cb4e79714b926ed # v3.0.11
+      uses: actions/cache@v2
       with:
         path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-
-    - uses: r-lib/actions/setup-tinytex@v2
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
 
     - name: Install dependencies
       shell: Rscript {0}
       run: |
-        source("./R-package/tests/helper_scripts/install_deps.R")
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+    - name: Install igraph on Windows
+      shell: Rscript {0}
+      if: matrix.config.os == 'windows-latest'
+      run: |
+        install.packages('igraph', type='binary', 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 }}" --task=check
+        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool='${{ matrix.config.build }}'
 
-  test-R-on-Debian:
-    name: Test R package on Debian
+  test-R-CRAN:
     runs-on: ubuntu-latest
-    container:
-      image: rhub/debian-gcc-devel
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {r: 'release'}
 
     steps:
-    - name: Install system dependencies
-      run: |
-        # Must run before checkout to have the latest git installed.
-        # No need to add pandoc, the container has it figured out.
-        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
-
-    - name: Trust git cloning project sources
-      run: |
-        git config --global --add safe.directory "${GITHUB_WORKSPACE}"
-
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+    - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - name: Install dependencies
-      shell: bash -l {0}
-      run: |
-        /tmp/R-devel/bin/Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
-
-    - name: Test R
-      shell: bash -l {0}
-      run: |
-        python3 tests/ci_build/test_r_package.py --r=/tmp/R-devel/bin/R --build-tool=autotools --task=check
-
-    - uses: dorny/paths-filter@v2
-      id: changes
+    - uses: r-lib/actions/setup-r@master
       with:
-        filters: |
-          r_package:
-            - 'R-package/**'
+        r-version: ${{ matrix.config.r }}
 
-    - name: Run document check
-      if: steps.changes.outputs.r_package == 'true'
+    - uses: r-lib/actions/setup-tinytex@master
+
+    - name: Install system packages
       run: |
-        python3 tests/ci_build/test_r_package.py --r=/tmp/R-devel/bin/R --task=doc
+        sudo apt-get update && sudo apt-get install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev pandoc pandoc-citeproc libglpk-dev
+
+    - name: Cache R packages
+      uses: actions/cache@v2
+      with:
+        path: ${{ env.R_LIBS_USER }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+        install.packages('igraph', 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

.github/workflows/scorecards.yml

@@ -1,54 +0,0 @@
-name: Scorecards supply-chain security
-on:
-  # Only the default branch is supported.
-  branch_protection_rule:
-  schedule:
-    - cron: '17 2 * * 6'
-  push:
-    branches: [ "master" ]
-
-# Declare default permissions as read only.
-permissions: read-all
-
-jobs:
-  analysis:
-    name: Scorecards analysis
-    runs-on: ubuntu-latest
-    permissions:
-      # Needed to upload the results to code-scanning dashboard.
-      security-events: write
-      # Used to receive a badge.
-      id-token: write
-
-    steps:
-      - name: "Checkout code"
-        uses: actions/checkout@a12a3943b4bdde767164f792f33f40b04645d846 # tag=v3.0.0
-        with:
-          persist-credentials: false
-
-      - name: "Run analysis"
-        uses: ossf/scorecard-action@08b4669551908b1024bb425080c797723083c031 # tag=v2.2.0
-        with:
-          results_file: results.sarif
-          results_format: sarif
-
-          # Publish the results for public repositories to enable scorecard badges. For more details, see
-          # https://github.com/ossf/scorecard-action#publishing-results.
-          # For private repositories, `publish_results` will automatically be set to `false`, regardless
-          # of the value entered here.
-          publish_results: true
-
-      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
-      # format to the repository Actions tab.
-      - name: "Upload artifact"
-        uses: actions/upload-artifact@0b7f8abb1508181956e8e162db84b466c27e18ce # tag=v3.1.2
-        with:
-          name: SARIF file
-          path: results.sarif
-          retention-days: 5
-
-      # Upload the results to GitHub's code scanning dashboard.
-      - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@7b6664fa89524ee6e3c3e9749402d5afd69b3cd8 # tag=v2.14.1
-        with:
-          sarif_file: results.sarif

.github/workflows/update_rapids.yml

@@ -1,44 +0,0 @@
-name: update-rapids
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 20 * * *"  # Run once daily
-
-permissions:
-  pull-requests: write
-  contents: write
-
-defaults:
-  run:
-    shell: bash -l {0}
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-env:
-  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}  # To use GitHub CLI
-
-jobs:
-  update-rapids:
-    name: Check latest RAPIDS
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Check latest RAPIDS and update conftest.sh
-      run: |
-        bash tests/buildkite/update-rapids.sh
-    - name: Create Pull Request
-      uses: peter-evans/create-pull-request@v5
-      if: github.ref == 'refs/heads/master'
-      with:
-        add-paths: |
-          tests/buildkite
-        branch: create-pull-request/update-rapids
-        base: master
-        title: "[CI] Update RAPIDS to latest stable"
-        commit-message: "[CI] Update RAPIDS to latest stable"
-      

.gitignore

@@ -48,13 +48,10 @@ Debug
 *.Rproj
 ./xgboost.mpi
 ./xgboost.mock
-*.bak
 #.Rbuildignore
 R-package.Rproj
 *.cache*
 .mypy_cache/
-doxygen
-
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -100,11 +97,8 @@ metastore_db
 R-package/src/Makevars
 *.lib
 
-# Visual Studio
-.vs/
-CMakeSettings.json
-*.ilk
-*.pdb
+# Visual Studio Code
+/.vscode/
 
 # IntelliJ/CLion
 .idea
@@ -137,16 +131,3 @@ credentials.csv
 .vscode
 .metals
 .bloop
-
-# python tests
-demo/**/*.txt
-*.dmatrix
-.hypothesis
-__MACOSX/
-model*.json
-
-# R tests
-*.libsvm
-*.rds
-Rplots.pdf
-*.zip

.gitmodules

@@ -2,9 +2,9 @@
 	path = dmlc-core
 	url = https://github.com/dmlc/dmlc-core
 	branch = main
+[submodule "cub"]
+	path = cub
+	url = https://github.com/NVlabs/cub
 [submodule "gputreeshap"]
 	path = gputreeshap
 	url = https://github.com/rapidsai/gputreeshap.git
-[submodule "rocgputreeshap"]
-	path = rocgputreeshap
-	url = https://github.com/ROCmSoftwarePlatform/rocgputreeshap

.readthedocs.yaml

@@ -1,34 +0,0 @@
-# .readthedocs.yaml
-# Read the Docs configuration file
-# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
-
-# Required
-version: 2
-
-submodules:
-  include: all
-
-# Set the version of Python and other tools you might need
-build:
-  os: ubuntu-22.04
-  tools:
-    python: "3.8"
-  apt_packages:
-    - graphviz
-    - cmake
-    - g++
-    - doxygen
-    - ninja-build
-
-# Build documentation in the docs/ directory with Sphinx
-sphinx:
-   configuration: doc/conf.py
-
-# If using Sphinx, optionally build your docs in additional formats such as PDF
-formats:
-   - pdf
-
-# Optionally declare the Python requirements required to build your docs
-python:
-  install:
-   - requirements: doc/requirements.txt

.travis.yml

@@ -0,0 +1,53 @@
+sudo: required
+
+dist: bionic
+
+env:
+  global:
+    - secure: "lqkL5SCM/CBwgVb1GWoOngpojsa0zCSGcvF0O3/45rBT1EpNYtQ4LRJ1+XcHi126vdfGoim/8i7AQhn5eOgmZI8yAPBeoUZ5zSrejD3RUpXr2rXocsvRRP25Z4mIuAGHD9VAHtvTdhBZRVV818W02pYduSzAeaY61q/lU3xmWsE="
+    - secure: "mzms6X8uvdhRWxkPBMwx+mDl3d+V1kUpZa7UgjT+dr4rvZMzvKtjKp/O0JZZVogdgZjUZf444B98/7AvWdSkGdkfz2QdmhWmXzNPfNuHtmfCYMdijsgFIGLuD3GviFL/rBiM2vgn32T3QqFiEJiC5StparnnXimPTc9TpXQRq5c="
+
+
+jobs:
+  include:
+    - os: linux
+      arch: s390x
+      env: TASK=s390x_test
+
+# dependent brew packages
+# the dependencies from homebrew is installed manually from setup script due to outdated image from travis.
+addons:
+  homebrew:
+    update: false
+  apt:
+    packages:
+      - unzip
+
+before_install:
+  - source tests/travis/travis_setup_env.sh
+
+install:
+  - source tests/travis/setup.sh
+
+script:
+  - tests/travis/run_test.sh
+
+cache:
+  directories:
+    - ${HOME}/.cache/usr
+    - ${HOME}/.cache/pip
+
+before_cache:
+  - tests/travis/travis_before_cache.sh
+
+after_failure:
+  - tests/travis/travis_after_failure.sh
+
+after_success:
+  - tree build
+  - bash <(curl -s https://codecov.io/bash) -a '-o src/ src/*.c'
+
+notifications:
+  email:
+    on_success: change
+    on_failure: always

CITATION

@@ -15,3 +15,4 @@
  address = {New York, NY, USA},
  keywords = {large-scale machine learning},
 }
+

CMakeLists.txt

@@ -1,10 +1,9 @@
-cmake_minimum_required(VERSION 3.18 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 2.0.1)
+cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
+project(xgboost LANGUAGES CXX C VERSION 1.6.2)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)
 cmake_policy(SET CMP0079 NEW)
-cmake_policy(SET CMP0076 NEW)
 set(CMAKE_POLICY_DEFAULT_CMP0063 NEW)
 cmake_policy(SET CMP0063 NEW)
 
@@ -14,24 +13,8 @@ endif ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUA
 
 message(STATUS "CMake version ${CMAKE_VERSION}")
 
-# Check compiler versions
-# Use recent compilers to ensure that std::filesystem is available
-if(MSVC)
-  if(MSVC_VERSION LESS 1920)
-    message(FATAL_ERROR "Need Visual Studio 2019 or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "8.1")
-    message(FATAL_ERROR "Need GCC 8.1 or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "11.0")
-    message(FATAL_ERROR "Need Xcode 11.0 (AppleClang 11.0) or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "9.0")
-    message(FATAL_ERROR "Need Clang 9.0 or newer to build XGBoost")
-  endif()
+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)
@@ -58,23 +41,18 @@ option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC
 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/HIP device debug info." 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)
-option(KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR "Output build artifacts in CMake binary dir" OFF)
 ## CUDA
 option(USE_CUDA  "Build with GPU acceleration" OFF)
-option(USE_PER_THREAD_DEFAULT_STREAM "Build with per-thread default stream" ON)
 option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
 option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
+option(BUILD_WITH_CUDA_CUB "Build with cub in CUDA installation" OFF)
 set(GPU_COMPUTE_VER "" CACHE STRING
   "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
-## HIP
-option(USE_HIP  "Build with GPU acceleration" OFF)
-option(USE_RCCL "Build with RCCL to enable distributed GPU support." OFF)
-option(BUILD_WITH_SHARED_RCCL "Build with shared RCCL library." OFF)
 ## Copied From dmlc
 option(USE_HDFS "Build with HDFS support" OFF)
 option(USE_AZURE "Build with AZURE support" OFF)
@@ -88,7 +66,6 @@ address, leak, undefined and thread.")
 ## Plugins
 option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
 option(PLUGIN_RMM "Build with RAPIDS Memory Manager (RMM)" OFF)
-option(PLUGIN_FEDERATED "Build with Federated Learning" 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)
@@ -97,7 +74,6 @@ option(ADD_PKGCONFIG "Add xgboost.pc into system." ON)
 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))
@@ -107,17 +83,6 @@ 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 (USE_RCCL AND NOT (USE_HIP))
-  message(SEND_ERROR "`USE_RCCL` must be enabled with `USE_HIP` flag.")
-endif (USE_RCCL AND NOT (USE_HIP))
-if (USE_DEVICE_DEBUG AND NOT (USE_HIP))
-  message(SEND_ERROR "`USE_DEVICE_DEBUG` must be enabled with `USE_HIP` flag.")
-endif (USE_DEVICE_DEBUG AND NOT (USE_HIP))
-if (BUILD_WITH_SHARED_RCCL AND (NOT USE_RCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_RCCL=ON to enable BUILD_WITH_SHARED_RCCL.")
-endif (BUILD_WITH_SHARED_RCCL AND (NOT USE_RCCL))
-
 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)
@@ -131,15 +96,9 @@ endif (USE_AVX)
 if (PLUGIN_LZ4)
   message(SEND_ERROR  "The option 'PLUGIN_LZ4' is removed from XGBoost.")
 endif (PLUGIN_LZ4)
-
 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 (USE_HIP))
-  message(SEND_ERROR "`PLUGIN_RMM` must be enabled with `USE_HIP` flag.")
-endif (PLUGIN_RMM AND NOT (USE_HIP))
-
 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")))
@@ -154,20 +113,9 @@ 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))
-if (PLUGIN_FEDERATED)
-  if (CMAKE_CROSSCOMPILING)
-    message(SEND_ERROR "Cannot cross compile with federated learning support")
-  endif ()
-  if (BUILD_STATIC_LIB)
-    message(SEND_ERROR "Cannot build static lib with federated learning support")
-  endif ()
-  if (R_LIB OR JVM_BINDINGS)
-    message(SEND_ERROR "Cannot enable federated learning support when R or JVM packages are enabled.")
-  endif ()
-  if (WIN32)
-    message(SEND_ERROR "Federated learning not supported for Windows platform")
-  endif ()
-endif ()
+if (PLUGIN_RMM AND (NOT BUILD_WITH_CUDA_CUB))
+  message(SEND_ERROR "Cannot build with RMM using cub submodule.")
+endif (PLUGIN_RMM AND (NOT BUILD_WITH_CUDA_CUB))
 
 #-- Sanitizer
 if (USE_SANITIZER)
@@ -182,34 +130,18 @@ if (USE_CUDA)
   message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
 
   enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 11.0)
-    message(FATAL_ERROR "CUDA version must be at least 11.0!")
+  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.1)
+    message(FATAL_ERROR "CUDA version must be at least 10.1!")
   endif()
   set(GEN_CODE "")
   format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
   add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
 
-  find_package(CUDAToolkit REQUIRED)
+  if ((${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 11.4) AND (NOT BUILD_WITH_CUDA_CUB))
+    set(BUILD_WITH_CUDA_CUB ON)
+  endif ()
 endif (USE_CUDA)
 
-if (USE_HIP)
-  set(USE_OPENMP ON CACHE BOOL "HIP requires OpenMP" FORCE)
-  # `export CXX=' is ignored by CMake HIP.
-  set(CMAKE_HIP_HOST_COMPILER ${CMAKE_CXX_COMPILER})
-  message(STATUS "Configured HIP host compiler: ${CMAKE_HIP_HOST_COMPILER}")
-
-  enable_language(HIP)
-  find_package(hip REQUIRED)
-  find_package(rocthrust REQUIRED)
-  find_package(hipcub REQUIRED)
-
-  set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} -I${HIP_INCLUDE_DIRS} -I${HIP_INCLUDE_DIRS}/hip")
-  set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} -Wunused-result -w")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__HIP_PLATFORM_AMD__")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -I${HIP_INCLUDE_DIRS}")
-  add_subdirectory(${PROJECT_SOURCE_DIR}/rocgputreeshap)
-endif (USE_HIP)
-
 if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
     ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
       (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
@@ -220,39 +152,17 @@ find_package(Threads REQUIRED)
 
 if (USE_OPENMP)
   if (APPLE)
-    find_package(OpenMP)
-    if (NOT OpenMP_FOUND)
-      # Try again with extra path info; required for libomp 15+ from Homebrew
-      execute_process(COMMAND brew --prefix libomp
-                      OUTPUT_VARIABLE HOMEBREW_LIBOMP_PREFIX
-                      OUTPUT_STRIP_TRAILING_WHITESPACE)
-      set(OpenMP_C_FLAGS
-        "-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include")
-      set(OpenMP_CXX_FLAGS
-        "-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include")
-      set(OpenMP_C_LIB_NAMES omp)
-      set(OpenMP_CXX_LIB_NAMES omp)
-      set(OpenMP_omp_LIBRARY ${HOMEBREW_LIBOMP_PREFIX}/lib/libomp.dylib)
-      find_package(OpenMP REQUIRED)
-    endif ()
-  else ()
-    find_package(OpenMP REQUIRED)
-  endif ()
+    # Require CMake 3.16+ on Mac OSX, as previous versions of CMake had trouble locating
+    # OpenMP on Mac. See https://github.com/dmlc/xgboost/pull/5146#issuecomment-568312706
+    cmake_minimum_required(VERSION 3.16)
+  endif (APPLE)
+  find_package(OpenMP REQUIRED)
 endif (USE_OPENMP)
-#Add for IBM i
-if (${CMAKE_SYSTEM_NAME} MATCHES "OS400")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
-  set(CMAKE_CXX_ARCHIVE_CREATE "<CMAKE_AR> -X64 qc <TARGET> <OBJECTS>")
-endif()
 
 if (USE_NCCL)
   find_package(Nccl REQUIRED)
 endif (USE_NCCL)
 
-if (USE_RCCL)
-  find_package(rccl REQUIRED)
-endif (USE_RCCL)
-
 # dmlc-core
 msvc_use_static_runtime()
 if (FORCE_SHARED_CRT)
@@ -277,11 +187,6 @@ endif (RABIT_BUILD_MPI)
 add_subdirectory(${xgboost_SOURCE_DIR}/src)
 target_link_libraries(objxgboost PUBLIC dmlc)
 
-# Link -lstdc++fs for GCC 8.x
-if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "9.0")
-  target_link_libraries(objxgboost PUBLIC stdc++fs)
-endif()
-
 # Exports some R specific definitions and objects
 if (R_LIB)
   add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
@@ -297,15 +202,6 @@ add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
 
 if (PLUGIN_RMM)
   find_package(rmm REQUIRED)
-
-  # Patch the rmm targets so they reference the static cudart
-  # Remove this patch once RMM stops specifying cudart requirement
-  # (since RMM is a header-only library, it should not specify cudart in its CMake config)
-  get_target_property(rmm_link_libs rmm::rmm INTERFACE_LINK_LIBRARIES)
-  list(REMOVE_ITEM rmm_link_libs CUDA::cudart)
-  list(APPEND rmm_link_libs CUDA::cudart_static)
-  set_target_properties(rmm::rmm PROPERTIES INTERFACE_LINK_LIBRARIES "${rmm_link_libs}")
-  get_target_property(rmm_link_libs rmm::rmm INTERFACE_LINK_LIBRARIES)
 endif (PLUGIN_RMM)
 
 #-- library
@@ -346,13 +242,8 @@ if (JVM_BINDINGS)
   xgboost_target_defs(xgboost4j)
 endif (JVM_BINDINGS)
 
-if (KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR)
-  set_output_directory(runxgboost ${xgboost_BINARY_DIR})
-  set_output_directory(xgboost ${xgboost_BINARY_DIR}/lib)
-else ()
-  set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
-  set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
-endif ()
+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)
 

Jenkinsfile

@@ -0,0 +1,453 @@
+#!/usr/bin/groovy
+// -*- mode: groovy -*-
+// Jenkins pipeline
+// See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
+
+// Command to run command inside a docker container
+dockerRun = 'tests/ci_build/ci_build.sh'
+
+// Which CUDA version to use when building reference distribution wheel
+ref_cuda_ver = '11.0.3'
+
+import groovy.transform.Field
+
+@Field
+def commit_id   // necessary to pass a variable from one stage to another
+
+pipeline {
+  // 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: 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}"
+        }
+        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 11.0
+            // using CentOS 7 image
+            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0.3', build_rmm: true) },
+            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '11.0.3') },
+            'build-jvm-packages-gpu-cuda11.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.1', cuda_version: '11.0.3') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.1') },
+            'build-jvm-doc': { BuildJVMDoc() }
+          ])
+        }
+      }
+    }
+    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-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', test_rmm: true) },
+            'test-python-mgpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', multi_gpu: true, test_rmm: true) },
+            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', test_rmm: true) },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') }
+          ])
+        }
+      }
+    }
+    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_centos7' : '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=11.0.3"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py --cuda-archs 75
+    """
+    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_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...'
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate aarch64_test && python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress"
+      """
+    }
+    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 = "manylinux2014_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...'
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress
+      """
+    }
+    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 -DBUILD_WITH_CUDA_CUB=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 ${commit_id} manylinux2014_x86_64
+      """
+      echo 'Stashing Python wheel...'
+      stash name: "xgboost_whl_rmm_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
+      echo 'Stashing C++ test executable (testxgboost)...'
+      stash name: "xgboost_cpp_tests_rmm_cuda${args.cuda_version}", includes: 'build/testxgboost'
+    }
+    deleteDir()
+  }
+}
+
+def BuildRPackageWithCUDA(args) {
+  node('linux && cpu_build') {
+    unstash name: 'srcs'
+    def container_type = 'gpu_build_r_centos7'
+    def docker_binary = "docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    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...'
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python -m awscli s3 cp xgboost_r_gpu_linux_*.tar.gz s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress
+      """
+    }
+    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...'
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} python -m awscli s3 cp jvm-packages/${BRANCH_NAME}.tar.bz2 s3://xgboost-docs/${BRANCH_NAME}.tar.bz2 --acl public-read --no-progress
+      """
+    }
+    deleteDir()
+  }
+}
+
+def TestPythonCPU() {
+  node('linux && cpu') {
+    unstash name: "xgboost_whl_cuda${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}, rmm: ${args.test_rmm}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${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"
+      """
+    }
+    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=11.0.3 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      """
+    }
+    deleteDir()
+  }
+}

Jenkinsfile-win64

@@ -0,0 +1,163 @@
+#!/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-cuda11.0': { BuildWin64() },
+            'build-rpkg-win64-cuda11.0': { BuildRPackageWithCUDAWin64() }
+          ])
+        }
+      }
+    }
+    stage('Jenkins Win64: Test') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'test-win64-cuda11.0': { 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 && cuda11_unified') {
+    deleteDir()
+    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}/"
+      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 BuildRPackageWithCUDAWin64() {
+  node('win64 && cuda11_unified') {
+    deleteDir()
+    unstash name: 'srcs'
+    bat "nvcc --version"
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      bat """
+      bash tests/ci_build/build_r_pkg_with_cuda_win64.sh ${commit_id}
+      """
+      echo 'Uploading R tarball...'
+      path = "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_win64_*.tar.gz'
+    }
+    deleteDir()
+  }
+}
+
+def TestWin64() {
+  node('win64 && cuda11_unified') {
+    deleteDir()
+    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 activate && mamba 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 -X faulthandler -m pytest -v -s -rxXs --fulltrace tests\\python"
+    bat """
+    conda activate ${env_name} && python -X faulthandler -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
+    """
+    bat "conda env remove --name ${env_name}"
+    deleteDir()
+  }
+}

Makefile

@@ -0,0 +1,169 @@
+ifndef DMLC_CORE
+	DMLC_CORE = dmlc-core
+endif
+
+ifndef RABIT
+	RABIT = rabit
+endif
+
+ROOTDIR = $(CURDIR)
+
+# workarounds for some buggy old make & msys2 versions seen in windows
+ifeq (NA, $(shell test ! -d "$(ROOTDIR)" && echo NA ))
+        $(warning Attempting to fix non-existing ROOTDIR [$(ROOTDIR)])
+        ROOTDIR := $(shell pwd)
+        $(warning New ROOTDIR [$(ROOTDIR)] $(shell test -d "$(ROOTDIR)" && echo " is OK" ))
+endif
+MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
+ifndef MAKE_OK
+        $(warning Attempting to recover non-functional MAKE [$(MAKE)])
+        MAKE := $(shell which make 2> /dev/null)
+        MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
+endif
+$(warning MAKE [$(MAKE)] - $(if $(MAKE_OK),checked OK,PROBLEM))
+
+include $(DMLC_CORE)/make/dmlc.mk
+
+# set compiler defaults for OSX versus *nix
+# let people override either
+OS := $(shell uname)
+ifeq ($(OS), Darwin)
+ifndef CC
+export CC = $(if $(shell which clang), clang, gcc)
+endif
+ifndef CXX
+export CXX = $(if $(shell which clang++), clang++, g++)
+endif
+else
+# linux defaults
+ifndef CC
+export CC = gcc
+endif
+ifndef CXX
+export CXX = g++
+endif
+endif
+
+export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++14 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
+CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
+
+ifeq ($(TEST_COVER), 1)
+	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
+else
+	CFLAGS += -O3 -funroll-loops
+endif
+
+ifndef LINT_LANG
+	LINT_LANG= "all"
+endif
+
+# specify tensor path
+.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck
+
+build/%.o: src/%.cc
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.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 $@
+
+rcpplint:
+	python3 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 \
+	  ${LINT_LANG} include src python-package
+
+ifeq ($(TEST_COVER), 1)
+cover: check
+	@- $(foreach COV_OBJ, $(COVER_OBJ), \
+		gcov -pbcul -o $(shell dirname $(COV_OBJ)) $(COV_OBJ) > gcov.log || cat gcov.log; \
+	)
+endif
+
+
+# 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 && \
+	mypy ./xgboost/rabit.py && \
+	mypy ./xgboost/tracker.py && \
+	mypy ./xgboost/sklearn.py && \
+	mypy ../demo/guide-python/external_memory.py && \
+	mypy ../demo/guide-python/categorical.py && \
+	mypy ../demo/guide-python/cat_in_the_dat.py && \
+	mypy ../tests/python-gpu/test_gpu_with_dask.py && \
+	mypy ../tests/python/test_data_iterator.py && \
+	mypy ../tests/python-gpu/test_gpu_data_iterator.py  || exit 1; \
+	mypy . || true ;
+
+clean:
+	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
+	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
+	if [ -d "R-package/src" ]; then \
+		cd R-package/src; \
+		$(RM) -rf rabit src include dmlc-core amalgamation *.so *.dll; \
+		cd $(ROOTDIR); \
+	fi
+
+clean_all: clean
+	cd $(DMLC_CORE); "$(MAKE)" clean; cd $(ROOTDIR)
+	cd $(RABIT); "$(MAKE)" clean; cd $(ROOTDIR)
+
+# create pip source dist (sdist) pack for PyPI
+pippack: clean_all
+	cd python-package; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
+
+# Script to make a clean installable R package.
+Rpack: clean_all
+	rm -rf xgboost xgboost*.tar.gz
+	cp -r R-package xgboost
+	rm -rf xgboost/src/*.o xgboost/src/*.so xgboost/src/*.dll
+	rm -rf xgboost/src/*/*.o
+	rm -rf xgboost/demo/*.model xgboost/demo/*.buffer xgboost/demo/*.txt
+	rm -rf xgboost/demo/runall.R
+	cp -r src xgboost/src/src
+	cp -r include xgboost/src/include
+	cp -r amalgamation xgboost/src/amalgamation
+	mkdir -p xgboost/src/rabit
+	cp -r rabit/include xgboost/src/rabit/include
+	cp -r rabit/src xgboost/src/rabit/src
+	rm -rf xgboost/src/rabit/src/*.o
+	mkdir -p xgboost/src/dmlc-core
+	cp -r dmlc-core/include xgboost/src/dmlc-core/include
+	cp -r dmlc-core/src xgboost/src/dmlc-core/src
+	cp ./LICENSE xgboost
+# 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)
+	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 xgboost/CMakeLists.txt
+	rm -rfv xgboost/tests/helper_scripts/
+
+R ?= R
+
+Rbuild: Rpack
+	$(R) CMD build xgboost
+	rm -rf xgboost
+
+Rcheck: Rbuild
+	$(R) CMD check --as-cran xgboost*.tar.gz
+
+-include build/*.d
+-include build/*/*.d

NEWS.md

@@ -3,483 +3,6 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
-## 1.7.6 (2023 Jun 16)
-
-This is a patch release for bug fixes. The CRAN package for the R binding is kept at 1.7.5.
-
-### Bug Fixes
-* Fix distributed training with mixed dense and sparse partitions. (#9272)
-* Fix monotone constraints on CPU with large trees. (#9122)
-* [spark] Make the spark model have the same UID as its estimator (#9022)
-* Optimize prediction with `QuantileDMatrix`. (#9096)
-
-### Document
-* Improve doxygen (#8959)
-* Update the cuDF pip index URL. (#9106)
-
-### Maintenance
-* Fix tests with pandas 2.0. (#9014)
-
-## 1.7.5 (2023 Mar 30)
-This is a patch release for bug fixes.
-
-* C++ requirement is updated to C++-17, along with which, CUDA 11.8 is used as the default CTK. (#8860, #8855, #8853)
-* Fix import for pyspark ranker. (#8692)
-* Fix Windows binary wheel to be compatible with Poetry (#8991)
-* Fix GPU hist with column sampling. (#8850)
-* Make sure iterative DMatrix is properly initialized. (#8997)
-* [R] Update link in document. (#8998)
-
-## 1.7.4 (2023 Feb 16)
-This is a patch release for bug fixes.
-
-* [R] Fix OpenMP detection on macOS. (#8684)
-* [Python] Make sure input numpy array is aligned. (#8690)
-* Fix feature interaction with column sampling in gpu_hist evaluator. (#8754)
-* Fix GPU L1 error. (#8749)
-* [PySpark] Fix feature types param (#8772)
-* Fix ranking with quantile dmatrix and group weight. (#8762)
-
-## 1.7.3 (2023 Jan 6)
-This is a patch release for bug fixes.
-
-* [Breaking] XGBoost Sklearn estimator method `get_params` no longer returns internally configured values. (#8634)
-* Fix linalg iterator, which may crash the L1 error. (#8603)
-* Fix loading pickled GPU model with a CPU-only XGBoost build. (#8632)
-* Fix inference with unseen categories with categorical features. (#8591, #8602)
-* CI fixes. (#8620, #8631, #8579)
-
-## v1.7.2 (2022 Dec 8)
-This is a patch release for bug fixes.
-
-* Work with newer thrust and libcudacxx (#8432)
-* Support null value in CUDA array interface namespace. (#8486)
-* Use `getsockname` instead of `SO_DOMAIN` on AIX. (#8437)
-* [pyspark] Make QDM optional based on a cuDF check (#8471)
-* [pyspark] sort qid for SparkRanker. (#8497)
-* [dask] Properly await async method client.wait_for_workers. (#8558)
-
-* [R] Fix CRAN test notes. (#8428)
-
-* [doc] Fix outdated document [skip ci]. (#8527)
-* [CI] Fix github action mismatched glibcxx. (#8551)
-
-## v1.7.1 (2022 Nov 3)
-This is a patch release to incorporate the following hotfix:
-
-* Add back xgboost.rabit for backwards compatibility (#8411)
-
-
-## v1.7.0 (2022 Oct 20)
-
-We are excited to announce the feature packed XGBoost 1.7 release. The release note will walk through some of the major new features first, then make a summary for other improvements and language-binding-specific changes.
-
-### PySpark
-
-XGBoost 1.7 features initial support for PySpark integration. The new interface is adapted from the existing PySpark XGBoost interface developed by databricks with additional features like `QuantileDMatrix` and the rapidsai plugin (GPU pipeline) support. The new Spark XGBoost Python estimators not only benefit from PySpark ml facilities for powerful distributed computing but also enjoy the rest of the Python ecosystem. Users can define a custom objective, callbacks, and metrics in Python and use them with this interface on distributed clusters. The support is labeled as experimental with more features to come in future releases. For a brief introduction please visit the tutorial on XGBoost's [document page](https://xgboost.readthedocs.io/en/latest/tutorials/spark_estimator.html). (#8355, #8344, #8335, #8284, #8271, #8283, #8250, #8231, #8219, #8245, #8217, #8200, #8173, #8172, #8145, #8117, #8131, #8088, #8082, #8085, #8066, #8068, #8067, #8020, #8385)
-
-Due to its initial support status, the new interface has some limitations; categorical features and multi-output models are not yet supported.
-
-### Development of categorical data support
-More progress on the experimental support for categorical features. In 1.7, XGBoost can handle missing values in categorical features and features a new parameter `max_cat_threshold`, which limits the number of categories that can be used in the split evaluation. The parameter is enabled when the partitioning algorithm is used and helps prevent over-fitting. Also, the sklearn interface can now accept the `feature_types` parameter to use data types other than dataframe for categorical features. (#8280, #7821, #8285, #8080, #7948, #7858, #7853, #8212, #7957, #7937, #7934)
-
-
-###  Experimental support for federated learning and new communication collective
-
-An exciting addition to XGBoost is the experimental federated learning support. The federated learning is implemented with a gRPC federated server that aggregates allreduce calls, and federated clients that train on local data and use existing tree methods (approx, hist, gpu_hist). Currently, this only supports horizontal federated learning (samples are split across participants, and each participant has all the features and labels). Future plans include vertical federated learning (features split across participants), and stronger privacy guarantees with homomorphic encryption and differential privacy. See [Demo with NVFlare integration](demo/nvflare/README.md) for example usage with nvflare.
-
-As part of the work, XGBoost 1.7 has replaced the old rabit module with the new collective module as the network communication interface with added support for runtime backend selection. In previous versions, the backend is defined at compile time and can not be changed once built. In this new release, users can choose between `rabit` and `federated.` (#8029, #8351, #8350, #8342, #8340, #8325, #8279, #8181, #8027, #7958, #7831, #7879, #8257, #8316, #8242, #8057, #8203, #8038, #7965, #7930, #7911)
-
-The feature is available in the public PyPI binary package for testing.
-
-### Quantile DMatrix
-Before 1.7, XGBoost has an internal data structure called `DeviceQuantileDMatrix` (and its distributed version). We now extend its support to CPU and renamed it to `QuantileDMatrix`. This data structure is used for optimizing memory usage for the `hist` and `gpu_hist` tree methods. The new feature helps reduce CPU memory usage significantly, especially for dense data. The new `QuantileDMatrix` can be initialized from both CPU and GPU data, and regardless of where the data comes from, the constructed instance can be used by both the CPU algorithm and GPU algorithm including training and prediction (with some overhead of conversion if the device of data and training algorithm doesn't match). Also, a new parameter `ref` is added to `QuantileDMatrix`, which can be used to construct validation/test datasets. Lastly, it's set as default in the scikit-learn interface when a supported tree method is specified by users. (#7889, #7923, #8136, #8215, #8284, #8268, #8220, #8346, #8327, #8130, #8116, #8103, #8094, #8086, #7898, #8060, #8019, #8045, #7901, #7912, #7922)
-
-### Mean absolute error
-The mean absolute error is a new member of the collection of objectives in XGBoost. It's noteworthy since MAE has zero hessian value, which is unusual to XGBoost as XGBoost relies on Newton optimization. Without valid Hessian values, the convergence speed can be slow. As part of the support for MAE, we added line searches into the XGBoost training algorithm to overcome the difficulty of training without valid Hessian values. In the future, we will extend the line search to other objectives where it's appropriate for faster convergence speed. (#8343, #8107, #7812, #8380)
-
-### XGBoost on Browser
-With the help of the [pyodide](https://github.com/pyodide/pyodide) project, you can now run XGBoost on browsers. (#7954, #8369)
-
-### Experimental IPv6 Support for Dask
-
-With the growing adaption of the new internet protocol, XGBoost joined the club. In the latest release, the Dask interface can be used on IPv6 clusters, see XGBoost's Dask tutorial for details. (#8225, #8234)
-
-### Optimizations
-We have new optimizations for both the `hist` and `gpu_hist` tree methods to make XGBoost's training even more efficient.
-
-* Hist
-Hist now supports optional by-column histogram build, which is automatically configured based on various conditions of input data. This helps the XGBoost CPU hist algorithm to scale better with different shapes of training datasets. (#8233, #8259). Also, the build histogram kernel now can better utilize CPU registers (#8218)
-
-* GPU Hist
-GPU hist performance is significantly improved for wide datasets. GPU hist now supports batched node build, which reduces kernel latency and increases throughput. The improvement is particularly significant when growing deep trees with the default ``depthwise`` policy. (#7919, #8073, #8051, #8118, #7867, #7964, #8026)
-
-### Breaking Changes
-Breaking changes made in the 1.7 release are summarized below.
-- The  `grow_local_histmaker`  updater is removed. This updater is rarely used in practice and has no test. We decided to remove it and focus have XGBoot focus on other more efficient algorithms. (#7992, #8091)
-- Single precision histogram is removed due to its lack of accuracy caused by significant floating point error. In some cases the error can be difficult to detect due to log-scale operations, which makes the parameter dangerous to use. (#7892, #7828)
-- Deprecated CUDA architectures are no longer supported in the release binaries. (#7774)
-- As part of the federated learning development, the `rabit` module is replaced with the new `collective` module. It's a drop-in replacement with added runtime backend selection, see the federated learning section for more details (#8257)
-
-### General new features and improvements
-Before diving into package-specific changes, some general new features other than those listed at the beginning are summarized here.
-* Users of `DMatrix` and `QuantileDMatrix` can get the data from XGBoost. In previous versions, only getters for meta info like labels are available. The new method is available in Python (`DMatrix::get_data`) and C. (#8269, #8323)
-* In previous versions, the GPU histogram tree method may generate phantom gradient for missing values due to floating point error. We fixed such an error in this release and XGBoost is much better equated to handle floating point errors when training on GPU. (#8274, #8246)
-* Parameter validation is no longer experimental. (#8206)
-* C pointer parameters and JSON parameters are vigorously checked. (#8254, #8254)
-* Improved handling of JSON model input. (#7953, #7918)
-* Support IBM i OS (#7920, #8178)
-
-### Fixes
-Some noteworthy bug fixes that are not related to specific language binding are listed in this section.
-* Rename misspelled config parameter for pseudo-Huber (#7904)
-* Fix feature weights with nested column sampling. (#8100)
-* Fix loading DMatrix binary in distributed env. (#8149)
-* Force auc.cc to be statically linked for unusual compiler platforms. (#8039)
-* New logic for detecting libomp on macos (#8384).
-
-### Python Package
-* Python 3.8 is now the minimum required Python version. (#8071)
-* More progress on type hint support. Except for the new PySpark interface, the XGBoost module is fully typed. (#7742, #7945, #8302, #7914, #8052)
-* XGBoost now validates the feature names in `inplace_predict`, which also affects the predict function in scikit-learn estimators as it uses `inplace_predict` internally. (#8359)
-* Users can now get the data from `DMatrix` using `DMatrix::get_data` or `QuantileDMatrix::get_data`.
-* Show `libxgboost.so` path in build info. (#7893)
-* Raise import error when using the sklearn module while scikit-learn is missing. (#8049)
-* Use `config_context` in the sklearn interface. (#8141)
-* Validate features for inplace prediction. (#8359)
-* Pandas dataframe handling is refactored to reduce data fragmentation. (#7843)
-* Support more pandas nullable types (#8262)
-* Remove pyarrow workaround. (#7884)
-
-* Binary wheel size
-We aim to enable as many features as possible in XGBoost's default binary distribution on PyPI (package installed with pip), but there's a upper limit on the size of the binary wheel. In 1.7, XGBoost reduces the size of the wheel by pruning unused CUDA architectures. (#8179, #8152, #8150)
-
-* Fixes
-  Some noteworthy fixes are listed here:
-  - Fix the Dask interface with the latest cupy. (#8210)
-  - Check cuDF lazily to avoid potential errors with cuda-python. (#8084)
-* Fix potential error in DMatrix constructor on 32-bit platform. (#8369)
-
-* Maintenance work
-  - Linter script is moved from dmlc-core to XGBoost with added support for formatting, mypy, and parallel run, along with some fixes (#7967, #8101, #8216)
-  - We now require the use of `isort` and `black` for selected files. (#8137, #8096)
-  - Code cleanups. (#7827)
-  - Deprecate `use_label_encoder` in XGBClassifier. The label encoder has already been deprecated and removed in the previous version. These changes only affect the indicator parameter (#7822)
-  - Remove the use of distutils. (#7770)
-  - Refactor and fixes for tests (#8077, #8064, #8078, #8076, #8013, #8010, #8244, #7833)
-
-* Documents
-  - [dask] Fix potential error in demo. (#8079)
-  - Improved documentation for the ranker. (#8356, #8347)
-  - Indicate lack of py-xgboost-gpu on Windows (#8127)
-  - Clarification for feature importance. (#8151)
-  - Simplify Python getting started example (#8153)
-
-### R Package
-We summarize improvements for the R package briefly here:
-* Feature info including names and types are now passed to DMatrix in preparation for categorical feature support. (#804)
-* XGBoost 1.7 can now gracefully load old R models from RDS for better compatibility with 3-party tuning libraries (#7864)
-* The R package now can be built with parallel compilation, along with fixes for warnings in CRAN tests. (#8330)
-* Emit error early if DiagrammeR is missing (#8037)
-* Fix R package Windows build. (#8065)
-
-### JVM Packages
-The consistency between JVM packages and other language bindings is greatly improved in 1.7, improvements range from model serialization format to the default value of hyper-parameters.
-
-* Java package now supports feature names and feature types for DMatrix in preparation for categorical feature support. (#7966)
-* Models trained by the JVM packages can now be safely used with other language bindings. (#7896, #7907)
-* Users can specify the model format when saving models with a stream. (#7940, #7955)
-* The default value for training parameters is now sourced from XGBoost directly, which helps JVM packages be consistent with other packages. (#7938)
-* Set the correct objective if the user doesn't explicitly set it (#7781)
-* Auto-detection of MUSL is replaced by system properties (#7921)
-* Improved error message for launching tracker. (#7952, #7968)
-* Fix a race condition in parameter configuration. (#8025)
-* [Breaking] ` timeoutRequestWorkers` is now removed. With the support for barrier mode, this parameter is no longer needed. (#7839)
-* Dependencies updates. (#7791, #8157, #7801, #8240)
-
-### Documents
-- Document for the C interface is greatly improved and is now displayed at the [sphinx document page](https://xgboost.readthedocs.io/en/latest/c.html). Thanks to the breathe project, you can view the C API just like the Python API. (#8300)
-- We now avoid having XGBoost internal text parser in demos and recommend users use dedicated libraries for loading data whenever it's feasible. (#7753)
-- Python survival training demos are now displayed at [sphinx gallery](https://xgboost.readthedocs.io/en/latest/python/survival-examples/index.html). (#8328)
-- Some typos, links, format, and grammar fixes. (#7800, #7832, #7861, #8099, #8163, #8166, #8229, #8028, #8214, #7777, #7905, #8270, #8309, d70e59fef, #7806)
-- Updated winning solution under readme.md (#7862)
-- New security policy. (#8360)
-- GPU document is overhauled as we consider CUDA support to be feature-complete. (#8378)
-
-### Maintenance
-* Code refactoring and cleanups. (#7850, #7826, #7910, #8332, #8204)
-* Reduce compiler warnings. (#7768, #7916, #8046, #8059, #7974, #8031, #8022)
-* Compiler workarounds. (#8211, #8314, #8226, #8093)
-* Dependencies update. (#8001, #7876, #7973, #8298, #7816)
-* Remove warnings emitted in previous versions. (#7815)
-* Small fixes occurred during development. (#8008)
-
-### CI and Tests
-* We overhauled the CI infrastructure to reduce the CI cost and lift the maintenance burdens. Jenkins is replaced with buildkite for better automation, with which, finer control of test runs is implemented to reduce overall cost. Also, we refactored some of the existing tests to reduce their runtime, drooped the size of docker images, and removed multi-GPU C++ tests. Lastly, `pytest-timeout` is added as an optional dependency for running Python tests to keep the test time in check. (#7772, #8291, #8286, #8276, #8306, #8287, #8243, #8313, #8235, #8288, #8303, #8142, #8092, #8333, #8312, #8348)
-* New documents for how to reproduce the CI environment (#7971, #8297)
-* Improved automation for JVM release. (#7882)
-* GitHub Action security-related updates. (#8263, #8267, #8360)
-* Other fixes and maintenance work. (#8154, #7848, #8069, #7943)
-* Small updates and fixes to GitHub action pipelines. (#8364, #8321, #8241, #7950, #8011)
-
-## v1.6.1 (2022 May 9)
-This is a patch release for bug fixes and Spark barrier mode support. The R package is unchanged.
-
-### Experimental support for categorical data
-- Fix segfault when the number of samples is smaller than the number of categories. (https://github.com/dmlc/xgboost/pull/7853)
-- Enable partition-based split for all model types. (https://github.com/dmlc/xgboost/pull/7857)
-
-### JVM packages
-We replaced the old parallelism tracker with spark barrier mode to improve the robustness of the JVM package and fix the GPU training pipeline.
-- Fix GPU training pipeline quantile synchronization. (#7823, #7834)
-- Use barrier model in spark package. (https://github.com/dmlc/xgboost/pull/7836, https://github.com/dmlc/xgboost/pull/7840, https://github.com/dmlc/xgboost/pull/7845, https://github.com/dmlc/xgboost/pull/7846)
-- Fix shared object loading on some platforms. (https://github.com/dmlc/xgboost/pull/7844)
-
-## v1.6.0 (2022 Apr 16)
-
-After a long period of development, XGBoost v1.6.0 is packed with many new features and
-improvements. We summarize them in the following sections starting with an introduction to
-some major new features, then moving on to language binding specific changes including new
-features and notable bug fixes for that binding.
-
-### Development of categorical data support
-This version of XGBoost features new improvements and full coverage of experimental
-categorical data support in Python and C package with tree model.  Both `hist`, `approx`
-and `gpu_hist` now support training with categorical data.  Also, partition-based
-categorical split is introduced in this release. This split type is first available in
-LightGBM in the context of gradient boosting. The previous XGBoost release supported one-hot split where the splitting criteria is of form `x \in {c}`, i.e. the categorical feature `x` is tested against a single candidate. The new release allows for more expressive conditions: `x \in S` where the categorical feature `x` is tested against multiple candidates. Moreover, it is now possible to use any tree algorithms (`hist`, `approx`, `gpu_hist`) when creating categorical splits. For more
-information, please see our tutorial on [categorical
-data](https://xgboost.readthedocs.io/en/latest/tutorials/categorical.html), along with
-examples linked on that page. (#7380, #7708, #7695, #7330, #7307, #7322, #7705,
-#7652, #7592, #7666, #7576, #7569, #7529, #7575, #7393, #7465, #7385, #7371, #7745, #7810)
-
-In the future, we will continue to improve categorical data support with new features and
-optimizations. Also, we are looking forward to bringing the feature beyond Python binding,
-contributions and feedback are welcomed! Lastly, as a result of experimental status, the
-behavior might be subject to change, especially the default value of related
-hyper-parameters.
-
-### Experimental support for multi-output model
-
-XGBoost 1.6 features initial support for the multi-output model, which includes
-multi-output regression and multi-label classification. Along with this, the XGBoost
-classifier has proper support for base margin without to need for the user to flatten the
-input. In this initial support, XGBoost builds one model for each target similar to the
-sklearn meta estimator, for more details, please see our [quick
-introduction](https://xgboost.readthedocs.io/en/latest/tutorials/multioutput.html).
-
-(#7365, #7736, #7607, #7574, #7521, #7514, #7456, #7453, #7455, #7434, #7429, #7405, #7381)
-
-### External memory support
-External memory support for both approx and hist tree method is considered feature
-complete in XGBoost 1.6.  Building upon the iterator-based interface introduced in the
-previous version, now both `hist` and `approx` iterates over each batch of data during
-training and prediction.  In previous versions, `hist` concatenates all the batches into
-an internal representation, which is removed in this version.  As a result, users can
-expect higher scalability in terms of data size but might experience lower performance due
-to disk IO. (#7531, #7320, #7638, #7372)
-
-### Rewritten approx
-
-The `approx` tree method is rewritten based on the existing `hist` tree method. The
-rewrite closes the feature gap between `approx` and `hist` and improves the performance.
-Now the behavior of `approx` should be more aligned with `hist` and `gpu_hist`. Here is a
-list of user-visible changes:
-
-- Supports both `max_leaves` and `max_depth`.
-- Supports `grow_policy`.
-- Supports monotonic constraint.
-- Supports feature weights.
-- Use `max_bin` to replace `sketch_eps`.
-- Supports categorical data.
-- Faster performance for many of the datasets.
-- Improved performance and robustness for distributed training.
-- Supports prediction cache.
-- Significantly better performance for external memory when `depthwise` policy is used.
-
-### New serialization format
-Based on the existing JSON serialization format, we introduce UBJSON support as a more
-efficient alternative. Both formats will be available in the future and we plan to
-gradually [phase out](https://github.com/dmlc/xgboost/issues/7547) support for the old
-binary model format.  Users can opt to use the different formats in the serialization
-function by providing the file extension `json` or `ubj`. Also, the `save_raw` function in
-all supported languages bindings gains a new parameter for exporting the model in different
-formats, available options are `json`, `ubj`, and `deprecated`, see document for the
-language binding you are using for details. Lastly, the default internal serialization
-format is set to UBJSON, which affects Python pickle and R RDS. (#7572, #7570, #7358,
-#7571, #7556, #7549, #7416)
-
-### General new features and improvements
-Aside from the major new features mentioned above, some others are summarized here:
-
-* Users can now access the build information of XGBoost binary in Python and C
-  interface. (#7399, #7553)
-* Auto-configuration of `seed_per_iteration` is removed, now distributed training should
-  generate closer results to single node training when sampling is used. (#7009)
-* A new parameter `huber_slope` is introduced for the `Pseudo-Huber` objective.
-* During source build, XGBoost can choose cub in the system path automatically. (#7579)
-* XGBoost now honors the CPU counts from CFS, which is usually set in docker
-  environments. (#7654, #7704)
-* The metric `aucpr` is rewritten for better performance and GPU support. (#7297, #7368)
-* Metric calculation is now performed in double precision. (#7364)
-* XGBoost no longer mutates the global OpenMP thread limit. (#7537, #7519, #7608, #7590,
-  #7589, #7588, #7687)
-* The default behavior of `max_leave` and `max_depth` is now unified (#7302, #7551).
-* CUDA fat binary is now compressed. (#7601)
-* Deterministic result for evaluation metric and linear model. In previous versions of
-  XGBoost, evaluation results might differ slightly for each run due to parallel reduction
-  for floating-point values, which is now addressed. (#7362, #7303, #7316, #7349)
-* XGBoost now uses double for GPU Hist node sum, which improves the accuracy of
-  `gpu_hist`. (#7507)
-
-### Performance improvements
-Most of the performance improvements are integrated into other refactors during feature
-developments. The `approx` should see significant performance gain for many datasets as
-mentioned in the previous section, while the `hist` tree method also enjoys improved
-performance with the removal of the internal `pruner` along with some other
-refactoring. Lastly, `gpu_hist` no longer synchronizes the device during training. (#7737)
-
-### General bug fixes
-This section lists bug fixes that are not specific to any language binding.
-* The `num_parallel_tree` is now a model parameter instead of a training hyper-parameter,
-  which fixes model IO with random forest. (#7751)
-* Fixes in CMake script for exporting configuration. (#7730)
-* XGBoost can now handle unsorted sparse input. This includes text file formats like
-  libsvm and scipy sparse matrix where column index might not be sorted. (#7731)
-* Fix tree param feature type, this affects inputs with the number of columns greater than
-  the maximum value of int32. (#7565)
-* Fix external memory with gpu_hist and subsampling. (#7481)
-* Check the number of trees in inplace predict, this avoids a potential segfault when an
-  incorrect value for `iteration_range` is provided. (#7409)
-* Fix non-stable result in cox regression (#7756)
-
-### Changes in the Python package
-Other than the changes in Dask, the XGBoost Python package gained some new features and
-improvements along with small bug fixes.
-
-* Python 3.7 is required as the lowest Python version. (#7682)
-* Pre-built binary wheel for Apple Silicon. (#7621, #7612, #7747) Apple Silicon users will
-  now be able to run `pip install xgboost` to install XGBoost.
-* MacOS users no longer need to install `libomp` from Homebrew, as the XGBoost wheel now
-  bundles `libomp.dylib` library.
-* There are new parameters for users to specify the custom metric with new
-  behavior. XGBoost can now output transformed prediction values when a custom objective is
-  not supplied.  See our explanation in the
-  [tutorial](https://xgboost.readthedocs.io/en/latest/tutorials/custom_metric_obj.html#reverse-link-function)
-  for details.
-* For the sklearn interface, following the estimator guideline from scikit-learn, all
-  parameters in `fit` that are not related to input data are moved into the constructor
-  and can be set by `set_params`. (#6751, #7420, #7375, #7369)
-* Apache arrow format is now supported, which can bring better performance to users'
-  pipeline (#7512)
-* Pandas nullable types are now supported (#7760)
-* A new function `get_group` is introduced for `DMatrix` to allow users to get the group
-  information in the custom objective function. (#7564)
-* More training parameters are exposed in the sklearn interface instead of relying on the
-  `**kwargs`. (#7629)
-* A new attribute `feature_names_in_` is defined for all sklearn estimators like
-  `XGBRegressor` to follow the convention of sklearn. (#7526)
-* More work on Python type hint. (#7432, #7348, #7338, #7513, #7707)
-* Support the latest pandas Index type. (#7595)
-* Fix for Feature shape mismatch error on s390x platform (#7715)
-* Fix using feature names for constraints with multiple groups (#7711)
-* We clarified the behavior of the callback function when it contains mutable
-  states. (#7685)
-* Lastly, there are some code cleanups and maintenance work. (#7585, #7426, #7634, #7665,
-  #7667, #7377, #7360, #7498, #7438, #7667, #7752, #7749, #7751)
-
-### Changes in the Dask interface
-* Dask module now supports user-supplied host IP and port address of scheduler node.
-  Please see [introduction](https://xgboost.readthedocs.io/en/latest/tutorials/dask.html#troubleshooting) and
-  [API document](https://xgboost.readthedocs.io/en/latest/python/python_api.html#optional-dask-configuration)
-  for reference. (#7645, #7581)
-* Internal `DMatrix` construction in dask now honers thread configuration. (#7337)
-* A fix for `nthread` configuration using the Dask sklearn interface. (#7633)
-* The Dask interface can now handle empty partitions.  An empty partition is different
-  from an empty worker, the latter refers to the case when a worker has no partition of an
-  input dataset, while the former refers to some partitions on a worker that has zero
-  sizes. (#7644, #7510)
-* Scipy sparse matrix is supported as Dask array partition. (#7457)
-* Dask interface is no longer considered experimental. (#7509)
-
-### Changes in the R package
-This section summarizes the new features, improvements, and bug fixes to the R package.
-
-* `load.raw` can optionally construct a booster as return. (#7686)
-* Fix parsing decision stump, which affects both transforming text representation to data
-  table and plotting. (#7689)
-* Implement feature weights. (#7660)
-* Some improvements for complying the CRAN release policy. (#7672, #7661, #7763)
-* Support CSR data for predictions (#7615)
-* Document update (#7263, #7606)
-* New maintainer for the CRAN package (#7691, #7649)
-* Handle non-standard installation of toolchain on macos (#7759)
-
-### Changes in JVM-packages
-Some new features for JVM-packages are introduced for a more integrated GPU pipeline and
-better compatibility with musl-based Linux. Aside from this, we have a few notable bug
-fixes.
-
-* User can specify the tracker IP address for training, which helps running XGBoost on
-  restricted network environments. (#7808)
-* Add support for detecting musl-based Linux (#7624)
-* Add `DeviceQuantileDMatrix` to Scala binding (#7459)
-* Add Rapids plugin support, now more of the JVM pipeline can be accelerated by RAPIDS (#7491, #7779, #7793, #7806)
-* The setters for CPU and GPU are more aligned (#7692, #7798)
-* Control logging for early stopping (#7326)
-* Do not repartition when nWorker = 1 (#7676)
-* Fix the prediction issue for `multi:softmax` (#7694)
-* Fix for serialization of custom objective and eval (#7274)
-* Update documentation about Python tracker (#7396)
-* Remove jackson from dependency, which fixes CVE-2020-36518. (#7791)
-* Some refactoring to the training pipeline for better compatibility between CPU and
-  GPU. (#7440, #7401, #7789, #7784)
-* Maintenance work. (#7550, #7335, #7641, #7523, #6792, #4676)
-
-### Deprecation
-Other than the changes in the Python package and serialization, we removed some deprecated
-features in previous releases. Also, as mentioned in the previous section, we plan to
-phase out the old binary format in future releases.
-
-* Remove old warning in 1.3 (#7279)
-* Remove label encoder deprecated in 1.3. (#7357)
-* Remove old callback deprecated in 1.3. (#7280)
-* Pre-built binary will no longer support deprecated CUDA architectures including sm35 and
-  sm50. Users can continue to use these platforms with source build. (#7767)
-
-### Documentation
-This section lists some of the general changes to XGBoost's document, for language binding
-specific change please visit related sections.
-
-* Document is overhauled to use the new RTD theme, along with integration of Python
-  examples using Sphinx gallery. Also, we replaced most of the hard-coded URLs with sphinx
-  references. (#7347, #7346, #7468, #7522, #7530)
-* Small update along with fixes for broken links, typos, etc. (#7684, #7324, #7334, #7655,
-  #7628, #7623, #7487, #7532, #7500, #7341, #7648, #7311)
-* Update document for GPU. [skip ci] (#7403)
-* Document the status of RTD hosting. (#7353)
-* Update document for building from source. (#7664)
-* Add note about CRAN release [skip ci] (#7395)
-
-### Maintenance
-This is a summary of maintenance work that is not specific to any language binding.
-
-* Add CMake option to use /MD runtime (#7277)
-* Add clang-format configuration. (#7383)
-* Code cleanups (#7539, #7536, #7466, #7499, #7533, #7735, #7722, #7668, #7304, #7293,
-  #7321, #7356, #7345, #7387, #7577, #7548, #7469, #7680, #7433, #7398)
-* Improved tests with better coverage and latest dependency (#7573, #7446, #7650, #7520,
-  #7373, #7723, #7611, #7771)
-* Improved automation of the release process. (#7278, #7332, #7470)
-* Compiler workarounds (#7673)
-* Change shebang used in CLI demo. (#7389)
-* Update affiliation (#7289)
-
-### CI
-Some fixes and update to XGBoost's CI infrastructure. (#7739, #7701, #7382, #7662, #7646,
-#7582, #7407, #7417, #7475, #7474, #7479, #7472, #7626)
-
-
 ## v1.5.0 (2021 Oct 11)
 
 This release comes with many exciting new features and optimizations, along with some bug

R-package/CMakeLists.txt

@@ -16,6 +16,7 @@ target_compile_definitions(xgboost-r
   -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
@@ -30,7 +31,7 @@ if (USE_OPENMP)
 endif (USE_OPENMP)
 set_target_properties(
   xgboost-r PROPERTIES
-  CXX_STANDARD 17
+  CXX_STANDARD 14
   CXX_STANDARD_REQUIRED ON
   POSITION_INDEPENDENT_CODE ON)
 

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 2.0.1.1
-Date: 2023-10-12
+Version: 1.6.2.1
+Date: 2022-03-29
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -54,8 +54,10 @@ Suggests:
     Ckmeans.1d.dp (>= 3.3.1),
     vcd (>= 1.3),
     testthat,
+    lintr,
     igraph (>= 1.0.1),
     float,
+    crayon,
     titanic
 Depends:
     R (>= 3.3.0)
@@ -64,6 +66,5 @@ Imports:
     methods,
     data.table (>= 1.9.6),
     jsonlite (>= 1.0),
-RoxygenNote: 7.2.3
-Encoding: UTF-8
-SystemRequirements: GNU make, C++17
+RoxygenNote: 7.1.1
+SystemRequirements: GNU make, C++14

R-package/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2014-2023, Tianqi Chen and XBGoost Contributors
+Copyright (c) 2014 by Tianqi Chen and Contributors 
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

R-package/R/callbacks.R

@@ -70,7 +70,7 @@ cb.print.evaluation <- function(period = 1, showsd = TRUE) {
         i == env$begin_iteration ||
         i == env$end_iteration) {
       stdev <- if (showsd) env$bst_evaluation_err else NULL
-      msg <- .format_eval_string(i, env$bst_evaluation, stdev)
+      msg <- format.eval.string(i, env$bst_evaluation, stdev)
       cat(msg, '\n')
     }
   }
@@ -114,7 +114,7 @@ cb.evaluation.log <- function() {
     if (is.null(mnames) || any(mnames == ""))
       stop("bst_evaluation must have non-empty names")
 
-    mnames <<- gsub('-', '_', names(env$bst_evaluation), fixed = TRUE)
+    mnames <<- gsub('-', '_', names(env$bst_evaluation))
     if (!is.null(env$bst_evaluation_err))
       mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
   }
@@ -185,7 +185,7 @@ cb.reset.parameters <- function(new_params) {
 
   if (typeof(new_params) != "list")
     stop("'new_params' must be a list")
-  pnames <- gsub(".", "_", names(new_params), fixed = TRUE)
+  pnames <- gsub("\\.", "_", names(new_params))
   nrounds <- NULL
 
   # run some checks in the beginning
@@ -300,9 +300,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
     if (length(env$bst_evaluation) == 0)
       stop("For early stopping, watchlist must have at least one element")
 
-    eval_names <- gsub('-', '_', names(env$bst_evaluation), fixed = TRUE)
+    eval_names <- gsub('-', '_', names(env$bst_evaluation))
     if (!is.null(metric_name)) {
-      metric_idx <<- which(gsub('-', '_', metric_name, fixed = TRUE) == eval_names)
+      metric_idx <<- which(gsub('-', '_', metric_name) == eval_names)
       if (length(metric_idx) == 0)
         stop("'metric_name' for early stopping is not one of the following:\n",
              paste(eval_names, collapse = ' '), '\n')
@@ -319,7 +319,7 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
 
     # maximize is usually NULL when not set in xgb.train and built-in metrics
     if (is.null(maximize))
-      maximize <<- grepl('(_auc|_map|_ndcg|_pre)', metric_name)
+      maximize <<- grepl('(_auc|_map|_ndcg)', metric_name)
 
     if (verbose && NVL(env$rank, 0) == 0)
       cat("Will train until ", metric_name, " hasn't improved in ",
@@ -380,9 +380,7 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
     if ((maximize && score > best_score) ||
         (!maximize && score < best_score)) {
 
-      best_msg <<- .format_eval_string(
-        i, env$bst_evaluation, env$bst_evaluation_err
-      )
+      best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
       best_score <<- score
       best_iteration <<- i
       best_ntreelimit <<- best_iteration * env$num_parallel_tree
@@ -513,7 +511,7 @@ cb.cv.predict <- function(save_models = FALSE) {
     if (save_models) {
       env$basket$models <- lapply(env$bst_folds, function(fd) {
         xgb.attr(fd$bst, 'niter') <- env$end_iteration - 1
-        xgb.Booster.complete(xgb.handleToBooster(handle = fd$bst, raw = NULL), saveraw = TRUE)
+        xgb.Booster.complete(xgb.handleToBooster(fd$bst), saveraw = TRUE)
       })
     }
   }
@@ -546,11 +544,9 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' @return
 #' Results are stored in the \code{coefs} element of the closure.
-#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy
-#' way to access it.
+#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
 #' With \code{xgb.train}, it is either a dense of a sparse matrix.
-#' While with \code{xgb.cv}, it is a list (an element per each fold) of such
-#' matrices.
+#' While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
 #'
 #' @seealso
 #' \code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
@@ -562,7 +558,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' # without considering the 2nd order interactions:
 #' x <- model.matrix(Species ~ .^2, iris)[,-1]
 #' colnames(x)
-#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
+#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
 #' param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
 #'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For 'shotgun', which is a default linear updater, using high eta values may result in
@@ -587,19 +583,19 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' # For xgb.cv:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-#'               callbacks = list(cb.gblinear.history()))
+#'              callbacks = list(cb.gblinear.history()))
 #' # coefficients in the CV fold #3
 #' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 #'
 #'
 #' #### Multiclass classification:
 #' #
-#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 1)
+#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
 #' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 1)
+#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For the default linear updater 'shotgun' it sometimes is helpful
 #' # to use smaller eta to reduce instability
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 50, eta = 0.5,
+#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
 #'                  callbacks = list(cb.gblinear.history()))
 #' # Will plot the coefficient paths separately for each class:
 #' matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
@@ -613,15 +609,13 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
 #'
 #' @export
-cb.gblinear.history <- function(sparse = FALSE) {
+cb.gblinear.history <- function(sparse=FALSE) {
   coefs <- NULL
 
   init <- function(env) {
-    # xgb.train(): bst will be present
-    # xgb.cv(): bst_folds will be present
-    if (is.null(env$bst) && is.null(env$bst_folds)) {
-        stop("Parent frame has neither 'bst' nor 'bst_folds'")
-    }
+    if (!is.null(env$bst)) { # xgb.train:
+    } else if (!is.null(env$bst_folds)) { # xgb.cv:
+    } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
   }
 
   # convert from list to (sparse) matrix
@@ -661,7 +655,7 @@ cb.gblinear.history <- function(sparse = FALSE) {
     } else { # xgb.cv:
       cf <- vector("list", length(env$bst_folds))
       for (i in seq_along(env$bst_folds)) {
-        dmp <- xgb.dump(xgb.handleToBooster(handle = env$bst_folds[[i]]$bst, raw = NULL))
+        dmp <- xgb.dump(xgb.handleToBooster(env$bst_folds[[i]]$bst))
         cf[[i]] <- as.numeric(grep('(booster|bias|weigh)', dmp, invert = TRUE, value = TRUE))
         if (sparse) cf[[i]] <- as(cf[[i]], "sparseVector")
       }
@@ -756,7 +750,7 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
 #
 
 # Format the evaluation metric string
-.format_eval_string <- function(iter, eval_res, eval_err = NULL) {
+format.eval.string <- function(iter, eval_res, eval_err = NULL) {
   if (length(eval_res) == 0)
     stop('no evaluation results')
   enames <- names(eval_res)

R-package/R/utils.R

@@ -38,11 +38,11 @@ check.booster.params <- function(params, ...) {
     stop("params must be a list")
 
   # in R interface, allow for '.' instead of '_' in parameter names
-  names(params) <- gsub(".", "_", names(params), fixed = TRUE)
+  names(params) <- gsub("\\.", "_", names(params))
 
   # merge parameters from the params and the dots-expansion
   dot_params <- list(...)
-  names(dot_params) <- gsub(".", "_", names(dot_params), fixed = TRUE)
+  names(dot_params) <- gsub("\\.", "_", names(dot_params))
   if (length(intersect(names(params),
                        names(dot_params))) > 0)
     stop("Same parameters in 'params' and in the call are not allowed. Please check your 'params' list.")
@@ -82,7 +82,7 @@ check.booster.params <- function(params, ...) {
 
   # interaction constraints parser (convert from list of column indices to string)
   if (!is.null(params[['interaction_constraints']]) &&
-      typeof(params[['interaction_constraints']]) != "character") {
+      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'))) {
@@ -140,7 +140,7 @@ check.custom.eval <- function(env = parent.frame()) {
 
 
 # Update a booster handle for an iteration with dtrain data
-xgb.iter.update <- function(booster_handle, dtrain, iter, obj) {
+xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
   if (!identical(class(booster_handle), "xgb.Booster.handle")) {
     stop("booster_handle must be of xgb.Booster.handle class")
   }
@@ -163,7 +163,7 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj) {
 # Evaluate one iteration.
 # Returns a named vector of evaluation metrics
 # with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(booster_handle, watchlist, iter, feval) {
+xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
   if (!identical(class(booster_handle), "xgb.Booster.handle"))
     stop("class of booster_handle must be xgb.Booster.handle")
 
@@ -234,7 +234,7 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
         y <- factor(y)
       }
     }
-    folds <- xgb.createFolds(y = y, k = nfold)
+    folds <- xgb.createFolds(y, nfold)
   } else {
     # make simple non-stratified folds
     kstep <- length(rnd_idx) %/% nfold
@@ -251,7 +251,8 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
 # Creates CV folds stratified by the values of y.
 # It was borrowed from caret::createFolds and simplified
 # by always returning an unnamed list of fold indices.
-xgb.createFolds <- function(y, k) {
+xgb.createFolds <- function(y, k = 10)
+{
   if (is.numeric(y)) {
     ## Group the numeric data based on their magnitudes
     ## and sample within those groups.

R-package/R/xgb.Booster.R

@@ -1,6 +1,7 @@
 # Construct an internal xgboost Booster and return a handle to it.
 # internal utility function
-xgb.Booster.handle <- function(params, cachelist, modelfile, handle) {
+xgb.Booster.handle <- function(params = list(), cachelist = list(),
+                               modelfile = NULL, handle = NULL) {
   if (typeof(cachelist) != "list" ||
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
@@ -11,7 +12,7 @@ xgb.Booster.handle <- function(params, cachelist, modelfile, handle) {
       ## A filename
       handle <- .Call(XGBoosterCreate_R, cachelist)
       modelfile <- path.expand(modelfile)
-      .Call(XGBoosterLoadModel_R, handle, enc2utf8(modelfile[1]))
+      .Call(XGBoosterLoadModel_R, handle, modelfile[1])
       class(handle) <- "xgb.Booster.handle"
       if (length(params) > 0) {
         xgb.parameters(handle) <- params
@@ -43,7 +44,7 @@ xgb.Booster.handle <- function(params, cachelist, modelfile, handle) {
 
 # Convert xgb.Booster.handle to xgb.Booster
 # internal utility function
-xgb.handleToBooster <- function(handle, raw) {
+xgb.handleToBooster <- function(handle, raw = NULL) {
   bst <- list(handle = handle, raw = raw)
   class(bst) <- "xgb.Booster"
   return(bst)
@@ -128,12 +129,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
     stop("argument type must be xgb.Booster")
 
   if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(
-      params = list(),
-      cachelist = list(),
-      modelfile = object$raw,
-      handle = object$handle
-    )
+    object$handle <- xgb.Booster.handle(modelfile = object$raw, handle = object$handle)
   } else {
     if (is.null(object$raw) && saveraw) {
       object$raw <- xgb.serialize(object$handle)
@@ -218,10 +214,6 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' Since it quadratically depends on the number of features, it is recommended to perform selection
 #' of the most important features first. See below about the format of the returned results.
 #'
-#' The \code{predict()} method uses as many threads as defined in \code{xgb.Booster} object (all by default).
-#' If you want to change their number, then assign a new number to \code{nthread} using \code{\link{xgb.parameters<-}}.
-#' Note also that converting a matrix to \code{\link{xgb.DMatrix}} uses multiple threads too.
-#'
 #' @return
 #' The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
 #' for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
@@ -336,9 +328,8 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
                                 predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
                                 reshape = FALSE, training = FALSE, iterationrange = NULL, strict_shape = FALSE, ...) {
   object <- xgb.Booster.complete(object, saveraw = FALSE)
-
   if (!inherits(newdata, "xgb.DMatrix"))
-    newdata <- xgb.DMatrix(newdata, missing = missing, nthread = NVL(object$params[["nthread"]], -1))
+    newdata <- xgb.DMatrix(newdata, missing = missing)
   if (!is.null(object[["feature_names"]]) &&
       !is.null(colnames(newdata)) &&
       !identical(object[["feature_names"]], colnames(newdata)))
@@ -479,7 +470,7 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
 #' @export
 predict.xgb.Booster.handle <- function(object, ...) {
 
-  bst <- xgb.handleToBooster(handle = object, raw = NULL)
+  bst <- xgb.handleToBooster(object)
 
   ret <- predict(bst, ...)
   return(ret)
@@ -638,7 +629,7 @@ xgb.attributes <- function(object) {
 #' @export
 xgb.config <- function(object) {
   handle <- xgb.get.handle(object)
-  .Call(XGBoosterSaveJsonConfig_R, handle)
+  .Call(XGBoosterSaveJsonConfig_R, handle);
 }
 
 #' @rdname xgb.config
@@ -680,7 +671,7 @@ xgb.config <- function(object) {
   if (is.null(names(p)) || any(nchar(names(p)) == 0)) {
     stop("parameter names cannot be empty strings")
   }
-  names(p) <- gsub(".", "_", names(p), fixed = TRUE)
+  names(p) <- gsub("\\.", "_", names(p))
   p <- lapply(p, function(x) as.character(x)[1])
   handle <- xgb.get.handle(object)
   for (i in seq_along(p)) {

R-package/R/xgb.DMatrix.R

@@ -18,7 +18,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = 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')
@@ -36,46 +36,25 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthre
     cnames <- colnames(data)
   } else if (inherits(data, "dgCMatrix")) {
     handle <- .Call(
-      XGDMatrixCreateFromCSC_R,
-      data@p,
-      data@i,
-      data@x,
-      nrow(data),
-      missing,
-      as.integer(NVL(nthread, -1))
+      XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data), as.integer(NVL(nthread, -1))
     )
     cnames <- colnames(data)
   } else if (inherits(data, "dgRMatrix")) {
     handle <- .Call(
-      XGDMatrixCreateFromCSR_R,
-      data@p,
-      data@j,
-      data@x,
-      ncol(data),
-      missing,
-      as.integer(NVL(nthread, -1))
+      XGDMatrixCreateFromCSR_R, data@p, data@j, data@x, ncol(data), as.integer(NVL(nthread, -1))
     )
     cnames <- colnames(data)
   } else if (inherits(data, "dsparseVector")) {
     indptr <- c(0L, as.integer(length(data@i)))
     ind <- as.integer(data@i) - 1L
     handle <- .Call(
-      XGDMatrixCreateFromCSR_R,
-      indptr,
-      ind,
-      data@x,
-      length(data),
-      missing,
-      as.integer(NVL(nthread, -1))
+      XGDMatrixCreateFromCSR_R, indptr, ind, data@x, length(data), as.integer(NVL(nthread, -1))
     )
   } else {
     stop("xgb.DMatrix does not support construction from ", typeof(data))
   }
   dmat <- handle
-  attributes(dmat) <- list(class = "xgb.DMatrix")
-  if (!is.null(cnames)) {
-    setinfo(dmat, "feature_name", cnames)
-  }
+  attributes(dmat) <- list(.Dimnames = list(NULL, cnames), class = "xgb.DMatrix")
 
   info <- append(info, list(...))
   for (i in seq_along(info)) {
@@ -88,13 +67,13 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthre
 
 # get dmatrix from data, label
 # internal helper method
-xgb.get.DMatrix <- function(data, label, missing, weight, nthread) {
+xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nthread = NULL) {
   if (inherits(data, "dgCMatrix") || is.matrix(data)) {
     if (is.null(label)) {
       stop("label must be provided when data is a matrix")
     }
     dtrain <- xgb.DMatrix(data, label = label, missing = missing, nthread = nthread)
-    if (!is.null(weight)) {
+    if (!is.null(weight)){
       setinfo(dtrain, "weight", weight)
     }
   } else {
@@ -128,7 +107,7 @@ xgb.get.DMatrix <- function(data, label, missing, weight, nthread) {
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #'
 #' stopifnot(nrow(dtrain) == nrow(train$data))
 #' stopifnot(ncol(dtrain) == ncol(train$data))
@@ -156,7 +135,7 @@ dim.xgb.DMatrix <- function(x) {
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' dimnames(dtrain)
 #' colnames(dtrain)
 #' colnames(dtrain) <- make.names(1:ncol(train$data))
@@ -165,9 +144,7 @@ dim.xgb.DMatrix <- function(x) {
 #' @rdname dimnames.xgb.DMatrix
 #' @export
 dimnames.xgb.DMatrix <- function(x) {
-  fn <- getinfo(x, "feature_name")
-  ## row names is null.
-  list(NULL, fn)
+  attr(x, '.Dimnames')
 }
 
 #' @rdname dimnames.xgb.DMatrix
@@ -178,13 +155,13 @@ dimnames.xgb.DMatrix <- function(x) {
   if (!is.null(value[[1L]]))
     stop("xgb.DMatrix does not have rownames")
   if (is.null(value[[2]])) {
-    setinfo(x, "feature_name", NULL)
+    attr(x, '.Dimnames') <- NULL
     return(x)
   }
-  if (ncol(x) != length(value[[2]])) {
-    stop("can't assign ", length(value[[2]]), " colnames to a ", ncol(x), " column xgb.DMatrix")
-  }
-  setinfo(x, "feature_name", value[[2]])
+  if (ncol(x) != length(value[[2]]))
+    stop("can't assign ", length(value[[2]]), " colnames to a ",
+         ncol(x), " column xgb.DMatrix")
+  attr(x, '.Dimnames') <- value
   x
 }
 
@@ -211,7 +188,7 @@ dimnames.xgb.DMatrix <- function(x) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -226,17 +203,13 @@ getinfo <- function(object, ...) UseMethod("getinfo")
 #' @export
 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', "feature_type", "feature_name")) {
-    stop(
-      "getinfo: name must be one of the following\n",
-      "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound', 'feature_type', 'feature_name'"
-    )
+      length(name) != 1 ||
+      !name %in% c('label', 'weight', 'base_margin', 'nrow',
+                   'label_lower_bound', 'label_upper_bound')) {
+    stop("getinfo: name must be one of the following\n",
+         "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound'")
   }
-  if (name == "feature_name" || name == "feature_type") {
-    ret <- .Call(XGDMatrixGetStrFeatureInfo_R, object, name)
-  } else if (name != "nrow") {
+  if (name != "nrow"){
     ret <- .Call(XGDMatrixGetInfo_R, object, name)
   } else {
     ret <- nrow(object)
@@ -267,7 +240,7 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -321,31 +294,8 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
     .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
     return(TRUE)
   }
-
-  set_feat_info <- function(name) {
-    msg <- sprintf(
-      "The number of %s must equal to the number of columns in the input data. %s vs. %s",
-      name,
-      length(info),
-      ncol(object)
-    )
-    if (!is.null(info)) {
-      info <- as.list(info)
-      if (length(info) != ncol(object)) {
-        stop(msg)
-      }
-    }
-    .Call(XGDMatrixSetStrFeatureInfo_R, object, name, info)
-  }
-  if (name == "feature_name") {
-    set_feat_info("feature_name")
-    return(TRUE)
-  }
-  if (name == "feature_type") {
-    set_feat_info("feature_type")
-    return(TRUE)
-  }
   stop("setinfo: unknown info name ", name)
+  return(FALSE)
 }
 
 
@@ -362,7 +312,7 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -418,7 +368,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' dtrain
 #' print(dtrain, verbose=TRUE)
@@ -435,7 +385,7 @@ print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
   cat(infos)
   cnames <- colnames(x)
   cat('  colnames:')
-  if (verbose && !is.null(cnames)) {
+  if (verbose & !is.null(cnames)) {
     cat("\n'")
     cat(cnames, sep = "','")
     cat("'")

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

@@ -7,7 +7,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = 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/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, nthread = 2))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 #'
 #' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 #' nrounds = 4
@@ -65,12 +65,8 @@
 #' new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
 #'
 #' # learning with new features
-#' new.dtrain <- xgb.DMatrix(
-#'   data = new.features.train, label = agaricus.train$label, nthread = 2
-#' )
-#' new.dtest <- xgb.DMatrix(
-#'   data = new.features.test, label = agaricus.test$label, nthread = 2
-#' )
+#' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
+#' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
 #' watchlist <- list(train = new.dtrain)
 #' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 #'
@@ -83,7 +79,7 @@
 #'           accuracy.after, "!\n"))
 #'
 #' @export
-xgb.create.features <- function(model, data, ...) {
+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)

R-package/R/xgb.cv.R

@@ -75,11 +75,9 @@
 #' @details
 #' The original sample is randomly partitioned into \code{nfold} equal size subsamples.
 #'
-#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model,
-#' and the remaining \code{nfold - 1} subsamples are used as training data.
+#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
 #'
-#' The cross-validation process is then repeated \code{nrounds} times, with each of the
-#' \code{nfold} subsamples used exactly once as the validation data.
+#' The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
 #'
 #' All observations are used for both training and validation.
 #'
@@ -112,17 +110,17 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-#'              max_depth = 3, eta = 1, objective = "binary:logistic")
+#'                   max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
 #' print(cv, verbose=TRUE)
 #'
 #' @export
-xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing = NA,
-                   prediction = FALSE, showsd = TRUE, metrics = list(),
+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,
-                   verbose = TRUE, print_every_n = 1L,
+                   verbose = TRUE, print_every_n=1L,
                    early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...) {
 
   check.deprecation(...)
@@ -135,6 +133,9 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
   check.custom.obj()
   check.custom.eval()
 
+  #if (is.null(params[['eval_metric']]) && is.null(feval))
+  #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
+
   # Check the labels
   if ((inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
       (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
@@ -158,6 +159,10 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
     folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, params)
   }
 
+  # Potential TODO: sequential CV
+  #if (strategy == 'sequential')
+  #  stop('Sequential CV strategy is not yet implemented')
+
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
   print_every_n <- max(as.integer(print_every_n), 1L)
@@ -187,13 +192,7 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
 
   # create the booster-folds
   # train_folds
-  dall <- xgb.get.DMatrix(
-    data = data,
-    label = label,
-    missing = missing,
-    weight = NULL,
-    nthread = params$nthread
-  )
+  dall <- xgb.get.DMatrix(data, label, missing)
   bst_folds <- lapply(seq_along(folds), function(k) {
     dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow
@@ -201,12 +200,7 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
        dtrain <- slice(dall, unlist(folds[-k]))
     else
        dtrain <- slice(dall, train_folds[[k]])
-    handle <- xgb.Booster.handle(
-      params = params,
-      cachelist = list(dtrain, dtest),
-      modelfile = NULL,
-      handle = NULL
-    )
+    handle <- xgb.Booster.handle(params, list(dtrain, dtest))
     list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test = dtest), index = folds[[k]])
   })
   rm(dall)
@@ -227,18 +221,8 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
     for (f in cb$pre_iter) f()
 
     msg <- lapply(bst_folds, function(fd) {
-      xgb.iter.update(
-        booster_handle = fd$bst,
-        dtrain = fd$dtrain,
-        iter = iteration - 1,
-        obj = obj
-      )
-      xgb.iter.eval(
-        booster_handle = fd$bst,
-        watchlist = fd$watchlist,
-        iter = iteration - 1,
-        feval = feval
-      )
+      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
+      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
     })
     msg <- simplify2array(msg)
     bst_evaluation <- rowMeans(msg)

R-package/R/xgb.dump.R

@@ -38,7 +38,7 @@
 #' cat(xgb.dump(bst, with_stats = TRUE, dump_format='json'))
 #'
 #' @export
-xgb.dump <- function(model, fname = NULL, fmap = "", with_stats = FALSE,
+xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
                      dump_format = c("text", "json"), ...) {
   check.deprecation(...)
   dump_format <- match.arg(dump_format)

R-package/R/xgb.ggplot.R

@@ -4,7 +4,7 @@
 #' @rdname xgb.plot.importance
 #' @export
 xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
-                                  rel_to_first = FALSE, n_clusters = seq_len(10), ...) {
+                                  rel_to_first = FALSE, n_clusters = c(1:10), ...) {
 
   importance_matrix <- xgb.plot.importance(importance_matrix, top_n = top_n, measure = measure,
                                            rel_to_first = rel_to_first, plot = FALSE, ...)
@@ -142,7 +142,6 @@ xgb.ggplot.shap.summary <- function(data, shap_contrib = NULL, features = NULL,
 #'
 #' @return A data.table containing the observation ID, the feature name, the
 #'   feature value (normalized if specified), and the SHAP contribution value.
-#' @noRd
 prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
   data <- data_list[["data"]]
   shap_contrib <- data_list[["shap_contrib"]]
@@ -171,7 +170,6 @@ prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
 #' @param x Numeric vector
 #'
 #' @return Numeric vector with mean 0 and sd 1.
-#' @noRd
 normalize <- function(x) {
   loc <- mean(x, na.rm = TRUE)
   scale <- stats::sd(x, na.rm = TRUE)
@@ -183,7 +181,7 @@ normalize <- function(x) {
 # ... the plots
 # cols number of columns
 # internal utility function
-multiplot <- function(..., cols) {
+multiplot <- function(..., cols = 1) {
   plots <- list(...)
   num_plots <- length(plots)
 

R-package/R/xgb.importance.R

@@ -82,7 +82,7 @@
 #'
 #' @export
 xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
-                           data = NULL, label = NULL, target = NULL) {
+                           data = NULL, label = NULL, target = NULL){
 
   if (!(is.null(data) && is.null(label) && is.null(target)))
     warning("xgb.importance: parameters 'data', 'label' and 'target' are deprecated")
@@ -104,11 +104,7 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
       XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
     )
     names(results) <- c("features", "shape", "weight")
-    if (length(results$shape) == 2) {
-        n_classes <- results$shape[2]
-    } else {
-        n_classes <- 0
-    }
+    n_classes <-  if (length(results$shape) == 2) { results$shape[2] } else { 0 }
     importance <- if (n_classes == 0) {
       data.table(Feature = results$features, Weight = results$weight)[order(-abs(Weight))]
     } else {

R-package/R/xgb.load.R

@@ -35,12 +35,7 @@ xgb.load <- function(modelfile) {
   if (is.null(modelfile))
     stop("xgb.load: modelfile cannot be NULL")
 
-  handle <- xgb.Booster.handle(
-    params = list(),
-    cachelist = list(),
-    modelfile = modelfile,
-    handle = NULL
-  )
+  handle <- xgb.Booster.handle(modelfile = modelfile)
   # re-use modelfile if it is raw so we do not need to serialize
   if (typeof(modelfile) == "raw") {
     warning(
@@ -50,9 +45,9 @@ xgb.load <- function(modelfile) {
         " `xgb.unserialize` instead. "
       )
     )
-    bst <- xgb.handleToBooster(handle = handle, raw = modelfile)
+    bst <- xgb.handleToBooster(handle, modelfile)
   } else {
-    bst <- xgb.handleToBooster(handle = handle, raw = NULL)
+    bst <- xgb.handleToBooster(handle, NULL)
   }
   bst <- xgb.Booster.complete(bst, saveraw = TRUE)
   return(bst)

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

@@ -62,7 +62,7 @@
 #'
 #' @export
 xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
-                              trees = NULL, use_int_id = FALSE, ...) {
+                              trees = NULL, use_int_id = FALSE, ...){
   check.deprecation(...)
 
   if (!inherits(model, "xgb.Booster") && !is.character(text)) {
@@ -82,11 +82,12 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
     stop("trees: must be a vector of integers.")
   }
 
-  if (is.null(text)) {
+  if (is.null(text)){
     text <- xgb.dump(model = model, with_stats = TRUE)
   }
 
-  if (length(text) < 2 || !any(grepl('leaf=(\\d+)', text))) {
+  if (length(text) < 2 ||
+      sum(grepl('leaf=(\\d+)', text)) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
 

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

@@ -136,7 +136,7 @@ get.leaf.depth <- function(dt_tree) {
     # list of paths to each leaf in a tree
     paths <- lapply(paths_tmp$vpath, names)
     # combine into a resulting path lengths table for a tree
-    data.table(Depth = lengths(paths), ID = To[Leaf == TRUE])
+    data.table(Depth = sapply(paths, length), ID = To[Leaf == TRUE])
   }, by = Tree]
 }
 

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

@@ -102,9 +102,7 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
     original_mar <- par()$mar
 
     # reset margins so this function doesn't have side effects
-    on.exit({
-        par(mar = original_mar)
-    })
+    on.exit({par(mar = original_mar)})
 
     mar <- original_mar
     if (!is.null(left_margin))

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

@@ -61,10 +61,7 @@
 #'
 #' @export
 xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5, plot_width = NULL, plot_height = NULL,
-                                 render = TRUE, ...) {
-  if (!requireNamespace("DiagrammeR", quietly = TRUE)) {
-    stop("DiagrammeR is required for xgb.plot.multi.trees")
-  }
+                                 render = TRUE, ...){
   check.deprecation(...)
   tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
 
@@ -97,9 +94,9 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
         , by = .(abs.node.position, Feature)
       ][, .(Text = paste0(
               paste0(
-                Feature[seq_len(min(length(Feature), features_keep))],
+                Feature[1:min(length(Feature), features_keep)],
                 " (",
-                format(Quality[seq_len(min(length(Quality), features_keep))], digits = 5),
+                format(Quality[1:min(length(Quality), features_keep)], digits = 5),
                 ")"
               ),
               collapse = "\n"

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

@@ -143,7 +143,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       y <- shap_contrib[, f][ord]
       x_lim <- range(x, na.rm = TRUE)
       y_lim <- range(y, na.rm = TRUE)
-      do_na <- plot_NA && anyNA(x)
+      do_na <- plot_NA && any(is.na(x))
       if (do_na) {
         x_range <- diff(x_lim)
         loc_na <- min(x, na.rm = TRUE) + x_range * pos_NA
@@ -193,7 +193,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 #' 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/shap/shap.
+#' \code{summary_plot} function from https://github.com/slundberg/shap.
 #'
 #' @inheritParams xgb.plot.shap
 #'
@@ -202,7 +202,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 #'
 #' @examples # See \code{\link{xgb.plot.shap}}.
 #' @seealso \code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-#'   \url{https://github.com/shap/shap}
+#'   \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.
@@ -272,8 +272,8 @@ xgb.shap.data <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       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$Feature[seq_len(min(top_n, NROW(imp)))]
+    if (top_n < 1 | top_n > 100) stop("top_n: must be an integer within [1, 100]")
+    features <- imp$Feature[1:min(top_n, NROW(imp))]
   }
   if (is.character(features)) {
     features <- match(features, colnames(data))

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

@@ -34,7 +34,7 @@
 #' The branches that also used for missing values are marked as bold
 #' (as in "carrying extra capacity").
 #'
-#' This function uses \href{https://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
+#' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
 #'
 #' @return
 #'
@@ -68,7 +68,7 @@
 #'
 #' @export
 xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot_width = NULL, plot_height = NULL,
-                          render = TRUE, show_node_id = FALSE, ...) {
+                          render = TRUE, show_node_id = FALSE, ...){
   check.deprecation(...)
   if (!inherits(model, "xgb.Booster")) {
     stop("model: Has to be an object of class xgb.Booster")

R-package/R/xgb.save.R

@@ -43,6 +43,6 @@ xgb.save <- function(model, fname) {
   }
   model <- xgb.Booster.complete(model, saveraw = FALSE)
   fname <- path.expand(fname)
-  .Call(XGBoosterSaveModel_R, model$handle, enc2utf8(fname[1]))
+  .Call(XGBoosterSaveModel_R, model$handle, fname[1])
   return(TRUE)
 }

R-package/R/xgb.train.R

@@ -18,37 +18,17 @@
 #' 2.1. Parameters for Tree Booster
 #'
 #' \itemize{
-#'   \item{ \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1}
-#'          when it is added to the current approximation.
-#'          Used to prevent overfitting by making the boosting process more conservative.
-#'          Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model
-#'          more robust to overfitting but slower to compute. Default: 0.3}
-#'   \item{ \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree.
-#'          the larger, the more conservative the algorithm will be.}
+#'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
+#'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
 #'   \item \code{max_depth} maximum depth of a tree. Default: 6
-#'   \item{\code{min_child_weight} minimum sum of instance weight (hessian) needed in a child.
-#'         If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight,
-#'         then the building process will give up further partitioning.
-#'         In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node.
-#'         The larger, the more conservative the algorithm will be. Default: 1}
-#'   \item{ \code{subsample} subsample ratio of the training instance.
-#'         Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees
-#'         and this will prevent overfitting. It makes computation shorter (because less data to analyse).
-#'         It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1}
+#'   \item \code{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.}
+#'   \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
@@ -62,53 +42,29 @@
 #' 3. Task Parameters
 #'
 #' \itemize{
-#' \item{ \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it.
-#'        The default objective options are below:
+#' \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:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
 #'     \item \code{reg:logistic} logistic regression.
 #'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
 #'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item{ \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution.
-#'            \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).}
-#'     \item{ \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored).
-#'            Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional
-#'            hazard function \code{h(t) = h0(t) * HR)}.}
-#'     \item{ \code{survival:aft}: Accelerated failure time model for censored survival time data. See
-#'            \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time}
-#'            for details.}
+#'     \item \code{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}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
-#'     \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{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{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.}
+#'   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
 #' }
 #'
 #' @param data training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
@@ -185,8 +141,7 @@
 #'      \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{https://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}
 #'   }
@@ -237,8 +192,8 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #'
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 #' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:
@@ -321,10 +276,6 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     if (is.null(evnames) || any(evnames == ""))
       stop("each element of the watchlist must have a name tag")
   }
-  # Handle multiple evaluation metrics given as a list
-  for (m in params$eval_metric) {
-    params <- c(params, list(eval_metric = m))
-  }
 
   # evaluation printing callback
   params <- c(params)
@@ -363,13 +314,8 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   is_update <- NVL(params[['process_type']], '.') == 'update'
 
   # Construct a booster (either a new one or load from xgb_model)
-  handle <- xgb.Booster.handle(
-    params = params,
-    cachelist = append(watchlist, dtrain),
-    modelfile = xgb_model,
-    handle = NULL
-  )
-  bst <- xgb.handleToBooster(handle = handle, raw = NULL)
+  handle <- xgb.Booster.handle(params, append(watchlist, dtrain), xgb_model)
+  bst <- xgb.handleToBooster(handle)
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
   num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
@@ -395,21 +341,10 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
 
     for (f in cb$pre_iter) f()
 
-    xgb.iter.update(
-        booster_handle = bst$handle,
-        dtrain = dtrain,
-        iter = iteration - 1,
-        obj = obj
-    )
+    xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
 
-    if (length(watchlist) > 0) {
-      bst_evaluation <- xgb.iter.eval(  # nolint: object_usage_linter
-        booster_handle = bst$handle,
-        watchlist = watchlist,
-        iter = iteration - 1,
-        feval = feval
-      )
-    }
+    if (length(watchlist) > 0)
+      bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
 
     xgb.attr(bst$handle, 'niter') <- iteration - 1
 

R-package/R/xgboost.R

@@ -10,13 +10,7 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
                     save_period = NULL, save_name = "xgboost.model",
                     xgb_model = NULL, callbacks = list(), ...) {
   merged <- check.booster.params(params, ...)
-  dtrain <- xgb.get.DMatrix(
-    data = data,
-    label = label,
-    missing = missing,
-    weight = weight,
-    nthread = merged$nthread
-  )
+  dtrain <- xgb.get.DMatrix(data, label, missing, weight, nthread = merged$nthread)
 
   watchlist <- list(train = dtrain)
 

R-package/configure.ac

@@ -2,25 +2,10 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[2.0.1],[],[xgboost],[])
+AC_INIT([xgboost],[1.6-0],[],[xgboost],[])
 
-: ${R_HOME=`R RHOME`}
-if test -z "${R_HOME}"; then
-  echo "could not determine R_HOME"
-  exit 1
-fi
-
-CXX17=`"${R_HOME}/bin/R" CMD config CXX17`
-CXX17STD=`"${R_HOME}/bin/R" CMD config CXX17STD`
-CXX="${CXX17} ${CXX17STD}"
-CXXFLAGS=`"${R_HOME}/bin/R" CMD config CXXFLAGS`
-
-CC=`"${R_HOME}/bin/R" CMD config CC`
-CFLAGS=`"${R_HOME}/bin/R" CMD config CFLAGS`
-CPPFLAGS=`"${R_HOME}/bin/R" CMD config CPPFLAGS`
-
-LDFLAGS=`"${R_HOME}/bin/R" CMD config LDFLAGS`
-AC_LANG(C++)
+# 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])
@@ -43,19 +28,12 @@ fi
 
 if test `uname -s` = "Darwin"
 then
-  if command -v brew &> /dev/null
-  then
-    HOMEBREW_LIBOMP_PREFIX=`brew --prefix libomp`
-  else
-    # Homebrew not found
-    HOMEBREW_LIBOMP_PREFIX=''
-  fi
-  OPENMP_CXXFLAGS="-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include"
-  OPENMP_LIB="-lomp -L${HOMEBREW_LIBOMP_PREFIX}/lib"
+  OPENMP_CXXFLAGS='-Xclang -fopenmp'
+  OPENMP_LIB='-lomp'
   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); ]])])
-  ${CXX} -o conftest conftest.cpp ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CC} -o conftest conftest.c ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''

R-package/demo/caret_wrapper.R

@@ -1,4 +1,5 @@
 # install development version of caret library that contains xgboost models
+devtools::install_github("topepo/caret/pkg/caret")
 require(caret)
 require(xgboost)
 require(data.table)
@@ -7,23 +8,14 @@ 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).
+# 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)
 
-# 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.
+# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
+# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
 df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old.
-# I choose this value based on nothing.
-# We will see later if simplifying the information based on arbitrary values is a good strategy
-# (I am sure you already have an idea of how well it will work!).
+# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
 df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
@@ -34,10 +26,9 @@ df[, ID := NULL]
 # Here we use 10-fold cross-validation, repeating twice, and using random search for tuning hyper-parameters.
 fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 2, search = "random")
 # train a xgbTree model using caret::train
-model <- train(factor(Improved) ~ ., data = df, method = "xgbTree", trControl = fitControl)
+model <- train(factor(Improved)~., data = df, method = "xgbTree", trControl = fitControl)
 
-# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model
-# using xgbLinear
+# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model using xgbLinear
 # model <- train(factor(Improved)~., data = df, method = "xgbLinear", trControl = fitControl)
 
 # See model results

R-package/demo/create_sparse_matrix.R

@@ -7,47 +7,34 @@ if (!require(vcd)) {
 }
 # According to its documentation, XGBoost works only on numbers.
 # Sometimes the dataset we have to work on have categorical data.
-# A categorical variable is one which have a fixed number of values.
-# By example, if for each observation a variable called "Colour" can have only
-# "red", "blue" or "green" as value, it is a categorical variable.
+# A categorical variable is one which have a fixed number of values. By example, if for each observation a variable called "Colour" can have only "red", "blue" or "green" as value, it is a categorical variable.
 #
 # In R, categorical variable is called Factor.
 # Type ?factor in console for more information.
 #
-# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix
-# before analyzing it in XGBoost.
+# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in XGBoost.
 # The method we are going to see is usually called "one hot encoding".
 
 #load Arthritis dataset in memory.
 data(Arthritis)
 
-# create a copy of the dataset with data.table package
-# (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent
-# and its performance are really good).
+# 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)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
 print(df)
 
-# 2 columns have factor type, one has ordinal type
-# (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
+# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
 cat("Structure of the dataset\n")
 str(df)
 
-# Let's add some new categorical features to see if it helps.
-# Of course these feature are highly correlated to the Age feature.
-# Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features,
-# even in case of highly correlated features.
+# 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 independent values.
+# 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 independent values.
 df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old.
-# I choose this value based on nothing.
-# We will see later if simplifying the information based on arbitrary values is a good strategy
-# (I am sure you already have an idea of how well it will work!).
+# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
 df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
@@ -61,10 +48,7 @@ print(levels(df[, Treatment]))
 # This method is also called one hot encoding.
 # The purpose is to transform each value of each categorical feature in one binary feature.
 #
-# Let's take, the column Treatment will be replaced by two columns, Placebo, and Treated.
-# Each of them will be binary.
-# For example an observation which had the value Placebo in column Treatment before the transformation will have, after the transformation,
-# the value 1 in the new column Placebo and the value 0 in the new column  Treated.
+# Let's take, the column Treatment will be replaced by two columns, Placebo, and Treated. Each of them will be binary. For example an observation which had the value Placebo in column Treatment before the transformation will have, after the transformation, the value 1 in the new column Placebo and the value 0 in the new column  Treated.
 #
 # Formulae Improved~.-1 used below means transform all categorical features but column Improved to binary values.
 # Column Improved is excluded because it will be our output column, the one we want to predict.
@@ -86,10 +70,7 @@ bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 9,
 
 importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst)
 print(importance)
-# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age.
-# The second most important feature is having received a placebo or not.
-# The sex is third.
-# Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
+# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age. The second most important feature is having received a placebo or not. The sex is third. Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
 
 # Does these result make sense?
 # Let's check some Chi2 between each of these features and the outcome.
@@ -101,17 +82,8 @@ print(chisq.test(df$AgeDiscret, df$Y))
 # Our first simplification of Age gives a Pearson correlation of 8.
 
 print(chisq.test(df$AgeCat, df$Y))
-# The perfectly random split I did between young and old at 30 years old have a low correlation of 2.
-# It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that),
-# but for the illness we are studying, the age to be vulnerable is not the same.
-# Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
+# The perfectly random split I did between young and old at 30 years old have a low correlation of 2. It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that), but  for the illness we are studying, the age to be vulnerable is not the same. Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
 
-# As you can see, in general destroying information by simplifying it won't improve your model.
-# Chi2 just demonstrates that.
-# But in more complex cases, creating a new feature based on existing one which makes link with the outcome
-# more obvious may help the algorithm and improve the model.
-# The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
+# As you can see, in general destroying information by simplifying it won't improve your model. Chi2 just demonstrates that. But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model. The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
 # However it's almost always worse when you add some arbitrary rules.
-# Moreover, you can notice that even if we have added some not useful new features highly correlated with
-# other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age.
-# Linear model may not be that strong in these scenario.
+# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.

R-package/demo/cross_validation.R

@@ -12,7 +12,7 @@ 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

R-package/demo/interaction_constraints.R

@@ -33,7 +33,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
   }
 
   # Extract nodes with interactions
-  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),  # nolint: object_usage_linter
+  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)))
@@ -44,7 +44,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
   # Remove non-interactions (same variable)
   interaction_list <- lapply(interaction_list, unique)  # remove same variables
-  interaction_length <- lengths(interaction_list)
+  interaction_length <- sapply(interaction_list, length)
   interaction_list <- interaction_list[interaction_length > 1]
   interaction_list <- unique(lapply(interaction_list, sort))
   return(interaction_list)

R-package/demo/predict_leaf_indices.R

@@ -24,7 +24,7 @@ accuracy.before <- (sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.te
 pred_with_leaf <- predict(bst, dtest, predleaf = TRUE)
 head(pred_with_leaf)
 
-create.new.tree.features <- function(model, original.features) {
+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) {

R-package/demo/runall.R

@@ -1,4 +1,4 @@
-# running all scripts in demo folder, removed during packaging.
+# running all scripts in demo folder
 demo(basic_walkthrough, package = 'xgboost')
 demo(custom_objective, package = 'xgboost')
 demo(boost_from_prediction, package = 'xgboost')

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

@@ -79,9 +79,9 @@ 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, fixed = TRUE)
+exported_symbols <- gsub("\t", "", exported_symbols)
 exported_symbols <- gsub(".*\\] ", "", exported_symbols)
-exported_symbols <- gsub(" ", "", exported_symbols, fixed = TRUE)
+exported_symbols <- gsub(" ", "", exported_symbols)
 
 # Write R.def file
 writeLines(

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

@@ -15,11 +15,9 @@ selected per iteration.}
 }
 \value{
 Results are stored in the \code{coefs} element of the closure.
-The \code{\link{xgb.gblinear.history}} convenience function provides an easy
-way to access it.
+The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
 With \code{xgb.train}, it is either a dense of a sparse matrix.
-While with \code{xgb.cv}, it is a list (an element per each fold) of such
-matrices.
+While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
 }
 \description{
 Callback closure for collecting the model coefficients history of a gblinear booster
@@ -40,7 +38,7 @@ Callback function expects the following values to be set in its calling frame:
 # without considering the 2nd order interactions:
 x <- model.matrix(Species ~ .^2, iris)[,-1]
 colnames(x)
-dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
+dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
 param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For 'shotgun', which is a default linear updater, using high eta values may result in
@@ -65,19 +63,19 @@ matplot(xgb.gblinear.history(bst), type = 'l')
 
 # For xgb.cv:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-              callbacks = list(cb.gblinear.history()))
+             callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
 matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 
 
 #### Multiclass classification:
 #
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 1)
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
 param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-              lambda = 0.0003, alpha = 0.0003, nthread = 1)
+              lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For the default linear updater 'shotgun' it sometimes is helpful
 # to use smaller eta to reduce instability
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 50, eta = 0.5,
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
                  callbacks = list(cb.gblinear.history()))
 # Will plot the coefficient paths separately for each class:
 matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')

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

@@ -19,7 +19,7 @@ be directly used with an \code{xgb.DMatrix} object.
 \examples{
 data(agaricus.train, package='xgboost')
 train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
+dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 stopifnot(nrow(dtrain) == nrow(train$data))
 stopifnot(ncol(dtrain) == ncol(train$data))

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

@@ -26,7 +26,7 @@ Since row names are irrelevant, it is recommended to use \code{colnames} directl
 \examples{
 data(agaricus.train, package='xgboost')
 train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
+dtrain <- xgb.DMatrix(train$data, label=train$label)
 dimnames(dtrain)
 colnames(dtrain)
 colnames(dtrain) <- make.names(1:ncol(train$data))

R-package/man/getinfo.Rd

@@ -34,7 +34,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

R-package/man/normalize.Rd

@@ -0,0 +1,18 @@
+% 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

@@ -122,10 +122,6 @@ With \code{predinteraction = TRUE}, SHAP values of contributions of interaction
 are computed. Note that this operation might be rather expensive in terms of compute and memory.
 Since it quadratically depends on the number of features, it is recommended to perform selection
 of the most important features first. See below about the format of the returned results.
-
-The \code{predict()} method uses as many threads as defined in \code{xgb.Booster} object (all by default).
-If you want to change their number, then assign a new number to \code{nthread} using \code{\link{xgb.parameters<-}}.
-Note also that converting a matrix to \code{\link{xgb.DMatrix}} uses multiple threads too.
 }
 \examples{
 ## binary classification:

R-package/man/prepare.ggplot.shap.data.Rd

@@ -0,0 +1,27 @@
+% 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/print.xgb.DMatrix.Rd

@@ -19,7 +19,7 @@ Currently it displays dimensions and presence of info-fields and colnames.
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 
 dtrain
 print(dtrain, verbose=TRUE)

R-package/man/setinfo.Rd

@@ -33,7 +33,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

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

@@ -28,7 +28,7 @@ original xgb.DMatrix object
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 
 dsub <- slice(dtrain, 1:42)
 labels1 <- getinfo(dsub, 'label')

R-package/man/xgb.DMatrix.Rd

@@ -38,7 +38,7 @@ Supported input file formats are either a LIBSVM text file or a binary file that
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = 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

@@ -16,7 +16,7 @@ Save xgb.DMatrix object to binary file
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = 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.create.features.Rd

@@ -59,8 +59,8 @@ a rule on certain features."
 \examples{
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 nrounds = 4
@@ -76,12 +76,8 @@ new.features.train <- xgb.create.features(model = bst, agaricus.train$data)
 new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
 
 # learning with new features
-new.dtrain <- xgb.DMatrix(
-  data = new.features.train, label = agaricus.train$label, nthread = 2
-)
-new.dtest <- xgb.DMatrix(
-  data = new.features.test, label = agaricus.test$label, nthread = 2
-)
+new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
+new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
 watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 

R-package/man/xgb.cv.Rd

@@ -148,11 +148,9 @@ The cross validation function of xgboost
 \details{
 The original sample is randomly partitioned into \code{nfold} equal size subsamples.
 
-Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model,
-and the remaining \code{nfold - 1} subsamples are used as training data.
+Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
 
-The cross-validation process is then repeated \code{nrounds} times, with each of the
-\code{nfold} subsamples used exactly once as the validation data.
+The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
 
 All observations are used for both training and validation.
 
@@ -160,9 +158,9 @@ Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-             max_depth = 3, eta = 1, objective = "binary:logistic")
+                  max_depth = 3, eta = 1, objective = "binary:logistic")
 print(cv)
 print(cv, verbose=TRUE)
 

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

@@ -10,7 +10,7 @@ xgb.ggplot.importance(
   top_n = NULL,
   measure = NULL,
   rel_to_first = FALSE,
-  n_clusters = seq_len(10),
+  n_clusters = c(1:10),
   ...
 )
 

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

@@ -67,12 +67,12 @@ 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/shap/shap.
+\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/shap/shap}
+  \url{https://github.com/slundberg/shap}
 }

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

@@ -67,7 +67,7 @@ The "Yes" branches are marked by the "< split_value" label.
 The branches that also used for missing values are marked as bold
 (as in "carrying extra capacity").
 
-This function uses \href{https://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
+This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
 }
 \examples{
 data(agaricus.train, package='xgboost')

R-package/man/xgb.train.Rd

@@ -57,37 +57,17 @@ xgboost(
 2.1. Parameters for Tree Booster
 
 \itemize{
-  \item{ \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1}
-         when it is added to the current approximation.
-         Used to prevent overfitting by making the boosting process more conservative.
-         Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model
-         more robust to overfitting but slower to compute. Default: 0.3}
-  \item{ \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree.
-         the larger, the more conservative the algorithm will be.}
+  \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
+  \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
   \item \code{max_depth} maximum depth of a tree. Default: 6
-  \item{\code{min_child_weight} minimum sum of instance weight (hessian) needed in a child.
-        If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight,
-        then the building process will give up further partitioning.
-        In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node.
-        The larger, the more conservative the algorithm will be. Default: 1}
-  \item{ \code{subsample} subsample ratio of the training instance.
-        Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees
-        and this will prevent overfitting. It makes computation shorter (because less data to analyse).
-        It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1}
+  \item \code{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.}
+  \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
@@ -101,53 +81,29 @@ xgboost(
 3. Task Parameters
 
 \itemize{
-\item{ \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it.
-       The default objective options are below:
+\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:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
     \item \code{reg:logistic} logistic regression.
     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-    \item{ \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution.
-           \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).}
-    \item{ \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored).
-           Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional
-           hazard function \code{h(t) = h0(t) * HR)}.}
-    \item{ \code{survival:aft}: Accelerated failure time model for censored survival time data. See
-           \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time}
-           for details.}
+    \item \code{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}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
-    \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{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{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.}
+  \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.
 }}
 
 \item{data}{training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
@@ -267,8 +223,7 @@ The following is the list of built-in metrics for which XGBoost provides optimiz
      \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{https://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}
   }
@@ -286,8 +241,8 @@ The following callbacks are automatically created when certain parameters are se
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:

R-package/src/Makevars.in

@@ -3,11 +3,12 @@ PKGROOT=../../
 ENABLE_STD_THREAD=1
 # _*_ mode: Makefile; _*_
 
-CXX_STD = CXX17
+CXX_STD = CXX14
 
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\
-           -DDMLC_LOG_CUSTOMIZE=1
+           -DDMLC_LOG_CUSTOMIZE=1 -DXGBOOST_CUSTOMIZE_LOGGER=1\
+           -DRABIT_CUSTOMIZE_MSG_
 
 # disable the use of thread_local for 32 bit windows:
 ifeq ($(R_OSTYPE)$(WIN),windows)
@@ -18,92 +19,7 @@ $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
 PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ @ENDIAN_FLAG@ -pthread $(CXX_VISIBILITY)
 PKG_LIBS = @OPENMP_CXXFLAGS@ @OPENMP_LIB@ @ENDIAN_FLAG@ @BACKTRACE_LIB@ -pthread
-
-OBJECTS= \
-    ./xgboost_R.o \
-    ./xgboost_custom.o \
-    ./init.o \
-    $(PKGROOT)/src/metric/metric.o \
-    $(PKGROOT)/src/metric/elementwise_metric.o \
-    $(PKGROOT)/src/metric/multiclass_metric.o \
-    $(PKGROOT)/src/metric/rank_metric.o \
-    $(PKGROOT)/src/metric/auc.o \
-    $(PKGROOT)/src/metric/survival_metric.o \
-    $(PKGROOT)/src/objective/objective.o \
-    $(PKGROOT)/src/objective/regression_obj.o \
-    $(PKGROOT)/src/objective/multiclass_obj.o \
-    $(PKGROOT)/src/objective/lambdarank_obj.o \
-    $(PKGROOT)/src/objective/hinge.o \
-    $(PKGROOT)/src/objective/aft_obj.o \
-    $(PKGROOT)/src/objective/adaptive.o \
-    $(PKGROOT)/src/objective/init_estimation.o \
-    $(PKGROOT)/src/objective/quantile_obj.o \
-    $(PKGROOT)/src/gbm/gbm.o \
-    $(PKGROOT)/src/gbm/gbtree.o \
-    $(PKGROOT)/src/gbm/gbtree_model.o \
-    $(PKGROOT)/src/gbm/gblinear.o \
-    $(PKGROOT)/src/gbm/gblinear_model.o \
-    $(PKGROOT)/src/data/simple_dmatrix.o \
-    $(PKGROOT)/src/data/data.o \
-    $(PKGROOT)/src/data/sparse_page_raw_format.o \
-    $(PKGROOT)/src/data/ellpack_page.o \
-    $(PKGROOT)/src/data/file_iterator.o \
-    $(PKGROOT)/src/data/gradient_index.o \
-    $(PKGROOT)/src/data/gradient_index_page_source.o \
-    $(PKGROOT)/src/data/gradient_index_format.o \
-    $(PKGROOT)/src/data/sparse_page_dmatrix.o \
-    $(PKGROOT)/src/data/proxy_dmatrix.o \
-    $(PKGROOT)/src/data/iterative_dmatrix.o \
-    $(PKGROOT)/src/predictor/predictor.o \
-    $(PKGROOT)/src/predictor/cpu_predictor.o \
-    $(PKGROOT)/src/predictor/cpu_treeshap.o \
-    $(PKGROOT)/src/tree/constraints.o \
-    $(PKGROOT)/src/tree/param.o \
-    $(PKGROOT)/src/tree/fit_stump.o \
-    $(PKGROOT)/src/tree/tree_model.o \
-    $(PKGROOT)/src/tree/tree_updater.o \
-    $(PKGROOT)/src/tree/multi_target_tree_model.o \
-    $(PKGROOT)/src/tree/updater_approx.o \
-    $(PKGROOT)/src/tree/updater_colmaker.o \
-    $(PKGROOT)/src/tree/updater_prune.o \
-    $(PKGROOT)/src/tree/updater_quantile_hist.o \
-    $(PKGROOT)/src/tree/updater_refresh.o \
-    $(PKGROOT)/src/tree/updater_sync.o \
-    $(PKGROOT)/src/tree/hist/param.o \
-    $(PKGROOT)/src/tree/hist/histogram.o \
-    $(PKGROOT)/src/linear/linear_updater.o \
-    $(PKGROOT)/src/linear/updater_coordinate.o \
-    $(PKGROOT)/src/linear/updater_shotgun.o \
-    $(PKGROOT)/src/learner.o \
-    $(PKGROOT)/src/context.o \
-    $(PKGROOT)/src/logging.o \
-    $(PKGROOT)/src/global_config.o \
-    $(PKGROOT)/src/collective/communicator.o \
-    $(PKGROOT)/src/collective/in_memory_communicator.o \
-    $(PKGROOT)/src/collective/in_memory_handler.o \
-    $(PKGROOT)/src/collective/socket.o \
-    $(PKGROOT)/src/common/charconv.o \
-    $(PKGROOT)/src/common/column_matrix.o \
-    $(PKGROOT)/src/common/common.o \
-    $(PKGROOT)/src/common/error_msg.o \
-    $(PKGROOT)/src/common/hist_util.o \
-    $(PKGROOT)/src/common/host_device_vector.o \
-    $(PKGROOT)/src/common/io.o \
-    $(PKGROOT)/src/common/json.o \
-    $(PKGROOT)/src/common/numeric.o \
-    $(PKGROOT)/src/common/pseudo_huber.o \
-    $(PKGROOT)/src/common/quantile.o \
-    $(PKGROOT)/src/common/random.o \
-    $(PKGROOT)/src/common/stats.o \
-    $(PKGROOT)/src/common/survival_util.o \
-    $(PKGROOT)/src/common/threading_utils.o \
-    $(PKGROOT)/src/common/ranking_utils.o \
-    $(PKGROOT)/src/common/quantile_loss_utils.o \
-    $(PKGROOT)/src/common/timer.o \
-    $(PKGROOT)/src/common/version.o \
-    $(PKGROOT)/src/c_api/c_api.o \
-    $(PKGROOT)/src/c_api/c_api_error.o \
-    $(PKGROOT)/amalgamation/dmlc-minimum0.o \
-    $(PKGROOT)/rabit/src/engine.o \
-    $(PKGROOT)/rabit/src/rabit_c_api.o \
-    $(PKGROOT)/rabit/src/allreduce_base.o
+OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o \
+         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o \
+         $(PKGROOT)/rabit/src/engine.o $(PKGROOT)/rabit/src/rabit_c_api.o \
+         $(PKGROOT)/rabit/src/allreduce_base.o

R-package/src/Makevars.win

@@ -1,13 +1,26 @@
 # package root
-PKGROOT=../../
+PKGROOT=./
 ENABLE_STD_THREAD=0
 # _*_ mode: Makefile; _*_
 
-CXX_STD = CXX17
+# This file is only used for Windows compilation from GitHub
+# It will be replaced with Makevars.in for the CRAN version
+.PHONY: all xgblib
+all: $(SHLIB)
+$(SHLIB): xgblib
+xgblib:
+	cp -r ../../src .
+	cp -r ../../rabit .
+	cp -r ../../dmlc-core .
+	cp -r ../../include .
+	cp -r ../../amalgamation .
+
+CXX_STD = CXX14
 
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\
-           -DDMLC_LOG_CUSTOMIZE=1
+           -DDMLC_LOG_CUSTOMIZE=1 -DXGBOOST_CUSTOMIZE_LOGGER=1\
+           -DRABIT_CUSTOMIZE_MSG_
 
 # disable the use of thread_local for 32 bit windows:
 ifeq ($(R_OSTYPE)$(WIN),windows)
@@ -16,94 +29,11 @@ endif
 $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
-PKG_CXXFLAGS= $(SHLIB_OPENMP_CXXFLAGS) -DDMLC_CMAKE_LITTLE_ENDIAN=1 $(SHLIB_PTHREAD_FLAGS) $(CXX_VISIBILITY)
-PKG_LIBS = $(SHLIB_OPENMP_CXXFLAGS)  -DDMLC_CMAKE_LITTLE_ENDIAN=1  $(SHLIB_PTHREAD_FLAGS) -lwsock32 -lws2_32
+PKG_CXXFLAGS= $(SHLIB_OPENMP_CXXFLAGS) $(SHLIB_PTHREAD_FLAGS)
+PKG_LIBS = $(SHLIB_OPENMP_CXXFLAGS) $(SHLIB_PTHREAD_FLAGS)
+OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o \
+         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o \
+         $(PKGROOT)/rabit/src/engine.o $(PKGROOT)/rabit/src/rabit_c_api.o \
+         $(PKGROOT)/rabit/src/allreduce_base.o
 
-OBJECTS= \
-    ./xgboost_R.o \
-    ./xgboost_custom.o \
-    ./init.o \
-    $(PKGROOT)/src/metric/metric.o \
-    $(PKGROOT)/src/metric/elementwise_metric.o \
-    $(PKGROOT)/src/metric/multiclass_metric.o \
-    $(PKGROOT)/src/metric/rank_metric.o \
-    $(PKGROOT)/src/metric/auc.o \
-    $(PKGROOT)/src/metric/survival_metric.o \
-    $(PKGROOT)/src/objective/objective.o \
-    $(PKGROOT)/src/objective/regression_obj.o \
-    $(PKGROOT)/src/objective/multiclass_obj.o \
-    $(PKGROOT)/src/objective/lambdarank_obj.o \
-    $(PKGROOT)/src/objective/hinge.o \
-    $(PKGROOT)/src/objective/aft_obj.o \
-    $(PKGROOT)/src/objective/adaptive.o \
-    $(PKGROOT)/src/objective/init_estimation.o \
-    $(PKGROOT)/src/objective/quantile_obj.o \
-    $(PKGROOT)/src/gbm/gbm.o \
-    $(PKGROOT)/src/gbm/gbtree.o \
-    $(PKGROOT)/src/gbm/gbtree_model.o \
-    $(PKGROOT)/src/gbm/gblinear.o \
-    $(PKGROOT)/src/gbm/gblinear_model.o \
-    $(PKGROOT)/src/data/simple_dmatrix.o \
-    $(PKGROOT)/src/data/data.o \
-    $(PKGROOT)/src/data/sparse_page_raw_format.o \
-    $(PKGROOT)/src/data/ellpack_page.o \
-    $(PKGROOT)/src/data/file_iterator.o \
-    $(PKGROOT)/src/data/gradient_index.o \
-    $(PKGROOT)/src/data/gradient_index_page_source.o \
-    $(PKGROOT)/src/data/gradient_index_format.o \
-    $(PKGROOT)/src/data/sparse_page_dmatrix.o \
-    $(PKGROOT)/src/data/proxy_dmatrix.o \
-    $(PKGROOT)/src/data/iterative_dmatrix.o \
-    $(PKGROOT)/src/predictor/predictor.o \
-    $(PKGROOT)/src/predictor/cpu_predictor.o \
-    $(PKGROOT)/src/predictor/cpu_treeshap.o \
-    $(PKGROOT)/src/tree/constraints.o \
-    $(PKGROOT)/src/tree/param.o \
-    $(PKGROOT)/src/tree/fit_stump.o \
-    $(PKGROOT)/src/tree/tree_model.o \
-    $(PKGROOT)/src/tree/multi_target_tree_model.o \
-    $(PKGROOT)/src/tree/tree_updater.o \
-    $(PKGROOT)/src/tree/updater_approx.o \
-    $(PKGROOT)/src/tree/updater_colmaker.o \
-    $(PKGROOT)/src/tree/updater_prune.o \
-    $(PKGROOT)/src/tree/updater_quantile_hist.o \
-    $(PKGROOT)/src/tree/updater_refresh.o \
-    $(PKGROOT)/src/tree/updater_sync.o \
-    $(PKGROOT)/src/tree/hist/param.o \
-    $(PKGROOT)/src/tree/hist/histogram.o \
-    $(PKGROOT)/src/linear/linear_updater.o \
-    $(PKGROOT)/src/linear/updater_coordinate.o \
-    $(PKGROOT)/src/linear/updater_shotgun.o \
-    $(PKGROOT)/src/learner.o \
-    $(PKGROOT)/src/context.o \
-    $(PKGROOT)/src/logging.o \
-    $(PKGROOT)/src/global_config.o \
-    $(PKGROOT)/src/collective/communicator.o \
-    $(PKGROOT)/src/collective/in_memory_communicator.o \
-    $(PKGROOT)/src/collective/in_memory_handler.o \
-    $(PKGROOT)/src/collective/socket.o \
-    $(PKGROOT)/src/common/charconv.o \
-    $(PKGROOT)/src/common/column_matrix.o \
-    $(PKGROOT)/src/common/common.o \
-    $(PKGROOT)/src/common/error_msg.o \
-    $(PKGROOT)/src/common/hist_util.o \
-    $(PKGROOT)/src/common/host_device_vector.o \
-    $(PKGROOT)/src/common/io.o \
-    $(PKGROOT)/src/common/json.o \
-    $(PKGROOT)/src/common/numeric.o \
-    $(PKGROOT)/src/common/pseudo_huber.o \
-    $(PKGROOT)/src/common/quantile.o \
-    $(PKGROOT)/src/common/random.o \
-    $(PKGROOT)/src/common/stats.o \
-    $(PKGROOT)/src/common/survival_util.o \
-    $(PKGROOT)/src/common/threading_utils.o \
-    $(PKGROOT)/src/common/ranking_utils.o \
-    $(PKGROOT)/src/common/quantile_loss_utils.o \
-    $(PKGROOT)/src/common/timer.o \
-    $(PKGROOT)/src/common/version.o \
-    $(PKGROOT)/src/c_api/c_api.o \
-    $(PKGROOT)/src/c_api/c_api_error.o \
-    $(PKGROOT)/amalgamation/dmlc-minimum0.o \
-    $(PKGROOT)/rabit/src/engine.o \
-    $(PKGROOT)/rabit/src/rabit_c_api.o \
-    $(PKGROOT)/rabit/src/allreduce_base.o
+$(OBJECTS) : xgblib

R-package/src/init.c

@@ -30,26 +30,25 @@ extern SEXP XGBoosterSaveJsonConfig_R(SEXP handle);
 extern SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value);
 extern SEXP XGBoosterSerializeToBuffer_R(SEXP handle);
 extern SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw);
+extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterPredictFromDMatrix_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSaveModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSetAttr_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSetParam_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterUpdateOneIter_R(SEXP, SEXP, SEXP);
 extern SEXP XGCheckNullPtr_R(SEXP);
-extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP, SEXP, SEXP);
-extern SEXP XGDMatrixCreateFromCSR_R(SEXP, SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSR_R(SEXP, SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixCreateFromFile_R(SEXP, SEXP);
 extern SEXP XGDMatrixCreateFromMat_R(SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixGetInfo_R(SEXP, SEXP);
-extern SEXP XGDMatrixGetStrFeatureInfo_R(SEXP, SEXP);
 extern SEXP XGDMatrixNumCol_R(SEXP);
 extern SEXP XGDMatrixNumRow_R(SEXP);
 extern SEXP XGDMatrixSaveBinary_R(SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixSetInfo_R(SEXP, SEXP, SEXP);
-extern SEXP XGDMatrixSetStrFeatureInfo_R(SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixSliceDMatrix_R(SEXP, SEXP);
 extern SEXP XGBSetGlobalConfig_R(SEXP);
-extern SEXP XGBGetGlobalConfig_R(void);
+extern SEXP XGBGetGlobalConfig_R();
 extern SEXP XGBoosterFeatureScore_R(SEXP, SEXP);
 
 static const R_CallMethodDef CallEntries[] = {
@@ -67,23 +66,22 @@ static const R_CallMethodDef CallEntries[] = {
   {"XGBoosterLoadJsonConfig_R",   (DL_FUNC) &XGBoosterLoadJsonConfig_R,   2},
   {"XGBoosterSerializeToBuffer_R",     (DL_FUNC) &XGBoosterSerializeToBuffer_R,     1},
   {"XGBoosterUnserializeFromBuffer_R", (DL_FUNC) &XGBoosterUnserializeFromBuffer_R, 2},
+  {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          5},
   {"XGBoosterPredictFromDMatrix_R", (DL_FUNC) &XGBoosterPredictFromDMatrix_R, 3},
   {"XGBoosterSaveModel_R",        (DL_FUNC) &XGBoosterSaveModel_R,        2},
   {"XGBoosterSetAttr_R",          (DL_FUNC) &XGBoosterSetAttr_R,          3},
   {"XGBoosterSetParam_R",         (DL_FUNC) &XGBoosterSetParam_R,         3},
   {"XGBoosterUpdateOneIter_R",    (DL_FUNC) &XGBoosterUpdateOneIter_R,    3},
   {"XGCheckNullPtr_R",            (DL_FUNC) &XGCheckNullPtr_R,            1},
-  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    6},
-  {"XGDMatrixCreateFromCSR_R",    (DL_FUNC) &XGDMatrixCreateFromCSR_R,    6},
+  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    5},
+  {"XGDMatrixCreateFromCSR_R",    (DL_FUNC) &XGDMatrixCreateFromCSR_R,    5},
   {"XGDMatrixCreateFromFile_R",   (DL_FUNC) &XGDMatrixCreateFromFile_R,   2},
   {"XGDMatrixCreateFromMat_R",    (DL_FUNC) &XGDMatrixCreateFromMat_R,    3},
   {"XGDMatrixGetInfo_R",          (DL_FUNC) &XGDMatrixGetInfo_R,          2},
-  {"XGDMatrixGetStrFeatureInfo_R", (DL_FUNC) &XGDMatrixGetStrFeatureInfo_R, 2},
   {"XGDMatrixNumCol_R",           (DL_FUNC) &XGDMatrixNumCol_R,           1},
   {"XGDMatrixNumRow_R",           (DL_FUNC) &XGDMatrixNumRow_R,           1},
   {"XGDMatrixSaveBinary_R",       (DL_FUNC) &XGDMatrixSaveBinary_R,       3},
   {"XGDMatrixSetInfo_R",          (DL_FUNC) &XGDMatrixSetInfo_R,          3},
-  {"XGDMatrixSetStrFeatureInfo_R", (DL_FUNC) &XGDMatrixSetStrFeatureInfo_R, 3},
   {"XGDMatrixSliceDMatrix_R",     (DL_FUNC) &XGDMatrixSliceDMatrix_R,     2},
   {"XGBSetGlobalConfig_R",        (DL_FUNC) &XGBSetGlobalConfig_R,        1},
   {"XGBGetGlobalConfig_R",        (DL_FUNC) &XGBGetGlobalConfig_R,        0},

R-package/src/xgboost_R.cc

@@ -1,11 +1,11 @@
 /**
- * Copyright 2014-2023 by XGBoost Contributors
+ * Copyright 2014-2022 by XGBoost Contributors
  */
 #include <dmlc/common.h>
 #include <dmlc/omp.h>
 #include <xgboost/c_api.h>
-#include <xgboost/context.h>
 #include <xgboost/data.h>
+#include <xgboost/generic_parameters.h>
 #include <xgboost/logging.h>
 
 #include <cstdio>
@@ -16,11 +16,9 @@
 #include <vector>
 
 #include "../../src/c_api/c_api_error.h"
-#include "../../src/c_api/c_api_utils.h"  // MakeSparseFromPtr
 #include "../../src/common/threading_utils.h"
 
-#include "./xgboost_R.h"  // Must follow other includes.
-#include "Rinternals.h"
+#include "./xgboost_R.h"
 
 /*!
  * \brief macro to annotate begin of api
@@ -48,14 +46,14 @@
 
 using dmlc::BeginPtr;
 
-xgboost::Context const *BoosterCtx(BoosterHandle handle) {
+xgboost::GenericParameter const *BoosterCtx(BoosterHandle handle) {
   CHECK_HANDLE();
   auto *learner = static_cast<xgboost::Learner *>(handle);
   CHECK(learner);
   return learner->Ctx();
 }
 
-xgboost::Context const *DMatrixCtx(DMatrixHandle handle) {
+xgboost::GenericParameter const *DMatrixCtx(DMatrixHandle handle) {
   CHECK_HANDLE();
   auto p_m = static_cast<std::shared_ptr<xgboost::DMatrix> *>(handle);
   CHECK(p_m);
@@ -116,29 +114,13 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
     din = REAL(mat);
   }
   std::vector<float> data(nrow * ncol);
-  xgboost::Context ctx;
-  ctx.nthread = asInteger(n_threads);
-  std::int32_t threads = ctx.Threads();
-
-  if (is_int) {
-    xgboost::common::ParallelFor(nrow, threads, [&](xgboost::omp_ulong i) {
-      for (size_t j = 0; j < ncol; ++j) {
-        auto v = iin[i + nrow * j];
-        if (v == NA_INTEGER) {
-          data[i * ncol + j] = std::numeric_limits<float>::quiet_NaN();
-        } else {
-          data[i * ncol + j] = static_cast<float>(v);
-        }
-      }
-    });
-  } else {
-    xgboost::common::ParallelFor(nrow, threads, [&](xgboost::omp_ulong i) {
-      for (size_t j = 0; j < ncol; ++j) {
-        data[i * ncol + j] = din[i + nrow * j];
-      }
-    });
-  }
+  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
 
+  xgboost::common::ParallelFor(nrow, threads, [&](xgboost::omp_ulong i) {
+    for (size_t j = 0; j < ncol; ++j) {
+      data[i * ncol + j] = is_int ? static_cast<float>(iin[i + nrow * j]) : din[i + nrow * j];
+    }
+  });
   DMatrixHandle handle;
   CHECK_CALL(XGDMatrixCreateFromMat_omp(BeginPtr(data), nrow, ncol,
                                         asReal(missing), &handle, threads));
@@ -149,78 +131,66 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
   return ret;
 }
 
-namespace {
-void CreateFromSparse(SEXP indptr, SEXP indices, SEXP data, std::string *indptr_str,
-                      std::string *indices_str, std::string *data_str) {
+XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
+                                      SEXP num_row, SEXP n_threads) {
+  SEXP ret;
+  R_API_BEGIN();
   const int *p_indptr = INTEGER(indptr);
   const int *p_indices = INTEGER(indices);
   const double *p_data = REAL(data);
+  size_t nindptr = static_cast<size_t>(length(indptr));
+  size_t ndata = static_cast<size_t>(length(data));
+  size_t nrow = static_cast<size_t>(INTEGER(num_row)[0]);
+  std::vector<size_t> col_ptr_(nindptr);
+  std::vector<unsigned> indices_(ndata);
+  std::vector<float> data_(ndata);
 
-  auto nindptr = static_cast<std::size_t>(length(indptr));
-  auto ndata = static_cast<std::size_t>(length(data));
-  CHECK_EQ(ndata, p_indptr[nindptr - 1]);
-  xgboost::detail::MakeSparseFromPtr(p_indptr, p_indices, p_data, nindptr, indptr_str, indices_str,
-                                     data_str);
-}
-}  // namespace
-
-XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_row,
-                                      SEXP missing, SEXP n_threads) {
-  SEXP ret;
-  R_API_BEGIN();
-  std::int32_t threads = asInteger(n_threads);
-
-  using xgboost::Integer;
-  using xgboost::Json;
-  using xgboost::Object;
-
-  std::string sindptr, sindices, sdata;
-  CreateFromSparse(indptr, indices, data, &sindptr, &sindices, &sdata);
-  auto nrow = static_cast<std::size_t>(INTEGER(num_row)[0]);
-
+  for (size_t i = 0; i < nindptr; ++i) {
+    col_ptr_[i] = static_cast<size_t>(p_indptr[i]);
+  }
+  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
+  xgboost::common::ParallelFor(ndata, threads, [&](xgboost::omp_ulong i) {
+    indices_[i] = static_cast<unsigned>(p_indices[i]);
+    data_[i] = static_cast<float>(p_data[i]);
+  });
   DMatrixHandle handle;
-  Json jconfig{Object{}};
-  // Construct configuration
-  jconfig["nthread"] = Integer{threads};
-  jconfig["missing"] = xgboost::Number{asReal(missing)};
-  std::string config;
-  Json::Dump(jconfig, &config);
-  CHECK_CALL(XGDMatrixCreateFromCSC(sindptr.c_str(), sindices.c_str(), sdata.c_str(), nrow,
-                                    config.c_str(), &handle));
-
+  CHECK_CALL(XGDMatrixCreateFromCSCEx(BeginPtr(col_ptr_), BeginPtr(indices_),
+                                      BeginPtr(data_), nindptr, ndata,
+                                      nrow, &handle));
   ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
-
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
   UNPROTECT(1);
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_col,
-                                      SEXP missing, SEXP n_threads) {
+XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data,
+                                      SEXP num_col, SEXP n_threads) {
   SEXP ret;
   R_API_BEGIN();
-  std::int32_t threads = asInteger(n_threads);
-
-  using xgboost::Integer;
-  using xgboost::Json;
-  using xgboost::Object;
-
-  std::string sindptr, sindices, sdata;
-  CreateFromSparse(indptr, indices, data, &sindptr, &sindices, &sdata);
-  auto ncol = static_cast<std::size_t>(INTEGER(num_col)[0]);
+  const int *p_indptr = INTEGER(indptr);
+  const int *p_indices = INTEGER(indices);
+  const double *p_data = REAL(data);
+  size_t nindptr = static_cast<size_t>(length(indptr));
+  size_t ndata = static_cast<size_t>(length(data));
+  size_t ncol = static_cast<size_t>(INTEGER(num_col)[0]);
+  std::vector<size_t> row_ptr_(nindptr);
+  std::vector<unsigned> indices_(ndata);
+  std::vector<float> data_(ndata);
 
+  for (size_t i = 0; i < nindptr; ++i) {
+    row_ptr_[i] = static_cast<size_t>(p_indptr[i]);
+  }
+  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
+  xgboost::common::ParallelFor(ndata, threads, [&](xgboost::omp_ulong i) {
+    indices_[i] = static_cast<unsigned>(p_indices[i]);
+    data_[i] = static_cast<float>(p_data[i]);
+  });
   DMatrixHandle handle;
-  Json jconfig{Object{}};
-  // Construct configuration
-  jconfig["nthread"] = Integer{threads};
-  jconfig["missing"] = xgboost::Number{asReal(missing)};
-  std::string config;
-  Json::Dump(jconfig, &config);
-  CHECK_CALL(XGDMatrixCreateFromCSR(sindptr.c_str(), sindices.c_str(), sdata.c_str(), ncol,
-                                    config.c_str(), &handle));
+  CHECK_CALL(XGDMatrixCreateFromCSREx(BeginPtr(row_ptr_), BeginPtr(indices_),
+                                      BeginPtr(data_), nindptr, ndata,
+                                      ncol, &handle));
   ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
-
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
   UNPROTECT(1);
@@ -279,53 +249,15 @@ XGB_DLL SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGDMatrixSetStrFeatureInfo_R(SEXP handle, SEXP field, SEXP array) {
-  R_API_BEGIN();
-  size_t len{0};
-  if (!isNull(array)) {
-    len = length(array);
-  }
-
-  const char *name = CHAR(asChar(field));
-  std::vector<std::string> str_info;
-  for (size_t i = 0; i < len; ++i) {
-    str_info.emplace_back(CHAR(asChar(VECTOR_ELT(array, i))));
-  }
-  std::vector<char const*> vec(len);
-  std::transform(str_info.cbegin(), str_info.cend(), vec.begin(),
-                 [](std::string const &str) { return str.c_str(); });
-  CHECK_CALL(XGDMatrixSetStrFeatureInfo(R_ExternalPtrAddr(handle), name, vec.data(), len));
-  R_API_END();
-  return R_NilValue;
-}
-
-XGB_DLL SEXP XGDMatrixGetStrFeatureInfo_R(SEXP handle, SEXP field) {
-  SEXP ret;
-  R_API_BEGIN();
-  char const **out_features{nullptr};
-  bst_ulong len{0};
-  const char *name = CHAR(asChar(field));
-  XGDMatrixGetStrFeatureInfo(R_ExternalPtrAddr(handle), name, &len, &out_features);
-
-  if (len > 0) {
-    ret = PROTECT(allocVector(STRSXP, len));
-    for (size_t i = 0; i < len; ++i) {
-      SET_STRING_ELT(ret, i, mkChar(out_features[i]));
-    }
-  } else {
-    ret = PROTECT(R_NilValue);
-  }
-  R_API_END();
-  UNPROTECT(1);
-  return ret;
-}
-
 XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong olen;
   const float *res;
-  CHECK_CALL(XGDMatrixGetFloatInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), &olen, &res));
+  CHECK_CALL(XGDMatrixGetFloatInfo(R_ExternalPtrAddr(handle),
+                                   CHAR(asChar(field)),
+                                 &olen,
+                                 &res));
   ret = PROTECT(allocVector(REALSXP, olen));
   for (size_t i = 0; i < olen; ++i) {
     REAL(ret)[i] = res[i];
@@ -452,6 +384,27 @@ XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evn
   return mkString(ret);
 }
 
+XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
+                                SEXP ntree_limit, SEXP training) {
+  SEXP ret;
+  R_API_BEGIN();
+  bst_ulong olen;
+  const float *res;
+  CHECK_CALL(XGBoosterPredict(R_ExternalPtrAddr(handle),
+                              R_ExternalPtrAddr(dmat),
+                              asInteger(option_mask),
+                              asInteger(ntree_limit),
+                              asInteger(training),
+                              &olen, &res));
+  ret = PROTECT(allocVector(REALSXP, olen));
+  for (size_t i = 0; i < olen; ++i) {
+    REAL(ret)[i] = res[i];
+  }
+  R_API_END();
+  UNPROTECT(1);
+  return ret;
+}
+
 XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_config)  {
   SEXP r_out_shape;
   SEXP r_out_result;

R-package/src/xgboost_R.h

@@ -59,12 +59,11 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat,
  * \param indices row indices
  * \param data content of the data
  * \param num_row numer of rows (when it's set to 0, then guess from data)
- * \param missing which value to represent missing value
  * \param n_threads Number of threads used to construct DMatrix from csc matrix.
  * \return created dmatrix
  */
 XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_row,
-                                      SEXP missing, SEXP n_threads);
+                                      SEXP n_threads);
 
 /*!
  * \brief create a matrix content from CSR format
@@ -72,12 +71,11 @@ XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP
  * \param indices column indices
  * \param data content of the data
  * \param num_col numer of columns (when it's set to 0, then guess from data)
- * \param missing which value to represent missing value
  * \param n_threads Number of threads used to construct DMatrix from csr matrix.
  * \return created dmatrix
  */
 XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_col,
-                                      SEXP missing, SEXP n_threads);
+                                      SEXP n_threads);
 
 /*!
  * \brief create a new dmatrix from sliced content of existing matrix
@@ -178,6 +176,17 @@ XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP h
  */
 XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames);
 
+/*!
+ * \brief (Deprecated) make prediction based on dmat
+ * \param handle handle
+ * \param dmat data matrix
+ * \param option_mask output_margin:1 predict_leaf:2
+ * \param ntree_limit limit number of trees used in prediction
+ * \param training Whether the prediction value is used for training.
+ */
+XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
+                                SEXP ntree_limit, SEXP training);
+
 /*!
  * \brief Run prediction on DMatrix, replacing `XGBoosterPredict_R`
  * \param handle handle

R-package/src/xgboost_assert.c

@@ -0,0 +1,26 @@
+// Copyright (c) 2014 by Contributors
+#include <stdio.h>
+#include <stdarg.h>
+#include <Rinternals.h>
+
+// implements error handling
+void XGBoostAssert_R(int exp, const char *fmt, ...) {
+  char buf[1024];
+  if (exp == 0) {
+    va_list args;
+    va_start(args, fmt);
+    vsprintf(buf, fmt, args);
+    va_end(args);
+    error("AssertError:%s\n", buf);
+  }
+}
+void XGBoostCheck_R(int exp, const char *fmt, ...) {
+  char buf[1024];
+  if (exp == 0) {
+    va_list args;
+    va_start(args, fmt);
+    vsprintf(buf, fmt, args);
+    va_end(args);
+    error("%s\n", buf);
+  }
+}

R-package/src/xgboost_custom.cc

@@ -32,7 +32,7 @@ namespace common {
 bool CheckNAN(double v) {
   return ISNAN(v);
 }
-#if !defined(XGBOOST_USE_CUDA) && !defined(XGBOOST_USE_HIP)
+#if !defined(XGBOOST_USE_CUDA)
 double LogGamma(double v) {
   return lgammafn(v);
 }

R-package/tests/helper_scripts/install_deps.R

@@ -1,51 +0,0 @@
-## Install dependencies of R package for testing. The list might not be
-## up-to-date, check DESCRIPTION for the latest list and update this one if
-## inconsistent is found.
-pkgs <- c(
-  ## CI
-  "caret",
-  "pkgbuild",
-  "roxygen2",
-  "XML",
-  "cplm",
-  "e1071",
-  ## suggests
-  "knitr",
-  "rmarkdown",
-  "ggplot2",
-  "DiagrammeR",
-  "Ckmeans.1d.dp",
-  "vcd",
-  "lintr",
-  "testthat",
-  "igraph",
-  "float",
-  "titanic",
-  ## imports
-  "Matrix",
-  "methods",
-  "data.table",
-  "jsonlite"
-)
-
-ncpus <- parallel::detectCores()
-print(paste0("Using ", ncpus, " cores to install dependencies."))
-
-if (.Platform$OS.type == "unix") {
-  print("Installing source packages on unix.")
-  install.packages(
-    pkgs,
-    repo = "https://cloud.r-project.org",
-    dependencies = c("Depends", "Imports", "LinkingTo"),
-    Ncpus = parallel::detectCores()
-  )
-} else {
-  print("Installing binary packages on Windows.")
-  install.packages(
-    pkgs,
-    repo = "https://cloud.r-project.org",
-    dependencies = c("Depends", "Imports", "LinkingTo"),
-    Ncpus = parallel::detectCores(),
-    type = "binary"
-  )
-}

R-package/tests/helper_scripts/run_lint.R

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

R-package/tests/testthat/test_basic.R

@@ -1,3 +1,6 @@
+require(xgboost)
+library(Matrix)
+
 context("basic functions")
 
 data(agaricus.train, package = 'xgboost')
@@ -85,18 +88,9 @@ test_that("dart prediction works", {
     rnorm(100)
 
   set.seed(1994)
-  booster_by_xgboost <- xgboost(
-    data = d,
-    label = y,
-    max_depth = 2,
-    booster = "dart",
-    rate_drop = 0.5,
-    one_drop = TRUE,
-    eta = 1,
-    nthread = 2,
-    nrounds = nrounds,
-    objective = "reg:squarederror"
-  )
+  booster_by_xgboost <- xgboost(data = d, label = y, max_depth = 2, booster = "dart",
+                                rate_drop = 0.5, one_drop = TRUE,
+                                eta = 1, nthread = 2, nrounds = nrounds, objective = "reg:squarederror")
   pred_by_xgboost_0 <- predict(booster_by_xgboost, newdata = d, ntreelimit = 0)
   pred_by_xgboost_1 <- predict(booster_by_xgboost, newdata = d, ntreelimit = nrounds)
   expect_true(all(matrix(pred_by_xgboost_0, byrow = TRUE) == matrix(pred_by_xgboost_1, byrow = TRUE)))
@@ -106,19 +100,19 @@ test_that("dart prediction works", {
 
   set.seed(1994)
   dtrain <- xgb.DMatrix(data = d, info = list(label = y))
-  booster_by_train <- xgb.train(
-    params = list(
-      booster = "dart",
-      max_depth = 2,
-      eta = 1,
-      rate_drop = 0.5,
-      one_drop = TRUE,
-      nthread = 1,
-      objective = "reg:squarederror"
-    ),
-    data = dtrain,
-    nrounds = nrounds
-  )
+  booster_by_train <- xgb.train(params = list(
+                                    booster = "dart",
+                                    max_depth = 2,
+                                    eta = 1,
+                                    rate_drop = 0.5,
+                                    one_drop = TRUE,
+                                    nthread = 1,
+                                    tree_method = "exact",
+                                    objective = "reg:squarederror"
+                                ),
+                                data = dtrain,
+                                nrounds = nrounds
+                                )
   pred_by_train_0 <- predict(booster_by_train, newdata = dtrain, ntreelimit = 0)
   pred_by_train_1 <- predict(booster_by_train, newdata = dtrain, ntreelimit = nrounds)
   pred_by_train_2 <- predict(booster_by_train, newdata = dtrain, training = TRUE)
@@ -241,20 +235,12 @@ test_that("train and predict RF with softprob", {
 test_that("use of multiple eval metrics works", {
   expect_output(
     bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-                   eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic",
-                   eval_metric = 'error', eval_metric = 'auc', eval_metric = "logloss")
+                  eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic",
+                  eval_metric = 'error', eval_metric = 'auc', eval_metric = "logloss")
   , "train-error.*train-auc.*train-logloss")
   expect_false(is.null(bst$evaluation_log))
   expect_equal(dim(bst$evaluation_log), c(2, 4))
   expect_equal(colnames(bst$evaluation_log), c("iter", "train_error", "train_auc", "train_logloss"))
-  expect_output(
-    bst2 <- xgboost(data = train$data, label = train$label, max_depth = 2,
-                    eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic",
-                    eval_metric = list("error", "auc", "logloss"))
-  , "train-error.*train-auc.*train-logloss")
-  expect_false(is.null(bst2$evaluation_log))
-  expect_equal(dim(bst2$evaluation_log), c(2, 4))
-  expect_equal(colnames(bst2$evaluation_log), c("iter", "train_error", "train_auc", "train_logloss"))
 })
 
 
@@ -408,7 +394,7 @@ test_that("colsample_bytree works", {
   xgb.importance(model = bst)
   # If colsample_bytree works properly, a variety of features should be used
   # in the 100 trees
-  expect_gte(nrow(xgb.importance(model = bst)), 28)
+  expect_gte(nrow(xgb.importance(model = bst)), 30)
 })
 
 test_that("Configuration works", {
@@ -418,7 +404,7 @@ test_that("Configuration works", {
   config <- xgb.config(bst)
   xgb.config(bst) <- config
   reloaded_config <- xgb.config(bst)
-  expect_equal(config, reloaded_config)
+  expect_equal(config, reloaded_config);
 })
 
 test_that("strict_shape works", {

R-package/tests/testthat/test_callbacks.R

@@ -1,4 +1,9 @@
 # More specific testing of callbacks
+
+require(xgboost)
+require(data.table)
+require(titanic)
+
 context("callbacks")
 
 data(agaricus.train, package = 'xgboost')
@@ -79,7 +84,7 @@ test_that("cb.evaluation.log works as expected", {
                list(c(iter = 1, bst_evaluation), c(iter = 2, bst_evaluation)))
   expect_silent(f(finalize = TRUE))
   expect_equal(evaluation_log,
-               data.table::data.table(iter = 1:2, train_auc = c(0.9, 0.9), test_auc = c(0.8, 0.8)))
+               data.table(iter = 1:2, train_auc = c(0.9, 0.9), test_auc = c(0.8, 0.8)))
 
   bst_evaluation_err  <- c('train-auc' = 0.1, 'test-auc' = 0.2)
   evaluation_log <- list()
@@ -96,7 +101,7 @@ test_that("cb.evaluation.log works as expected", {
                     c(iter = 2, c(bst_evaluation, bst_evaluation_err))))
   expect_silent(f(finalize = TRUE))
   expect_equal(evaluation_log,
-               data.table::data.table(iter = 1:2,
+               data.table(iter = 1:2,
                           train_auc_mean = c(0.9, 0.9), train_auc_std = c(0.1, 0.1),
                           test_auc_mean = c(0.8, 0.8), test_auc_std = c(0.2, 0.2)))
 })
@@ -251,9 +256,6 @@ test_that("early stopping using a specific metric works", {
 })
 
 test_that("early stopping works with titanic", {
-  if (!requireNamespace("titanic")) {
-    testthat::skip("Optional testing dependency 'titanic' not found.")
-  }
   # This test was inspired by https://github.com/dmlc/xgboost/issues/5935
   # It catches possible issues on noLD R
   titanic <- titanic::titanic_train
@@ -320,7 +322,7 @@ test_that("prediction in early-stopping xgb.cv works", {
   expect_output(
     cv <- xgb.cv(param, dtrain, nfold = 5, eta = 0.1, nrounds = 20,
                  early_stopping_rounds = 5, maximize = FALSE, stratified = FALSE,
-                 prediction = TRUE, base_score = 0.5)
+                 prediction = TRUE)
   , "Stopping. Best iteration")
 
   expect_false(is.null(cv$best_iteration))

R-package/tests/testthat/test_custom_objective.R

@@ -1,5 +1,7 @@
 context('Test models with custom objective')
 
+require(xgboost)
+
 set.seed(1994)
 
 data(agaricus.train, package = 'xgboost')

R-package/tests/testthat/test_dmatrix.R

@@ -1,7 +1,9 @@
-library(Matrix)
+require(xgboost)
+require(Matrix)
+
 context("testing xgb.DMatrix functionality")
 
-data(agaricus.test, package = "xgboost")
+data(agaricus.test, package = 'xgboost')
 test_data <- agaricus.test$data[1:100, ]
 test_label <- agaricus.test$label[1:100]
 
@@ -11,85 +13,14 @@ test_that("xgb.DMatrix: basic construction", {
 
   # from dense matrix
   dtest2 <- xgb.DMatrix(as.matrix(test_data), label = test_label)
-  expect_equal(getinfo(dtest1, "label"), getinfo(dtest2, "label"))
+  expect_equal(getinfo(dtest1, 'label'), getinfo(dtest2, 'label'))
   expect_equal(dim(dtest1), dim(dtest2))
 
-  # from dense integer matrix
+  #from dense integer matrix
   int_data <- as.matrix(test_data)
   storage.mode(int_data) <- "integer"
   dtest3 <- xgb.DMatrix(int_data, label = test_label)
   expect_equal(dim(dtest1), dim(dtest3))
-
-  n_samples <- 100
-  X <- cbind(
-    x1 = sample(x = 4, size = n_samples, replace = TRUE),
-    x2 = sample(x = 4, size = n_samples, replace = TRUE),
-    x3 = sample(x = 4, size = n_samples, replace = TRUE)
-  )
-  X <- matrix(X, nrow = n_samples)
-  y <- rbinom(n = n_samples, size = 1, prob = 1 / 2)
-
-  fd <- xgb.DMatrix(X, label = y, missing = 1)
-
-  dgc <- as(X, "dgCMatrix")
-  fdgc <- xgb.DMatrix(dgc, label = y, missing = 1.0)
-
-  dgr <- as(X, "dgRMatrix")
-  fdgr <- xgb.DMatrix(dgr, label = y, missing = 1)
-
-  params <- list(tree_method = "hist")
-  bst_fd <- xgb.train(
-    params, nrounds = 8, fd, watchlist = list(train = fd)
-  )
-  bst_dgr <- xgb.train(
-    params, nrounds = 8, fdgr, watchlist = list(train = fdgr)
-  )
-  bst_dgc <- xgb.train(
-    params, nrounds = 8, fdgc, watchlist = list(train = fdgc)
-  )
-
-  raw_fd <- xgb.save.raw(bst_fd, raw_format = "ubj")
-  raw_dgr <- xgb.save.raw(bst_dgr, raw_format = "ubj")
-  raw_dgc <- xgb.save.raw(bst_dgc, raw_format = "ubj")
-
-  expect_equal(raw_fd, raw_dgr)
-  expect_equal(raw_fd, raw_dgc)
-})
-
-test_that("xgb.DMatrix: NA", {
-  n_samples <- 3
-  x <- cbind(
-    x1 = sample(x = 4, size = n_samples, replace = TRUE),
-    x2 = sample(x = 4, size = n_samples, replace = TRUE)
-  )
-  x[1, "x1"] <- NA
-
-  m <- xgb.DMatrix(x)
-  xgb.DMatrix.save(m, "int.dmatrix")
-
-  x <- matrix(as.numeric(x), nrow = n_samples, ncol = 2)
-  colnames(x) <- c("x1", "x2")
-  m <- xgb.DMatrix(x)
-
-  xgb.DMatrix.save(m, "float.dmatrix")
-
-  iconn <- file("int.dmatrix", "rb")
-  fconn <- file("float.dmatrix", "rb")
-
-  expect_equal(file.size("int.dmatrix"), file.size("float.dmatrix"))
-
-  bytes <- file.size("int.dmatrix")
-  idmatrix <- readBin(iconn, "raw", n = bytes)
-  fdmatrix <- readBin(fconn, "raw", n = bytes)
-
-  expect_equal(length(idmatrix), length(fdmatrix))
-  expect_equal(idmatrix, fdmatrix)
-
-  close(iconn)
-  close(fconn)
-
-  file.remove("int.dmatrix")
-  file.remove("float.dmatrix")
 })
 
 test_that("xgb.DMatrix: saving, loading", {
@@ -106,26 +37,11 @@ test_that("xgb.DMatrix: saving, loading", {
 
   # from a libsvm text file
   tmp <- c("0 1:1 2:1", "1 3:1", "0 1:1")
-  tmp_file <- tempfile(fileext = ".libsvm")
+  tmp_file <- 'tmp.libsvm'
   writeLines(tmp, tmp_file)
-  expect_true(file.exists(tmp_file))
-  dtest4 <- xgb.DMatrix(paste(tmp_file, "?format=libsvm", sep = ""), silent = TRUE)
+  dtest4 <- xgb.DMatrix(tmp_file, silent = TRUE)
   expect_equal(dim(dtest4), c(3, 4))
   expect_equal(getinfo(dtest4, 'label'), c(0, 1, 0))
-
-  # check that feature info is saved
-  data(agaricus.train, package = 'xgboost')
-  dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
-  cnames <- colnames(dtrain)
-  expect_equal(length(cnames), 126)
-  tmp_file <- tempfile('xgb.DMatrix_')
-  xgb.DMatrix.save(dtrain, tmp_file)
-  dtrain <- xgb.DMatrix(tmp_file)
-  expect_equal(colnames(dtrain), cnames)
-
-  ft <- rep(c("c", "q"), each = length(cnames) / 2)
-  setinfo(dtrain, "feature_type", ft)
-  expect_equal(ft, getinfo(dtrain, "feature_type"))
 })
 
 test_that("xgb.DMatrix: getinfo & setinfo", {
@@ -193,62 +109,9 @@ test_that("xgb.DMatrix: colnames", {
 test_that("xgb.DMatrix: nrow is correct for a very sparse matrix", {
   set.seed(123)
   nr <- 1000
-  x <- Matrix::rsparsematrix(nr, 100, density = 0.0005)
+  x <- rsparsematrix(nr, 100, density = 0.0005)
   # we want it very sparse, so that last rows are empty
   expect_lt(max(x@i), nr)
   dtest <- xgb.DMatrix(x)
   expect_equal(dim(dtest), dim(x))
 })
-
-test_that("xgb.DMatrix: print", {
-    data(agaricus.train, package = 'xgboost')
-
-    # core DMatrix with just data and labels
-    dtrain <- xgb.DMatrix(
-        data = agaricus.train$data
-        , label = agaricus.train$label
-    )
-    txt <- capture.output({
-        print(dtrain)
-    })
-    expect_equal(txt, "xgb.DMatrix  dim: 6513 x 126  info: label  colnames: yes")
-
-    # verbose=TRUE prints feature names
-    txt <- capture.output({
-        print(dtrain, verbose = TRUE)
-    })
-    expect_equal(txt[[1L]], "xgb.DMatrix  dim: 6513 x 126  info: label  colnames:")
-    expect_equal(txt[[2L]], sprintf("'%s'", paste(colnames(dtrain), collapse = "','")))
-
-    # DMatrix with weights and base_margin
-    dtrain <- xgb.DMatrix(
-        data = agaricus.train$data
-        , label = agaricus.train$label
-        , weight = seq_along(agaricus.train$label)
-        , base_margin = agaricus.train$label
-    )
-    txt <- capture.output({
-        print(dtrain)
-    })
-    expect_equal(txt, "xgb.DMatrix  dim: 6513 x 126  info: label weight base_margin  colnames: yes")
-
-    # DMatrix with just features
-    dtrain <- xgb.DMatrix(
-        data = agaricus.train$data
-    )
-    txt <- capture.output({
-        print(dtrain)
-    })
-    expect_equal(txt, "xgb.DMatrix  dim: 6513 x 126  info: NA  colnames: yes")
-
-    # DMatrix with no column names
-    data_no_colnames <- agaricus.train$data
-    colnames(data_no_colnames) <- NULL
-    dtrain <- xgb.DMatrix(
-        data = data_no_colnames
-    )
-    txt <- capture.output({
-        print(dtrain)
-    })
-    expect_equal(txt, "xgb.DMatrix  dim: 6513 x 126  info: NA  colnames: no")
-})

R-package/tests/testthat/test_feature_weights.R

@@ -1,3 +1,5 @@
+library(xgboost)
+
 context("feature weights")
 
 test_that("training with feature weights works", {

R-package/tests/testthat/test_gc_safety.R

@@ -1,3 +1,5 @@
+require(xgboost)
+
 context("Garbage Collection Safety Check")
 
 test_that("train and prediction when gctorture is on", {

R-package/tests/testthat/test_glm.R

@@ -1,5 +1,7 @@
 context('Test generalized linear models')
 
+require(xgboost)
+
 test_that("gblinear works", {
   data(agaricus.train, package = 'xgboost')
   data(agaricus.test, package = 'xgboost')

R-package/tests/testthat/test_helpers.R

@@ -1,11 +1,10 @@
+library(testthat)
 context('Test helper functions')
 
-VCD_AVAILABLE <- requireNamespace("vcd", quietly = TRUE)
-.skip_if_vcd_not_available <- function() {
-    if (!VCD_AVAILABLE) {
-        testthat::skip("Optional testing dependency 'vcd' not found.")
-    }
-}
+require(xgboost)
+require(data.table)
+require(Matrix)
+require(vcd, quietly = TRUE)
 
 float_tolerance <- 5e-6
 
@@ -13,30 +12,25 @@ float_tolerance <- 5e-6
 flag_32bit <- .Machine$sizeof.pointer != 8
 
 set.seed(1982)
+data(Arthritis)
+df <- data.table(Arthritis, keep.rownames = FALSE)
+df[, AgeDiscret := as.factor(round(Age / 10, 0))]
+df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[, ID := NULL]
+sparse_matrix <- sparse.model.matrix(Improved~.-1, data = df) # nolint
+label <- df[, ifelse(Improved == "Marked", 1, 0)]
 
+# binary
 nrounds <- 12
-if (isTRUE(VCD_AVAILABLE)) {
-    data(Arthritis, package = "vcd")
-    df <- data.table::data.table(Arthritis, keep.rownames = FALSE)
-    df[, AgeDiscret := as.factor(round(Age / 10, 0))]
-    df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
-    df[, ID := NULL]
-    sparse_matrix <- Matrix::sparse.model.matrix(Improved~.-1, data = df) # nolint
-    label <- df[, ifelse(Improved == "Marked", 1, 0)]
+bst.Tree <- xgboost(data = sparse_matrix, label = label, max_depth = 9,
+                    eta = 1, nthread = 2, nrounds = nrounds, verbose = 0,
+                    objective = "binary:logistic", booster = "gbtree")
 
-    # binary
-    bst.Tree <- xgboost(data = sparse_matrix, label = label, max_depth = 9,
-                        eta = 1, nthread = 2, nrounds = nrounds, verbose = 0,
-                        objective = "binary:logistic", booster = "gbtree",
-                        base_score = 0.5)
+bst.GLM <- xgboost(data = sparse_matrix, label = label,
+                   eta = 1, nthread = 1, nrounds = nrounds, verbose = 0,
+                   objective = "binary:logistic", booster = "gblinear")
 
-    bst.GLM <- xgboost(data = sparse_matrix, label = label,
-                       eta = 1, nthread = 1, nrounds = nrounds, verbose = 0,
-                       objective = "binary:logistic", booster = "gblinear",
-                       base_score = 0.5)
-
-    feature.names <- colnames(sparse_matrix)
-}
+feature.names <- colnames(sparse_matrix)
 
 # multiclass
 mlabel <- as.numeric(iris$Species) - 1
@@ -51,7 +45,6 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 
 
 test_that("xgb.dump works", {
-  .skip_if_vcd_not_available()
   if (!flag_32bit)
     expect_length(xgb.dump(bst.Tree), 200)
   dump_file <- file.path(tempdir(), 'xgb.model.dump')
@@ -63,11 +56,10 @@ test_that("xgb.dump works", {
   dmp <- xgb.dump(bst.Tree, dump_format = "json")
   expect_length(dmp, 1)
   if (!flag_32bit)
-    expect_length(grep('nodeid', strsplit(dmp, '\n', fixed = TRUE)[[1]], fixed = TRUE), 188)
+    expect_length(grep('nodeid', strsplit(dmp, '\n')[[1]]), 188)
 })
 
 test_that("xgb.dump works for gblinear", {
-  .skip_if_vcd_not_available()
   expect_length(xgb.dump(bst.GLM), 14)
   # also make sure that it works properly for a sparse model where some coefficients
   # are 0 from setting large L1 regularization:
@@ -80,11 +72,10 @@ test_that("xgb.dump works for gblinear", {
   # JSON format
   dmp <- xgb.dump(bst.GLM.sp, dump_format = "json")
   expect_length(dmp, 1)
-  expect_length(grep('\\d', strsplit(dmp, '\n', fixed = TRUE)[[1]]), 11)
+  expect_length(grep('\\d', strsplit(dmp, '\n')[[1]]), 11)
 })
 
 test_that("predict leafs works", {
-  .skip_if_vcd_not_available()
   # no error for gbtree
   expect_error(pred_leaf <- predict(bst.Tree, sparse_matrix, predleaf = TRUE), regexp = NA)
   expect_equal(dim(pred_leaf), c(nrow(sparse_matrix), nrounds))
@@ -93,7 +84,6 @@ test_that("predict leafs works", {
 })
 
 test_that("predict feature contributions works", {
-  .skip_if_vcd_not_available()
   # gbtree binary classifier
   expect_error(pred_contr <- predict(bst.Tree, sparse_matrix, predcontrib = TRUE), regexp = NA)
   expect_equal(dim(pred_contr), c(nrow(sparse_matrix), ncol(sparse_matrix) + 1))
@@ -180,16 +170,15 @@ test_that("SHAPs sum to predictions, with or without DART", {
       label = y,
       nrounds = nrounds)
 
-    pr <- function(...) {
+    pr <- function(...)
       predict(fit, newdata = d, ...)
-    }
     pred <- pr()
     shap <- pr(predcontrib = TRUE)
     shapi <- pr(predinteraction = TRUE)
     tol <- 1e-5
 
     expect_equal(rowSums(shap), pred, tol = tol)
-    expect_equal(rowSums(shapi), pred, tol = tol)
+    expect_equal(apply(shapi, 1, sum), pred, tol = tol)
     for (i in seq_len(nrow(d)))
       for (f in list(rowSums, colSums))
         expect_equal(f(shapi[i, , ]), shap[i, ], tol = tol)
@@ -197,7 +186,6 @@ test_that("SHAPs sum to predictions, with or without DART", {
 })
 
 test_that("xgb-attribute functionality", {
-  .skip_if_vcd_not_available()
   val <- "my attribute value"
   list.val <- list(my_attr = val, a = 123, b = 'ok')
   list.ch <- list.val[order(names(list.val))]
@@ -231,11 +219,10 @@ test_that("xgb-attribute functionality", {
   expect_null(xgb.attributes(bst))
 })
 
-if (grepl('Windows', Sys.info()[['sysname']], fixed = TRUE) ||
-    grepl('Linux', Sys.info()[['sysname']], fixed = TRUE) ||
-    grepl('Darwin', Sys.info()[['sysname']], fixed = TRUE)) {
+if (grepl('Windows', Sys.info()[['sysname']]) ||
+    grepl('Linux', Sys.info()[['sysname']]) ||
+    grepl('Darwin', Sys.info()[['sysname']])) {
     test_that("xgb-attribute numeric precision", {
-      .skip_if_vcd_not_available()
       # check that lossless conversion works with 17 digits
       # numeric -> character -> numeric
       X <- 10^runif(100, -20, 20)
@@ -254,7 +241,6 @@ if (grepl('Windows', Sys.info()[['sysname']], fixed = TRUE) ||
 }
 
 test_that("xgb.Booster serializing as R object works", {
-  .skip_if_vcd_not_available()
   saveRDS(bst.Tree, 'xgb.model.rds')
   bst <- readRDS('xgb.model.rds')
   dtrain <- xgb.DMatrix(sparse_matrix, label = label)
@@ -273,7 +259,6 @@ test_that("xgb.Booster serializing as R object works", {
 })
 
 test_that("xgb.model.dt.tree works with and without feature names", {
-  .skip_if_vcd_not_available()
   names.dt.trees <- c("Tree", "Node", "ID", "Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
   dt.tree <- xgb.model.dt.tree(feature_names = feature.names, model = bst.Tree)
   expect_equal(names.dt.trees, names(dt.tree))
@@ -293,18 +278,16 @@ test_that("xgb.model.dt.tree works with and without feature names", {
 
   # using integer node ID instead of character
   dt.tree.int <- xgb.model.dt.tree(model = bst.Tree, use_int_id = TRUE)
-  expect_equal(as.integer(data.table::tstrsplit(dt.tree$Yes, '-', fixed = TRUE)[[2]]), dt.tree.int$Yes)
-  expect_equal(as.integer(data.table::tstrsplit(dt.tree$No, '-', fixed = TRUE)[[2]]), dt.tree.int$No)
-  expect_equal(as.integer(data.table::tstrsplit(dt.tree$Missing, '-', fixed = TRUE)[[2]]), dt.tree.int$Missing)
+  expect_equal(as.integer(tstrsplit(dt.tree$Yes, '-')[[2]]), dt.tree.int$Yes)
+  expect_equal(as.integer(tstrsplit(dt.tree$No, '-')[[2]]), dt.tree.int$No)
+  expect_equal(as.integer(tstrsplit(dt.tree$Missing, '-')[[2]]), dt.tree.int$Missing)
 })
 
 test_that("xgb.model.dt.tree throws error for gblinear", {
-  .skip_if_vcd_not_available()
   expect_error(xgb.model.dt.tree(model = bst.GLM))
 })
 
 test_that("xgb.importance works with and without feature names", {
-  .skip_if_vcd_not_available()
   importance.Tree <- xgb.importance(feature_names = feature.names, model = bst.Tree)
   if (!flag_32bit)
     expect_equal(dim(importance.Tree), c(7, 4))
@@ -362,8 +345,7 @@ test_that("xgb.importance works with and without feature names", {
   m <- xgboost::xgboost(
     data = as.matrix(data.frame(x = c(0, 1))),
     label = c(1, 2),
-    nrounds = 1,
-    base_score = 0.5
+    nrounds = 1
   )
   df <- xgb.model.dt.tree(model = m)
   expect_equal(df$Feature, "Leaf")
@@ -371,7 +353,6 @@ test_that("xgb.importance works with and without feature names", {
 })
 
 test_that("xgb.importance works with GLM model", {
-  .skip_if_vcd_not_available()
   importance.GLM <- xgb.importance(feature_names = feature.names, model = bst.GLM)
   expect_equal(dim(importance.GLM), c(10, 2))
   expect_equal(colnames(importance.GLM), c("Feature", "Weight"))
@@ -387,7 +368,6 @@ test_that("xgb.importance works with GLM model", {
 })
 
 test_that("xgb.model.dt.tree and xgb.importance work with a single split model", {
-  .skip_if_vcd_not_available()
   bst1 <- xgboost(data = sparse_matrix, label = label, max_depth = 1,
                   eta = 1, nthread = 2, nrounds = 1, verbose = 0,
                   objective = "binary:logistic")
@@ -399,19 +379,16 @@ test_that("xgb.model.dt.tree and xgb.importance work with a single split model",
 })
 
 test_that("xgb.plot.tree works with and without feature names", {
-  .skip_if_vcd_not_available()
   expect_silent(xgb.plot.tree(feature_names = feature.names, model = bst.Tree))
   expect_silent(xgb.plot.tree(model = bst.Tree))
 })
 
 test_that("xgb.plot.multi.trees works with and without feature names", {
-  .skip_if_vcd_not_available()
   xgb.plot.multi.trees(model = bst.Tree, feature_names = feature.names, features_keep = 3)
   xgb.plot.multi.trees(model = bst.Tree, features_keep = 3)
 })
 
 test_that("xgb.plot.deepness works", {
-  .skip_if_vcd_not_available()
   d2p <- xgb.plot.deepness(model = bst.Tree)
   expect_equal(colnames(d2p), c("ID", "Tree", "Depth", "Cover", "Weight"))
   xgb.plot.deepness(model = bst.Tree, which = "med.depth")
@@ -419,7 +396,6 @@ test_that("xgb.plot.deepness works", {
 })
 
 test_that("xgb.shap.data works when top_n is provided", {
-  .skip_if_vcd_not_available()
   data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2)
   expect_equal(names(data_list), c("data", "shap_contrib"))
   expect_equal(NCOL(data_list$data), 2)
@@ -437,14 +413,12 @@ test_that("xgb.shap.data works when top_n is provided", {
 })
 
 test_that("xgb.shap.data works with subsampling", {
-  .skip_if_vcd_not_available()
   data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2, subsample = 0.8)
   expect_equal(NROW(data_list$data), as.integer(0.8 * nrow(sparse_matrix)))
   expect_equal(NROW(data_list$data), NROW(data_list$shap_contrib))
 })
 
 test_that("prepare.ggplot.shap.data works", {
-  .skip_if_vcd_not_available()
   data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2)
   plot_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
   expect_s3_class(plot_data, "data.frame")
@@ -455,19 +429,17 @@ test_that("prepare.ggplot.shap.data works", {
 })
 
 test_that("xgb.plot.shap works", {
-  .skip_if_vcd_not_available()
   sh <- xgb.plot.shap(data = sparse_matrix, model = bst.Tree, top_n = 2, col = 4)
   expect_equal(names(sh), c("data", "shap_contrib"))
 })
 
 test_that("xgb.plot.shap.summary works", {
-  .skip_if_vcd_not_available()
   expect_silent(xgb.plot.shap.summary(data = sparse_matrix, model = bst.Tree, top_n = 2))
   expect_silent(xgb.ggplot.shap.summary(data = sparse_matrix, model = bst.Tree, top_n = 2))
 })
 
 test_that("check.deprecation works", {
-  ttt <- function(a = NNULL, DUMMY = NULL, ...) {
+  ttt <- function(a = NNULL, DUMMY=NULL, ...) {
     check.deprecation(...)
     as.list((environment()))
   }

R-package/tests/testthat/test_interaction_constraints.R

@@ -17,7 +17,7 @@ test_that("interaction constraints for regression", {
 
   # Set all observations to have the same x3 values then increment
   #  by the same amount
-  preds <- lapply(c(1, 2, 3), function(x) {
+  preds <- lapply(c(1, 2, 3), function(x){
     tmat <- matrix(c(x1, x2, rep(x, 1000)), ncol = 3)
     return(predict(bst, tmat))
   })

R-package/tests/testthat/test_interactions.R

@@ -1,5 +1,7 @@
 context('Test prediction of feature interactions')
 
+require(xgboost)
+
 set.seed(123)
 
 test_that("predict feature interactions works", {

R-package/tests/testthat/test_io.R

@@ -1,4 +1,7 @@
 context("Test model IO.")
+## some other tests are in test_basic.R
+require(xgboost)
+require(testthat)
 
 data(agaricus.train, package = "xgboost")
 data(agaricus.test, package = "xgboost")

R-package/tests/testthat/test_model_compatibility.R

@@ -1,3 +1,6 @@
+require(xgboost)
+require(jsonlite)
+
 context("Models from previous versions of XGBoost can be loaded")
 
 metadata <- list(
@@ -59,12 +62,11 @@ test_that("Models from previous versions of XGBoost can be loaded", {
   bucket <- 'xgboost-ci-jenkins-artifacts'
   region <- 'us-west-2'
   file_name <- 'xgboost_r_model_compatibility_test.zip'
-  zipfile <- tempfile(fileext = ".zip")
-  extract_dir <- tempdir()
+  zipfile <- file.path(getwd(), file_name)
+  model_dir <- file.path(getwd(), 'models')
   download.file(paste('https://', bucket, '.s3-', region, '.amazonaws.com/', file_name, sep = ''),
                 destfile = zipfile, mode = 'wb', quiet = TRUE)
-  unzip(zipfile, exdir = extract_dir, overwrite = TRUE)
-  model_dir <- file.path(extract_dir, 'models')
+  unzip(zipfile, overwrite = TRUE)
 
   pred_data <- xgb.DMatrix(matrix(c(0, 0, 0, 0), nrow = 1, ncol = 4))
 
@@ -75,21 +77,34 @@ test_that("Models from previous versions of XGBoost can be loaded", {
     model_xgb_ver <- m[2]
     name <- m[3]
     is_rds <- endsWith(model_file, '.rds')
-    is_json <- endsWith(model_file, '.json')
-    # Expect an R warning when a model is loaded from RDS and it was generated by version < 1.1.x
-    if (is_rds && compareVersion(model_xgb_ver, '1.1.1.1') < 0) {
-      booster <- readRDS(model_file)
-      expect_warning(predict(booster, newdata = pred_data))
-      booster <- readRDS(model_file)
-      expect_warning(run_booster_check(booster, name))
-    } else {
-      if (is_rds) {
+
+    cpp_warning <- capture.output({
+      # Expect an R warning when a model is loaded from RDS and it was generated by version < 1.1.x
+      if (is_rds && compareVersion(model_xgb_ver, '1.1.1.1') < 0) {
         booster <- readRDS(model_file)
+        expect_warning(predict(booster, newdata = pred_data))
+        booster <- readRDS(model_file)
+        expect_warning(run_booster_check(booster, name))
       } else {
-        booster <- xgb.load(model_file)
+        if (is_rds) {
+          booster <- readRDS(model_file)
+        } else {
+          booster <- xgb.load(model_file)
+        }
+        predict(booster, newdata = pred_data)
+        run_booster_check(booster, name)
       }
-      predict(booster, newdata = pred_data)
-      run_booster_check(booster, name)
+    })
+    if (compareVersion(model_xgb_ver, '1.0.0.0') < 0) {
+      # Expect a C++ warning when a model was generated in version < 1.0.x
+      m <- grepl(paste0('.*Loading model from XGBoost < 1\\.0\\.0, consider saving it again for ',
+                        'improved compatibility.*'), cpp_warning, perl = TRUE)
+      expect_true(length(m) > 0 && all(m))
+    } else if (is_rds && model_xgb_ver == '1.1.1.1') {
+      # Expect a C++ warning when a model is loaded from RDS and it was generated by version 1.1.x
+      m <- grepl(paste0('.*Attempted to load internal configuration for a model file that was ',
+                        'generated by a previous version of XGBoost.*'), cpp_warning, perl = TRUE)
+      expect_true(length(m) > 0 && all(m))
     }
   })
 })

R-package/tests/testthat/test_monotone.R

@@ -1,3 +1,5 @@
+require(xgboost)
+
 context("monotone constraints")
 
 set.seed(1024)

R-package/tests/testthat/test_parameter_exposure.R

@@ -1,5 +1,7 @@
 context('Test model params and call are exposed to R')
 
+require(xgboost)
+
 data(agaricus.train, package = 'xgboost')
 data(agaricus.test, package = 'xgboost')
 

R-package/tests/testthat/test_poisson_regression.R

@@ -1,5 +1,6 @@
 context('Test Poisson regression model')
 
+require(xgboost)
 set.seed(1994)
 
 test_that("Poisson regression works", {

R-package/tests/testthat/test_ranking.R

@@ -1,12 +1,12 @@
+require(xgboost)
+require(Matrix)
+
 context('Learning to rank')
 
 test_that('Test ranking with unweighted data', {
-  X <- Matrix::sparseMatrix(
-    i = c(2, 3, 7, 9, 12, 15, 17, 18)
-    , j = c(1, 1, 2, 2,  3,  3,  4,  4)
-    , x = rep(1.0, 8)
-    , dims = c(20, 4)
-  )
+  X <- sparseMatrix(i = c(2, 3, 7, 9, 12, 15, 17, 18),
+                    j = c(1, 1, 2, 2,  3,  3,  4,  4),
+                    x = rep(1.0, 8), dims = c(20, 4))
   y <- c(0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0)
   group <- c(5, 5, 5, 5)
   dtrain <- xgb.DMatrix(X, label = y, group = group)
@@ -20,12 +20,9 @@ test_that('Test ranking with unweighted data', {
 })
 
 test_that('Test ranking with weighted data', {
-  X <- Matrix::sparseMatrix(
-    i = c(2, 3, 7, 9, 12, 15, 17, 18)
-    , j = c(1, 1, 2, 2,  3,  3,  4,  4)
-    , x = rep(1.0, 8)
-    , dims = c(20, 4)
-  )
+  X <- sparseMatrix(i = c(2, 3, 7, 9, 12, 15, 17, 18),
+                    j = c(1, 1, 2, 2,  3,  3,  4,  4),
+                    x = rep(1.0, 8), dims = c(20, 4))
   y <- c(0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0)
   group <- c(5, 5, 5, 5)
   weight <- c(1.0, 2.0, 3.0, 4.0)

R-package/tests/testthat/test_unicode.R

@@ -1,21 +0,0 @@
-context("Test Unicode handling")
-
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
-train <- agaricus.train
-test <- agaricus.test
-set.seed(1994)
-
-test_that("Can save and load models with Unicode paths", {
-  nrounds <- 2
-  bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-                 eta = 1, nthread = 2, nrounds = nrounds, objective = "binary:logistic",
-                 eval_metric = "error")
-  tmpdir <- tempdir()
-  lapply(c("모델.json", "がうる・ぐら.json", "类继承.ubj"), function(x) {
-    path <- file.path(tmpdir, x)
-    xgb.save(bst, path)
-    bst2 <- xgb.load(path)
-    expect_equal(predict(bst, test$data), predict(bst2, test$data))
-  })
-})

R-package/tests/testthat/test_update.R

@@ -1,3 +1,5 @@
+require(xgboost)
+
 context("update trees in an existing model")
 
 data(agaricus.train, package = 'xgboost')
@@ -13,10 +15,7 @@ test_that("updating the model works", {
   watchlist <- list(train = dtrain, test = dtest)
 
   # no-subsampling
-  p1 <- list(
-    objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2,
-    updater = "grow_colmaker,prune"
-  )
+  p1 <- list(objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2)
   set.seed(11)
   bst1 <- xgb.train(p1, dtrain, nrounds = 10, watchlist, verbose = 0)
   tr1 <- xgb.model.dt.tree(model = bst1)

R-package/vignettes/discoverYourData.Rmd

@@ -28,9 +28,7 @@ Package loading:
 require(xgboost)
 require(Matrix)
 require(data.table)
-if (!require('vcd')) {
-  install.packages('vcd')
-}
+if (!require('vcd')) install.packages('vcd')
 ```
 
 > **VCD** package is used for one of its embedded dataset only.
@@ -51,24 +49,24 @@ A *categorical* variable has a fixed number of different values. For instance, i
 >
 > Type `?factor` in the console for more information.
 
-To answer the question above we will convert *categorical* variables to `numeric` ones.
+To answer the question above we will convert *categorical* variables to `numeric` one.
 
 ### Conversion from categorical to numeric variables
 
 #### Looking at the raw data
 
-+In this Vignette we will see how to transform a *dense* `data.frame` (*dense* = the majority of the matrix is non-zero) with *categorical* variables to a very *sparse* matrix (*sparse* = lots of zero entries in the matrix) of `numeric` features.
+In this Vignette we will see how to transform a *dense* `data.frame` (*dense* = few zeroes in the matrix) with *categorical* variables to a very *sparse* matrix (*sparse* = lots of zero in the matrix) of `numeric` features.
 
 The method we are going to see is usually called [one-hot encoding](https://en.wikipedia.org/wiki/One-hot).
 
-The first step is to load the `Arthritis` dataset in memory and wrap it with the `data.table` package.
+The first step is to load `Arthritis` dataset in memory and wrap it with `data.table` package.
 
 ```{r, results='hide'}
 data(Arthritis)
 df <- data.table(Arthritis, keep.rownames = FALSE)
 ```
 
-> `data.table` is 100% compliant with **R** `data.frame` but its syntax is more consistent and its performance for large dataset is [best in class](https://stackoverflow.com/questions/21435339/data-table-vs-dplyr-can-one-do-something-well-the-other-cant-or-does-poorly) (`dplyr` from **R** and `Pandas` from **Python** [included](https://github.com/Rdatatable/data.table/wiki/Benchmarks-%3A-Grouping)). Some parts of **XGBoost's** **R** package use `data.table`.
+> `data.table` is 100% compliant with **R** `data.frame` but its syntax is more consistent and its performance for large dataset is [best in class](https://stackoverflow.com/questions/21435339/data-table-vs-dplyr-can-one-do-something-well-the-other-cant-or-does-poorly) (`dplyr` from **R** and `Pandas` from **Python** [included](https://github.com/Rdatatable/data.table/wiki/Benchmarks-%3A-Grouping)). Some parts of **XGBoost** **R** package use `data.table`.
 
 The first thing we want to do is to have a look to the first few lines of the `data.table`:
 
@@ -95,22 +93,22 @@ We will add some new *categorical* features to see if it helps.
 
 ##### Grouping per 10 years
 
-For the first features we create groups of age by rounding the real age.
+For the first feature we create groups of age by rounding the real age.
 
-Note that we transform it to `factor` so the algorithm treats these age groups as independent values.
+Note that we transform it to `factor` so the algorithm treat these age groups as independent values.
 
-Therefore, 20 is not closer to 30 than 60. In other words, the distance between ages is lost in this transformation.
+Therefore, 20 is not closer to 30 than 60. To make it short, the distance between ages is lost in this transformation.
 
 ```{r}
-head(df[, AgeDiscret := as.factor(round(Age / 10, 0))])
+head(df[,AgeDiscret := as.factor(round(Age/10,0))])
 ```
 
-##### Randomly split into two groups
+##### Random split into two groups
 
-The following 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 (you may already have an idea of how well it will work...).
+Following is an even stronger simplification of the real age with an arbitrary split at 30 years old. We choose this value **based on nothing**. We will see later if simplifying the information based on arbitrary values is a good strategy (you may already have an idea of how well it will work...).
 
 ```{r}
-head(df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))])
+head(df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))])
 ```
 
 ##### Risks in adding correlated features
@@ -119,20 +117,20 @@ These new features are highly correlated to the `Age` feature because they are s
 
 For many machine learning algorithms, using correlated features is not a good idea. It may sometimes make prediction less accurate, and most of the time make interpretation of the model almost impossible. GLM, for instance, assumes that the features are uncorrelated.
 
-Fortunately, decision tree algorithms (including boosted trees) are very robust to these features. Therefore we don't have to do anything to manage this situation.
+Fortunately, decision tree algorithms (including boosted trees) are very robust to these features. Therefore we have nothing to do to manage this situation.
 
 ##### Cleaning data
 
 We remove ID as there is nothing to learn from this feature (it would just add some noise).
 
 ```{r, results='hide'}
-df[, ID := NULL]
+df[,ID:=NULL]
 ```
 
 We will list the different values for the column `Treatment`:
 
 ```{r}
-levels(df[, Treatment])
+levels(df[,Treatment])
 ```
 
 
@@ -144,12 +142,12 @@ We will use the [dummy contrast coding](https://stats.oarc.ucla.edu/r/library/r-
 
 The purpose is to transform each value of each *categorical* feature into a *binary* feature `{0, 1}`.
 
-For example, the column `Treatment` will be replaced by two columns, `TreatmentPlacebo`, and `TreatmentTreated`. Each of them will be *binary*. Therefore, an observation which has the value `Placebo` in column `Treatment` before the transformation will have the value `1` in the new column `TreatmentPlacebo` and the value `0` in the new column `TreatmentTreated` after the transformation. The column `TreatmentPlacebo` will disappear during the contrast encoding, as it would be absorbed into a common constant intercept column.
+For example, the column `Treatment` will be replaced by two columns, `TreatmentPlacebo`, and `TreatmentTreated`. Each of them will be *binary*. Therefore, an observation which has the value `Placebo` in column `Treatment` before the transformation will have after the transformation the value `1` in the new column `TreatmentPlacebo` and the value `0` in the new column `TreatmentTreated`. The column `TreatmentPlacebo` will disappear during the contrast encoding, as it would be absorbed into a common constant intercept column.
 
 Column `Improved` is excluded because it will be our `label` column, the one we want to predict.
 
 ```{r, warning=FALSE,message=FALSE}
-sparse_matrix <- sparse.model.matrix(Improved ~ ., data = df)[, -1]
+sparse_matrix <- sparse.model.matrix(Improved ~ ., data = df)[,-1]
 head(sparse_matrix)
 ```
 
@@ -158,7 +156,7 @@ head(sparse_matrix)
 Create the output `numeric` vector (not as a sparse `Matrix`):
 
 ```{r}
-output_vector <- df[, Improved] == "Marked"
+output_vector = df[,Improved] == "Marked"
 ```
 
 1. set `Y` vector to `0`;
@@ -172,13 +170,17 @@ The code below is very usual. For more information, you can look at the document
 
 ```{r}
 bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 4,
-               eta = 1, nthread = 2, nrounds = 10, objective = "binary:logistic")
+               eta = 1, nthread = 2, nrounds = 10,objective = "binary:logistic")
 
 ```
 
-You can see some `train-logloss: 0.XXXXX` lines followed by a number. It decreases. Each line shows how well the model explains the data. Lower is better.
+You can see some `train-error: 0.XXXXX` lines followed by a number. It decreases. Each line shows how well the model explains your data. Lower is better.
 
-A small value for training error may be a symptom of [overfitting](https://en.wikipedia.org/wiki/Overfitting), meaning the model will not accurately predict unseen values.
+A small value for training error may be a symptom of [overfitting](https://en.wikipedia.org/wiki/Overfitting), meaning the model will not accurately predict the future values.
+
+> Here you can see the numbers decrease until line 7 and then increase.
+>
+> It probably means we are overfitting. To fix that I should reduce the number of rounds to `nrounds = 4`. I will let things like that because I don't really care for the purpose of this example :-)
 
 Feature importance
 ------------------
@@ -195,35 +197,64 @@ importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bs
 head(importance)
 ```
 
-> The column `Gain` provides the information we are looking for.
+> The column `Gain` provide the information we are looking for.
 >
 > As you can see, features are classified by `Gain`.
 
-`Gain` is the improvement in accuracy brought by a feature to the branches it is on. The idea is that before adding a new split on a feature X to the branch there were some wrongly classified elements; after adding the split on this feature, there are two new branches, and each of these branches is more accurate (one branch saying if your observation is on this branch then it should be classified as `1`, and the other branch saying the exact opposite).
+`Gain` is the improvement in accuracy brought by a feature to the branches it is on. The idea is that before adding a new split on a feature X to the branch there was some wrongly classified elements, after adding the split on this feature, there are two new branches, and each of these branch is more accurate (one branch saying if your observation is on this branch then it should be classified as `1`, and the other branch saying the exact opposite).
 
-`Cover` is related to the second order derivative (or Hessian) of the loss function with respect to a particular variable; thus, a large value indicates a variable has a large potential impact on the loss function and so is important.
+`Cover` measures the relative quantity of observations concerned by a feature.
 
 `Frequency` is a simpler way to measure the `Gain`. It just counts the number of times a feature is used in all generated trees. You should not use it (unless you know why you want to use it).
 
+#### Improvement in the interpretability of feature importance data.table
+
+We can go deeper in the analysis of the model. In the `data.table` above, we have discovered which features counts to predict if the illness will go or not. But we don't yet know the role of these features. For instance, one of the question we may want to answer would be: does receiving a placebo treatment helps to recover from the illness?
+
+One simple solution is to count the co-occurrences of a feature and a class of the classification.
+
+For that purpose we will execute the same function as above but using two more parameters, `data` and `label`.
+
+```{r}
+importanceRaw <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst, data = sparse_matrix, label = output_vector)
+
+# Cleaning for better display
+importanceClean <- importanceRaw[,`:=`(Cover=NULL, Frequency=NULL)]
+
+head(importanceClean)
+```
+
+> In the table above we have removed two not needed columns and select only the first lines.
+
+First thing you notice is the new column `Split`. It is the split applied to the feature on a branch of one of the tree. Each split is present, therefore a feature can appear several times in this table. Here we can see the feature `Age` is used several times with different splits.
+
+How the split is applied to count the co-occurrences? It is always `<`. For instance, in the second line, we measure the number of persons under 61.5 years with the illness gone after the treatment.
+
+The two other new columns are `RealCover` and `RealCover %`. In the first column it measures the number of observations in the dataset where the split is respected and the label marked as `1`. The second column is the percentage of the whole population that `RealCover` represents.
+
+Therefore, according to our findings, getting a placebo doesn't seem to help but being younger than 61 years may help (seems logic).
+
+> You may wonder how to interpret the `< 1.00001` on the first line. Basically, in a sparse `Matrix`, there is no `0`, therefore, looking for one hot-encoded categorical observations validating the rule `< 1.00001` is like just looking for `1` for this feature.
+
 ### Plotting the feature importance
 
+
 All these things are nice, but it would be even better to plot the results.
 
 ```{r, fig.width=8, fig.height=5, fig.align='center'}
 xgb.plot.importance(importance_matrix = importance)
 ```
 
-Running this line of code, you should get a bar chart showing the importance of the 6 features (containing the same data as the output we saw earlier, but displaying it visually for easier consumption).  Note that `xgb.ggplot.importance` is also available for all the ggplot2 fans!
+Feature have automatically been divided in 2 clusters: the interesting features... and the others.
 
 > Depending of the dataset and the learning parameters you may have more than two clusters. Default value is to limit them to `10`, but you can increase this limit. Look at the function documentation for more information.
 
 According to the plot above, the most important features in this dataset to predict if the treatment will work are :
 
-* An individual's age;
-* Having received a placebo or not;
-* Gender;
-* Our generated feature AgeDiscret. We can see that its contribution is very low.
-
+* the Age ;
+* having received a placebo or not ;
+* the sex is third but already included in the not interesting features group ;
+* then we see our generated features (AgeDiscret). We can see that their contribution is very low.
 
 ### Do these results make sense?
 
@@ -237,84 +268,69 @@ c2 <- chisq.test(df$Age, output_vector)
 print(c2)
 ```
 
-The Pearson correlation between Age and illness disappearing is **`r round(c2$statistic, 2 )`**.
+Pearson correlation between Age and illness disappearing is **`r round(c2$statistic, 2 )`**.
 
 ```{r, warning=FALSE, message=FALSE}
 c2 <- chisq.test(df$AgeDiscret, output_vector)
 print(c2)
 ```
 
-Our first simplification of Age gives a Pearson correlation of **`r round(c2$statistic, 2)`**.
+Our first simplification of Age gives a Pearson correlation is **`r round(c2$statistic, 2)`**.
 
 ```{r, warning=FALSE, message=FALSE}
 c2 <- chisq.test(df$AgeCat, output_vector)
 print(c2)
 ```
 
-The perfectly random split we did between young and old at 30 years old has a low correlation of **2.36**. This suggests that, for the particular illness we are studying, the age at which someone is vulnerable to this disease is likely very different from 30.
+The perfectly random split I did between young and old at 30 years old have a low correlation of **`r round(c2$statistic, 2)`**. It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that), but for the illness we are studying, the age to be vulnerable is not the same.
 
-Moral of the story: don't let your *gut* lower the quality of your model.
+Morality: don't let your *gut* lower the quality of your model.
 
-In *data science*, there is the word *science* :-)
+In *data science* expression, there is the word *science* :-)
 
 Conclusion
 ----------
 
 As you can see, in general *destroying information by simplifying it won't improve your model*. **Chi2** just demonstrates that.
 
-But in more complex cases, creating a new feature from an existing one may help the algorithm and improve the model.
+But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model.
 
-+The case studied here is not complex enough to show that. Check [Kaggle website](https://www.kaggle.com/) for some challenging datasets.
+The case studied here is not enough complex to show that. Check [Kaggle website](http://www.kaggle.com/) for some challenging datasets. However it's almost always worse when you add some arbitrary rules.
 
-Moreover, you can see that even if we have added some new features which are not very useful/highly correlated with other features, the boosting tree algorithm was still able to choose the best one (which in this case is the Age).
+Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age.
 
-Linear models may not perform as well.
+Linear model may not be that smart in this scenario.
 
 Special Note: What about Random Forests™?
 -----------------------------------------
 
-As you may know, the [Random Forests](https://en.wikipedia.org/wiki/Random_forest) algorithm is cousin with boosting and both are part of the [ensemble learning](https://en.wikipedia.org/wiki/Ensemble_learning) family.
+As you may know, [Random Forests](https://en.wikipedia.org/wiki/Random_forest) algorithm is cousin with boosting and both are part of the [ensemble learning](https://en.wikipedia.org/wiki/Ensemble_learning) family.
 
-Both train several decision trees for one dataset. The *main* difference is that in Random Forests, trees are independent and in boosting, the `N+1`-st tree focuses its learning on the loss (<=> what has not been well modeled by the tree `N`).
+Both trains several decision trees for one dataset. The *main* difference is that in Random Forests, trees are independent and in boosting, the tree `N+1` focus its learning on the loss (<=> what has not been well modeled by the tree `N`).
 
-This difference can have an impact on a edge case in feature importance analysis: *correlated features*.
+This difference have an impact on a corner case in feature importance analysis: the *correlated features*.
 
 Imagine two features perfectly correlated, feature `A` and feature `B`. For one specific tree, if the algorithm needs one of them, it will choose randomly (true in both boosting and Random Forests).
 
-However, in Random Forests this random choice will be done for each tree, because each tree is independent from the others. Therefore, approximately (and depending on your parameters) 50% of the trees will choose feature `A` and the other 50% will choose feature `B`. So the *importance* of the information contained in `A` and `B` (which is the same, because they are perfectly correlated) is diluted in `A` and `B`. So you won't easily know this information is important to predict what you want to predict! It is even worse when you have 10 correlated features...
+However, in Random Forests this random choice will be done for each tree, because each tree is independent from the others. Therefore, approximatively, depending of your parameters, 50% of the trees will choose feature `A` and the other 50% will choose feature `B`. So the *importance* of the information contained in `A` and `B` (which is the same, because they are perfectly correlated) is diluted in `A` and `B`. So you won't easily know this information is important to predict what you want to predict! It is even worse when you have 10 correlated features...
 
-In boosting, when a specific link between feature and outcome have been learned by the algorithm, it will try to not refocus on it (in theory it is what happens, reality is not always that simple). Therefore, all the importance will be on feature `A` or on feature `B` (but not both). You will know that one feature has an important role in the link between the observations and the label. It is still up to you to search for the correlated features to the one detected as important if you need to know all of them.
+In boosting, when a specific link between feature and outcome have been learned by the algorithm, it will try to not refocus on it (in theory it is what happens, reality is not always that simple). Therefore, all the importance will be on feature `A` or on feature `B` (but not both). You will know that one feature have an important role in the link between the observations and the label. It is still up to you to search for the correlated features to the one detected as important if you need to know all of them.
 
 If you want to try Random Forests algorithm, you can tweak XGBoost parameters!
 
 For instance, to compute a model with 1000 trees, with a 0.5 factor on sampling rows and columns:
 
 ```{r, warning=FALSE, message=FALSE}
-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
 
 #Random Forest - 1000 trees
-bst <- xgboost(
-    data = train$data
-    , label = train$label
-    , max_depth = 4
-    , num_parallel_tree = 1000
-    , subsample = 0.5
-    , colsample_bytree = 0.5
-    , nrounds = 1
-    , objective = "binary:logistic"
-)
+bst <- xgboost(data = train$data, label = train$label, max_depth = 4, num_parallel_tree = 1000, subsample = 0.5, colsample_bytree =0.5, nrounds = 1, objective = "binary:logistic")
 
 #Boosting - 3 rounds
-bst <- xgboost(
-    data = train$data
-    , label = train$label
-    , max_depth = 4
-    , nrounds = 3
-    , objective = "binary:logistic"
-)
+bst <- xgboost(data = train$data, label = train$label, max_depth = 4, nrounds = 3, objective = "binary:logistic")
 ```
 
 > Note that the parameter `round` is set to `1`.

R-package/vignettes/xgboost.bib

@@ -18,11 +18,13 @@
   publisher={Institute of Mathematical Statistics}
 }
 
+
 @misc{
     Bache+Lichman:2013 ,
     author = "K. Bache and M. Lichman",
     year = "2013",
     title = "{UCI} Machine Learning Repository",
-    url = "https://archive.ics.uci.edu/",
+    url = "http://archive.ics.uci.edu/ml/",
     institution = "University of California, Irvine, School of Information and Computer Sciences" 
 }
+