Bump release version to 1.5.2. (#7567)

* Add new classifiers.
* Typehint.

.clang-format

@@ -1,214 +0,0 @@
----
-Language:        Cpp
-# BasedOnStyle:  Google
-AccessModifierOffset: -1
-AlignAfterOpenBracket: Align
-AlignArrayOfStructures: None
-AlignConsecutiveMacros: None
-AlignConsecutiveAssignments: None
-AlignConsecutiveBitFields: None
-AlignConsecutiveDeclarations: None
-AlignEscapedNewlines: Left
-AlignOperands:   Align
-AlignTrailingComments: true
-AllowAllArgumentsOnNextLine: true
-AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortEnumsOnASingleLine: true
-AllowShortBlocksOnASingleLine: Never
-AllowShortCaseLabelsOnASingleLine: false
-AllowShortFunctionsOnASingleLine: All
-AllowShortLambdasOnASingleLine: All
-AllowShortIfStatementsOnASingleLine: WithoutElse
-AllowShortLoopsOnASingleLine: true
-AlwaysBreakAfterDefinitionReturnType: None
-AlwaysBreakAfterReturnType: None
-AlwaysBreakBeforeMultilineStrings: true
-AlwaysBreakTemplateDeclarations: Yes
-AttributeMacros:
-  - __capability
-BinPackArguments: true
-BinPackParameters: true
-BraceWrapping:
-  AfterCaseLabel:  false
-  AfterClass:      false
-  AfterControlStatement: Never
-  AfterEnum:       false
-  AfterFunction:   false
-  AfterNamespace:  false
-  AfterObjCDeclaration: false
-  AfterStruct:     false
-  AfterUnion:      false
-  AfterExternBlock: false
-  BeforeCatch:     false
-  BeforeElse:      false
-  BeforeLambdaBody: false
-  BeforeWhile:     false
-  IndentBraces:    false
-  SplitEmptyFunction: true
-  SplitEmptyRecord: true
-  SplitEmptyNamespace: true
-BreakBeforeBinaryOperators: None
-BreakBeforeConceptDeclarations: true
-BreakBeforeBraces: Attach
-BreakBeforeInheritanceComma: false
-BreakInheritanceList: BeforeColon
-BreakBeforeTernaryOperators: true
-BreakConstructorInitializersBeforeComma: false
-BreakConstructorInitializers: BeforeColon
-BreakAfterJavaFieldAnnotations: false
-BreakStringLiterals: true
-ColumnLimit:     100
-CommentPragmas:  '^ IWYU pragma:'
-QualifierAlignment: Leave
-CompactNamespaces: false
-ConstructorInitializerIndentWidth: 4
-ContinuationIndentWidth: 4
-Cpp11BracedListStyle: true
-DeriveLineEnding: true
-DerivePointerAlignment: true
-DisableFormat:   false
-EmptyLineAfterAccessModifier: Never
-EmptyLineBeforeAccessModifier: LogicalBlock
-ExperimentalAutoDetectBinPacking: false
-PackConstructorInitializers: NextLine
-BasedOnStyle:    ''
-ConstructorInitializerAllOnOneLineOrOnePerLine: false
-AllowAllConstructorInitializersOnNextLine: true
-FixNamespaceComments: true
-ForEachMacros:
-  - foreach
-  - Q_FOREACH
-  - BOOST_FOREACH
-IfMacros:
-  - KJ_IF_MAYBE
-IncludeBlocks:   Regroup
-IncludeCategories:
-  - Regex:           '^<ext/.*\.h>'
-    Priority:        2
-    SortPriority:    0
-    CaseSensitive:   false
-  - Regex:           '^<.*\.h>'
-    Priority:        1
-    SortPriority:    0
-    CaseSensitive:   false
-  - Regex:           '^<.*'
-    Priority:        2
-    SortPriority:    0
-    CaseSensitive:   false
-  - Regex:           '.*'
-    Priority:        3
-    SortPriority:    0
-    CaseSensitive:   false
-IncludeIsMainRegex: '([-_](test|unittest))?$'
-IncludeIsMainSourceRegex: ''
-IndentAccessModifiers: false
-IndentCaseLabels: true
-IndentCaseBlocks: false
-IndentGotoLabels: true
-IndentPPDirectives: None
-IndentExternBlock: AfterExternBlock
-IndentRequires:  false
-IndentWidth:     2
-IndentWrappedFunctionNames: false
-InsertTrailingCommas: None
-JavaScriptQuotes: Leave
-JavaScriptWrapImports: true
-KeepEmptyLinesAtTheStartOfBlocks: false
-LambdaBodyIndentation: Signature
-MacroBlockBegin: ''
-MacroBlockEnd:   ''
-MaxEmptyLinesToKeep: 1
-NamespaceIndentation: None
-ObjCBinPackProtocolList: Never
-ObjCBlockIndentWidth: 2
-ObjCBreakBeforeNestedBlockParam: true
-ObjCSpaceAfterProperty: false
-ObjCSpaceBeforeProtocolList: true
-PenaltyBreakAssignment: 2
-PenaltyBreakBeforeFirstCallParameter: 1
-PenaltyBreakComment: 300
-PenaltyBreakFirstLessLess: 120
-PenaltyBreakString: 1000
-PenaltyBreakTemplateDeclaration: 10
-PenaltyExcessCharacter: 1000000
-PenaltyReturnTypeOnItsOwnLine: 200
-PenaltyIndentedWhitespace: 0
-PointerAlignment: Left
-PPIndentWidth:   -1
-RawStringFormats:
-  - Language:        Cpp
-    Delimiters:
-      - cc
-      - CC
-      - cpp
-      - Cpp
-      - CPP
-      - 'c++'
-      - 'C++'
-    CanonicalDelimiter: ''
-    BasedOnStyle:    google
-  - Language:        TextProto
-    Delimiters:
-      - pb
-      - PB
-      - proto
-      - PROTO
-    EnclosingFunctions:
-      - EqualsProto
-      - EquivToProto
-      - PARSE_PARTIAL_TEXT_PROTO
-      - PARSE_TEST_PROTO
-      - PARSE_TEXT_PROTO
-      - ParseTextOrDie
-      - ParseTextProtoOrDie
-      - ParseTestProto
-      - ParsePartialTestProto
-    CanonicalDelimiter: pb
-    BasedOnStyle:    google
-ReferenceAlignment: Pointer
-ReflowComments:  true
-ShortNamespaceLines: 1
-SortIncludes:    CaseSensitive
-SortJavaStaticImport: Before
-SortUsingDeclarations: true
-SpaceAfterCStyleCast: false
-SpaceAfterLogicalNot: false
-SpaceAfterTemplateKeyword: true
-SpaceBeforeAssignmentOperators: true
-SpaceBeforeCaseColon: false
-SpaceBeforeCpp11BracedList: false
-SpaceBeforeCtorInitializerColon: true
-SpaceBeforeInheritanceColon: true
-SpaceBeforeParens: ControlStatements
-SpaceAroundPointerQualifiers: Default
-SpaceBeforeRangeBasedForLoopColon: true
-SpaceInEmptyBlock: false
-SpaceInEmptyParentheses: false
-SpacesBeforeTrailingComments: 2
-SpacesInAngles:  Never
-SpacesInConditionalStatement: false
-SpacesInContainerLiterals: true
-SpacesInCStyleCastParentheses: false
-SpacesInLineCommentPrefix:
-  Minimum:         1
-  Maximum:         -1
-SpacesInParentheses: false
-SpacesInSquareBrackets: false
-SpaceBeforeSquareBrackets: false
-BitFieldColonSpacing: Both
-Standard:        Auto
-StatementAttributeLikeMacros:
-  - Q_EMIT
-StatementMacros:
-  - Q_UNUSED
-  - QT_REQUIRE_VERSION
-TabWidth:        8
-UseCRLF:         false
-UseTab:          Never
-WhitespaceSensitiveMacros:
-  - STRINGIZE
-  - PP_STRINGIZE
-  - BOOST_PP_STRINGIZE
-  - NS_SWIFT_NAME
-  - CF_SWIFT_NAME
-...

.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 }}
@@ -12,7 +9,7 @@ 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@v2

.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:
@@ -17,14 +14,17 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-11]
+        os: [macos-10.15]
     steps:
     - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - name: Install system packages
       run: |
+        # Use libomp 11.1.0: https://github.com/dmlc/xgboost/issues/7039
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
         brew install ninja libomp
+        brew pin libomp
     - name: Build gtest binary
       run: |
         mkdir build
@@ -75,18 +75,19 @@ jobs:
     - 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: |
@@ -108,7 +109,6 @@ jobs:
         cd ..
         rm -rf ./build
         popd
-
     - name: Build and install XGBoost shared library
       shell: bash -l {0}
       run: |
@@ -132,21 +132,40 @@ jobs:
 
   lint:
     runs-on: ubuntu-latest
-    name: Code linting for C++
+    name: Code linting for Python and C++
     steps:
     - uses: actions/checkout@v2
       with:
         submodules: 'true'
     - 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: |
-        LINT_LANG=cpp make lint
+        make lint
+
+  mypy:
+    runs-on: ubuntu-latest
+    name: Type checking for Python
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+        architecture: 'x64'
+    - name: Install Python packages
+      run: |
+        python -m pip install wheel setuptools mypy pandas dask[complete] distributed
+    - name: Run mypy
+      run: |
+        make mypy
 
   doxygen:
     runs-on: ubuntu-latest
@@ -157,7 +176,7 @@ jobs:
         submodules: 'true'
     - uses: actions/setup-python@v2
       with:
-        python-version: "3.8"
+        python-version: '3.7'
         architecture: 'x64'
     - name: Install system packages
       run: |
@@ -194,7 +213,7 @@ jobs:
         submodules: 'true'
     - uses: actions/setup-python@v2
       with:
-        python-version: "3.8"
+        python-version: '3.8'
         architecture: 'x64'
     - name: Install system packages
       run: |

.github/workflows/python_tests.yml

@@ -2,95 +2,30 @@ name: XGBoost-Python-Tests
 
 on: [push, pull_request]
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 jobs:
-  python-mypy-lint:
-    runs-on: ubuntu-latest
-    name: Type and format checks for the Python package
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-        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.python-version }}
-        activate-environment: python_lint
-        environment-file: tests/ci_build/conda_env/python_lint.yml
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Run mypy
-      shell: bash -l {0}
-      run: |
-        python tests/ci_build/lint_python.py --format=0 --type-check=1 --pylint=0
-    - name: Run formatter
-      shell: bash -l {0}
-      run: |
-        python tests/ci_build/lint_python.py --format=1 --type-check=0 --pylint=0
-    - name: Run pylint
-      shell: bash -l {0}
-      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: false
-        environment-name: sdist_test
-        environment-file: tests/ci_build/conda_env/sdist_test.yml
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py sdist
-        pip install -v ./dist/xgboost-*.tar.gz
-        cd ..
-        python -c 'import xgboost'
-
   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@v2
       with:
         submodules: 'true'
     - name: Install osx system dependencies
-      if: matrix.os == 'macos-11'
+      if: matrix.os == 'macos-10.15'
       run: |
+        # Use libomp 11.1.0: https://github.com/dmlc/xgboost/issues/7039
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
         brew install ninja libomp
-    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
+        brew pin libomp
+    - name: Install Ubuntu system dependencies
+      if: matrix.os == 'ubuntu-latest'
+      run: |
+        sudo apt-get install -y --no-install-recommends ninja-build
+    - uses: conda-incubator/setup-miniconda@v2
       with:
         auto-update-conda: true
         python-version: ${{ matrix.python-version }}
@@ -110,65 +45,13 @@ jobs:
         cd ..
         python -c 'import xgboost'
 
-  python-tests-on-macos:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 60
-    strategy:
-      matrix:
-        config:
-          - {os: macos-11}
-
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: false
-        environment-name: macos_test
-        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
-
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on macos
-      shell: bash -l {0}
-      run: |
-        brew install ninja
-
-        mkdir build
-        cd build
-        # Set prefix, to use OpenMP library from Conda env
-        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
-        # to learn why we don't use libomp from Homebrew.
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja
-
-    - name: Install Python package
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py install
-
-    - name: Test Python package
-      shell: bash -l {0}
-      run: |
-        pytest -s -v -rxXs --durations=0 ./tests/python
-
   python-tests-on-win:
     name: Test XGBoost Python package on ${{ matrix.config.os }}
     runs-on: ${{ matrix.config.os }}
     strategy:
       matrix:
         config:
-          - {os: windows-latest, python-version: '3.8'}
+          - {os: windows-2016, python-version: '3.8'}
 
     steps:
     - uses: actions/checkout@v2
@@ -193,7 +76,7 @@ jobs:
       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 .. -G"Visual Studio 15 2017" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
         cmake --build . --config Release --parallel $(nproc)
 
     - name: Install Python package
@@ -207,4 +90,75 @@ jobs:
     - name: Test Python package
       shell: bash -l {0}
       run: |
-        pytest -s -v -rxXs --durations=0 ./tests/python
+        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
+      run: |
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
+        brew install ninja libomp
+        brew pin libomp
+
+        mkdir build
+        cd build
+        cmake .. -GNinja -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
+        ninja
+
+    - 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
+
+    - name: Rename Python wheel
+      shell: bash -l {0}
+      run: |
+        TAG=macosx_10_15_x86_64.macosx_11_0_x86_64.macosx_12_0_x86_64
+        python tests/ci_build/rename_whl.py python-package/dist/*.whl ${{ github.sha }} ${TAG}
+
+    - name: Extract branch name
+      shell: bash
+      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+      id: extract_branch
+      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
+
+    - name: Upload Python wheel
+      shell: bash -l {0}
+      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
+      run: |
+        python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
+      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 }}

.github/workflows/python_wheels.yml

@@ -1,41 +0,0 @@
-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 }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        include:
-        - os: macos-latest
-          platform_id: macosx_x86_64
-        - os: macos-latest
-          platform_id: macosx_arm64
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Setup Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-    - name: Build wheels
-      run: bash tests/ci_build/build_python_wheels.sh ${{ matrix.platform_id }} ${{ github.sha }}
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Upload Python wheel
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      run: |
-        python -m pip install awscli
-        python -m awscli s3 cp wheelhouse/*.whl s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      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 }}

.github/workflows/r_nold.yml

@@ -10,9 +10,6 @@ on:
 env:
   R_PACKAGES: c('XML', 'igraph', 'data.table', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
 
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
 jobs:
   test-R-noLD:
     if: github.event.comment.body == '/gha run r-nold-test' && contains('OWNER,MEMBER,COLLABORATOR', github.event.comment.author_association)

.github/workflows/r_tests.yml

@@ -5,10 +5,6 @@ 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 }}
-  _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
 
 jobs:
   lintr:
@@ -17,7 +13,7 @@ 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 }}
@@ -27,7 +23,7 @@ jobs:
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@v2
+    - uses: r-lib/actions/setup-r@master
       with:
         r-version: ${{ matrix.config.r }}
 
@@ -35,8 +31,8 @@ jobs:
       uses: actions/cache@v2
       with:
         path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
 
     - name: Install dependencies
       shell: Rscript {0}
@@ -53,9 +49,8 @@ jobs:
     - name: Run lintr
       run: |
         cd R-package
-        R CMD INSTALL .
-        # Disable lintr errors for now: https://github.com/dmlc/xgboost/issues/8012
-        Rscript tests/helper_scripts/run_lint.R || true
+        R.exe CMD INSTALL .
+        Rscript.exe tests/helper_scripts/run_lint.R
 
   test-with-R:
     runs-on: ${{ matrix.config.os }}
@@ -64,12 +59,11 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
+          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
@@ -77,7 +71,7 @@ jobs:
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@v2
+    - uses: r-lib/actions/setup-r@master
       with:
         r-version: ${{ matrix.config.r }}
 
@@ -85,29 +79,24 @@ jobs:
       uses: actions/cache@v2
       with:
         path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
 
     - name: Install dependencies
       shell: Rscript {0}
-      if: matrix.config.os != 'windows-latest'
       run: |
         install.packages(${{ env.R_PACKAGES }},
                          repos = 'http://cloud.r-project.org',
                          dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Install binary dependencies
+    - name: Install igraph on Windows
       shell: Rscript {0}
-      if: matrix.config.os == 'windows-latest'
+      if: matrix.config.os == 'windows-2016'
       run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         type = 'binary',
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+        install.packages('igraph', type='binary', dependencies = c('Depends', 'Imports', 'LinkingTo'))
 
     - uses: actions/setup-python@v2
       with:
-        python-version: "3.8"
+        python-version: '3.7'
         architecture: 'x64'
 
     - name: Test R
@@ -123,20 +112,16 @@ jobs:
         config:
           - {r: 'release'}
 
-    env:
-      _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
-      MAKE: "make -j$(nproc)"
-
     steps:
     - uses: actions/checkout@v2
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@v2
+    - uses: r-lib/actions/setup-r@master
       with:
         r-version: ${{ matrix.config.r }}
 
-    - uses: r-lib/actions/setup-tinytex@v2
+    - uses: r-lib/actions/setup-tinytex@master
 
     - name: Install system packages
       run: |
@@ -146,8 +131,8 @@ jobs:
       uses: actions/cache@v2
       with:
         path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
 
     - name: Install dependencies
       shell: Rscript {0}

.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@865b4092859256271290c77adbd10a43f4779972 # tag=v2.0.3
-        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@6673cd052c4cd6fcf4b4e6e60ea986c889389535 # tag=v3.0.0
-        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@5f532563584d71fdef14ee64d17bafb34f751ce5 # tag=v1.0.26
-        with:
-          sarif_file: results.sarif

.gitignore

@@ -52,8 +52,6 @@ Debug
 R-package.Rproj
 *.cache*
 .mypy_cache/
-doxygen
-
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -65,7 +63,6 @@ nb-configuration*
 # Eclipse
 .project
 .cproject
-.classpath
 .pydevproject
 .settings/
 build
@@ -99,11 +96,8 @@ metastore_db
 R-package/src/Makevars
 *.lib
 
-# Visual Studio
-.vs/
-CMakeSettings.json
-*.ilk
-*.pdb
+# Visual Studio Code
+/.vscode/
 
 # IntelliJ/CLion
 .idea
@@ -131,11 +125,3 @@ credentials.csv
 *.pub
 *.rdp
 *_rsa
-
-# Visual Studio code + extensions
-.vscode
-.metals
-.bloop
-
-# hypothesis python tests
-.hypothesis

.readthedocs.yaml

@@ -1,35 +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
-  system_packages: true

CMakeLists.txt

@@ -1,10 +1,9 @@
 cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.7.4)
+project(xgboost LANGUAGES CXX C VERSION 1.5.2)
 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)
 
@@ -29,7 +28,6 @@ set_default_configuration_release()
 option(BUILD_C_DOC "Build documentation for C APIs using Doxygen." OFF)
 option(USE_OPENMP "Build with OpenMP support." ON)
 option(BUILD_STATIC_LIB "Build static library" OFF)
-option(FORCE_SHARED_CRT "Build with dynamic CRT on Windows (/MD)" OFF)
 option(RABIT_BUILD_MPI "Build MPI" OFF)
 ## Bindings
 option(JVM_BINDINGS "Build JVM bindings" OFF)
@@ -67,7 +65,6 @@ 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)
@@ -118,20 +115,6 @@ endif (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
 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))
-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 ()
 
 #-- Sanitizer
 if (USE_SANITIZER)
@@ -146,15 +129,15 @@ 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)
 
   if ((${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 11.4) AND (NOT BUILD_WITH_CUDA_CUB))
-    set(BUILD_WITH_CUDA_CUB ON)
+    message(SEND_ERROR "`BUILD_WITH_CUDA_CUB` should be set to `ON` for CUDA >= 11.4")
   endif ()
 endif (USE_CUDA)
 
@@ -171,30 +154,9 @@ if (USE_OPENMP)
     # 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)
-    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 ${HOMEBREW_LIBOMP_PREFIX}/lib/libomp.dylib)
-      find_package(OpenMP REQUIRED)
-    endif ()
-  else ()
-    find_package(OpenMP REQUIRED)
-  endif ()
+  endif (APPLE)
+  find_package(OpenMP REQUIRED)
 endif (USE_OPENMP)
-#Add for IBM i
-if (${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)
@@ -202,9 +164,6 @@ endif (USE_NCCL)
 
 # dmlc-core
 msvc_use_static_runtime()
-if (FORCE_SHARED_CRT)
-  set(DMLC_FORCE_SHARED_CRT ON)
-endif ()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
 
 if (MSVC)
@@ -237,10 +196,6 @@ endif (JVM_BINDINGS)
 # Plugin
 add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
 
-if (PLUGIN_RMM)
-  find_package(rmm REQUIRED)
-endif (PLUGIN_RMM)
-
 #-- library
 if (BUILD_STATIC_LIB)
   add_library(xgboost STATIC)
@@ -345,7 +300,7 @@ write_basic_package_version_file(
   COMPATIBILITY AnyNewerVersion)
 install(
   FILES
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
+  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
   ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
   DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
 

CONTRIBUTORS.md

@@ -10,8 +10,8 @@ The Project Management Committee(PMC) consists group of active committers that m
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [Michael Benesty](https://github.com/pommedeterresautee)
   - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Akuity
-  - Yuan is a founding engineer at Akuity. He contributed mostly in R and Python packages.
+* [Yuan Tang](https://github.com/terrytangyuan), Ant Group
+  - Yuan is a software engineer in Ant Group. He contributed mostly in R and Python packages.
 * [Nan Zhu](https://github.com/CodingCat), Uber
   - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
 * [Jiaming Yuan](https://github.com/trivialfis)

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 = '10.1'
+
+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 10.1
+            // using CentOS 7 image
+            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
+            // The build-gpu-* builds below use Ubuntu image
+            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0', build_rmm: true) },
+            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '10.1') },
+            'build-jvm-packages-gpu-cuda10.1': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '11.0') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
+            '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-cross': { TestPythonGPU(artifact_cuda_version: '10.1', host_cuda_version: '11.0', test_rmm: true) },
+            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
+            'test-python-mgpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '10.1', host_cuda_version: '11.0', multi_gpu: true, test_rmm: true) },
+            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0', test_rmm: true) },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
+            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
+            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') }
+          ])
+        }
+      }
+    }
+    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=10.1"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
+    """
+    deleteDir()
+  }
+}
+
+def BuildCPU() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} rm -fv dmlc-core/include/dmlc/build_config_default.h
+      # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
+      # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
+      # See discussion at https://github.com/dmlc/xgboost/issues/5510
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_DENSE_PARSER=ON
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
+    """
+    // Sanitizer test
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
+      -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose"
+    """
+
+    stash name: 'xgboost_cli', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCPUARM64() {
+  node('linux && arm64') {
+    unstash name: 'srcs'
+    echo "Build CPU ARM64"
+    def container_type = "aarch64"
+    def docker_binary = "docker"
+    def wheel_tag = "manylinux2014_aarch64"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh --conda-env=aarch64_test -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOL=ON
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
+    ${dockerRun} ${container_type} ${docker_binary} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl && python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}"
+    mv -v wheelhouse/*.whl python-package/dist/
+    # Make sure that libgomp.so is vendored in the wheel
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp || exit -1"
+    """
+    echo 'Stashing Python wheel...'
+    stash name: "xgboost_whl_arm64_cpu", includes: 'python-package/dist/*.whl'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading Python wheel...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    }
+    stash name: 'xgboost_cli_arm64', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCPUMock() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU with rabit mock"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_mock_cmake.sh
+    """
+    echo 'Stashing rabit C++ test executable (xgboost)...'
+    stash name: 'xgboost_rabit_tests', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCUDA(args) {
+  node('linux && cpu_build') {
+    unstash name: 'srcs'
+    echo "Build with CUDA ${args.cuda_version}"
+    def container_type = GetCUDABuildContainerType(args.cuda_version)
+    def docker_binary = "docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def arch_flag = ""
+    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
+      arch_flag = "-DGPU_COMPUTE_VER=75"
+    }
+    def wheel_tag = "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...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    }
+    echo 'Stashing C++ test executable (testxgboost)...'
+    stash name: "xgboost_cpp_tests_cuda${args.cuda_version}", includes: 'build/testxgboost'
+    if (args.build_rmm) {
+      echo "Build with CUDA ${args.cuda_version} and RMM"
+      container_type = "rmm"
+      docker_binary = "docker"
+      docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+      sh """
+      rm -rf build/
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON -DUSE_NCCL=ON -DPLUGIN_RMM=ON -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 ${commit_id}
+      """
+      echo 'Uploading R tarball...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_linux_*.tar.gz'
+    }
+    deleteDir()
+  }
+}
+
+def BuildJVMPackagesWithCUDA(args) {
+  node('linux && mgpu') {
+    unstash name: 'srcs'
+    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
+    def container_type = "jvm_gpu_build"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def arch_flag = ""
+    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
+      arch_flag = "-DGPU_COMPUTE_VER=75"
+    }
+    // Use only 4 CPU cores
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
+    """
+    echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
+    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
+    deleteDir()
+  }
+}
+
+def BuildJVMPackages(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}"
+    def container_type = "jvm"
+    def docker_binary = "docker"
+    // Use only 4 CPU cores
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
+    """
+    echo 'Stashing XGBoost4J JAR...'
+    stash name: 'xgboost4j_jar', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
+    deleteDir()
+  }
+}
+
+def BuildJVMDoc() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Building JVM doc..."
+    def container_type = "jvm"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
+    """
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading doc...'
+      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
+    }
+    deleteDir()
+  }
+}
+
+def TestPythonCPU() {
+  node('linux && cpu') {
+    unstash name: "xgboost_whl_cuda${ref_cuda_ver}"
+    unstash name: 'srcs'
+    unstash name: 'xgboost_cli'
+    echo "Test Python CPU"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
+    """
+    deleteDir()
+  }
+}
+
+def TestPythonCPUARM64() {
+  node('linux && arm64') {
+    unstash name: "xgboost_whl_arm64_cpu"
+    unstash name: 'srcs'
+    unstash name: 'xgboost_cli_arm64'
+    echo "Test Python CPU ARM64"
+    def container_type = "aarch64"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-arm64
+    """
+    deleteDir()
+  }
+}
+
+def TestPythonGPU(args) {
+  def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
+  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
+  node(nodeReq) {
+    unstash name: "xgboost_whl_cuda${artifact_cuda_version}"
+    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
+    unstash name: 'srcs'
+    echo "Test Python GPU: CUDA ${args.host_cuda_version}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+    def mgpu_indicator = (args.multi_gpu) ? 'mgpu' : 'gpu'
+    // Allocate extra space in /dev/shm to enable NCCL
+    def docker_extra_params = (args.multi_gpu) ? "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'" : ''
+    sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator}"
+    if (args.test_rmm) {
+      sh "rm -rfv build/ python-package/dist/"
+      unstash name: "xgboost_whl_rmm_cuda${args.host_cuda_version}"
+      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
+      sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator} --use-rmm-pool"
+    }
+    deleteDir()
+  }
+}
+
+def TestCppGPU(args) {
+  def nodeReq = 'linux && mgpu'
+  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
+  node(nodeReq) {
+    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
+    unstash name: 'srcs'
+    echo "Test C++, CUDA ${args.host_cuda_version}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
+    if (args.test_rmm) {
+      sh "rm -rfv build/"
+      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
+      echo "Test C++, CUDA ${args.host_cuda_version} with RMM"
+      container_type = "rmm"
+      docker_binary = "nvidia-docker"
+      docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "source activate gpu_test && build/testxgboost --use-rmm-pool --gtest_filter=-*DeathTest.*"
+      """
+    }
+    deleteDir()
+  }
+}
+
+def CrossTestJVMwithJDK(args) {
+  node('linux && cpu') {
+    unstash name: 'xgboost4j_jar'
+    unstash name: 'srcs'
+    if (args.spark_version != null) {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
+    } else {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
+    }
+    def container_type = "jvm_cross"
+    def docker_binary = "docker"
+    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
+    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
+    // Run integration tests only when spark_version is given
+    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
+    """
+    deleteDir()
+  }
+}
+
+def DeployJVMPackages(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Deploying to xgboost-maven-repo S3 repo...'
+      sh """
+      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.1 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-cuda10.1': { BuildWin64() },
+            'build-rpkg-win64-cuda10.1': { BuildRPackageWithCUDAWin64() }
+          ])
+        }
+      }
+    }
+    stage('Jenkins Win64: Test') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'test-win64-cuda10.1': { TestWin64() },
+          ])
+        }
+      }
+    }
+  }
+}
+
+// check out source code from git
+def checkoutSrcs() {
+  retry(5) {
+    try {
+      timeout(time: 2, unit: 'MINUTES') {
+        checkout scm
+        sh 'git submodule update --init'
+      }
+    } catch (exc) {
+      deleteDir()
+      error "Failed to fetch source codes"
+    }
+  }
+}
+
+def BuildWin64() {
+  node('win64 && cuda10_unified') {
+    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}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    }
+    echo 'Stashing C++ test executable (testxgboost)...'
+    stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
+    stash name: 'xgboost_cli', includes: 'xgboost.exe'
+    deleteDir()
+  }
+}
+
+def BuildRPackageWithCUDAWin64() {
+  node('win64 && cuda10_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}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_win64_*.tar.gz'
+    }
+    deleteDir()
+  }
+}
+
+def TestWin64() {
+  node('win64 && cuda10_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 -m pytest -v -s -rxXs --fulltrace tests\\python"
+    bat """
+    conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
+    """
+    bat "conda env remove --name ${env_name}"
+    deleteDir()
+  }
+}

Makefile

@@ -87,6 +87,19 @@ cover: check
 endif
 
 
+# dask is required to pass, others are not
+# If any of the dask tests failed, contributor won't see the other error.
+mypy:
+	cd python-package; \
+	mypy ./xgboost/dask.py && \
+	mypy ./xgboost/rabit.py && \
+	mypy ../demo/guide-python/external_memory.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 && \
+	mypy ./xgboost/sklearn.py || exit 1; \
+	mypy . || true ;
+
 clean:
 	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
 	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
@@ -123,13 +136,20 @@ Rpack: clean_all
 	cp -r dmlc-core/include xgboost/src/dmlc-core/include
 	cp -r dmlc-core/src xgboost/src/dmlc-core/src
 	cp ./LICENSE xgboost
+# Modify PKGROOT in Makevars.in
 	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
-	cat R-package/src/Makevars.win|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.win
+# 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

NEWS.md

@@ -3,499 +3,6 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
-## 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
-fixes.  We will describe the experimental categorical data support and the external memory
-interface independently. Package-specific new features will be listed in respective
-sections.
-
-### Development on categorical data support
-In version 1.3, XGBoost introduced an experimental feature for handling categorical data
-natively, without one-hot encoding. XGBoost can fit categorical splits in decision
-trees. (Currently, the generated splits will be of form `x \in {v}`, where the input is
-compared to a single category value. A future version of XGBoost will generate splits that
-compare the input against a list of multiple category values.)
-
-Most of the other features, including prediction, SHAP value computation, feature
-importance, and model plotting were revised to natively handle categorical splits.  Also,
-all Python interfaces including native interface with and without quantized `DMatrix`,
-scikit-learn interface, and Dask interface now accept categorical data with a wide range
-of data structures support including numpy/cupy array and cuDF/pandas/modin dataframe.  In
-practice, the following are required for enabling categorical data support during
-training:
-
-  - Use Python package.
-  - Use `gpu_hist` to train the model.
-  - Use JSON model file format for saving the model.
-
-Once the model is trained, it can be used with most of the features that are available on
-the Python package.  For a quick introduction, see
-https://xgboost.readthedocs.io/en/latest/tutorials/categorical.html
-
-Related PRs: (#7011, #7001, #7042, #7041, #7047, #7043, #7036, #7054, #7053, #7065, #7213, #7228, #7220, #7221, #7231, #7306)
-
-* Next steps
-
-	- Revise the CPU training algorithm to handle categorical data natively and generate categorical splits
-	- Extend the CPU and GPU algorithms to generate categorical splits of form `x \in S`
-	where the input is compared with multiple category values.  split. (#7081)
-
-### External memory
-This release features a brand-new interface and implementation for external memory (also
-known as out-of-core training).  (#6901, #7064, #7088, #7089, #7087, #7092, #7070,
-#7216). The new implementation leverages the data iterator interface, which is currently
-used to create `DeviceQuantileDMatrix`. For a quick introduction, see
-https://xgboost.readthedocs.io/en/latest/tutorials/external_memory.html#data-iterator
-. During the development of this new interface, `lz4` compression is removed. (#7076).
-Please note that external memory support is still experimental and not ready for
-production use yet.  All future development will focus on this new interface and users are
-advised to migrate. (You are using the old interface if you are using a URL suffix to use
-external memory.)
-
-### New features in Python package
-* Support numpy array interface and all numeric types from numpy in `DMatrix`
-  construction and `inplace_predict` (#6998, #7003).  Now XGBoost no longer makes data
-  copy when input is numpy array view.
-* The early stopping callback in Python has a new `min_delta` parameter to control the
-  stopping behavior (#7137)
-* Python package now supports calculating feature scores for the linear model, which is
-  also available on R package. (#7048)
-* Python interface now supports configuring constraints using feature names instead of
-  feature indices.
-* Typehint support for more Python code including scikit-learn interface and rabit
-  module. (#6799, #7240)
-* Add tutorial for XGBoost-Ray (#6884)
-
-### New features in R package
-* In 1.4 we have a new prediction function in the C API which is used by the Python
-  package.  This release revises the R package to use the new prediction function as well.
-  A new parameter `iteration_range` for the predict function is available, which can be
-  used for specifying the range of trees for running prediction. (#6819, #7126)
-* R package now supports the `nthread` parameter in `DMatrix` construction. (#7127)
-
-### New features in JVM packages
-* Support GPU dataframe and `DeviceQuantileDMatrix` (#7195).  Constructing `DMatrix`
-  with GPU data structures and the interface for quantized `DMatrix` were first
-  introduced in the Python package and are now available in the xgboost4j package.
-* JVM packages now support saving and getting early stopping attributes. (#7095) Here is a
-  quick [example](https://github.com/dmlc/xgboost/jvm-packages/xgboost4j-example/src/main/java/ml/dmlc/xgboost4j/java/example/EarlyStopping.java "example") in JAVA (#7252).
-
-### General new features
-* We now have a pre-built binary package for R on Windows with GPU support. (#7185)
-* CUDA compute capability 86 is now part of the default CMake build configuration with
-  newly added support for CUDA 11.4. (#7131, #7182, #7254)
-* XGBoost can be compiled using system CUB provided by CUDA 11.x installation. (#7232)
-
-### Optimizations
-The performance for both `hist` and `gpu_hist` has been significantly improved in 1.5
-with the following optimizations:
-* GPU multi-class model training now supports prediction cache. (#6860)
-* GPU histogram building is sped up and the overall training time is 2-3 times faster on
-  large datasets (#7180, #7198).  In addition, we removed the parameter `deterministic_histogram` and now
-  the GPU algorithm is always deterministic.
-* CPU hist has an optimized procedure for data sampling (#6922)
-* More performance optimization in regression and binary classification objectives on
-  CPU (#7206)
-* Tree model dump is now performed in parallel (#7040)
-
-### Breaking changes
-* `n_gpus` was deprecated in 1.0 release and is now removed.
-* Feature grouping in CPU hist tree method is removed, which was disabled long
-  ago. (#7018)
-* C API for Quantile DMatrix is changed to be consistent with the new external memory
-  implementation. (#7082)
-
-### Notable general bug fixes
-* XGBoost no long changes global CUDA device ordinal when `gpu_id` is specified (#6891,
-  #6987)
-* Fix `gamma` negative likelihood evaluation metric. (#7275)
-* Fix integer value of `verbose_eal` for `xgboost.cv` function in Python. (#7291)
-* Remove extra sync in CPU hist for dense data, which can lead to incorrect tree node
-  statistics. (#7120, #7128)
-* Fix a bug in GPU hist when data size is larger than `UINT32_MAX` with missing
-  values. (#7026)
-* Fix a thread safety issue in prediction with the `softmax` objective. (#7104)
-* Fix a thread safety issue in CPU SHAP value computation. (#7050) Please note that all
-  prediction functions in Python are thread-safe.
-* Fix model slicing. (#7149, #7078)
-* Workaround a bug in old GCC which can lead to segfault during construction of
-  DMatrix. (#7161)
-* Fix histogram truncation in GPU hist, which can lead to slightly-off results. (#7181)
-* Fix loading GPU linear model pickle files on CPU-only machine. (#7154)
-* Check input value is duplicated when CPU quantile queue is full (#7091)
-* Fix parameter loading with training continuation. (#7121)
-* Fix CMake interface for exposing C library by specifying dependencies. (#7099)
-* Callback and early stopping are explicitly disabled for the scikit-learn interface
-  random forest estimator. (#7236)
-* Fix compilation error on x86 (32-bit machine) (#6964)
-* Fix CPU memory usage with extremely sparse datasets (#7255)
-* Fix a bug in GPU multi-class AUC implementation with weighted data (#7300)
-
-### Python package
-Other than the items mentioned in the previous sections, there are some Python-specific
-improvements.
-* Change development release postfix to `dev` (#6988)
-* Fix early stopping behavior with MAPE metric (#7061)
-* Fixed incorrect feature mismatch error message (#6949)
-* Add predictor to skl constructor. (#7000, #7159)
-* Re-enable feature validation in predict proba. (#7177)
-* scikit learn interface regression estimator now can pass the scikit-learn estimator
-  check and is fully compatible with scikit-learn utilities.  `__sklearn_is_fitted__` is
-  implemented as part of the changes (#7130, #7230)
-* Conform the latest pylint. (#7071, #7241)
-* Support latest panda range index in DMatrix construction. (#7074)
-* Fix DMatrix construction from pandas series. (#7243)
-* Fix typo and grammatical mistake in error message (#7134)
-* [dask] disable work stealing explicitly for training tasks (#6794)
-* [dask] Set dataframe index in predict. (#6944)
-* [dask] Fix prediction on df with latest dask. (#6969)
-* [dask] Fix dask predict on `DaskDMatrix` with `iteration_range`. (#7005)
-* [dask] Disallow importing non-dask estimators from xgboost.dask (#7133)
-
-### R package
-Improvements other than new features on R package:
-* Optimization for updating R handles in-place (#6903)
-* Removed the magrittr dependency. (#6855, #6906, #6928)
-* The R package now hides all C++ symbols to avoid conflicts. (#7245)
-* Other maintenance including code cleanups, document updates. (#6863, #6915, #6930, #6966, #6967)
-
-### JVM packages
-Improvements other than new features on JVM packages:
-* Constructors with implicit missing value are deprecated due to confusing behaviors. (#7225)
-* Reduce scala-compiler, scalatest dependency scopes (#6730)
-* Making the Java library loader emit helpful error messages on missing dependencies. (#6926)
-* JVM packages now use the Python tracker in XGBoost instead of dmlc.  The one in XGBoost
-  is shared between JVM packages and Python Dask and enjoys better maintenance (#7132)
-* Fix "key not found: train" error (#6842)
-* Fix model loading from stream (#7067)
-
-### General document improvements
-* Overhaul the installation documents. (#6877)
-* A few demos are added for AFT with dask (#6853), callback with dask (#6995), inference
-  in C (#7151), `process_type`. (#7135)
-* Fix PDF format of document. (#7143)
-* Clarify the behavior of `use_rmm`. (#6808)
-* Clarify prediction function. (#6813)
-* Improve tutorial on feature interactions (#7219)
-* Add small example for dask sklearn interface. (#6970)
-* Update Python intro.  (#7235)
-* Some fixes/updates (#6810, #6856, #6935, #6948, #6976, #7084, #7097, #7170, #7173, #7174, #7226, #6979, #6809, #6796, #6979)
-
-### Maintenance
-* Some refactoring around CPU hist, which lead to better performance but are listed under general maintenance tasks:
-  - Extract evaluate splits from CPU hist. (#7079)
-  - Merge lossgude and depthwise strategies for CPU hist (#7007)
-  - Simplify sparse and dense CPU hist kernels (#7029)
-  - Extract histogram builder from CPU Hist. (#7152)
-
-* Others
-  - Fix `gpu_id` with custom objective. (#7015)
-  - Fix typos in AUC. (#6795)
-  - Use constexpr in `dh::CopyIf`. (#6828)
-  - Update dmlc-core. (#6862)
-  - Bump version to 1.5.0 snapshot in master. (#6875)
-  - Relax shotgun test. (#6900)
-  - Guard against index error in prediction. (#6982)
-  - Hide symbols in CI build + hide symbols for C and CUDA (#6798)
-  - Persist data in dask test. (#7077)
-  - Fix typo in arguments of PartitionBuilder::Init (#7113)
-  - Fix typo in src/common/hist.cc BuildHistKernel (#7116)
-  - Use upstream URI in distributed quantile tests. (#7129)
-  - Include cpack (#7160)
-  - Remove synchronization in monitor. (#7164)
-  - Remove unused code. (#7175)
-  - Fix building on CUDA 11.0. (#7187)
-  - Better error message for `ncclUnhandledCudaError`. (#7190)
-  - Add noexcept to JSON objects. (#7205)
-  - Improve wording for warning (#7248)
-  - Fix typo in release script. [skip ci] (#7238)
-  - Relax shotgun test. (#6918)
-  - Relax test for decision stump in distributed environment. (#6919)
-  -	[dask] speed up tests (#7020)
-
-### CI
-* [CI] Rotate access keys for uploading MacOS artifacts from Travis CI (#7253)
-* Reduce Travis environment setup time. (#6912)
-* Restore R cache on github action. (#6985)
-* [CI] Remove stray build artifact to avoid error in artifact packaging (#6994)
-* [CI] Move appveyor tests to action (#6986)
-* Remove appveyor badge. [skip ci] (#7035)
-* [CI] Configure RAPIDS, dask, modin (#7033)
-* Test on s390x. (#7038)
-* [CI] Upgrade to CMake 3.14 (#7060)
-* [CI] Update R cache. (#7102)
-* [CI] Pin libomp to 11.1.0  (#7107)
-* [CI] Upgrade build image to CentOS 7 + GCC 8; require CUDA 10.1 and later (#7141)
-* [dask] Work around segfault in prediction. (#7112)
-* [dask] Remove the workaround for segfault. (#7146)
-* [CI] Fix hanging Python setup in Windows CI (#7186)
-* [CI] Clean up in beginning of each task in Win CI (#7189)
-* Fix travis. (#7237)
-
-### Acknowledgement
-* **Contributors**: Adam Pocock (@Craigacp), Jeff H (@JeffHCross), Johan Hansson (@JohanWork), Jose Manuel Llorens (@JoseLlorensRipolles), Benjamin Szőke (@Livius90), @ReeceGoding, @ShvetsKS, Robert Zabel (@ZabelTech), Ali (@ali5h), Andrew Ziem (@az0), Andy Adinets (@canonizer), @david-cortes, Daniel Saxton (@dsaxton), Emil Sadek (@esadek), @farfarawayzyt, Gil Forsyth (@gforsyth), @giladmaya, @graue70, Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), José Morales (@jmoralez), Kai Fricke (@krfricke), Christian Lorentzen (@lorentzenchr), Mads R. B. Kristensen (@madsbk), Anton Kostin (@masguit42), Martin Petříček (@mpetricek-corp), @naveenkb, Taewoo Kim (@oOTWK), Viktor Szathmáry (@phraktle), Robert Maynard (@robertmaynard), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), Paul Taylor (@trxcllnt), @vslaykovsky, Bobby Wang (@wbo4958),
-* **Reviewers**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Jose Manuel Llorens (@JoseLlorensRipolles), Kodi Arfer (@Kodiologist), Benjamin Szőke (@Livius90), Mark Guryanov (@MarkGuryanov), Rory Mitchell (@RAMitchell), @ReeceGoding, @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Andrew Ziem (@az0), @candalfigomoro, Andy Adinets (@canonizer), Dante Gama Dessavre (@dantegd), @david-cortes, Daniel Saxton (@dsaxton), @farfarawayzyt, Gil Forsyth (@gforsyth), Harutaka Kawamura (@harupy), Philip Hyunsu Cho (@hcho3), @jakirkham, James Lamb (@jameslamb), José Morales (@jmoralez), James Bourbeau (@jrbourbeau), Christian Lorentzen (@lorentzenchr), Martin Petříček (@mpetricek-corp), Nikolay Petrov (@napetrov), @naveenkb, Viktor Szathmáry (@phraktle), Robin Teuwens (@rteuwens), Yuan Tang (@terrytangyuan), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), @vkuzmin-uber, Bobby Wang (@wbo4958), William Hicks (@wphicks)
-
-
 ## v1.4.2 (2021.05.13)
 This is a patch release for Python package with following fixes:
 

R-package/DESCRIPTION

@@ -1,12 +1,12 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.7.4.1
-Date: 2023-02-15
+Version: 1.5.2.1
+Date: 2022-1-17
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut"),
+  person("Tong", "He", role = c("aut", "cre"),
          email = "hetong007@gmail.com"),
   person("Michael", "Benesty", role = c("aut"),
          email = "michael@benesty.fr"),
@@ -26,12 +26,9 @@ Authors@R: c(
   person("Min", "Lin", role = c("aut")),
   person("Yifeng", "Geng", role = c("aut")),
   person("Yutian", "Li", role = c("aut")),
-  person("Jiaming", "Yuan", role = c("aut", "cre"),
-         email = "jm.yuan@outlook.com"),
   person("XGBoost contributors", role = c("cph"),
          comment = "base XGBoost implementation")
   )
-Maintainer: Jiaming Yuan <jm.yuan@outlook.com>
 Description: Extreme Gradient Boosting, which is an efficient implementation
     of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
     This package is its R interface. The package includes efficient linear
@@ -66,5 +63,5 @@ Imports:
     methods,
     data.table (>= 1.9.6),
     jsonlite (>= 1.0),
-RoxygenNote: 7.2.2
+RoxygenNote: 7.1.1
 SystemRequirements: GNU make, C++14

R-package/R/callbacks.R

@@ -544,11 +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}}.
@@ -560,7 +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
@@ -585,14 +583,14 @@ 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$Species) - 1, nthread = 2)
+#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
 #' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
 #'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For the default linear updater 'shotgun' it sometimes is helpful

R-package/R/xgb.Booster.R

@@ -162,11 +162,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' Predicted values based on either xgboost model or model handle object.
 #'
 #' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}
-#' @param newdata takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-#'        local data file or \code{xgb.DMatrix}.
-#'
-#'        For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-#'        a sparse vector, it will take it as a row vector.
+#' @param newdata takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.
 #' @param missing Missing is only used when input is dense matrix. Pick a float value that represents
 #'        missing values in data (e.g., sometimes 0 or some other extreme value is used).
 #' @param outputmargin whether the prediction should be returned in the for of original untransformed
@@ -184,7 +180,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #'        training predicting will perform dropout.
 #' @param iterationrange Specifies which layer of trees are used in prediction.  For
 #'        example, if a random forest is trained with 100 rounds.  Specifying
-#'        `iterationrange=(1, 21)`, then only the forests built during [1, 21) (half open set)
+#'        `iteration_range=(1, 21)`, then only the forests built during [1, 21) (half open set)
 #'        rounds are used in this prediction.  It's 1-based index just like R vector.  When set
 #'        to \code{c(1, 1)} XGBoost will use all trees.
 #' @param strict_shape  Default is \code{FALSE}. When it's set to \code{TRUE}, output
@@ -328,9 +324,8 @@ 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)))

R-package/R/xgb.DMatrix.R

@@ -4,10 +4,8 @@
 #' Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
 #' \code{\link{xgb.DMatrix.save}}).
 #'
-#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-#'        a \code{dgRMatrix} object (only when making predictions from a fitted model),
-#'        a \code{dsparseVector} object (only when making predictions from a fitted model, will be
-#'        interpreted as a row vector), or a character string representing a filename.
+#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
+#'        string representing a filename.
 #' @param info a named list of additional information to store in the \code{xgb.DMatrix} object.
 #'        See \code{\link{setinfo}} for the specific allowed kinds of
 #' @param missing a float value to represents missing values in data (used only when input is a dense matrix).
@@ -18,7 +16,7 @@
 #'
 #' @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')
@@ -35,29 +33,13 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthre
     handle <- .Call(XGDMatrixCreateFromMat_R, data, missing, as.integer(NVL(nthread, -1)))
     cnames <- colnames(data)
   } else if (inherits(data, "dgCMatrix")) {
-    handle <- .Call(
-      XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data), as.integer(NVL(nthread, -1))
-    )
+    handle <- .Call(XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data))
     cnames <- colnames(data)
-  } else if (inherits(data, "dgRMatrix")) {
-    handle <- .Call(
-      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), 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)) {
@@ -110,7 +92,7 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nth
 #' @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))
@@ -138,7 +120,7 @@ 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))
@@ -147,9 +129,7 @@ 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
@@ -160,13 +140,13 @@ 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
 }
 
@@ -193,7 +173,7 @@ 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)
@@ -208,17 +188,13 @@ 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)
@@ -249,7 +225,7 @@ 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)
@@ -296,37 +272,6 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
     .Call(XGDMatrixSetInfo_R, object, name, as.integer(info))
     return(TRUE)
   }
-  if (name == "feature_weights") {
-    if (length(info) != ncol(object)) {
-      stop("The number of feature weights must equal to the number of columns in the input data")
-    }
-    .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)
 }
@@ -345,7 +290,7 @@ 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')
@@ -401,7 +346,7 @@ 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)

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

@@ -18,7 +18,7 @@
 #'
 #' International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
 #'
-#' \url{https://research.facebook.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+#' \url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
 #'
 #' Extract explaining the method:
 #'
@@ -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

@@ -110,9 +110,9 @@
 #'
 #' @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)
 #'
@@ -192,7 +192,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # create the booster-folds
   # train_folds
-  dall <- xgb.get.DMatrix(data, label, missing, 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

R-package/R/xgb.dump.R

@@ -6,6 +6,8 @@
 #' @param fname the name of the text file where to save the model text dump.
 #'        If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.
 #' @param fmap feature map file representing feature types.
+#'        Detailed description could be found at
+#'        \url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
 #'        See demo/ for walkthrough example in R, and
 #'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
 #'        for example Format.

R-package/R/xgb.load.R

@@ -5,7 +5,7 @@
 #' @param modelfile the name of the binary input file.
 #'
 #' @details
-#' The input file is expected to contain a model saved in an xgboost model format
+#' The input file is expected to contain a model saved in an xgboost-internal binary format
 #' using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
 #' appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 #' saved from there in xgboost format, could be loaded from R.
@@ -38,13 +38,6 @@ xgb.load <- function(modelfile) {
   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(
-      paste(
-        "The support for loading raw booster with `xgb.load` will be ",
-        "discontinued in upcoming release. Use `xgb.load.raw` or",
-        " `xgb.unserialize` instead. "
-      )
-    )
     bst <- xgb.handleToBooster(handle, modelfile)
   } else {
     bst <- xgb.handleToBooster(handle, NULL)

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

@@ -3,21 +3,12 @@
 #' User can generate raw memory buffer by calling xgb.save.raw
 #'
 #' @param buffer the buffer returned by xgb.save.raw
-#' @param as_booster Return the loaded model as xgb.Booster instead of xgb.Booster.handle.
 #'
 #' @export
-xgb.load.raw <- function(buffer, as_booster = FALSE) {
+xgb.load.raw <- function(buffer) {
   cachelist <- list()
   handle <- .Call(XGBoosterCreate_R, cachelist)
   .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
   class(handle) <- "xgb.Booster.handle"
-
-  if (as_booster) {
-    booster <- list(handle = handle, raw = NULL)
-    class(booster) <- "xgb.Booster"
-    booster <- xgb.Booster.complete(booster, saveraw = TRUE)
-    return(booster)
-  } else {
-    return (handle)
-  }
+  return (handle)
 }

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

@@ -87,7 +87,7 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   }
 
   if (length(text) < 2 ||
-      sum(grepl('leaf=(\\d+)', text)) < 1) {
+      sum(grepl('yes=(\\d+),no=(\\d+)', text)) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
 
@@ -116,28 +116,16 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
                       "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
-  td[
-    isLeaf == FALSE,
-    (branch_cols) := {
-      matches <- regmatches(t, regexec(branch_rx, t))
-      # skip some indices with spurious capture groups from anynumber_regex
-      xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
-      xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-      if (length(xtr) == 0) {
-        as.data.table(
-          list(Feature = "NA", Split = "NA", Yes = "NA", No = "NA", Missing = "NA", Quality = "NA", Cover = "NA")
-        )
-      } else {
-        as.data.table(xtr)
-      }
-    }
-  ]
-
+  td[isLeaf == FALSE,
+     (branch_cols) := {
+       matches <- regmatches(t, regexec(branch_rx, t))
+       # skip some indices with spurious capture groups from anynumber_regex
+       xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
+       xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
+       as.data.table(xtr)
+    }]
   # assign feature_names when available
-  is_stump <- function() {
-    return(length(td$Feature) == 1 && is.na(td$Feature))
-  }
-  if (!is.null(feature_names) && !is_stump()) {
+  if (!is.null(feature_names)) {
     if (length(feature_names) <= max(as.numeric(td$Feature), na.rm = TRUE))
       stop("feature_names has less elements than there are features used in the model")
     td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1]]
@@ -146,18 +134,12 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   # parse leaf lines
   leaf_rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   leaf_cols <- c("Feature", "Quality", "Cover")
-  td[
-    isLeaf == TRUE,
-    (leaf_cols) := {
-      matches <- regmatches(t, regexec(leaf_rx, t))
-      xtr <- do.call(rbind, matches)[, c(2, 4)]
-      if (length(xtr) == 2) {
-        c("Leaf", as.data.table(xtr[1]), as.data.table(xtr[2]))
-      } else {
-        c("Leaf", as.data.table(xtr))
-      }
-    }
-  ]
+  td[isLeaf == TRUE,
+     (leaf_cols) := {
+       matches <- regmatches(t, regexec(leaf_rx, t))
+       xtr <- do.call(rbind, matches)[, c(2, 4)]
+       c("Leaf", as.data.table(xtr))
+    }]
 
   # convert some columns to numeric
   numeric_cols <- c("Split", "Quality", "Cover")

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

@@ -62,9 +62,6 @@
 #' @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")
-  }
   check.deprecation(...)
   tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
 

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

@@ -98,22 +98,18 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
     data      = dt$Feature,
     fontcolor = "black")
 
-  if (nrow(dt[Feature != "Leaf"]) != 0) {
-    edges <- DiagrammeR::create_edge_df(
-      from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
-      to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-      label = c(
-        dt[Feature != "Leaf", paste("<", Split)],
-        rep("", nrow(dt[Feature != "Leaf"]))
-      ),
-      style = c(
-        dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
-        dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
-      ),
-      rel   = "leading_to")
-  } else {
-    edges <- NULL
-  }
+  edges <- DiagrammeR::create_edge_df(
+    from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
+    to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
+    label = c(
+      dt[Feature != "Leaf", paste("<", Split)],
+      rep("", nrow(dt[Feature != "Leaf"]))
+    ),
+    style = c(
+      dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
+      dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
+    ),
+    rel   = "leading_to")
 
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,

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

@@ -4,14 +4,6 @@
 #' Save xgboost model from xgboost or xgb.train
 #'
 #' @param model the model object.
-#' @param raw_format The format for encoding the booster.  Available options are
-#' \itemize{
-#'     \item \code{json}: Encode the booster into JSON text document.
-#'     \item \code{ubj}:  Encode the booster into Universal Binary JSON.
-#'     \item \code{deprecated}: Encode the booster into old customized binary format.
-#' }
-#'
-#' Right now the default is \code{deprecated} but will be changed to \code{ubj} in upcoming release.
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
@@ -25,8 +17,7 @@
 #' pred <- predict(bst, test$data)
 #'
 #' @export
-xgb.save.raw <- function(model, raw_format = "deprecated") {
+xgb.save.raw <- function(model) {
   handle <- xgb.get.handle(model)
-  args <- list(format = raw_format)
-  .Call(XGBoosterSaveModelToRaw_R, handle, jsonlite::toJSON(args, auto_unbox = TRUE))
+  .Call(XGBoosterModelToRaw_R, handle)
 }

R-package/R/xgb.train.R

@@ -192,8 +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:

R-package/configure.ac

@@ -2,25 +2,10 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[1.7.4],[],[xgboost],[])
+AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
-: ${R_HOME=`R RHOME`}
-if test -z "${R_HOME}"; then
-  echo "could not determine R_HOME"
-  exit 1
-fi
-
-CXX14=`"${R_HOME}/bin/R" CMD config CXX14`
-CXX14STD=`"${R_HOME}/bin/R" CMD config CXX14STD`
-CXX="${CXX14} ${CXX14STD}"
-CXXFLAGS=`"${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 ${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/basic_walkthrough.R

@@ -63,7 +63,7 @@ print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
 # save model to R's raw vector
 raw <- xgb.save.raw(bst)
 # load binary model to R
-bst3 <- xgb.load.raw(raw)
+bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
 print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))

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
@@ -65,14 +63,14 @@ 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$Species) - 1, nthread = 2)
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
 param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For the default linear updater 'shotgun' it sometimes is helpful

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/predict.xgb.Booster.Rd

@@ -27,11 +27,7 @@
 \arguments{
 \item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
 
-\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-       local data file or \code{xgb.DMatrix}.
-
-       For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-       a sparse vector, it will take it as a row vector.}
+\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.}
 
 \item{missing}{Missing is only used when input is dense matrix. Pick a float value that represents
 missing values in data (e.g., sometimes 0 or some other extreme value is used).}
@@ -59,7 +55,7 @@ training predicting will perform dropout.}
 
 \item{iterationrange}{Specifies which layer of trees are used in prediction.  For
 example, if a random forest is trained with 100 rounds.  Specifying
-`iterationrange=(1, 21)`, then only the forests built during [1, 21) (half open set)
+`iteration_range=(1, 21)`, then only the forests built during [1, 21) (half open set)
 rounds are used in this prediction.  It's 1-based index just like R vector.  When set
 to \code{c(1, 1)} XGBoost will use all trees.}
 

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

@@ -14,10 +14,8 @@ xgb.DMatrix(
 )
 }
 \arguments{
-\item{data}{a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-a \code{dgRMatrix} object (only when making predictions from a fitted model),
-a \code{dsparseVector} object (only when making predictions from a fitted model, will be
-interpreted as a row vector), or a character string representing a filename.}
+\item{data}{a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
+string representing a filename.}
 
 \item{info}{a named list of additional information to store in the \code{xgb.DMatrix} object.
 See \code{\link{setinfo}} for the specific allowed kinds of}
@@ -38,7 +36,7 @@ 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

@@ -29,7 +29,7 @@ Joaquin Quinonero Candela)}
 
 International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
 
-\url{https://research.facebook.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+\url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
 
 Extract explaining the method:
 
@@ -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

@@ -158,9 +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.dump.Rd

@@ -20,6 +20,8 @@ xgb.dump(
 If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.}
 
 \item{fmap}{feature map file representing feature types.
+Detailed description could be found at
+\url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
 See demo/ for walkthrough example in R, and
 \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
 for example Format.}

R-package/man/xgb.load.Rd

@@ -16,7 +16,7 @@ An object of \code{xgb.Booster} class.
 Load xgboost model from the binary model file.
 }
 \details{
-The input file is expected to contain a model saved in an xgboost model format
+The input file is expected to contain a model saved in an xgboost-internal binary format
 using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
 appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 saved from there in xgboost format, could be loaded from R.

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

@@ -4,12 +4,10 @@
 \alias{xgb.load.raw}
 \title{Load serialised xgboost model from R's raw vector}
 \usage{
-xgb.load.raw(buffer, as_booster = FALSE)
+xgb.load.raw(buffer)
 }
 \arguments{
 \item{buffer}{the buffer returned by xgb.save.raw}
-
-\item{as_booster}{Return the loaded model as xgb.Booster instead of xgb.Booster.handle.}
 }
 \description{
 User can generate raw memory buffer by calling xgb.save.raw

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

@@ -5,19 +5,10 @@
 \title{Save xgboost model to R's raw vector,
 user can call xgb.load.raw to load the model back from raw vector}
 \usage{
-xgb.save.raw(model, raw_format = "deprecated")
+xgb.save.raw(model)
 }
 \arguments{
 \item{model}{the model object.}
-
-\item{raw_format}{The format for encoding the booster.  Available options are
-\itemize{
-    \item \code{json}: Encode the booster into JSON text document.
-    \item \code{ubj}:  Encode the booster into Universal Binary JSON.
-    \item \code{deprecated}: Encode the booster into old customized binary format.
-}
-
-Right now the default is \code{deprecated} but will be changed to \code{ubj} in upcoming release.}
 }
 \description{
 Save xgboost model from xgboost or xgb.train

R-package/man/xgb.train.Rd

@@ -241,8 +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

@@ -19,77 +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/rank_obj.o \
-    $(PKGROOT)/src/objective/hinge.o \
-    $(PKGROOT)/src/objective/aft_obj.o \
-    $(PKGROOT)/src/objective/adaptive.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/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/tree/constraints.o \
-    $(PKGROOT)/src/tree/param.o \
-    $(PKGROOT)/src/tree/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/linear/linear_updater.o \
-    $(PKGROOT)/src/linear/updater_coordinate.o \
-    $(PKGROOT)/src/linear/updater_shotgun.o \
-    $(PKGROOT)/src/learner.o \
-    $(PKGROOT)/src/logging.o \
-    $(PKGROOT)/src/global_config.o \
-    $(PKGROOT)/src/collective/communicator.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/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/survival_util.o \
-    $(PKGROOT)/src/common/threading_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

@@ -1,8 +1,20 @@
 # package root
-PKGROOT=../../
+PKGROOT=./
 ENABLE_STD_THREAD=0
 # _*_ mode: Makefile; _*_
 
+# 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\
@@ -17,79 +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/rank_obj.o \
-    $(PKGROOT)/src/objective/hinge.o \
-    $(PKGROOT)/src/objective/aft_obj.o \
-    $(PKGROOT)/src/objective/adaptive.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/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/tree/constraints.o \
-    $(PKGROOT)/src/tree/param.o \
-    $(PKGROOT)/src/tree/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/linear/linear_updater.o \
-    $(PKGROOT)/src/linear/updater_coordinate.o \
-    $(PKGROOT)/src/linear/updater_shotgun.o \
-    $(PKGROOT)/src/learner.o \
-    $(PKGROOT)/src/logging.o \
-    $(PKGROOT)/src/global_config.o \
-    $(PKGROOT)/src/collective/communicator.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/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/survival_util.o \
-    $(PKGROOT)/src/common/threading_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

@@ -24,12 +24,12 @@ extern SEXP XGBoosterEvalOneIter_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterGetAttrNames_R(SEXP);
 extern SEXP XGBoosterGetAttr_R(SEXP, SEXP);
 extern SEXP XGBoosterLoadModelFromRaw_R(SEXP, SEXP);
-extern SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP config);
 extern SEXP XGBoosterLoadModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSaveJsonConfig_R(SEXP handle);
 extern SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value);
 extern SEXP XGBoosterSerializeToBuffer_R(SEXP handle);
 extern SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw);
+extern SEXP XGBoosterModelToRaw_R(SEXP);
 extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterPredictFromDMatrix_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSaveModel_R(SEXP, SEXP);
@@ -37,20 +37,17 @@ 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);
-extern SEXP XGDMatrixCreateFromCSR_R(SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSC_R(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[] = {
@@ -62,12 +59,12 @@ static const R_CallMethodDef CallEntries[] = {
   {"XGBoosterGetAttrNames_R",     (DL_FUNC) &XGBoosterGetAttrNames_R,     1},
   {"XGBoosterGetAttr_R",          (DL_FUNC) &XGBoosterGetAttr_R,          2},
   {"XGBoosterLoadModelFromRaw_R", (DL_FUNC) &XGBoosterLoadModelFromRaw_R, 2},
-  {"XGBoosterSaveModelToRaw_R",   (DL_FUNC) &XGBoosterSaveModelToRaw_R,   2},
   {"XGBoosterLoadModel_R",        (DL_FUNC) &XGBoosterLoadModel_R,        2},
   {"XGBoosterSaveJsonConfig_R",   (DL_FUNC) &XGBoosterSaveJsonConfig_R,   1},
   {"XGBoosterLoadJsonConfig_R",   (DL_FUNC) &XGBoosterLoadJsonConfig_R,   2},
   {"XGBoosterSerializeToBuffer_R",     (DL_FUNC) &XGBoosterSerializeToBuffer_R,     1},
   {"XGBoosterUnserializeFromBuffer_R", (DL_FUNC) &XGBoosterUnserializeFromBuffer_R, 2},
+  {"XGBoosterModelToRaw_R",       (DL_FUNC) &XGBoosterModelToRaw_R,       1},
   {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          5},
   {"XGBoosterPredictFromDMatrix_R", (DL_FUNC) &XGBoosterPredictFromDMatrix_R, 3},
   {"XGBoosterSaveModel_R",        (DL_FUNC) &XGBoosterSaveModel_R,        2},
@@ -75,17 +72,14 @@ static const R_CallMethodDef CallEntries[] = {
   {"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,    5},
-  {"XGDMatrixCreateFromCSR_R",    (DL_FUNC) &XGDMatrixCreateFromCSR_R,    5},
+  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    4},
   {"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

@@ -1,23 +1,16 @@
-/**
- * Copyright 2014-2022 by XGBoost Contributors
- */
-#include <dmlc/common.h>
+// Copyright (c) 2014 by Contributors
+#include <dmlc/logging.h>
 #include <dmlc/omp.h>
+#include <dmlc/common.h>
 #include <xgboost/c_api.h>
-#include <xgboost/data.h>
-#include <xgboost/generic_parameters.h>
-#include <xgboost/logging.h>
-
-#include <cstdio>
-#include <cstring>
-#include <sstream>
+#include <vector>
 #include <string>
 #include <utility>
-#include <vector>
+#include <cstring>
+#include <cstdio>
+#include <sstream>
 
-#include "../../src/c_api/c_api_error.h"
 #include "../../src/common/threading_utils.h"
-
 #include "./xgboost_R.h"
 
 /*!
@@ -44,21 +37,8 @@
     error(XGBGetLastError());                   \
   }
 
-using dmlc::BeginPtr;
 
-xgboost::GenericParameter const *BoosterCtx(BoosterHandle handle) {
-  CHECK_HANDLE();
-  auto *learner = static_cast<xgboost::Learner *>(handle);
-  CHECK(learner);
-  return learner->Ctx();
-}
-
-xgboost::GenericParameter const *DMatrixCtx(DMatrixHandle handle) {
-  CHECK_HANDLE();
-  auto p_m = static_cast<std::shared_ptr<xgboost::DMatrix> *>(handle);
-  CHECK(p_m);
-  return p_m->get()->Ctx();
-}
+using namespace dmlc;
 
 XGB_DLL SEXP XGCheckNullPtr_R(SEXP handle) {
   return ScalarLogical(R_ExternalPtrAddr(handle) == NULL);
@@ -114,13 +94,18 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
     din = REAL(mat);
   }
   std::vector<float> data(nrow * ncol);
+  dmlc::OMPException exc;
   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];
-    }
-  });
+#pragma omp parallel for schedule(static) num_threads(threads)
+  for (omp_ulong i = 0; i < nrow; ++i) {
+    exc.Run([&]() {
+      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];
+      }
+    });
+  }
+  exc.Rethrow();
   DMatrixHandle handle;
   CHECK_CALL(XGDMatrixCreateFromMat_omp(BeginPtr(data), nrow, ncol,
                                         asReal(missing), &handle, threads));
@@ -132,7 +117,7 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
 }
 
 XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
-                                      SEXP num_row, SEXP n_threads) {
+                                      SEXP num_row) {
   SEXP ret;
   R_API_BEGIN();
   const int *p_indptr = INTEGER(indptr);
@@ -148,11 +133,15 @@ XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
   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]);
-  });
+  dmlc::OMPException exc;
+  #pragma omp parallel for schedule(static)
+  for (int64_t i = 0; i < static_cast<int64_t>(ndata); ++i) {
+    exc.Run([&]() {
+      indices_[i] = static_cast<unsigned>(p_indices[i]);
+      data_[i] = static_cast<float>(p_data[i]);
+    });
+  }
+  exc.Rethrow();
   DMatrixHandle handle;
   CHECK_CALL(XGDMatrixCreateFromCSCEx(BeginPtr(col_ptr_), BeginPtr(indices_),
                                       BeginPtr(data_), nindptr, ndata,
@@ -164,39 +153,6 @@ XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data,
-                                      SEXP num_col, 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 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;
-  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);
-  return ret;
-}
-
 XGB_DLL SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
   SEXP ret;
   R_API_BEGIN();
@@ -230,64 +186,34 @@ XGB_DLL SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
   R_API_BEGIN();
   int len = length(array);
   const char *name = CHAR(asChar(field));
-  auto ctx = DMatrixCtx(R_ExternalPtrAddr(handle));
+  dmlc::OMPException exc;
   if (!strcmp("group", name)) {
     std::vector<unsigned> vec(len);
-    xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
-      vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
-    });
-    CHECK_CALL(
-        XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
+    #pragma omp parallel for schedule(static)
+    for (int i = 0; i < len; ++i) {
+      exc.Run([&]() {
+        vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
+      });
+    }
+    exc.Rethrow();
+    CHECK_CALL(XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle),
+                                    CHAR(asChar(field)),
+                                    BeginPtr(vec), len));
   } else {
     std::vector<float> vec(len);
-    xgboost::common::ParallelFor(len, ctx->Threads(),
-                                 [&](xgboost::omp_ulong i) { vec[i] = REAL(array)[i]; });
-    CHECK_CALL(
-        XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
-  }
-  R_API_END();
-  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]));
+    #pragma omp parallel for schedule(static)
+    for (int i = 0; i < len; ++i) {
+      exc.Run([&]() {
+        vec[i] = REAL(array)[i];
+      });
     }
-  } else {
-    ret = PROTECT(R_NilValue);
+    exc.Rethrow();
+    CHECK_CALL(XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle),
+                                     CHAR(asChar(field)),
+                                     BeginPtr(vec), len));
   }
   R_API_END();
-  UNPROTECT(1);
-  return ret;
+  return R_NilValue;
 }
 
 XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
@@ -295,7 +221,10 @@ XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   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];
@@ -384,11 +313,15 @@ XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP h
       << "gradient and hess must have same length";
   int len = length(grad);
   std::vector<float> tgrad(len), thess(len);
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong j) {
-    tgrad[j] = REAL(grad)[j];
-    thess[j] = REAL(hess)[j];
-  });
+  dmlc::OMPException exc;
+  #pragma omp parallel for schedule(static)
+  for (int j = 0; j < len; ++j) {
+    exc.Run([&]() {
+      tgrad[j] = REAL(grad)[j];
+      thess[j] = REAL(hess)[j];
+    });
+  }
+  exc.Rethrow();
   CHECK_CALL(XGBoosterBoostOneIter(R_ExternalPtrAddr(handle),
                                  R_ExternalPtrAddr(dtrain),
                                  BeginPtr(tgrad), BeginPtr(thess),
@@ -465,10 +398,11 @@ XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_con
     len *= out_shape[i];
   }
   r_out_result = PROTECT(allocVector(REALSXP, len));
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
+
+#pragma omp parallel for
+  for (omp_ulong i = 0; i < len; ++i) {
     REAL(r_out_result)[i] = out_result[i];
-  });
+  }
 
   r_out = PROTECT(allocVector(VECSXP, 2));
 
@@ -495,6 +429,21 @@ XGB_DLL SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
   return R_NilValue;
 }
 
+XGB_DLL SEXP XGBoosterModelToRaw_R(SEXP handle) {
+  SEXP ret;
+  R_API_BEGIN();
+  bst_ulong olen;
+  const char *raw;
+  CHECK_CALL(XGBoosterGetModelRaw(R_ExternalPtrAddr(handle), &olen, &raw));
+  ret = PROTECT(allocVector(RAWSXP, olen));
+  if (olen != 0) {
+    memcpy(RAW(ret), raw, olen);
+  }
+  R_API_END();
+  UNPROTECT(1);
+  return ret;
+}
+
 XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadModelFromBuffer(R_ExternalPtrAddr(handle),
@@ -504,22 +453,6 @@ XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP json_config) {
-  SEXP ret;
-  R_API_BEGIN();
-  bst_ulong olen;
-  char const *c_json_config = CHAR(asChar(json_config));
-  char const *raw;
-  CHECK_CALL(XGBoosterSaveModelToBuffer(R_ExternalPtrAddr(handle), c_json_config, &olen, &raw))
-  ret = PROTECT(allocVector(RAWSXP, olen));
-  if (olen != 0) {
-    std::memcpy(RAW(ret), raw, olen);
-  }
-  R_API_END();
-  UNPROTECT(1);
-  return ret;
-}
-
 XGB_DLL SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
   const char* ret;
   R_API_BEGIN();
@@ -666,6 +599,7 @@ XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config) {
   CHECK_CALL(XGBoosterFeatureScore(R_ExternalPtrAddr(handle), c_json_config,
                                    &out_n_features, &out_features,
                                    &out_dim, &out_shape, &out_scores));
+
   out_shape_sexp = PROTECT(allocVector(INTSXP, out_dim));
   size_t len = 1;
   for (size_t i = 0; i < out_dim; ++i) {
@@ -674,10 +608,10 @@ XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config) {
   }
 
   out_scores_sexp = PROTECT(allocVector(REALSXP, len));
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
+#pragma omp parallel for
+  for (omp_ulong i = 0; i < len; ++i) {
     REAL(out_scores_sexp)[i] = out_scores[i];
-  });
+  }
 
   out_features_sexp = PROTECT(allocVector(STRSXP, out_n_features));
   for (size_t i = 0; i < out_n_features; ++i) {

R-package/src/xgboost_R.h

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2014-2022 by XGBoost Contributors
+ * Copyright 2014 (c) by Contributors
  * \file xgboost_R.h
  * \author Tianqi Chen
  * \brief R wrapper of xgboost
@@ -59,23 +59,12 @@ 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 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 n_threads);
-
-/*!
- * \brief create a matrix content from CSR format
- * \param indptr pointer to row headers
- * \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 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 n_threads);
+XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
+                                      SEXP indices,
+                                      SEXP data,
+                                      SEXP num_row);
 
 /*!
  * \brief create a new dmatrix from sliced content of existing matrix
@@ -220,21 +209,11 @@ XGB_DLL SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname);
 XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw);
 
 /*!
- * \brief Save model into R's raw array
- *
+ * \brief save model into R's raw array
  * \param handle handle
- * \param json_config JSON encoded string storing parameters for the function.  Following
- *                    keys are expected in the JSON document:
- *
- *     "format": str
- *       - json: Output booster will be encoded as JSON.
- *       - ubj:  Output booster will be encoded as Univeral binary JSON.
- *       - deprecated: Output booster will be encoded as old custom binary format.  Do now use
- *         this format except for compatibility reasons.
- *
- * \return Raw array
+ * \return raw array
  */
-XGB_DLL SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP json_config);
+XGB_DLL SEXP XGBoosterModelToRaw_R(SEXP handle);
 
 /*!
  * \brief Save internal parameters as a JSON string

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/tests/helper_scripts/run_lint.R

@@ -13,7 +13,7 @@ my_linters <- list(
   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(semicolon = c("compound", "trailing")),
+  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,

R-package/tests/testthat/test_basic.R

@@ -1,5 +1,4 @@
 require(xgboost)
-library(Matrix)
 
 context("basic functions")
 
@@ -460,18 +459,3 @@ test_that("strict_shape works", {
   test_iris()
   test_agaricus()
 })
-
-test_that("'predict' accepts CSR data", {
-  X <- agaricus.train$data
-  y <- agaricus.train$label
-  x_csc <- as(X[1L, , drop = FALSE], "CsparseMatrix")
-  x_csr <- as(x_csc, "RsparseMatrix")
-  x_spv <- as(x_csc, "sparseVector")
-  bst <- xgboost(data = X, label = y, objective = "binary:logistic",
-                 nrounds = 5L, verbose = FALSE)
-  p_csc <- predict(bst, x_csc)
-  p_csr <- predict(bst, x_csr)
-  p_spv <- predict(bst, x_spv)
-  expect_equal(p_csc, p_csr)
-  expect_equal(p_csc, p_spv)
-})

R-package/tests/testthat/test_dmatrix.R

@@ -27,7 +27,6 @@ test_that("xgb.DMatrix: saving, loading", {
   # save to a local file
   dtest1 <- xgb.DMatrix(test_data, label = test_label)
   tmp_file <- tempfile('xgb.DMatrix_')
-  on.exit(unlink(tmp_file))
   expect_true(xgb.DMatrix.save(dtest1, tmp_file))
   # read from a local file
   expect_output(dtest3 <- xgb.DMatrix(tmp_file), "entries loaded from")
@@ -42,20 +41,7 @@ test_that("xgb.DMatrix: saving, loading", {
   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"))
+  unlink(tmp_file)
 })
 
 test_that("xgb.DMatrix: getinfo & setinfo", {

R-package/tests/testthat/test_feature_weights.R

@@ -1,27 +0,0 @@
-library(xgboost)
-
-context("feature weights")
-
-test_that("training with feature weights works", {
-  nrows <- 1000
-  ncols <- 9
-  set.seed(2022)
-  x <- matrix(rnorm(nrows * ncols), nrow = nrows)
-  y <- rowSums(x)
-  weights <- seq(from = 1, to = ncols)
-
-  test <- function(tm) {
-    names <- paste0("f", 1:ncols)
-    xy <- xgb.DMatrix(data = x, label = y, feature_weights = weights)
-    params <- list(colsample_bynode = 0.4, tree_method = tm, nthread = 1)
-    model <- xgb.train(params = params, data = xy, nrounds = 32)
-    importance <- xgb.importance(model = model, feature_names = names)
-    expect_equal(dim(importance), c(ncols, 4))
-    importance <- importance[order(importance$Feature)]
-    expect_lt(importance[1, Frequency], importance[9, Frequency])
-  }
-
-  for (tm in c("hist", "approx", "exact")) {
-    test(tm)
-  }
-})

R-package/tests/testthat/test_helpers.R

@@ -340,16 +340,6 @@ test_that("xgb.importance works with and without feature names", {
     imp
   }
   expect_equal(importance_from_dump(), importance, tolerance = 1e-6)
-
-  ## decision stump
-  m <- xgboost::xgboost(
-    data = as.matrix(data.frame(x = c(0, 1))),
-    label = c(1, 2),
-    nrounds = 1
-  )
-  df <- xgb.model.dt.tree(model = m)
-  expect_equal(df$Feature, "Leaf")
-  expect_equal(df$Cover, 2)
 })
 
 test_that("xgb.importance works with GLM model", {

R-package/tests/testthat/test_io.R

@@ -1,30 +0,0 @@
-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")
-train <- agaricus.train
-test <- agaricus.test
-
-test_that("load/save raw works", {
-  nrounds <- 8
-  booster <- xgboost(
-    data = train$data, label = train$label,
-    nrounds = nrounds, objective = "binary:logistic"
-  )
-
-  json_bytes <- xgb.save.raw(booster, raw_format = "json")
-  ubj_bytes <- xgb.save.raw(booster, raw_format = "ubj")
-  old_bytes <- xgb.save.raw(booster, raw_format = "deprecated")
-
-  from_json <- xgb.load.raw(json_bytes, as_booster = TRUE)
-  from_ubj <- xgb.load.raw(ubj_bytes, as_booster = TRUE)
-
-  json2old <- xgb.save.raw(from_json, raw_format = "deprecated")
-  ubj2old <- xgb.save.raw(from_ubj, raw_format = "deprecated")
-
-  expect_equal(json2old, ubj2old)
-  expect_equal(json2old, old_bytes)
-})

R-package/tests/testthat/test_model_compatibility.R

@@ -77,7 +77,6 @@ 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')
 
     cpp_warning <- capture.output({
       # Expect an R warning when a model is loaded from RDS and it was generated by version < 1.1.x
@@ -96,13 +95,15 @@ test_that("Models from previous versions of XGBoost can be loaded", {
         run_booster_check(booster, name)
       }
     })
-    cpp_warning <- paste0(cpp_warning, collapse = ' ')
-    if (is_rds && compareVersion(model_xgb_ver, '1.1.1.1') >= 0) {
-      # Expect a C++ warning when a model is loaded from RDS and it was generated by old XGBoost`
-      m <- grepl(paste0('.*If you are loading a serialized model ',
-                        '\\(like pickle in Python, RDS in R\\).*',
-                        'for more details about differences between ',
-                        'saving model and serializing.*'), cpp_warning, perl = TRUE)
+    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/vignettes/discoverYourData.Rmd

@@ -138,7 +138,7 @@ levels(df[,Treatment])
 
 Next step, we will transform the categorical data to dummy variables.
 Several encoding methods exist, e.g., [one-hot encoding](https://en.wikipedia.org/wiki/One-hot) is a common approach.
-We will use the [dummy contrast coding](https://stats.oarc.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/) which is popular because it produces "full rank" encoding (also see [this blog post by Max Kuhn](http://appliedpredictivemodeling.com/blog/2013/10/23/the-basics-of-encoding-categorical-data-for-predictive-models)).
+We will use the [dummy contrast coding](https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/) which is popular because it produces "full rank" encoding (also see [this blog post by Max Kuhn](http://appliedpredictivemodeling.com/blog/2013/10/23/the-basics-of-encoding-categorical-data-for-predictive-models)).
 
 The purpose is to transform each value of each *categorical* feature into a *binary* feature `{0, 1}`.
 

README.md

@@ -10,7 +10,6 @@
 [![Conda version](https://img.shields.io/conda/vn/conda-forge/py-xgboost.svg)](https://anaconda.org/conda-forge/py-xgboost)
 [![Optuna](https://img.shields.io/badge/Optuna-integrated-blue)](https://optuna.org)
 [![Twitter](https://img.shields.io/badge/@XGBoostProject--_.svg?style=social&logo=twitter)](https://twitter.com/XGBoostProject)
-[![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/dmlc/xgboost/badge)](https://api.securityscorecards.dev/projects/github.com/dmlc/xgboost)
 
 [Community](https://xgboost.ai/community) |
 [Documentation](https://xgboost.readthedocs.org) |
@@ -47,11 +46,24 @@ Become a sponsor and get a logo here. See details at [Sponsoring the XGBoost Pro
 ### Sponsors
 [[Become a sponsor](https://opencollective.com/xgboost#sponsor)]
 
+<!--<a href="https://opencollective.com/xgboost/sponsor/0/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/0/avatar.svg"></a>-->
 <a href="https://www.nvidia.com/en-us/" target="_blank"><img src="https://raw.githubusercontent.com/xgboost-ai/xgboost-ai.github.io/master/images/sponsors/nvidia.jpg" alt="NVIDIA" width="72" height="72"></a>
-<a href="https://www.intel.com/" target="_blank"><img src="https://images.opencollective.com/intel-corporation/2fa85c1/logo/256.png" width="72" height="72"></a>
-<a href="https://getkoffie.com/?utm_source=opencollective&utm_medium=github&utm_campaign=xgboost" target="_blank"><img src="https://images.opencollective.com/koffielabs/f391ab8/logo/256.png" width="72" height="72"></a>
+<a href="https://opencollective.com/xgboost/sponsor/1/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/1/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/2/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/2/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/3/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/3/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/4/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/4/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/5/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/5/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/6/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/6/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/7/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/7/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/8/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/8/avatar.svg"></a>
+<a href="https://opencollective.com/xgboost/sponsor/9/website" target="_blank"><img src="https://opencollective.com/xgboost/sponsor/9/avatar.svg"></a>
 
 ### Backers
 [[Become a backer](https://opencollective.com/xgboost#backer)]
 
 <a href="https://opencollective.com/xgboost#backers" target="_blank"><img src="https://opencollective.com/xgboost/backers.svg?width=890"></a>
+
+## Other sponsors
+The sponsors in this list are donating cloud hours in lieu of cash donation.
+
+<a href="https://aws.amazon.com/" target="_blank"><img src="https://raw.githubusercontent.com/xgboost-ai/xgboost-ai.github.io/master/images/sponsors/aws.png" alt="Amazon Web Services" width="72" height="72"></a>

SECURITY.md

@@ -1,22 +0,0 @@
-# Security Policy
-
-## Supported Versions
-
-<!-- Use this section to tell people about which versions of your project are
-currently being supported with security updates. -->
-Security updates are applied only to the most recent release.
-
-## Reporting a Vulnerability
-
-<!-- Use this section to tell people how to report a vulnerability.
-
-Tell them where to go, how often they can expect to get an update on a
-reported vulnerability, what to expect if the vulnerability is accepted or
-declined, etc. -->
-
-To report a security issue, please email
-[security@xgboost-ci.net](mailto:security@xgboost-ci.net)
-with a description of the issue, the steps you took to create the issue,
-affected versions, and, if known, mitigations for the issue.
-
-All support will be made on the best effort base, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.

amalgamation/xgboost-all0.cc

@@ -0,0 +1,85 @@
+/*!
+ * Copyright 2015-2019 by Contributors.
+ * \brief XGBoost Amalgamation.
+ *  This offers an alternative way to compile the entire library from this single file.
+ *
+ *  Example usage command.
+ *  - $(CXX) -std=c++0x -fopenmp -o -shared libxgboost.so xgboost-all0.cc -ldmlc -lrabit
+ *
+ * \author Tianqi Chen.
+ */
+
+// metrics
+#include "../src/metric/metric.cc"
+#include "../src/metric/elementwise_metric.cc"
+#include "../src/metric/multiclass_metric.cc"
+#include "../src/metric/rank_metric.cc"
+#include "../src/metric/auc.cc"
+#include "../src/metric/survival_metric.cc"
+
+// objectives
+#include "../src/objective/objective.cc"
+#include "../src/objective/regression_obj.cc"
+#include "../src/objective/multiclass_obj.cc"
+#include "../src/objective/rank_obj.cc"
+#include "../src/objective/hinge.cc"
+#include "../src/objective/aft_obj.cc"
+
+// gbms
+#include "../src/gbm/gbm.cc"
+#include "../src/gbm/gbtree.cc"
+#include "../src/gbm/gbtree_model.cc"
+#include "../src/gbm/gblinear.cc"
+#include "../src/gbm/gblinear_model.cc"
+
+// data
+#include "../src/data/data.cc"
+#include "../src/data/simple_dmatrix.cc"
+#include "../src/data/sparse_page_raw_format.cc"
+#include "../src/data/ellpack_page.cc"
+#include "../src/data/gradient_index.cc"
+#include "../src/data/gradient_index_page_source.cc"
+#include "../src/data/gradient_index_format.cc"
+#include "../src/data/sparse_page_dmatrix.cc"
+#include "../src/data/proxy_dmatrix.cc"
+
+// prediction
+#include "../src/predictor/predictor.cc"
+#include "../src/predictor/cpu_predictor.cc"
+
+// trees
+#include "../src/tree/param.cc"
+#include "../src/tree/tree_model.cc"
+#include "../src/tree/tree_updater.cc"
+#include "../src/tree/updater_colmaker.cc"
+#include "../src/tree/updater_quantile_hist.cc"
+#include "../src/tree/updater_prune.cc"
+#include "../src/tree/updater_refresh.cc"
+#include "../src/tree/updater_sync.cc"
+#include "../src/tree/updater_histmaker.cc"
+#include "../src/tree/constraints.cc"
+
+// linear
+#include "../src/linear/linear_updater.cc"
+#include "../src/linear/updater_coordinate.cc"
+#include "../src/linear/updater_shotgun.cc"
+
+// global
+#include "../src/learner.cc"
+#include "../src/logging.cc"
+#include "../src/global_config.cc"
+#include "../src/common/common.cc"
+#include "../src/common/random.cc"
+#include "../src/common/charconv.cc"
+#include "../src/common/timer.cc"
+#include "../src/common/quantile.cc"
+#include "../src/common/host_device_vector.cc"
+#include "../src/common/hist_util.cc"
+#include "../src/common/json.cc"
+#include "../src/common/io.cc"
+#include "../src/common/survival_util.cc"
+#include "../src/common/version.cc"
+
+// c_api
+#include "../src/c_api/c_api.cc"
+#include "../src/c_api/c_api_error.cc"

cmake/Python_version.in

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

cmake/Utils.cmake

@@ -15,7 +15,7 @@ endfunction(auto_source_group)
 
 # Force static runtime for MSVC
 function(msvc_use_static_runtime)
-  if(MSVC AND (NOT BUILD_SHARED_LIBS) AND (NOT FORCE_SHARED_CRT))
+  if(MSVC)
       set(variables
           CMAKE_C_FLAGS_DEBUG
           CMAKE_C_FLAGS_MINSIZEREL
@@ -91,24 +91,23 @@ function(format_gencode_flags flags out)
   # Set up architecture flags
   if(NOT flags)
     if (CUDA_VERSION VERSION_GREATER_EQUAL "11.1")
-      set(flags "50;60;70;80")
+      set(flags "50;52;60;61;70;75;80;86")
     elseif (CUDA_VERSION VERSION_GREATER_EQUAL "11.0")
-      set(flags "50;60;70;80")
+      set(flags "35;50;52;60;61;70;75;80")
     elseif(CUDA_VERSION VERSION_GREATER_EQUAL "10.0")
-      set(flags "35;50;60;70")
+      set(flags "35;50;52;60;61;70;75")
     elseif(CUDA_VERSION VERSION_GREATER_EQUAL "9.0")
-      set(flags "35;50;60;70")
+      set(flags "35;50;52;60;61;70")
     else()
-      set(flags "35;50;60")
+      set(flags "35;50;52;60;61")
     endif()
   endif()
 
   if (CMAKE_VERSION VERSION_GREATER_EQUAL "3.18")
     cmake_policy(SET CMP0104 NEW)
-    list(GET flags -1 latest_arch)
-    list(TRANSFORM flags APPEND "-real")
-    list(APPEND flags ${latest_arch})
-    set(CMAKE_CUDA_ARCHITECTURES ${flags})
+    foreach(ver ${flags})
+      set(CMAKE_CUDA_ARCHITECTURES "${ver}-real;${ver}-virtual;${CMAKE_CUDA_ARCHITECTURES}")
+    endforeach()
     set(CMAKE_CUDA_ARCHITECTURES "${CMAKE_CUDA_ARCHITECTURES}" PARENT_SCOPE)
     message(STATUS "CMAKE_CUDA_ARCHITECTURES: ${CMAKE_CUDA_ARCHITECTURES}")
   else()
@@ -137,22 +136,12 @@ function(xgboost_set_cuda_flags target)
     $<$<COMPILE_LANGUAGE:CUDA>:--expt-extended-lambda>
     $<$<COMPILE_LANGUAGE:CUDA>:--expt-relaxed-constexpr>
     $<$<COMPILE_LANGUAGE:CUDA>:${GEN_CODE}>
-    $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=${OpenMP_CXX_FLAGS}>
-    $<$<COMPILE_LANGUAGE:CUDA>:-Xfatbin=-compress-all>)
+    $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=${OpenMP_CXX_FLAGS}>)
 
   if (CMAKE_VERSION VERSION_GREATER_EQUAL "3.18")
     set_property(TARGET ${target} PROPERTY CUDA_ARCHITECTURES ${CMAKE_CUDA_ARCHITECTURES})
   endif (CMAKE_VERSION VERSION_GREATER_EQUAL "3.18")
 
-  if (FORCE_COLORED_OUTPUT)
-    if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
-        ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
-          (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
-      target_compile_options(${target} PRIVATE
-        $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=-fdiagnostics-color=always>)
-    endif()
-  endif (FORCE_COLORED_OUTPUT)
-
   if (USE_DEVICE_DEBUG)
     target_compile_options(${target} PRIVATE
       $<$<AND:$<CONFIG:DEBUG>,$<COMPILE_LANGUAGE:CUDA>>:-G;-src-in-ptx>)
@@ -178,17 +167,10 @@ function(xgboost_set_cuda_flags target)
       $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=/utf-8>)
   endif (MSVC)
 
-  if (PLUGIN_RMM)
-    set_target_properties(${target} PROPERTIES
-      CUDA_STANDARD 17
-      CUDA_STANDARD_REQUIRED ON
-      CUDA_SEPARABLE_COMPILATION OFF)
-  else ()
-    set_target_properties(${target} PROPERTIES
-      CUDA_STANDARD 14
-      CUDA_STANDARD_REQUIRED ON
-      CUDA_SEPARABLE_COMPILATION OFF)
-  endif (PLUGIN_RMM)
+  set_target_properties(${target} PROPERTIES
+    CUDA_STANDARD 14
+    CUDA_STANDARD_REQUIRED ON
+    CUDA_SEPARABLE_COMPILATION OFF)
 endfunction(xgboost_set_cuda_flags)
 
 macro(xgboost_link_nccl target)
@@ -205,18 +187,10 @@ endmacro(xgboost_link_nccl)
 
 # compile options
 macro(xgboost_target_properties target)
-  if (PLUGIN_RMM)
-    set_target_properties(${target} PROPERTIES
-      CXX_STANDARD 17
-      CXX_STANDARD_REQUIRED ON
-      POSITION_INDEPENDENT_CODE ON)
-  else ()
-    set_target_properties(${target} PROPERTIES
-      CXX_STANDARD 14
-      CXX_STANDARD_REQUIRED ON
-      POSITION_INDEPENDENT_CODE ON)
-  endif (PLUGIN_RMM)
-
+  set_target_properties(${target} PROPERTIES
+    CXX_STANDARD 14
+    CXX_STANDARD_REQUIRED ON
+    POSITION_INDEPENDENT_CODE ON)
   if (HIDE_CXX_SYMBOLS)
     #-- Hide all C++ symbols
     set_target_properties(${target} PROPERTIES
@@ -228,9 +202,7 @@ macro(xgboost_target_properties target)
 
   if (ENABLE_ALL_WARNINGS)
     target_compile_options(${target} PUBLIC
-      $<IF:$<COMPILE_LANGUAGE:CUDA>,
-      -Xcompiler=-Wall -Xcompiler=-Wextra -Xcompiler=-Wno-expansion-to-defined,
-      -Wall -Wextra -Wno-expansion-to-defined>
+      $<IF:$<COMPILE_LANGUAGE:CUDA>,-Xcompiler=-Wall -Xcompiler=-Wextra,-Wall -Wextra>
     )
   endif(ENABLE_ALL_WARNINGS)
 
@@ -244,7 +216,7 @@ macro(xgboost_target_properties target)
       $<$<NOT:$<COMPILE_LANGUAGE:CUDA>>:/utf-8>
       -D_CRT_SECURE_NO_WARNINGS
       -D_CRT_SECURE_NO_DEPRECATE
-    )
+      )
   endif (MSVC)
 
   if (WIN32 AND MINGW)
@@ -273,10 +245,6 @@ macro(xgboost_target_defs target)
       PRIVATE
       -DXGBOOST_BUILTIN_PREFETCH_PRESENT=1)
   endif (XGBOOST_BUILTIN_PREFETCH_PRESENT)
-
-  if (PLUGIN_RMM)
-    target_compile_definitions(objxgboost PUBLIC -DXGBOOST_USE_RMM=1)
-  endif (PLUGIN_RMM)
 endmacro(xgboost_target_defs)
 
 # handles dependencies
@@ -299,10 +267,6 @@ macro(xgboost_target_link_libraries target)
     xgboost_set_cuda_flags(${target})
   endif (USE_CUDA)
 
-  if (PLUGIN_RMM)
-    target_link_libraries(${target} PRIVATE rmm::rmm)
-  endif (PLUGIN_RMM)
-
   if (USE_NCCL)
     xgboost_link_nccl(${target})
   endif (USE_NCCL)
@@ -314,8 +278,4 @@ macro(xgboost_target_link_libraries target)
   if (RABIT_BUILD_MPI)
     target_link_libraries(${target} PRIVATE MPI::MPI_CXX)
   endif (RABIT_BUILD_MPI)
-
-  if (MINGW)
-    target_link_libraries(${target} PRIVATE wsock32 ws2_32)
-  endif (MINGW)
 endmacro(xgboost_target_link_libraries)

demo/CLI/binary_classification/mapfeat.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python3
+#!/usr/bin/python
 
 def loadfmap( fname ):
     fmap = {}

demo/CLI/binary_classification/mknfold.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python3
-
+#!/usr/bin/python
 import sys
 import random
 
@@ -27,3 +26,4 @@ for l in fi:
 fi.close()
 ftr.close()
 fte.close()
+

demo/CLI/regression/mapfeat.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python3
+#!/usr/bin/python
 
 fo = open('machine.txt', 'w')
 cnt = 6

demo/CLI/regression/mknfold.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python3
-
+#!/usr/bin/python
 import sys
 import random
 

demo/CLI/yearpredMSD/csv2libsvm.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python3
-
 import sys
 fo = open(sys.argv[2], 'w')
 

demo/README.md

@@ -78,7 +78,7 @@ XGBoost is extensively used by machine learning practitioners to create state of
 this is a list of machine learning winning solutions with XGBoost.
 Please send pull requests if you find ones that are missing here.
 
-- Bishwarup Bhattacharjee, 1st place winner of [Allstate Claims Severity](https://www.kaggle.com/competitions/allstate-claims-severity/overview) conducted on December 2016. Link to [discussion](https://www.kaggle.com/competitions/allstate-claims-severity/discussion/26416)
+
 - Benedikt Schifferer, Gilberto Titericz, Chris Deotte, Christof Henkel, Kazuki Onodera, Jiwei Liu, Bojan Tunguz, Even Oldridge, Gabriel De Souza Pereira Moreira and Ahmet Erdem, 1st place winner of [Twitter RecSys Challenge 2020](https://recsys-twitter.com/) conducted from June,20-August,20. [GPU Accelerated Feature Engineering and Training for Recommender Systems](https://medium.com/rapids-ai/winning-solution-of-recsys2020-challenge-gpu-accelerated-feature-engineering-and-training-for-cd67c5a87b1f)
 - Eugene Khvedchenya,Jessica Fridrich, Jan Butora, Yassine Yousfi 1st place winner in [ALASKA2 Image Steganalysis](https://www.kaggle.com/c/alaska2-image-steganalysis/overview). Link to [discussion](https://www.kaggle.com/c/alaska2-image-steganalysis/discussion/168546)
 - Dan Ofer, Seffi Cohen, Noa Dagan, Nurit, 1st place in WiDS Datathon 2020. Link to [discussion](https://www.kaggle.com/c/widsdatathon2020/discussion/133189)
@@ -136,7 +136,7 @@ Send a PR to add a one sentence description:)
 
 - XGBoost is used in [Kaggle Script](https://www.kaggle.com/scripts) to solve data science challenges.
 - Distribute XGBoost as Rest API server from Jupyter notebook with [BentoML](https://github.com/bentoml/bentoml). [Link to notebook](https://github.com/bentoml/BentoML/blob/master/examples/xgboost-predict-titanic-survival/XGBoost-titanic-survival-prediction.ipynb)
-- [Seldon predictive service powered by XGBoost](https://docs.seldon.io/projects/seldon-core/en/latest/servers/xgboost.html)
+- [Seldon predictive service powered by XGBoost](http://docs.seldon.io/iris-demo.html)
 - XGBoost Distributed is used in [ODPS Cloud Service by Alibaba](https://yq.aliyun.com/articles/6355) (in Chinese)
 - XGBoost is incoporated as part of [Graphlab Create](https://dato.com/products/create/) for scalable machine learning.
 - [Hanjing Su](https://www.52cs.org) from Tencent data platform team: "We use distributed XGBoost for click through prediction in wechat shopping and lookalikes. The problems involve hundreds millions of users and thousands of features. XGBoost is cleanly designed and can be easily integrated into our production environment, reducing our cost in developments."
@@ -146,7 +146,7 @@ Send a PR to add a one sentence description:)
 
 - [BayesBoost](https://github.com/mpearmain/BayesBoost) - Bayesian Optimization using xgboost and sklearn API
 - [FLAML](https://github.com/microsoft/FLAML) - An open source AutoML library 
-designed to automatically produce accurate machine learning models with low computational cost. FLAML includes [XGBoost as one of the default learners](https://github.com/microsoft/FLAML/blob/main/flaml/model.py) and can also be used as a fast hyperparameter tuning tool for XGBoost ([code example](https://microsoft.github.io/FLAML/docs/Examples/AutoML-for-XGBoost)).
+designed to automatically produce accurate machine learning models with low computational cost. FLAML includes [XGBoost as one of the default learners](https://github.com/microsoft/FLAML/blob/main/flaml/model.py) and can also be used as a fast hyperparameter tuning tool for XGBoost ([code example](https://github.com/microsoft/FLAML/blob/main/notebook/flaml_xgboost.ipynb)).
 - [gp_xgboost_gridsearch](https://github.com/vatsan/gp_xgboost_gridsearch) - In-database parallel grid-search for XGBoost on [Greenplum](https://github.com/greenplum-db/gpdb) using PL/Python
 - [tpot](https://github.com/rhiever/tpot) - A Python tool that automatically creates and optimizes machine learning pipelines using genetic programming.
 

demo/aft_survival/README.rst

@@ -1,5 +0,0 @@
-Survival Analysis Walkthrough
-=============================
-
-This is a collection of examples for using the XGBoost Python package for training
-survival models. For an introduction, see :doc:`/tutorials/aft_survival_analysis`

demo/aft_survival/aft_survival_demo.py

@@ -1,10 +1,6 @@
 """
-Demo for survival analysis (regression).
-========================================
-
-Demo for survival analysis (regression). using Accelerated Failure Time (AFT) model.
+Demo for survival analysis (regression) using Accelerated Failure Time (AFT) model
 """
-
 import os
 from sklearn.model_selection import ShuffleSplit
 import pandas as pd

demo/aft_survival/aft_survival_demo_with_optuna.py

@@ -1,10 +1,6 @@
 """
-Demo for survival analysis (regression) with Optuna.
-====================================================
-
-Demo for survival analysis (regression) using Accelerated Failure Time (AFT) model,
-using Optuna to tune hyperparameters
-
+Demo for survival analysis (regression) using Accelerated Failure Time (AFT) model, using Optuna
+to tune hyperparameters
 """
 from sklearn.model_selection import ShuffleSplit
 import pandas as pd
@@ -49,7 +45,7 @@ def objective(trial):
     params.update(base_params)
     pruning_callback = optuna.integration.XGBoostPruningCallback(trial, 'valid-aft-nloglik')
     bst = xgb.train(params, dtrain, num_boost_round=10000,
-                    evals=[(dtrain, 'train'), (dvalid, 'valid')],
+                    evals=[(dtrain, 'train'), (dvalid, 'valid')], 
                     early_stopping_rounds=50, verbose_eval=False, callbacks=[pruning_callback])
     if bst.best_iteration >= 25:
         return bst.best_score
@@ -67,7 +63,7 @@ params.update(study.best_trial.params)
 # Re-run training with the best hyperparameter combination
 print('Re-running the best trial... params = {}'.format(params))
 bst = xgb.train(params, dtrain, num_boost_round=10000,
-                evals=[(dtrain, 'train'), (dvalid, 'valid')],
+                evals=[(dtrain, 'train'), (dvalid, 'valid')], 
                 early_stopping_rounds=50)
 
 # Run prediction on the validation set

demo/aft_survival/aft_survival_viz_demo.py

@@ -1,10 +1,9 @@
 """
 Visual demo for survival analysis (regression) with Accelerated Failure Time (AFT) model.
-=========================================================================================
 
-This demo uses 1D toy data and visualizes how XGBoost fits a tree ensemble. The ensemble
-model starts out as a flat line and evolves into a step function in order to account for
-all ranged labels.
+This demo uses 1D toy data and visualizes how XGBoost fits a tree ensemble. The ensemble model
+starts out as a flat line and evolves into a step function in order to account for all ranged
+labels.
 """
 import numpy as np
 import xgboost as xgb
@@ -58,7 +57,7 @@ def plot_intermediate_model_callback(env):
     #              the corresponding predicted label (y_pred)
     acc = np.sum(np.logical_and(y_pred >= y_lower, y_pred <= y_upper)/len(X) * 100)
     accuracy_history.append(acc)
-
+    
     # Plot ranged labels as well as predictions by the model
     plt.subplot(5, 3, env.iteration + 1)
     plot_censored_labels(X, y_lower, y_upper)

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

@@ -18,7 +18,7 @@ if (err != 0) {                                                         \
 }                                                                       \
 }
 
-int main() {
+int main(int argc, char** argv) {
   int silent = 0;
   int use_gpu = 0;  // set to 1 to use the GPU for training
 
@@ -67,21 +67,10 @@ int main() {
 
   // predict
   bst_ulong out_len = 0;
+  const float* out_result = NULL;
   int n_print = 10;
 
-  /* Run prediction with DMatrix object. */
-  char const config[] =
-      "{\"training\": false, \"type\": 0, "
-      "\"iteration_begin\": 0, \"iteration_end\": 0, \"strict_shape\": false}";
-  /* Shape of output prediction */
-  uint64_t const* out_shape;
-  /* Dimension of output prediction */
-  uint64_t out_dim;
-  /* Pointer to a thread local contigious array, assigned in prediction function. */
-  float const* out_result = NULL;
-  safe_xgboost(
-      XGBoosterPredictFromDMatrix(booster, dtest, config, &out_shape, &out_dim, &out_result));
-
+  safe_xgboost(XGBoosterPredict(booster, dtest, 0, 0, 0, &out_len, &out_result));
   printf("y_pred: ");
   for (int i = 0; i < n_print; ++i) {
     printf("%1.4f ", out_result[i]);
@@ -109,12 +98,12 @@ int main() {
     DMatrixHandle dmat;
     safe_xgboost(XGDMatrixCreateFromMat(values, 1, 127, 0.0, &dmat));
 
+    bst_ulong out_len = 0;
     const float* out_result = NULL;
 
-    safe_xgboost(
-        XGBoosterPredictFromDMatrix(booster, dmat, config, &out_shape, &out_dim, &out_result));
-    assert(out_dim == 1);
-    assert(out_shape[0] == 1);
+    safe_xgboost(XGBoosterPredict(booster, dmat, 0, 0, 0, &out_len,
+          &out_result));
+    assert(out_len == 1);
 
     printf("%1.4f \n", out_result[0]);
     safe_xgboost(XGDMatrixFree(dmat));
@@ -133,12 +122,12 @@ int main() {
     safe_xgboost(XGDMatrixCreateFromCSREx(indptr, indices, data, 2, 22, 127,
       &dmat));
 
+    bst_ulong out_len = 0;
     const float* out_result = NULL;
 
-    safe_xgboost(
-        XGBoosterPredictFromDMatrix(booster, dmat, config, &out_shape, &out_dim, &out_result));
-    assert(out_dim == 1);
-    assert(out_shape[0] == 1);
+    safe_xgboost(XGBoosterPredict(booster, dmat, 0, 0, 0, &out_len,
+          &out_result));
+    assert(out_len == 1);
 
     printf("%1.4f \n", out_result[0]);
     safe_xgboost(XGDMatrixFree(dmat));
@@ -165,12 +154,12 @@ int main() {
     safe_xgboost(XGDMatrixCreateFromCSCEx(col_ptr, indices, data, 128, 22, 1,
       &dmat));
 
+    bst_ulong out_len = 0;
     const float* out_result = NULL;
 
-    safe_xgboost(
-        XGBoosterPredictFromDMatrix(booster, dmat, config, &out_shape, &out_dim, &out_result));
-    assert(out_dim == 1);
-    assert(out_shape[0] == 1);
+    safe_xgboost(XGBoosterPredict(booster, dmat, 0, 0, 0, &out_len,
+          &out_result));
+    assert(out_len == 1);
 
     printf("%1.4f \n", out_result[0]);
     safe_xgboost(XGDMatrixFree(dmat));

demo/c-api/external-memory/external_memory.c

@@ -139,8 +139,8 @@ void TrainModel(DMatrix Xy) {
   Booster booster;
   DMatrix cache[] = {Xy};
   safe_xgboost(XGBoosterCreate(cache, 1, &booster));
-  /* Use approx or hist for external memory training. */
-  safe_xgboost(XGBoosterSetParam(booster, "tree_method", "hist"));
+  /* Use approx for external memory training. */
+  safe_xgboost(XGBoosterSetParam(booster, "tree_method", "approx"));
   safe_xgboost(XGBoosterSetParam(booster, "objective", "reg:squarederror"));
 
   /* Start training. */

demo/dask/README.md

@@ -0,0 +1,6 @@
+Dask
+====
+
+This directory contains some demonstrations for using `dask` with `XGBoost`.
+For an overview, see
+https://xgboost.readthedocs.io/en/latest/tutorials/dask.html .

demo/dask/README.rst

@@ -1,7 +0,0 @@
-.. _dask-examples:
-
-XGBoost Dask Feature Walkthrough
-================================
-
-This directory contains some demonstrations for using `dask` with `XGBoost`.  For an
-overview, see :doc:`/tutorials/dask`

demo/dask/callbacks.py

@@ -1,7 +1,4 @@
-"""
-Example of using callbacks with Dask
-====================================
-"""
+"""Example of using callbacks in Dask"""
 import numpy as np
 import xgboost as xgb
 from xgboost.dask import DaskDMatrix

demo/dask/cpu_survival.py

@@ -1,9 +1,3 @@
-"""
-Example of training survival model with Dask on CPU
-===================================================
-
-"""
-
 import xgboost as xgb
 import os
 from xgboost.dask import DaskDMatrix

demo/dask/cpu_training.py

@@ -1,8 +1,3 @@
-"""
-Example of training with Dask on CPU
-====================================
-
-"""
 import xgboost as xgb
 from xgboost.dask import DaskDMatrix
 from dask.distributed import Client

demo/dask/gpu_training.py

@@ -1,15 +1,11 @@
-"""
-Example of training with Dask on GPU
-====================================
-"""
 from dask_cuda import LocalCUDACluster
-import dask_cudf
 from dask.distributed import Client
 from dask import array as da
-from dask import dataframe as dd
 import xgboost as xgb
 from xgboost import dask as dxgb
 from xgboost.dask import DaskDMatrix
+import cupy as cp
+import argparse
 
 
 def using_dask_matrix(client: Client, X, y):
@@ -45,12 +41,12 @@ def using_quantile_device_dmatrix(client: Client, X, y):
 
     '''
     # Input must be on GPU for `DaskDeviceQuantileDMatrix`.
-    X = dask_cudf.from_dask_dataframe(dd.from_dask_array(X))
-    y = dask_cudf.from_dask_dataframe(dd.from_dask_array(y))
+    X = X.map_blocks(cp.array)
+    y = y.map_blocks(cp.array)
 
     # `DaskDeviceQuantileDMatrix` is used instead of `DaskDMatrix`, be careful
-    # that it can not be used for anything else other than training.
-    dtrain = dxgb.DaskQuantileDMatrix(client, X, y)
+    # that it can not be used for anything else than training.
+    dtrain = dxgb.DaskDeviceQuantileDMatrix(client, X, y)
     output = xgb.dask.train(client,
                             {'verbosity': 2,
                              'tree_method': 'gpu_hist'},
@@ -62,6 +58,12 @@ def using_quantile_device_dmatrix(client: Client, X, y):
 
 
 if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--ddqdm', choices=[0, 1], type=int, default=1,
+        help='''Whether should we use `DaskDeviceQuantileDMatrix`''')
+    args = parser.parse_args()
+
     # `LocalCUDACluster` is used for assigning GPU to XGBoost processes.  Here
     # `n_workers` represents the number of GPUs since we use one GPU per worker
     # process.
@@ -70,10 +72,12 @@ if __name__ == '__main__':
             # generate some random data for demonstration
             m = 100000
             n = 100
-            X = da.random.random(size=(m, n), chunks=10000)
-            y = da.random.random(size=(m, ), chunks=10000)
+            X = da.random.random(size=(m, n), chunks=100)
+            y = da.random.random(size=(m, ), chunks=100)
 
-            print('Using DaskQuantileDMatrix')
-            from_ddqdm = using_quantile_device_dmatrix(client, X, y)
-            print('Using DMatrix')
-            from_dmatrix = using_dask_matrix(client, X, y)
+            if args.ddqdm == 1:
+                print('Using DaskDeviceQuantileDMatrix')
+                from_ddqdm = using_quantile_device_dmatrix(client, X, y)
+            else:
+                print('Using DMatrix')
+                from_dmatrix = using_dask_matrix(client, X, y)

demo/dask/sklearn_cpu_training.py

@@ -1,7 +1,6 @@
-"""
-Use scikit-learn regressor interface with CPU histogram tree method
-===================================================================
-"""
+'''Dask interface demo:
+
+Use scikit-learn regressor interface with CPU histogram tree method.'''
 from dask.distributed import Client
 from dask.distributed import LocalCluster
 from dask import array as da
@@ -17,7 +16,7 @@ def main(client):
     y = da.random.random(m, partition_size)
 
     regressor = xgboost.dask.DaskXGBRegressor(verbosity=1, n_estimators=2)
-    regressor.set_params(tree_method="hist")
+    regressor.set_params(tree_method='hist')
     # assigning client here is optional
     regressor.client = client
 
@@ -27,13 +26,13 @@ def main(client):
     bst = regressor.get_booster()
     history = regressor.evals_result()
 
-    print("Evaluation history:", history)
+    print('Evaluation history:', history)
     # returned prediction is always a dask array.
     assert isinstance(prediction, da.Array)
-    return bst  # returning the trained model
+    return bst                  # returning the trained model
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     # or use other clusters for scaling
     with LocalCluster(n_workers=4, threads_per_worker=1) as cluster:
         with Client(cluster) as client:

demo/dask/sklearn_gpu_training.py

@@ -1,7 +1,6 @@
-"""
-Use scikit-learn regressor interface with GPU histogram tree method
-===================================================================
-"""
+'''Dask interface demo:
+
+Use scikit-learn regressor interface with GPU histogram tree method.'''
 
 from dask.distributed import Client
 # It's recommended to use dask_cuda for GPU assignment

demo/guide-python/README.md

@@ -0,0 +1,18 @@
+XGBoost Python Feature Walkthrough
+==================================
+* [Basic walkthrough of wrappers](basic_walkthrough.py)
+* [Customize loss function, and evaluation metric](custom_objective.py)
+* [Re-implement RMSLE as customized metric and objective](custom_rmsle.py)
+* [Re-Implement `multi:softmax` objective as customized objective](custom_softmax.py)
+* [Boosting from existing prediction](boost_from_prediction.py)
+* [Predicting using first n trees](predict_first_ntree.py)
+* [Generalized Linear Model](generalized_linear_model.py)
+* [Cross validation](cross_validation.py)
+* [Predicting leaf indices](predict_leaf_indices.py)
+* [Sklearn Wrapper](sklearn_examples.py)
+* [Sklearn Parallel](sklearn_parallel.py)
+* [Sklearn access evals result](sklearn_evals_result.py)
+* [Access evals result](evals_result.py)
+* [External Memory](external_memory.py)
+* [Training continuation](continuation.py)
+* [Feature weights for column sampling](feature_weights.py)

demo/guide-python/README.rst

@@ -1,5 +0,0 @@
-XGBoost Python Feature Walkthrough
-==================================
-
-
-This is a collection of examples for using the XGBoost Python package.

demo/guide-python/basic_walkthrough.py

@@ -1,65 +1,46 @@
-"""
-Getting started with XGBoost
-============================
-
-This is a simple example of using the native XGBoost interface, there are other
-interfaces in the Python package like scikit-learn interface and Dask interface.
-
-
-See :doc:`/python/python_intro` and :doc:`/tutorials/index` for other references.
-
-"""
 import numpy as np
+import scipy.sparse
 import pickle
 import xgboost as xgb
 import os
 
-from sklearn.datasets import load_svmlight_file
-
 # Make sure the demo knows where to load the data.
 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 XGBOOST_ROOT_DIR = os.path.dirname(os.path.dirname(CURRENT_DIR))
-DEMO_DIR = os.path.join(XGBOOST_ROOT_DIR, "demo")
+DEMO_DIR = os.path.join(XGBOOST_ROOT_DIR, 'demo')
 
-# X is a scipy csr matrix, XGBoost supports many other input types,
-X, y = load_svmlight_file(os.path.join(DEMO_DIR, "data", "agaricus.txt.train"))
-dtrain = xgb.DMatrix(X, y)
-# validation set
-X_test, y_test = load_svmlight_file(os.path.join(DEMO_DIR, "data", "agaricus.txt.test"))
-dtest = xgb.DMatrix(X_test, y_test)
+# simple example
+# load file from text file, also binary buffer generated by xgboost
+dtrain = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train?indexing_mode=1'))
+dtest = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.test?indexing_mode=1'))
 
 # specify parameters via map, definition are same as c++ version
-param = {"max_depth": 2, "eta": 1, "objective": "binary:logistic"}
+param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
 
 # specify validations set to watch performance
-watchlist = [(dtest, "eval"), (dtrain, "train")]
-# number of boosting rounds
+watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 num_round = 2
-bst = xgb.train(param, dtrain, num_boost_round=num_round, evals=watchlist)
+bst = xgb.train(param, dtrain, num_round, watchlist)
 
-# run prediction
+# this is prediction
 preds = bst.predict(dtest)
 labels = dtest.get_label()
-print(
-    "error=%f"
-    % (
-        sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i])
-        / float(len(preds))
-    )
-)
-bst.save_model("model-0.json")
+print('error=%f' %
+      (sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) /
+       float(len(preds))))
+bst.save_model('0001.model')
 # dump model
-bst.dump_model("dump.raw.txt")
+bst.dump_model('dump.raw.txt')
 # dump model with feature map
-bst.dump_model("dump.nice.txt", os.path.join(DEMO_DIR, "data/featmap.txt"))
+bst.dump_model('dump.nice.txt', os.path.join(DEMO_DIR, 'data/featmap.txt'))
 
 # save dmatrix into binary buffer
-dtest.save_binary("dtest.dmatrix")
+dtest.save_binary('dtest.buffer')
 # save model
-bst.save_model("model-1.json")
+bst.save_model('xgb.model')
 # load model and data in
-bst2 = xgb.Booster(model_file="model-1.json")
-dtest2 = xgb.DMatrix("dtest.dmatrix")
+bst2 = xgb.Booster(model_file='xgb.model')
+dtest2 = xgb.DMatrix('dtest.buffer')
 preds2 = bst2.predict(dtest2)
 # assert they are the same
 assert np.sum(np.abs(preds2 - preds)) == 0
@@ -71,3 +52,40 @@ bst3 = pickle.loads(pks)
 preds3 = bst3.predict(dtest2)
 # assert they are the same
 assert np.sum(np.abs(preds3 - preds)) == 0
+
+###
+# build dmatrix from scipy.sparse
+print('start running example of build DMatrix from scipy.sparse CSR Matrix')
+labels = []
+row = []
+col = []
+dat = []
+i = 0
+for l in open(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train')):
+    arr = l.split()
+    labels.append(int(arr[0]))
+    for it in arr[1:]:
+        k, v = it.split(':')
+        row.append(i)
+        col.append(int(k))
+        dat.append(float(v))
+    i += 1
+csr = scipy.sparse.csr_matrix((dat, (row, col)))
+dtrain = xgb.DMatrix(csr, label=labels)
+watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+bst = xgb.train(param, dtrain, num_round, watchlist)
+
+print('start running example of build DMatrix from scipy.sparse CSC Matrix')
+# we can also construct from csc matrix
+csc = scipy.sparse.csc_matrix((dat, (row, col)))
+dtrain = xgb.DMatrix(csc, label=labels)
+watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+bst = xgb.train(param, dtrain, num_round, watchlist)
+
+print('start running example of build DMatrix from numpy array')
+# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix
+# in internal implementation then convert to DMatrix
+npymat = csr.todense()
+dtrain = xgb.DMatrix(npymat, label=labels)
+watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+bst = xgb.train(param, dtrain, num_round, watchlist)

demo/guide-python/boost_from_prediction.py

@@ -1,7 +1,3 @@
-"""
-Demo for boosting from prediction
-=================================
-"""
 import os
 import xgboost as xgb
 

demo/guide-python/callbacks.py

@@ -1,6 +1,5 @@
 '''
-Demo for using and defining callback functions
-==============================================
+Demo for using and defining callback functions.
 
     .. versionadded:: 1.3.0
 '''

demo/guide-python/cat_in_the_dat.py

@@ -1,124 +0,0 @@
-"""
-Train XGBoost with cat_in_the_dat dataset
-=========================================
-
-A simple demo for categorical data support using dataset from Kaggle categorical data
-tutorial.
-
-The excellent tutorial is at:
-https://www.kaggle.com/shahules/an-overview-of-encoding-techniques
-
-And the data can be found at:
-https://www.kaggle.com/shahules/an-overview-of-encoding-techniques/data
-
-Also, see the tutorial for using XGBoost with categorical data:
-:doc:`/tutorials/categorical`.
-
-    .. versionadded 1.6.0
-
-"""
-
-from __future__ import annotations
-
-import os
-from tempfile import TemporaryDirectory
-from time import time
-
-import pandas as pd
-from sklearn.metrics import roc_auc_score
-from sklearn.model_selection import train_test_split
-
-import xgboost as xgb
-
-
-def load_cat_in_the_dat() -> tuple[pd.DataFrame, pd.Series]:
-    """Assuming you have already downloaded the data into `input` directory."""
-
-    df_train = pd.read_csv("./input/cat-in-the-dat/train.csv")
-
-    print(
-        "train data set has got {} rows and {} columns".format(
-            df_train.shape[0], df_train.shape[1]
-        )
-    )
-    X = df_train.drop(["target"], axis=1)
-    y = df_train["target"]
-
-    for i in range(0, 5):
-        X["bin_" + str(i)] = X["bin_" + str(i)].astype("category")
-
-    for i in range(0, 5):
-        X["nom_" + str(i)] = X["nom_" + str(i)].astype("category")
-
-    for i in range(5, 10):
-        X["nom_" + str(i)] = X["nom_" + str(i)].apply(int, base=16)
-
-    for i in range(0, 6):
-        X["ord_" + str(i)] = X["ord_" + str(i)].astype("category")
-
-    print(
-        "train data set has got {} rows and {} columns".format(X.shape[0], X.shape[1])
-    )
-    return X, y
-
-
-params = {
-    "tree_method": "gpu_hist",
-    "n_estimators": 32,
-    "colsample_bylevel": 0.7,
-}
-
-
-def categorical_model(X: pd.DataFrame, y: pd.Series, output_dir: str) -> None:
-    """Train using builtin categorical data support from XGBoost"""
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, random_state=1994, test_size=0.2
-    )
-    # Specify `enable_categorical` to True.
-    clf = xgb.XGBClassifier(
-        **params,
-        eval_metric="auc",
-        enable_categorical=True,
-        max_cat_to_onehot=1,  # We use optimal partitioning exclusively
-    )
-    clf.fit(X_train, y_train, eval_set=[(X_test, y_test), (X_train, y_train)])
-    clf.save_model(os.path.join(output_dir, "categorical.json"))
-
-    y_score = clf.predict_proba(X_test)[:, 1]  # proba of positive samples
-    auc = roc_auc_score(y_test, y_score)
-    print("AUC of using builtin categorical data support:", auc)
-
-
-def onehot_encoding_model(X: pd.DataFrame, y: pd.Series, output_dir: str) -> None:
-    """Train using one-hot encoded data."""
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, random_state=42, test_size=0.2
-    )
-    # Specify `enable_categorical` to False as we are using encoded data.
-    clf = xgb.XGBClassifier(**params, eval_metric="auc", enable_categorical=False)
-    clf.fit(
-        X_train,
-        y_train,
-        eval_set=[(X_test, y_test), (X_train, y_train)],
-    )
-    clf.save_model(os.path.join(output_dir, "one-hot.json"))
-
-    y_score = clf.predict_proba(X_test)[:, 1]  # proba of positive samples
-    auc = roc_auc_score(y_test, y_score)
-    print("AUC of using onehot encoding:", auc)
-
-
-if __name__ == "__main__":
-    X, y = load_cat_in_the_dat()
-
-    with TemporaryDirectory() as tmpdir:
-        start = time()
-        categorical_model(X, y, tmpdir)
-        end = time()
-        print("Duration:categorical", end - start)
-
-        X = pd.get_dummies(X)
-        start = time()
-        onehot_encoding_model(X, y, tmpdir)
-        end = time()
-        print("Duration:onehot", end - start)

demo/guide-python/categorical.py

@@ -1,27 +1,17 @@
-"""
-Getting started with categorical data
-=====================================
-
-Experimental support for categorical data.  After 1.5 XGBoost `gpu_hist` tree method has
-experimental support for one-hot encoding based tree split, and in 1.6 `approx` support
-was added.
+"""Experimental support for categorical data.  After 1.5 XGBoost `gpu_hist` tree method
+has experimental support for one-hot encoding based tree split.
 
 In before, users need to run an encoder themselves before passing the data into XGBoost,
-which creates a sparse matrix and potentially increase memory usage.  This demo
-showcases the experimental categorical data support, more advanced features are planned.
-
-Also, see :doc:`the tutorial </tutorials/categorical>` for using XGBoost with
-categorical data.
+which creates a sparse matrix and potentially increase memory usage.  This demo showcases
+the experimental categorical data support, more advanced features are planned.
 
     .. versionadded:: 1.5.0
 
 """
-from typing import Tuple
-
-import numpy as np
 import pandas as pd
-
+import numpy as np
 import xgboost as xgb
+from typing import Tuple
 
 
 def make_categorical(
@@ -57,11 +47,8 @@ def main() -> None:
     # For scikit-learn interface, the input data must be pandas DataFrame or cudf
     # DataFrame with categorical features
     X, y = make_categorical(100, 10, 4, False)
-    # Specify `enable_categorical` to True, also we use onehot encoding based split
-    # here for demonstration. For details see the document of `max_cat_to_onehot`.
-    reg = xgb.XGBRegressor(
-        tree_method="gpu_hist", enable_categorical=True, max_cat_to_onehot=5
-    )
+    # Specify `enable_categorical` to True.
+    reg = xgb.XGBRegressor(tree_method="gpu_hist", enable_categorical=True)
     reg.fit(X, y, eval_set=[(X, y)])
 
     # Pass in already encoded data

demo/guide-python/continuation.py

@@ -1,6 +1,5 @@
 """
-Demo for training continuation
-==============================
+Demo for training continuation.
 """
 
 from sklearn.datasets import load_breast_cancer
@@ -14,13 +13,13 @@ def training_continuation(tmpdir: str, use_pickle: bool) -> None:
     """Basic training continuation."""
     # Train 128 iterations in 1 session
     X, y = load_breast_cancer(return_X_y=True)
-    clf = xgboost.XGBClassifier(n_estimators=128)
+    clf = xgboost.XGBClassifier(n_estimators=128, use_label_encoder=False)
     clf.fit(X, y, eval_set=[(X, y)], eval_metric="logloss")
     print("Total boosted rounds:", clf.get_booster().num_boosted_rounds())
 
     # Train 128 iterations in 2 sessions, with the first one runs for 32 iterations and
     # the second one runs for 96 iterations
-    clf = xgboost.XGBClassifier(n_estimators=32)
+    clf = xgboost.XGBClassifier(n_estimators=32, use_label_encoder=False)
     clf.fit(X, y, eval_set=[(X, y)], eval_metric="logloss")
     assert clf.get_booster().num_boosted_rounds() == 32
 
@@ -54,14 +53,14 @@ def training_continuation_early_stop(tmpdir: str, use_pickle: bool) -> None:
     n_estimators = 512
 
     X, y = load_breast_cancer(return_X_y=True)
-    clf = xgboost.XGBClassifier(n_estimators=n_estimators)
+    clf = xgboost.XGBClassifier(n_estimators=n_estimators, use_label_encoder=False)
     clf.fit(X, y, eval_set=[(X, y)], eval_metric="logloss", callbacks=[early_stop])
     print("Total boosted rounds:", clf.get_booster().num_boosted_rounds())
     best = clf.best_iteration
 
     # Train 512 iterations in 2 sessions, with the first one runs for 128 iterations and
     # the second one runs until early stop.
-    clf = xgboost.XGBClassifier(n_estimators=128)
+    clf = xgboost.XGBClassifier(n_estimators=128, use_label_encoder=False)
     # Reinitialize the early stop callback
     early_stop = xgboost.callback.EarlyStopping(
         rounds=early_stopping_rounds, save_best=True
@@ -79,13 +78,15 @@ def training_continuation_early_stop(tmpdir: str, use_pickle: bool) -> None:
     else:
         path = os.path.join(tmpdir, "model-first-128.json")
         clf.save_model(path)
-        loaded = xgboost.XGBClassifier()
+        loaded = xgboost.XGBClassifier(use_label_encoder=False)
         loaded.load_model(path)
 
     early_stop = xgboost.callback.EarlyStopping(
         rounds=early_stopping_rounds, save_best=True
     )
-    clf = xgboost.XGBClassifier(n_estimators=n_estimators - 128)
+    clf = xgboost.XGBClassifier(
+        n_estimators=n_estimators - 128, use_label_encoder=False
+    )
     clf.fit(
         X,
         y,

demo/guide-python/cross_validation.py

@@ -1,7 +1,3 @@
-"""
-Demo for using cross validation
-===============================
-"""
 import os
 import numpy as np
 import xgboost as xgb

demo/guide-python/custom_objective.py

@@ -0,0 +1,61 @@
+###
+# advanced: customized loss function
+#
+import os
+import numpy as np
+import xgboost as xgb
+
+print('start running example to used customized objective function')
+
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
+
+# note: what we are getting is margin value in prediction you must know what
+# you are doing
+param = {'max_depth': 2, 'eta': 1, 'objective': 'reg:logistic'}
+watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+num_round = 10
+
+
+# user define objective function, given prediction, return gradient and second
+# order gradient this is log likelihood loss
+def logregobj(preds, dtrain):
+    labels = dtrain.get_label()
+    preds = 1.0 / (1.0 + np.exp(-preds))  # transform raw leaf weight
+    grad = preds - labels
+    hess = preds * (1.0 - preds)
+    return grad, hess
+
+
+# user defined evaluation function, return a pair metric_name, result
+
+# NOTE: when you do customized loss function, the default prediction value is
+# margin, which means the prediction is score before logistic transformation.
+def evalerror(preds, dtrain):
+    labels = dtrain.get_label()
+    preds = 1.0 / (1.0 + np.exp(-preds))  # transform raw leaf weight
+    # return a pair metric_name, result. The metric name must not contain a
+    # colon (:) or a space
+    return 'my-error', float(sum(labels != (preds > 0.5))) / len(labels)
+
+
+py_evals_result = {}
+
+# training with customized objective, we can also do step by step training
+# simply look at training.py's implementation of train
+py_params = param.copy()
+py_params.update({'disable_default_eval_metric': True})
+py_logreg = xgb.train(py_params, dtrain, num_round, watchlist, obj=logregobj,
+                      feval=evalerror, evals_result=py_evals_result)
+
+evals_result = {}
+params = param.copy()
+params.update({'eval_metric': 'error'})
+logreg = xgb.train(params, dtrain, num_boost_round=num_round, evals=watchlist,
+                   evals_result=evals_result)
+
+
+for i in range(len(py_evals_result['train']['my-error'])):
+    np.testing.assert_almost_equal(py_evals_result['train']['my-error'],
+                                   evals_result['train']['error'])