Make 2.0 release. (#9567)

---------

Co-authored-by: Bobby Wang <wbo4958@gmail.com>

.clang-format

@@ -0,0 +1,214 @@
+---
+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
+...

.clang-tidy

@@ -1,4 +1,4 @@
-Checks: 'modernize-*,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
+Checks: 'modernize-*,-modernize-use-nodiscard,-modernize-concat-nested-namespaces,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
 CheckOptions:
   - { key: readability-identifier-naming.ClassCase,                 value: CamelCase  }
   - { key: readability-identifier-naming.StructCase,                value: CamelCase  }

.gitattributes

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

.github/dependabot.yml

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

.github/workflows/jvm_tests.yml

@@ -0,0 +1,87 @@
+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 }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [windows-latest, ubuntu-latest, macos-11]
+
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+
+    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+      with:
+        python-version: '3.8'
+        architecture: 'x64'
+
+    - uses: actions/setup-java@d202f5dbf7256730fb690ec59f6381650114feb2 # v3.6.0
+      with:
+        java-version: 1.8
+
+    - name: Install Python packages
+      run: |
+        python -m pip install wheel setuptools
+        python -m pip install awscli
+
+    - name: Cache Maven packages
+      uses: actions/cache@6998d139ddd3e68c71e9e398d8e40b71a2f39812 # v3.2.5
+      with:
+        path: ~/.m2
+        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
+        restore-keys: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
+
+    - name: Test XGBoost4J (Core)
+      run: |
+        cd jvm-packages
+        mvn test -B -pl :xgboost4j_2.12
+
+    - name: Extract branch name
+      shell: bash
+      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+      id: extract_branch
+      if: |
+        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
+        matrix.os == 'windows-latest'
+
+    - name: Publish artifact xgboost4j.dll to S3
+      run: |
+        cd lib/
+        Rename-Item -Path xgboost4j.dll -NewName xgboost4j_${{ github.sha }}.dll
+        dir
+        python -m awscli s3 cp xgboost4j_${{ github.sha }}.dll s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
+      if: |
+        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
+        matrix.os == 'windows-latest'
+      env:
+        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
+        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
+
+
+    - name: Test XGBoost4J (Core, Spark, Examples)
+      run: |
+        rm -rfv build/
+        cd jvm-packages
+        mvn -B test
+      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
+      env:
+        RABIT_MOCK: ON
+
+
+    - name: Build and Test XGBoost4J with scala 2.13
+      run: |
+        rm -rfv build/
+        cd jvm-packages
+        mvn -B clean install test -Pdefault,scala-2.13
+      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
+      env:
+        RABIT_MOCK: ON

.github/workflows/main.yml

@@ -6,6 +6,9 @@ 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:
@@ -14,24 +17,25 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-10.15]
+        os: [macos-11]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
     - name: Install system packages
       run: |
-        brew install lz4 ninja libomp
+        brew install ninja libomp
     - name: Build gtest binary
       run: |
         mkdir build
         cd build
-        cmake .. -DGOOGLE_TEST=ON -DUSE_OPENMP=ON -DUSE_DMLC_GTEST=ON -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON -GNinja
+        cmake .. -DGOOGLE_TEST=ON -DUSE_OPENMP=ON -DUSE_DMLC_GTEST=ON -DPLUGIN_DENSE_PARSER=ON -GNinja
         ninja -v
     - name: Run gtest binary
       run: |
         cd build
-        ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose
+        ./testxgboost
+        ctest -R TestXGBoostCLI --extra-verbose
 
   gtest-cpu-nonomp:
     name: Test Google C++ unittest (CPU Non-OMP)
@@ -41,7 +45,7 @@ jobs:
       matrix:
         os: [ubuntu-latest]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
     - name: Install system packages
@@ -59,255 +63,96 @@ jobs:
         cd build
         ctest --extra-verbose
 
-  python-sdist-test:
-    name: Test installing XGBoost Python source package
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-10.15, windows-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install osx system dependencies
-      if: matrix.os == 'macos-10.15'
-      run: |
-        brew install ninja libomp
-    - name: Install Ubuntu system dependencies
-      if: matrix.os == 'ubuntu-latest'
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py sdist
-        pip install -v ./dist/xgboost-*.tar.gz
-        cd ..
-        python -c 'import xgboost'
-
   c-api-demo:
     name: Test installing XGBoost lib + building the C API demo
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: bash -l {0}
     strategy:
       fail-fast: false
       matrix:
         os: ["ubuntu-latest"]
         python-version: ["3.8"]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
-    - name: Install system packages
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
       with:
-        auto-update-conda: true
+        cache-downloads: true
-        python-version: ${{ matrix.python-version }}
+        cache-env: true
-        activate-environment: test
+        environment-name: cpp_test
+        environment-file: tests/ci_build/conda_env/cpp_test.yml
     - name: Display Conda env
-      shell: bash -l {0}
       run: |
         conda info
         conda list
-    - name: Build and install XGBoost
+
-      shell: bash -l {0}
+    - name: Build and install XGBoost static library
       run: |
         mkdir build
         cd build
         cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
         ninja -v install
-    - name: Build and run C API demo
+        cd -
-      shell: bash -l {0}
+    - name: Build and run C API demo with static
       run: |
+        pushd .
         cd demo/c-api/
         mkdir build
         cd build
         cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
         ninja -v
+        ctest
         cd ..
-        ./build/api-demo
+        rm -rf ./build
+        popd
 
-  test-with-jvm:
+    - name: Build and install XGBoost shared library
-    name: Test JVM on OS ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [windows-latest, ubuntu-latest]
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-        architecture: 'x64'
-
-    - uses: actions/setup-java@v1
-      with:
-        java-version: 1.8
-
-    - name: Install Python packages
       run: |
-        python -m pip install wheel setuptools
+        cd build
-        python -m pip install awscli
+        cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-
+        ninja -v install
-    - name: Cache Maven packages
+        cd -
-      uses: actions/cache@v2
+    - name: Build and run C API demo with shared
-      with:
-        path: ~/.m2
-        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2
-
-    - name: Test XGBoost4J
-      run: |
-        cd jvm-packages
-        mvn test -B -pl :xgboost4j_2.12
-
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-
-    - name: Publish artifact xgboost4j.dll to S3
-      run: |
-        cd lib/
-        Rename-Item -Path xgboost4j.dll -NewName xgboost4j_${{ github.sha }}.dll
-        dir
-        python -m awscli s3 cp xgboost4j_${{ github.sha }}.dll s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-
-    - name: Test XGBoost4J-Spark
-      run: |
-        rm -rfv build/
-        cd jvm-packages
-        mvn -B test
-      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
-      env:
-        RABIT_MOCK: ON
-
-  lint:
-    runs-on: ubuntu-latest
-    name: Code linting for Python and C++
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools
-        python -m pip install pylint cpplint numpy scipy scikit-learn
-    - name: Run lint
-      run: |
-        make lint
-
-  mypy:
-    runs-on: ubuntu-latest
-    name: Type checking for Python
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools mypy dask[complete] distributed
-    - name: Run mypy
-      run: |
-        make mypy
-
-  doxygen:
-    runs-on: ubuntu-latest
-    name: Generate C/C++ API doc using Doxygen
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends doxygen graphviz ninja-build
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-    - name: Run Doxygen
       run: |
+        pushd .
+        cd demo/c-api/
         mkdir build
         cd build
-        cmake .. -DBUILD_C_DOC=ON -GNinja
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v doc_doxygen
+        ninja -v
-    - name: Extract branch name
+        ctest
-      shell: bash
+        popd
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
-      id: extract_branch
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Publish
-      run: |
-        cd build/
-        tar cvjf ${{ steps.extract_branch.outputs.branch }}.tar.bz2 doc_doxygen/
-        python -m awscli s3 cp ./${{ steps.extract_branch.outputs.branch }}.tar.bz2 s3://xgboost-docs/ --acl public-read
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
 
-  sphinx:
+  cpp-lint:
     runs-on: ubuntu-latest
-    name: Build docs using Sphinx
+    name: Code linting for C++
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
       with:
-        python-version: '3.8'
+        python-version: "3.8"
         architecture: 'x64'
-    - name: Install system packages
+    - name: Install Python packages
       run: |
-        sudo apt-get install -y --no-install-recommends graphviz
+        python -m pip install wheel setuptools cpplint pylint
-        python -m pip install wheel setuptools
+    - name: Run lint
-        python -m pip install -r doc/requirements.txt
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Run Sphinx
       run: |
-        make -C doc html
+        python3 dmlc-core/scripts/lint.py xgboost cpp R-package/src
-      env:
+
-        SPHINX_GIT_BRANCH: ${{ steps.extract_branch.outputs.branch }}
+        python3 dmlc-core/scripts/lint.py --exclude_path \
+            python-package/xgboost/dmlc-core \
+            python-package/xgboost/include \
+            python-package/xgboost/lib \
+            python-package/xgboost/rabit \
+            python-package/xgboost/src \
+            --pylint-rc python-package/.pylintrc \
+            xgboost \
+            cpp \
+            include src python-package

.github/workflows/python_tests.yml

@@ -0,0 +1,298 @@
+name: XGBoost-Python-Tests
+
+on: [push, pull_request]
+
+permissions:
+  contents: read # to fetch code (actions/checkout)
+
+defaults:
+  run:
+    shell: bash -l {0}
+
+jobs:
+  python-mypy-lint:
+    runs-on: ubuntu-latest
+    name: Type and format checks for the Python package
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: true
+        environment-name: python_lint
+        environment-file: tests/ci_build/conda_env/python_lint.yml
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+    - name: Run mypy
+      run: |
+        python tests/ci_build/lint_python.py --format=0 --type-check=1 --pylint=0
+    - name: Run formatter
+      run: |
+        python tests/ci_build/lint_python.py --format=1 --type-check=0 --pylint=0
+    - name: Run pylint
+      run: |
+        python tests/ci_build/lint_python.py --format=0 --type-check=0 --pylint=1
+
+  python-sdist-test-on-Linux:
+    # Mismatched glibcxx version between system and conda forge.
+    runs-on: ${{ matrix.os }}
+    name: Test installing XGBoost Python source package on ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: true
+        environment-name: sdist_test
+        environment-file: tests/ci_build/conda_env/sdist_test.yml
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+    - name: Build and install XGBoost
+      run: |
+        cd python-package
+        python --version
+        python -m build --sdist
+        pip install -v ./dist/xgboost-*.tar.gz --config-settings use_openmp=False
+        cd ..
+        python -c 'import xgboost'
+
+  python-sdist-test:
+    # Use system toolchain instead of conda toolchain for macos and windows.
+    # MacOS has linker error if clang++ from conda-forge is used
+    runs-on: ${{ matrix.os }}
+    name: Test installing XGBoost Python source package on ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-11, windows-latest]
+        python-version: ["3.8"]
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+    - name: Install osx system dependencies
+      if: matrix.os == 'macos-11'
+      run: |
+        brew install ninja libomp
+    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
+      with:
+        auto-update-conda: true
+        python-version: ${{ matrix.python-version }}
+        activate-environment: test
+    - name: Install build
+      run: |
+        conda install -c conda-forge python-build
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+    - name: Build and install XGBoost
+      run: |
+        cd python-package
+        python --version
+        python -m build --sdist
+        pip install -v ./dist/xgboost-*.tar.gz
+        cd ..
+        python -c 'import xgboost'
+
+  python-tests-on-macos:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    timeout-minutes: 60
+    strategy:
+      matrix:
+        config:
+          - {os: macos-11}
+
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: true
+        environment-name: macos_test
+        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
+
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on macos
+      run: |
+        brew install ninja
+
+        mkdir build
+        cd build
+        # Set prefix, to use OpenMP library from Conda env
+        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
+        # to learn why we don't use libomp from Homebrew.
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        ninja
+
+    - name: Install Python package
+      run: |
+        cd python-package
+        python --version
+        pip install -v .
+
+    - name: Test Python package
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/python
+
+    - name: Test Dask Interface
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_dask
+
+  python-tests-on-win:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    timeout-minutes: 60
+    strategy:
+      matrix:
+        config:
+          - {os: windows-latest, python-version: '3.8'}
+
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+
+    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
+      with:
+        auto-update-conda: true
+        python-version: ${{ matrix.config.python-version }}
+        activate-environment: win64_env
+        environment-file: tests/ci_build/conda_env/win64_cpu_test.yml
+
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on Windows
+      run: |
+        mkdir build_msvc
+        cd build_msvc
+        cmake .. -G"Visual Studio 17 2022" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
+        cmake --build . --config Release --parallel $(nproc)
+
+    - name: Install Python package
+      run: |
+        cd python-package
+        python --version
+        pip wheel -v . --wheel-dir dist/
+        pip install ./dist/*.whl
+
+    - name: Test Python package
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/python
+
+  python-tests-on-ubuntu:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    timeout-minutes: 90
+    strategy:
+      matrix:
+        config:
+          - {os: ubuntu-latest, python-version: "3.8"}
+
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: true
+        environment-name: linux_cpu_test
+        environment-file: tests/ci_build/conda_env/linux_cpu_test.yml
+
+    - name: Display Conda env
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on Ubuntu
+      run: |
+        mkdir build
+        cd build
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        ninja
+
+    - name: Install Python package
+      run: |
+        cd python-package
+        python --version
+        pip install -v .
+
+    - name: Test Python package
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/python
+
+    - name: Test Dask Interface
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_dask
+
+    - name: Test PySpark Interface
+      shell: bash -l {0}
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/test_distributed/test_with_spark
+
+  python-system-installation-on-ubuntu:
+    name: Test XGBoost Python package System Installation on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          submodules: 'true'
+
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.8
+
+      - name: Install ninja
+        run: |
+          sudo apt-get update && sudo apt-get install -y ninja-build
+
+      - name: Build XGBoost on Ubuntu
+        run: |
+          mkdir build
+          cd build
+          cmake .. -GNinja
+          ninja
+
+      - name: Copy lib to system lib
+        run: |
+          cp lib/* "$(python -c 'import sys; print(sys.base_prefix)')/lib"
+
+      - name: Install XGBoost in Virtual Environment
+        run: |
+          cd python-package
+          pip install virtualenv
+          virtualenv venv
+          source venv/bin/activate && \
+            pip install -v . --config-settings use_system_libxgboost=True && \
+            python -c 'import xgboost'

.github/workflows/python_wheels.yml

@@ -0,0 +1,41 @@
+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@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+    - name: Setup Python
+      uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+      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

@@ -1,4 +1,4 @@
-# Run R tests with noLD R. Only triggered by a pull request review
+# Run expensive R tests with the help of rhub. Only triggered by a pull request review
 # See discussion at https://github.com/dmlc/xgboost/pull/6378
 
 name: XGBoost-R-noLD
@@ -7,34 +7,30 @@ on:
   pull_request_review_comment:
     types: [created]
 
-env:
+permissions:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
+  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)
     timeout-minutes: 120
     runs-on: ubuntu-latest
-    container: rhub/debian-gcc-devel-nold
+    container:
+      image: rhub/debian-gcc-devel-nold
     steps:
     - name: Install git and system packages
       shell: bash
       run: |
-        apt-get update && apt-get install -y git libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libxml2-dev
+        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
 
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
 
     - name: Install dependencies
-      shell: bash
+      shell: bash -l {0}
       run: |
-        cat > install_libs.R <<EOT
+        /tmp/R-devel/bin/Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
-          install.packages(${{ env.R_PACKAGES }},
-                           repos = 'http://cloud.r-project.org',
-                           dependencies = c('Depends', 'Imports', 'LinkingTo'))
-        EOT
-        /tmp/R-devel/bin/Rscript install_libs.R
 
     - name: Run R tests
       shell: bash

.github/workflows/r_tests.yml

@@ -3,7 +3,10 @@ name: XGBoost-R-Tests
 on: [push, pull_request]
 
 env:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
+  GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+permissions:
+  contents: read # to fetch code (actions/checkout)
 
 jobs:
   lintr:
@@ -12,105 +15,121 @@ jobs:
     strategy:
       matrix:
         config:
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: ubuntu-latest, r: 'release'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@master
+    - uses: r-lib/actions/setup-r@11a22a908006c25fe054c4ef0ac0436b1de3edbe # v2.6.4
       with:
         r-version: ${{ matrix.config.r }}
 
+    - name: Cache R packages
+      uses: actions/cache@937d24475381cd9c75ae6db12cb4e79714b926ed # v3.0.11
+      with:
+        path: ${{ env.R_LIBS_USER }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
+
     - name: Install dependencies
       shell: Rscript {0}
       run: |
-        install.packages(${{ env.R_PACKAGES }},
+        source("./R-package/tests/helper_scripts/install_deps.R")
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
 
     - name: Run lintr
       run: |
-        cd R-package
+        MAKEFLAGS="-j$(nproc)" R CMD INSTALL R-package/
-        R.exe CMD INSTALL .
+        Rscript tests/ci_build/lint_r.R $(pwd)
-        Rscript.exe tests/helper_scripts/run_lint.R
 
-  test-with-R:
+  test-R-on-Windows:
     runs-on: ${{ matrix.config.os }}
     name: Test R on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
     strategy:
       fail-fast: false
       matrix:
         config:
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-latest, r: '4.2.0', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@master
+    - uses: r-lib/actions/setup-r@11a22a908006c25fe054c4ef0ac0436b1de3edbe # v2.6.4
       with:
         r-version: ${{ matrix.config.r }}
 
+    - name: Cache R packages
+      uses: actions/cache@937d24475381cd9c75ae6db12cb4e79714b926ed # v3.0.11
+      with:
+        path: ${{ env.R_LIBS_USER }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-6-${{ hashFiles('R-package/DESCRIPTION') }}
+
+    - uses: actions/setup-python@7f80679172b057fc5e90d70d197929d454754a5a # v4.3.0
+      with:
+        python-version: "3.8"
+        architecture: 'x64'
+
+    - uses: r-lib/actions/setup-tinytex@v2
+
     - name: Install dependencies
       shell: Rscript {0}
       run: |
-        install.packages(${{ env.R_PACKAGES }},
+        source("./R-package/tests/helper_scripts/install_deps.R")
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
 
     - name: Test R
       run: |
-        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool='${{ matrix.config.build }}'
+        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool="${{ matrix.config.build }}" --task=check
 
-  test-R-CRAN:
+  test-R-on-Debian:
+    name: Test R package on Debian
     runs-on: ubuntu-latest
-
+    container:
-    strategy:
+      image: rhub/debian-gcc-devel
-      fail-fast: false
-      matrix:
-        config:
-          - {r: 'release'}
 
     steps:
-    - uses: actions/checkout@v2
+    - name: Install system dependencies
+      run: |
+        # Must run before checkout to have the latest git installed.
+        # No need to add pandoc, the container has it figured out.
+        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
+
+    - name: Trust git cloning project sources
+      run: |
+        git config --global --add safe.directory "${GITHUB_WORKSPACE}"
+
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
       with:
         submodules: 'true'
 
-    - uses: r-lib/actions/setup-r@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - uses: r-lib/actions/setup-tinytex@master
-
-    - name: Install system packages
-      run: |
-        sudo apt-get update && sudo apt-get install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev
-
     - name: Install dependencies
-      shell: Rscript {0}
+      shell: bash -l {0}
       run: |
-        install.packages(${{ env.R_PACKAGES }},
+        /tmp/R-devel/bin/Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
 
-    - name: Check R Package
+    - name: Test R
+      shell: bash -l {0}
       run: |
-        # Print stacktrace upon success of failure
+        python3 tests/ci_build/test_r_package.py --r=/tmp/R-devel/bin/R --build-tool=autotools --task=check
-        make Rcheck || tests/ci_build/print_r_stacktrace.sh fail
+
-        tests/ci_build/print_r_stacktrace.sh success
+    - uses: dorny/paths-filter@v2
+      id: changes
+      with:
+        filters: |
+          r_package:
+            - 'R-package/**'
+
+    - name: Run document check
+      if: steps.changes.outputs.r_package == 'true'
+      run: |
+        python3 tests/ci_build/test_r_package.py --r=/tmp/R-devel/bin/R --task=doc

.github/workflows/scorecards.yml

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

.github/workflows/update_rapids.yml

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

.gitignore

@@ -48,10 +48,13 @@ Debug
 *.Rproj
 ./xgboost.mpi
 ./xgboost.mock
+*.bak
 #.Rbuildignore
 R-package.Rproj
 *.cache*
 .mypy_cache/
+doxygen
+
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -63,6 +66,7 @@ nb-configuration*
 # Eclipse
 .project
 .cproject
+.classpath
 .pydevproject
 .settings/
 build
@@ -96,8 +100,11 @@ metastore_db
 R-package/src/Makevars
 *.lib
 
-# Visual Studio Code
+# Visual Studio
-/.vscode/
+.vs/
+CMakeSettings.json
+*.ilk
+*.pdb
 
 # IntelliJ/CLion
 .idea
@@ -125,3 +132,21 @@ credentials.csv
 *.pub
 *.rdp
 *_rsa
+
+# Visual Studio code + extensions
+.vscode
+.metals
+.bloop
+
+# python tests
+demo/**/*.txt
+*.dmatrix
+.hypothesis
+__MACOSX/
+model*.json
+
+# R tests
+*.libsvm
+*.rds
+Rplots.pdf
+*.zip

.gitmodules

@@ -2,9 +2,6 @@
 	path = dmlc-core
 	url = https://github.com/dmlc/dmlc-core
 	branch = main
-[submodule "cub"]
-	path = cub
-	url = https://github.com/NVlabs/cub
 [submodule "gputreeshap"]
 	path = gputreeshap
 	url = https://github.com/rapidsai/gputreeshap.git

.readthedocs.yaml

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

.travis.yml

@@ -1,68 +0,0 @@
-sudo: required
-
-dist: bionic
-
-env:
-  global:
-    - secure: "PR16i9F8QtNwn99C5NDp8nptAS+97xwDtXEJJfEiEVhxPaaRkOp0MPWhogCaK0Eclxk1TqkgWbdXFknwGycX620AzZWa/A1K3gAs+GrpzqhnPMuoBJ0Z9qxXTbSJvCyvMbYwVrjaxc/zWqdMU8waWz8A7iqKGKs/SqbQ3rO6v7c="
-    - secure: "dAGAjBokqm/0nVoLMofQni/fWIBcYSmdq4XvCBX1ZAMDsWnuOfz/4XCY6h2lEI1rVHZQ+UdZkc9PioOHGPZh5BnvE49/xVVWr9c4/61lrDOlkD01ZjSAeoV0fAZq+93V/wPl4QV+MM+Sem9hNNzFSbN5VsQLAiWCSapWsLdKzqA="
-
-jobs:
-  include:
-    - os: osx
-      arch: amd64
-      osx_image: xcode10.2
-      env: TASK=python_test
-    - os: osx
-      arch: amd64
-      osx_image: xcode10.2
-      env: TASK=java_test
-
-# dependent brew packages
-addons:
-  homebrew:
-    packages:
-      - cmake
-      - libomp
-      - graphviz
-      - openssl
-      - libgit2
-      - lz4
-      - wget
-      - r
-    update: true
-  apt:
-    packages:
-      - snapd
-      - unzip
-
-before_install:
-  - source tests/travis/travis_setup_env.sh
-  - if [ "${TASK}" != "python_sdist_test" ]; then export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package; fi
-  - echo "MAVEN_OPTS='-Xmx2g -XX:MaxPermSize=1024m -XX:ReservedCodeCacheSize=512m -Dorg.slf4j.simpleLogger.defaultLogLevel=error'" > ~/.mavenrc
-
-install:
-  - source tests/travis/setup.sh
-
-script:
-  - tests/travis/run_test.sh
-
-cache:
-  directories:
-    - ${HOME}/.cache/usr
-    - ${HOME}/.cache/pip
-
-before_cache:
-  - tests/travis/travis_before_cache.sh
-
-after_failure:
-  - tests/travis/travis_after_failure.sh
-
-after_success:
-  - tree build
-  - bash <(curl -s https://codecov.io/bash) -a '-o src/ src/*.c'
-
-notifications:
-  email:
-    on_success: change
-    on_failure: always

CITATION

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

CMakeLists.txt

@@ -1,9 +1,10 @@
-cmake_minimum_required(VERSION 3.13)
+cmake_minimum_required(VERSION 3.18 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.4.0)
+project(xgboost LANGUAGES CXX C VERSION 2.0.0)
 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)
 
@@ -13,8 +14,24 @@ endif ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUA
 
 message(STATUS "CMake version ${CMAKE_VERSION}")
 
-if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 5.0)
+# Check compiler versions
-  message(FATAL_ERROR "GCC version must be at least 5.0!")
+# Use recent compilers to ensure that std::filesystem is available
+if(MSVC)
+  if(MSVC_VERSION LESS 1920)
+    message(FATAL_ERROR "Need Visual Studio 2019 or newer to build XGBoost")
+  endif()
+elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "8.1")
+    message(FATAL_ERROR "Need GCC 8.1 or newer to build XGBoost")
+  endif()
+elseif(CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang")
+  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "11.0")
+    message(FATAL_ERROR "Need Xcode 11.0 (AppleClang 11.0) or newer to build XGBoost")
+  endif()
+elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
+  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "9.0")
+    message(FATAL_ERROR "Need Clang 9.0 or newer to build XGBoost")
+  endif()
 endif()
 
 include(${xgboost_SOURCE_DIR}/cmake/FindPrefetchIntrinsics.cmake)
@@ -28,6 +45,7 @@ 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)
@@ -45,8 +63,10 @@ option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
 set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
 option(RABIT_MOCK "Build rabit with mock" OFF)
 option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
+option(KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR "Output build artifacts in CMake binary dir" OFF)
 ## CUDA
 option(USE_CUDA  "Build with GPU acceleration" OFF)
+option(USE_PER_THREAD_DEFAULT_STREAM "Build with per-thread default stream" ON)
 option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
 option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
 set(GPU_COMPUTE_VER "" CACHE STRING
@@ -62,9 +82,9 @@ set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
   "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
 address, leak, undefined and thread.")
 ## Plugins
-option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
 option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
 option(PLUGIN_RMM "Build with RAPIDS Memory Manager (RMM)" OFF)
+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)
@@ -92,6 +112,9 @@ endif (R_LIB AND GOOGLE_TEST)
 if (USE_AVX)
   message(SEND_ERROR  "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from XGBoost.")
 endif (USE_AVX)
+if (PLUGIN_LZ4)
+  message(SEND_ERROR  "The option 'PLUGIN_LZ4' is removed from XGBoost.")
+endif (PLUGIN_LZ4)
 if (PLUGIN_RMM AND NOT (USE_CUDA))
   message(SEND_ERROR "`PLUGIN_RMM` must be enabled with `USE_CUDA` flag.")
 endif (PLUGIN_RMM AND NOT (USE_CUDA))
@@ -109,6 +132,20 @@ endif (ENABLE_ALL_WARNINGS)
 if (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
   message(SEND_ERROR "Cannot build a static library libxgboost.a when R or JVM packages are enabled.")
 endif (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
+if (PLUGIN_FEDERATED)
+  if (CMAKE_CROSSCOMPILING)
+    message(SEND_ERROR "Cannot cross compile with federated learning support")
+  endif ()
+  if (BUILD_STATIC_LIB)
+    message(SEND_ERROR "Cannot build static lib with federated learning support")
+  endif ()
+  if (R_LIB OR JVM_BINDINGS)
+    message(SEND_ERROR "Cannot enable federated learning support when R or JVM packages are enabled.")
+  endif ()
+  if (WIN32)
+    message(SEND_ERROR "Federated learning not supported for Windows platform")
+  endif ()
+endif ()
 
 #-- Sanitizer
 if (USE_SANITIZER)
@@ -117,18 +154,20 @@ if (USE_SANITIZER)
 endif (USE_SANITIZER)
 
 if (USE_CUDA)
-  SET(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
+  set(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
   # `export CXX=' is ignored by CMake CUDA.
   set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
   message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
 
   enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.0)
+  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 11.0)
-    message(FATAL_ERROR "CUDA version must be at least 10.0!")
+    message(FATAL_ERROR "CUDA version must be at least 11.0!")
   endif()
   set(GEN_CODE "")
   format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
   add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
+
+  find_package(CUDAToolkit REQUIRED)
 endif (USE_CUDA)
 
 if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
@@ -141,34 +180,54 @@ find_package(Threads REQUIRED)
 
 if (USE_OPENMP)
   if (APPLE)
-    # Require CMake 3.16+ on Mac OSX, as previous versions of CMake had trouble locating
+    find_package(OpenMP)
-    # OpenMP on Mac. See https://github.com/dmlc/xgboost/pull/5146#issuecomment-568312706
+    if (NOT OpenMP_FOUND)
-    cmake_minimum_required(VERSION 3.16)
+      # Try again with extra path info; required for libomp 15+ from Homebrew
-  endif (APPLE)
+      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 ${HOMEBREW_LIBOMP_PREFIX}/lib/libomp.dylib)
       find_package(OpenMP REQUIRED)
+    endif ()
+  else ()
+    find_package(OpenMP REQUIRED)
+  endif ()
 endif (USE_OPENMP)
+#Add for IBM i
+if (${CMAKE_SYSTEM_NAME} MATCHES "OS400")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
+  set(CMAKE_CXX_ARCHIVE_CREATE "<CMAKE_AR> -X64 qc <TARGET> <OBJECTS>")
+endif()
+
+if (USE_NCCL)
+  find_package(Nccl REQUIRED)
+endif (USE_NCCL)
 
 # dmlc-core
 msvc_use_static_runtime()
+if (FORCE_SHARED_CRT)
+  set(DMLC_FORCE_SHARED_CRT ON)
+endif ()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-set_target_properties(dmlc PROPERTIES
+
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
 if (MSVC)
-  target_compile_options(dmlc PRIVATE
-                         -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
   if (TARGET dmlc_unit_tests)
     target_compile_options(dmlc_unit_tests PRIVATE
                            -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
   endif (TARGET dmlc_unit_tests)
 endif (MSVC)
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(dmlc PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
 
 # rabit
 add_subdirectory(rabit)
+if (RABIT_BUILD_MPI)
+  find_package(MPI REQUIRED)
+endif (RABIT_BUILD_MPI)
 
 # core xgboost
 add_subdirectory(${xgboost_SOURCE_DIR}/src)
@@ -179,9 +238,27 @@ if (R_LIB)
   add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
 endif (R_LIB)
 
+# This creates its own shared library `xgboost4j'.
+if (JVM_BINDINGS)
+  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
+endif (JVM_BINDINGS)
+
 # Plugin
 add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
 
+if (PLUGIN_RMM)
+  find_package(rmm REQUIRED)
+
+  # Patch the rmm targets so they reference the static cudart
+  # Remove this patch once RMM stops specifying cudart requirement
+  # (since RMM is a header-only library, it should not specify cudart in its CMake config)
+  get_target_property(rmm_link_libs rmm::rmm INTERFACE_LINK_LIBRARIES)
+  list(REMOVE_ITEM rmm_link_libs CUDA::cudart)
+  list(APPEND rmm_link_libs CUDA::cudart_static)
+  set_target_properties(rmm::rmm PROPERTIES INTERFACE_LINK_LIBRARIES "${rmm_link_libs}")
+  get_target_property(rmm_link_libs rmm::rmm INTERFACE_LINK_LIBRARIES)
+endif (PLUGIN_RMM)
+
 #-- library
 if (BUILD_STATIC_LIB)
   add_library(xgboost STATIC)
@@ -189,50 +266,44 @@ else (BUILD_STATIC_LIB)
   add_library(xgboost SHARED)
 endif (BUILD_STATIC_LIB)
 target_link_libraries(xgboost PRIVATE objxgboost)
-
-if (USE_CUDA)
-  xgboost_set_cuda_flags(xgboost)
-endif (USE_CUDA)
-
-#-- Hide all C++ symbols
-if (HIDE_CXX_SYMBOLS)
-  foreach(target objxgboost xgboost dmlc)
-    set_target_properties(${target} PROPERTIES CXX_VISIBILITY_PRESET hidden)
-  endforeach()
-endif (HIDE_CXX_SYMBOLS)
-
 target_include_directories(xgboost
   INTERFACE
   $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
   $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
-
-# This creates its own shared library `xgboost4j'.
-if (JVM_BINDINGS)
-  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
-endif (JVM_BINDINGS)
 #-- End shared library
 
 #-- CLI for xgboost
 add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
 target_link_libraries(runxgboost PRIVATE objxgboost)
-if (USE_NVTX)
-  enable_nvtx(runxgboost)
-endif (USE_NVTX)
-
 target_include_directories(runxgboost
   PRIVATE
   ${xgboost_SOURCE_DIR}/include
   ${xgboost_SOURCE_DIR}/dmlc-core/include
-  ${xgboost_SOURCE_DIR}/rabit/include)
+  ${xgboost_SOURCE_DIR}/rabit/include
-set_target_properties(
+)
-  runxgboost PROPERTIES
+set_target_properties(runxgboost PROPERTIES OUTPUT_NAME xgboost)
-  OUTPUT_NAME xgboost
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON)
 #-- End CLI for xgboost
 
+# Common setup for all targets
+foreach(target xgboost objxgboost dmlc runxgboost)
+  xgboost_target_properties(${target})
+  xgboost_target_link_libraries(${target})
+  xgboost_target_defs(${target})
+endforeach()
+
+if (JVM_BINDINGS)
+  xgboost_target_properties(xgboost4j)
+  xgboost_target_link_libraries(xgboost4j)
+  xgboost_target_defs(xgboost4j)
+endif (JVM_BINDINGS)
+
+if (KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR)
+  set_output_directory(runxgboost ${xgboost_BINARY_DIR})
+  set_output_directory(xgboost ${xgboost_BINARY_DIR}/lib)
+else ()
   set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
   set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
+endif ()
 # Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
 add_dependencies(xgboost runxgboost)
 
@@ -255,6 +326,8 @@ if (BUILD_C_DOC)
   run_doxygen()
 endif (BUILD_C_DOC)
 
+include(CPack)
+
 include(GNUInstallDirs)
 # Install all headers.  Please note that currently the C++ headers does not form an "API".
 install(DIRECTORY ${xgboost_SOURCE_DIR}/include/xgboost
@@ -295,7 +368,7 @@ write_basic_package_version_file(
   COMPATIBILITY AnyNewerVersion)
 install(
   FILES
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
+  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
   ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
   DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
 
@@ -303,12 +376,18 @@ install(
 if (GOOGLE_TEST)
   enable_testing()
   # Unittests.
+  add_executable(testxgboost)
+  target_link_libraries(testxgboost PRIVATE objxgboost)
+  xgboost_target_properties(testxgboost)
+  xgboost_target_link_libraries(testxgboost)
+  xgboost_target_defs(testxgboost)
+
   add_subdirectory(${xgboost_SOURCE_DIR}/tests/cpp)
+
   add_test(
     NAME TestXGBoostLib
     COMMAND testxgboost
     WORKING_DIRECTORY ${xgboost_BINARY_DIR})
-
   # CLI tests
   configure_file(
     ${xgboost_SOURCE_DIR}/tests/cli/machine.conf.in

CONTRIBUTORS.md

@@ -10,8 +10,8 @@ The Project Management Committee(PMC) consists group of active committers that m
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [Michael Benesty](https://github.com/pommedeterresautee)
   - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Ant Group
+* [Yuan Tang](https://github.com/terrytangyuan), Akuity
-  - Yuan is a software engineer in Ant Group. He contributed mostly in R and Python packages.
+  - Yuan is a founding engineer at Akuity. 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)
@@ -59,7 +59,7 @@ List of Contributors
 * [Skipper Seabold](https://github.com/jseabold)
   - Skipper is the major contributor to the scikit-learn module of XGBoost.
 * [Zygmunt Zając](https://github.com/zygmuntz)
-  - Zygmunt is the master behind the early stopping feature frequently used by kagglers.
+  - Zygmunt is the master behind the early stopping feature frequently used by Kagglers.
 * [Ajinkya Kale](https://github.com/ajkl)
 * [Boliang Chen](https://github.com/cblsjtu)
 * [Yangqing Men](https://github.com/yanqingmen)
@@ -91,7 +91,7 @@ List of Contributors
 * [Henry Gouk](https://github.com/henrygouk)
 * [Pierre de Sahb](https://github.com/pdesahb)
 * [liuliang01](https://github.com/liuliang01)
-  - liuliang01 added support for the qid column for LibSVM input format. This makes ranking task easier in distributed setting.
+  - liuliang01 added support for the qid column for LIBSVM input format. This makes ranking task easier in distributed setting.
 * [Andrew Thia](https://github.com/BlueTea88)
   - Andrew Thia implemented feature interaction constraints
 * [Wei Tian](https://github.com/weitian)

Jenkinsfile

@@ -1,456 +0,0 @@
-#!/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 = '10.0'
-
-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 10.0
-            // using CentOS 6 image
-            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            // The build-gpu-* builds below use Ubuntu image
-            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-gpu-cuda10.2': { BuildCUDA(cuda_version: '10.2', build_rmm: true) },
-            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0') },
-            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '10.0') },
-            'build-jvm-packages-gpu-cuda10.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '10.0') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
-            'build-jvm-doc': { BuildJVMDoc() }
-          ])
-        }
-      }
-    }
-    stage('Jenkins Linux: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-python-cpu': { TestPythonCPU() },
-            'test-python-cpu-arm64': { TestPythonCPUARM64() },
-            // artifact_cuda_version doesn't apply to RMM tests; RMM tests will always match CUDA version between artifact and host env
-            'test-python-gpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', test_rmm: true) },
-            'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '11.0') },
-            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', multi_gpu: true, test_rmm: true) },
-            'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2', test_rmm: true) },
-            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
-            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
-            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') }
-          ])
-        }
-      }
-    }
-    stage('Jenkins Linux: Deploy') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '3.0.0') }
-          ])
-        }
-      }
-    }
-  }
-}
-
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def GetCUDABuildContainerType(cuda_version) {
-  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos6' : 'gpu_build'
-}
-
-def ClangTidy() {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    echo "Running clang-tidy job..."
-    def container_type = "clang_tidy"
-    def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION_ARG=10.1"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
-    """
-    deleteDir()
-  }
-}
-
-def BuildCPU() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} rm -fv dmlc-core/include/dmlc/build_config_default.h
-      # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
-      # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
-      # See discussion at https://github.com/dmlc/xgboost/issues/5510
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
-    """
-    // Sanitizer test
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
-      -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose"
-    """
-
-    stash name: 'xgboost_cli', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCPUARM64() {
-  node('linux && arm64') {
-    unstash name: 'srcs'
-    echo "Build CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    def wheel_tag = "manylinux2014_aarch64"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh --conda-env=aarch64_test -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOL=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
-    ${dockerRun} ${container_type} ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
-    mv -v wheelhouse/*.whl python-package/dist/
-    # Make sure that libgomp.so is vendored in the wheel
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
-    """
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_arm64_cpu", includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
-    stash name: 'xgboost_cli_arm64', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCPUMock() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build CPU with rabit mock"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_mock_cmake.sh
-    """
-    echo 'Stashing rabit C++ test executable (xgboost)...'
-    stash name: 'xgboost_rabit_tests', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
-def BuildCUDA(args) {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    echo "Build with CUDA ${args.cuda_version}"
-    def container_type = GetCUDABuildContainerType(args.cuda_version)
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    def wheel_tag = "manylinux2010_x86_64"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOLS=ON ${arch_flag}
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
-    """
-    if (args.cuda_version == ref_cuda_ver) {
-      sh """
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
-      mv -v wheelhouse/*.whl python-package/dist/
-      # Make sure that libgomp.so is vendored in the wheel
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
-      """
-    }
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-    if (args.cuda_version == ref_cuda_ver && (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release'))) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
-    echo 'Stashing C++ test executable (testxgboost)...'
-    stash name: "xgboost_cpp_tests_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    if (args.build_rmm) {
-      echo "Build with CUDA ${args.cuda_version} and RMM"
-      container_type = "rmm"
-      docker_binary = "docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-      sh """
-      rm -rf build/
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON -DUSE_NCCL=ON -DPLUGIN_RMM=ON ${arch_flag}
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
-      """
-      echo 'Stashing Python wheel...'
-      stash name: "xgboost_whl_rmm_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-      echo 'Stashing C++ test executable (testxgboost)...'
-      stash name: "xgboost_cpp_tests_rmm_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    }
-    deleteDir()
-  }
-}
-
-def BuildRPackageWithCUDA(args) {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    def container_type = 'gpu_build_r_centos6'
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=10.0"
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_r_pkg_with_cuda.sh ${commit_id}
-      """
-      echo 'Uploading R tarball...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_linux_*.tar.gz'
-    }
-    deleteDir()
-  }
-}
-
-def BuildJVMPackagesWithCUDA(args) {
-  node('linux && mgpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
-    def container_type = "jvm_gpu_build"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    // Use only 4 CPU cores
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
-    """
-    echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
-    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
-    deleteDir()
-  }
-}
-
-def BuildJVMPackages(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}"
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    // Use only 4 CPU cores
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
-    """
-    echo 'Stashing XGBoost4J JAR...'
-    stash name: 'xgboost4j_jar', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
-    deleteDir()
-  }
-}
-
-def BuildJVMDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Building JVM doc..."
-    def container_type = "jvm"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
-    """
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading doc...'
-      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
-    }
-    deleteDir()
-  }
-}
-
-def TestPythonCPU() {
-  node('linux && cpu') {
-    unstash name: "xgboost_whl_cuda${ref_cuda_ver}"
-    unstash name: 'srcs'
-    unstash name: 'xgboost_cli'
-    echo "Test Python CPU"
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonCPUARM64() {
-  node('linux && arm64') {
-    unstash name: "xgboost_whl_arm64_cpu"
-    unstash name: 'srcs'
-    unstash name: 'xgboost_cli_arm64'
-    echo "Test Python CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-arm64
-    """
-    deleteDir()
-  }
-}
-
-def TestPythonGPU(args) {
-  def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
-  node(nodeReq) {
-    unstash name: "xgboost_whl_cuda${artifact_cuda_version}"
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
-    unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.host_cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    def mgpu_indicator = (args.multi_gpu) ? 'mgpu' : 'gpu'
-    // Allocate extra space in /dev/shm to enable NCCL
-    def docker_extra_params = (args.multi_gpu) ? "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'" : ''
-    sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator}"
-    if (args.test_rmm) {
-      sh "rm -rfv build/ python-package/dist/"
-      unstash name: "xgboost_whl_rmm_cuda${args.host_cuda_version}"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator} --use-rmm-pool"
-    }
-    deleteDir()
-  }
-}
-
-def TestCppGPU(args) {
-  def nodeReq = 'linux && mgpu'
-  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
-  node(nodeReq) {
-    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
-    unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.host_cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
-    if (args.test_rmm) {
-      sh "rm -rfv build/"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      echo "Test C++, CUDA ${args.host_cuda_version} with RMM"
-      container_type = "rmm"
-      docker_binary = "nvidia-docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "source activate gpu_test && build/testxgboost --use-rmm-pool --gtest_filter=-*DeathTest.*"
-      """
-    }
-    deleteDir()
-  }
-}
-
-def CrossTestJVMwithJDK(args) {
-  node('linux && cpu') {
-    unstash name: 'xgboost4j_jar'
-    unstash name: 'srcs'
-    if (args.spark_version != null) {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
-    } else {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
-    }
-    def container_type = "jvm_cross"
-    def docker_binary = "docker"
-    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
-    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
-    // Run integration tests only when spark_version is given
-    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
-    sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
-    """
-    deleteDir()
-  }
-}
-
-def DeployJVMPackages(args) {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Deploying to xgboost-maven-repo S3 repo...'
-      sh """
-      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
-      """
-    }
-    deleteDir()
-  }
-}

Jenkinsfile-win64

@@ -1,143 +0,0 @@
-#!/usr/bin/groovy
-// -*- mode: groovy -*-
-
-/* Jenkins pipeline for Windows AMD64 target */
-
-import groovy.transform.Field
-
-@Field
-def commit_id   // necessary to pass a variable from one stage to another
-
-pipeline {
-  agent none
-
-  // Setup common job properties
-  options {
-    timestamps()
-    timeout(time: 240, unit: 'MINUTES')
-    buildDiscarder(logRotator(numToKeepStr: '10'))
-    preserveStashes()
-  }
-
-  // Build stages
-  stages {
-    stage('Jenkins Win64: Initialize') {
-      agent { label 'job_initializer' }
-      steps {
-        script {
-          def buildNumber = env.BUILD_NUMBER as int
-          if (buildNumber > 1) milestone(buildNumber - 1)
-          milestone(buildNumber)
-          checkoutSrcs()
-          commit_id = "${GIT_COMMIT}"
-        }
-        sh 'python3 tests/jenkins_get_approval.py'
-        stash name: 'srcs'
-      }
-    }
-    stage('Jenkins Win64: Build') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'build-win64-cuda10.1': { BuildWin64() }
-          ])
-        }
-      }
-    }
-    stage('Jenkins Win64: Test') {
-      agent none
-      steps {
-        script {
-          parallel ([
-            'test-win64-cuda10.1': { TestWin64() },
-          ])
-        }
-      }
-    }
-  }
-}
-
-// check out source code from git
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-def BuildWin64() {
-  node('win64 && cuda10_unified') {
-    unstash name: 'srcs'
-    echo "Building XGBoost for Windows AMD64 target..."
-    bat "nvcc --version"
-    def arch_flag = ""
-    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
-      arch_flag = "-DGPU_COMPUTE_VER=75"
-    }
-    bat """
-    mkdir build
-    cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON ${arch_flag} -DCMAKE_UNITY_BUILD=ON
-    """
-    bat """
-    cd build
-    "C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Community\\MSBuild\\15.0\\Bin\\MSBuild.exe" xgboost.sln /m /p:Configuration=Release /nodeReuse:false
-    """
-    bat """
-    cd python-package
-    conda activate && python setup.py bdist_wheel --universal && for /R %%i in (dist\\*.whl) DO python ../tests/ci_build/rename_whl.py "%%i" ${commit_id} win_amd64
-    """
-    echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
-    bat """
-    cd python-package\\dist
-    COPY /B ..\\..\\tests\\ci_build\\insert_vcomp140.py
-    conda activate && python insert_vcomp140.py *.whl
-    """
-    echo 'Stashing Python wheel...'
-    stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-    }
-    echo 'Stashing C++ test executable (testxgboost)...'
-    stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
-    stash name: 'xgboost_cli', includes: 'xgboost.exe'
-    deleteDir()
-  }
-}
-
-def TestWin64() {
-  node('win64 && cuda10_unified') {
-    unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    unstash name: 'xgboost_cli'
-    unstash name: 'xgboost_cpp_tests'
-    echo "Test Win64"
-    bat "nvcc --version"
-    echo "Running C++ tests..."
-    bat "build\\testxgboost.exe"
-    echo "Installing Python dependencies..."
-    def env_name = 'win64_' + UUID.randomUUID().toString().replaceAll('-', '')
-    bat "conda env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
-    echo "Installing Python wheel..."
-    bat """
-    conda activate ${env_name} && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "Running Python tests..."
-    bat "conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace tests\\python"
-    bat """
-    conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
-    """
-    bat "conda env remove --name ${env_name}"
-    deleteDir()
-  }
-}

Makefile

@@ -1,160 +0,0 @@
-ifndef DMLC_CORE
-	DMLC_CORE = dmlc-core
-endif
-
-ifndef RABIT
-	RABIT = rabit
-endif
-
-ROOTDIR = $(CURDIR)
-
-# workarounds for some buggy old make & msys2 versions seen in windows
-ifeq (NA, $(shell test ! -d "$(ROOTDIR)" && echo NA ))
-        $(warning Attempting to fix non-existing ROOTDIR [$(ROOTDIR)])
-        ROOTDIR := $(shell pwd)
-        $(warning New ROOTDIR [$(ROOTDIR)] $(shell test -d "$(ROOTDIR)" && echo " is OK" ))
-endif
-MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
-ifndef MAKE_OK
-        $(warning Attempting to recover non-functional MAKE [$(MAKE)])
-        MAKE := $(shell which make 2> /dev/null)
-        MAKE_OK := $(shell "$(MAKE)" -v 2> /dev/null)
-endif
-$(warning MAKE [$(MAKE)] - $(if $(MAKE_OK),checked OK,PROBLEM))
-
-include $(DMLC_CORE)/make/dmlc.mk
-
-# set compiler defaults for OSX versus *nix
-# let people override either
-OS := $(shell uname)
-ifeq ($(OS), Darwin)
-ifndef CC
-export CC = $(if $(shell which clang), clang, gcc)
-endif
-ifndef CXX
-export CXX = $(if $(shell which clang++), clang++, g++)
-endif
-else
-# linux defaults
-ifndef CC
-export CC = gcc
-endif
-ifndef CXX
-export CXX = g++
-endif
-endif
-
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++14 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
-CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
-
-ifeq ($(TEST_COVER), 1)
-	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
-else
-	CFLAGS += -O3 -funroll-loops
-endif
-
-ifndef LINT_LANG
-	LINT_LANG= "all"
-endif
-
-# specify tensor path
-.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck
-
-build/%.o: src/%.cc
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.d
-	$(CXX) -c $(CFLAGS) $< -o $@
-
-# The should be equivalent to $(ALL_OBJ)  except for build/cli_main.o
-amalgamation/xgboost-all0.o: amalgamation/xgboost-all0.cc
-	$(CXX) -c $(CFLAGS) $< -o $@
-
-rcpplint:
-	python3 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
-
-lint: rcpplint
-	python3 dmlc-core/scripts/lint.py --exclude_path python-package/xgboost/dmlc-core \
-	  python-package/xgboost/include python-package/xgboost/lib \
-	  python-package/xgboost/make python-package/xgboost/rabit \
-	  python-package/xgboost/src --pylint-rc ${PWD}/python-package/.pylintrc xgboost \
-	  ${LINT_LANG} include src python-package
-
-ifeq ($(TEST_COVER), 1)
-cover: check
-	@- $(foreach COV_OBJ, $(COVER_OBJ), \
-		gcov -pbcul -o $(shell dirname $(COV_OBJ)) $(COV_OBJ) > gcov.log || cat gcov.log; \
-	)
-endif
-
-
-# dask is required to pass, others are not
-# If any of the dask tests failed, contributor won't see the other error.
-mypy:
-	cd python-package; \
-	mypy ./xgboost/dask.py ../tests/python/test_with_dask.py --follow-imports=silent; \
-	mypy ../tests/python-gpu/test_gpu_with_dask.py --follow-imports=silent; \
-	mypy . || true ;
-
-clean:
-	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
-	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
-	if [ -d "R-package/src" ]; then \
-		cd R-package/src; \
-		$(RM) -rf rabit src include dmlc-core amalgamation *.so *.dll; \
-		cd $(ROOTDIR); \
-	fi
-
-clean_all: clean
-	cd $(DMLC_CORE); "$(MAKE)" clean; cd $(ROOTDIR)
-	cd $(RABIT); "$(MAKE)" clean; cd $(ROOTDIR)
-
-# create pip source dist (sdist) pack for PyPI
-pippack: clean_all
-	cd python-package; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
-
-# Script to make a clean installable R package.
-Rpack: clean_all
-	rm -rf xgboost xgboost*.tar.gz
-	cp -r R-package xgboost
-	rm -rf xgboost/src/*.o xgboost/src/*.so xgboost/src/*.dll
-	rm -rf xgboost/src/*/*.o
-	rm -rf xgboost/demo/*.model xgboost/demo/*.buffer xgboost/demo/*.txt
-	rm -rf xgboost/demo/runall.R
-	cp -r src xgboost/src/src
-	cp -r include xgboost/src/include
-	cp -r amalgamation xgboost/src/amalgamation
-	mkdir -p xgboost/src/rabit
-	cp -r rabit/include xgboost/src/rabit/include
-	cp -r rabit/src xgboost/src/rabit/src
-	rm -rf xgboost/src/rabit/src/*.o
-	mkdir -p xgboost/src/dmlc-core
-	cp -r dmlc-core/include xgboost/src/dmlc-core/include
-	cp -r dmlc-core/src xgboost/src/dmlc-core/src
-	cp ./LICENSE xgboost
-# Modify PKGROOT in Makevars.in
-	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
-# Configure Makevars.win (Windows-specific Makevars, likely using MinGW)
-	cp xgboost/src/Makevars.in xgboost/src/Makevars.win
-	cat xgboost/src/Makevars.in| sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.win
-	sed -i -e 's/@OPENMP_CXXFLAGS@/$$\(SHLIB_OPENMP_CXXFLAGS\)/g' xgboost/src/Makevars.win
-	sed -i -e 's/-pthread/$$\(SHLIB_PTHREAD_FLAGS\)/g' xgboost/src/Makevars.win
-	sed -i -e 's/@ENDIAN_FLAG@/-DDMLC_CMAKE_LITTLE_ENDIAN=1/g' xgboost/src/Makevars.win
-	sed -i -e 's/@BACKTRACE_LIB@//g' xgboost/src/Makevars.win
-	sed -i -e 's/@OPENMP_LIB@//g' xgboost/src/Makevars.win
-	rm -f xgboost/src/Makevars.win-e   # OSX sed create this extra file; remove it
-	bash R-package/remove_warning_suppression_pragma.sh
-	bash xgboost/remove_warning_suppression_pragma.sh
-	rm xgboost/remove_warning_suppression_pragma.sh
-	rm -rfv xgboost/tests/helper_scripts/
-
-R ?= R
-
-Rbuild: Rpack
-	$(R) CMD build xgboost
-	rm -rf xgboost
-
-Rcheck: Rbuild
-	$(R) CMD check --as-cran xgboost*.tar.gz
-
--include build/*.d
--include build/*/*.d

R-package/CMakeLists.txt

@@ -16,7 +16,6 @@ target_compile_definitions(xgboost-r
   -DDMLC_LOG_BEFORE_THROW=0
   -DDMLC_DISABLE_STDIN=1
   -DDMLC_LOG_CUSTOMIZE=1
-  -DRABIT_CUSTOMIZE_MSG_
   -DRABIT_STRICT_CXX98_)
 target_include_directories(xgboost-r
   PRIVATE
@@ -31,7 +30,7 @@ if (USE_OPENMP)
 endif (USE_OPENMP)
 set_target_properties(
   xgboost-r PROPERTIES
-  CXX_STANDARD 14
+  CXX_STANDARD 17
   CXX_STANDARD_REQUIRED ON
   POSITION_INDEPENDENT_CODE ON)
 

R-package/DESCRIPTION

@@ -1,12 +1,12 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.4.0.1
+Version: 2.0.0.1
-Date: 2020-08-28
+Date: 2023-09-11
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut", "cre"),
+  person("Tong", "He", role = c("aut"),
          email = "hetong007@gmail.com"),
   person("Michael", "Benesty", role = c("aut"),
          email = "michael@benesty.fr"),
@@ -26,9 +26,12 @@ 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
@@ -51,10 +54,8 @@ Suggests:
     Ckmeans.1d.dp (>= 3.3.1),
     vcd (>= 1.3),
     testthat,
-    lintr,
     igraph (>= 1.0.1),
     float,
-    crayon,
     titanic
 Depends:
     R (>= 3.3.0)
@@ -62,7 +63,7 @@ Imports:
     Matrix (>= 1.1-0),
     methods,
     data.table (>= 1.9.6),
-    magrittr (>= 1.5),
     jsonlite (>= 1.0),
-RoxygenNote: 7.1.1
+RoxygenNote: 7.2.3
-SystemRequirements: GNU make, C++14
+Encoding: UTF-8
+SystemRequirements: GNU make, C++17

R-package/LICENSE

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

R-package/NAMESPACE

@@ -82,7 +82,6 @@ importFrom(graphics,points)
 importFrom(graphics,title)
 importFrom(jsonlite,fromJSON)
 importFrom(jsonlite,toJSON)
-importFrom(magrittr,"%>%")
 importFrom(stats,median)
 importFrom(stats,predict)
 importFrom(utils,head)

R-package/R/callbacks.R

@@ -114,7 +114,7 @@ cb.evaluation.log <- function() {
     if (is.null(mnames) || any(mnames == ""))
       stop("bst_evaluation must have non-empty names")
 
-    mnames <<- gsub('-', '_', names(env$bst_evaluation))
+    mnames <<- gsub('-', '_', names(env$bst_evaluation), fixed = TRUE)
     if (!is.null(env$bst_evaluation_err))
       mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
   }
@@ -185,10 +185,10 @@ cb.reset.parameters <- function(new_params) {
 
   if (typeof(new_params) != "list")
     stop("'new_params' must be a list")
-  pnames <- gsub("\\.", "_", names(new_params))
+  pnames <- gsub(".", "_", names(new_params), fixed = TRUE)
   nrounds <- NULL
 
-  # run some checks in the begining
+  # run some checks in the beginning
   init <- function(env) {
     nrounds <<- env$end_iteration - env$begin_iteration + 1
 
@@ -263,10 +263,7 @@ cb.reset.parameters <- function(new_params) {
 #' \itemize{
 #' \item \code{best_score} the evaluation score at the best iteration
 #' \item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
-#' \item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
-#'      It differs from \code{best_iteration} in multiclass or random forest settings.
 #' }
-#'
 #' The Same values are also stored as xgb-attributes:
 #' \itemize{
 #' \item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)
@@ -303,9 +300,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
     if (length(env$bst_evaluation) == 0)
       stop("For early stopping, watchlist must have at least one element")
 
-    eval_names <- gsub('-', '_', names(env$bst_evaluation))
+    eval_names <- gsub('-', '_', names(env$bst_evaluation), fixed = TRUE)
     if (!is.null(metric_name)) {
-      metric_idx <<- which(gsub('-', '_', metric_name) == eval_names)
+      metric_idx <<- which(gsub('-', '_', metric_name, fixed = TRUE) == eval_names)
       if (length(metric_idx) == 0)
         stop("'metric_name' for early stopping is not one of the following:\n",
              paste(eval_names, collapse = ' '), '\n')
@@ -322,7 +319,7 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
 
     # maximize is usually NULL when not set in xgb.train and built-in metrics
     if (is.null(maximize))
-      maximize <<- grepl('(_auc|_map|_ndcg)', metric_name)
+      maximize <<- grepl('(_auc|_map|_ndcg|_pre)', metric_name)
 
     if (verbose && NVL(env$rank, 0) == 0)
       cat("Will train until ", metric_name, " hasn't improved in ",
@@ -498,13 +495,12 @@ cb.cv.predict <- function(save_models = FALSE) {
         rep(NA_real_, N)
       }
 
-    ntreelimit <- NVL(env$basket$best_ntreelimit,
+    iterationrange <- c(1, NVL(env$basket$best_iteration, env$end_iteration) + 1)
-                      env$end_iteration * env$num_parallel_tree)
     if (NVL(env$params[['booster']], '') == 'gblinear') {
-      ntreelimit <- 0 # must be 0 for gblinear
+      iterationrange <- c(1, 1)  # must be 0 for gblinear
     }
     for (fd in env$bst_folds) {
-      pr <- predict(fd$bst, fd$watchlist[[2]], ntreelimit = ntreelimit, reshape = TRUE)
+      pr <- predict(fd$bst, fd$watchlist[[2]], iterationrange = iterationrange, reshape = TRUE)
       if (is.matrix(pred)) {
         pred[fd$index, ] <- pr
       } else {
@@ -515,7 +511,7 @@ cb.cv.predict <- function(save_models = FALSE) {
     if (save_models) {
       env$basket$models <- lapply(env$bst_folds, function(fd) {
         xgb.attr(fd$bst, 'niter') <- env$end_iteration - 1
-        xgb.Booster.complete(xgb.handleToBooster(fd$bst), saveraw = TRUE)
+        xgb.Booster.complete(xgb.handleToBooster(handle = fd$bst, raw = NULL), saveraw = TRUE)
       })
     }
   }
@@ -533,7 +529,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' Callback closure for collecting the model coefficients history of a gblinear booster
 #' during its training.
 #'
-#' @param sparse when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
+#' @param sparse when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
 #'       Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 #'       when using the "thrifty" feature selector with fairly small number of top features
 #'       selected per iteration.
@@ -548,9 +544,11 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' @return
 #' Results are stored in the \code{coefs} element of the closure.
-#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
+#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy
+#' way to access it.
 #' With \code{xgb.train}, it is either a dense of a sparse matrix.
-#' While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
+#' While with \code{xgb.cv}, it is a list (an element per each fold) of such
+#' matrices.
 #'
 #' @seealso
 #' \code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
@@ -560,10 +558,9 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' #
 #' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
 #' # without considering the 2nd order interactions:
-#' require(magrittr)
 #' x <- model.matrix(Species ~ .^2, iris)[,-1]
 #' colnames(x)
-#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
+#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
 #' param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
 #'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For 'shotgun', which is a default linear updater, using high eta values may result in
@@ -581,7 +578,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
 #'                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
 #'                  callbacks = list(cb.gblinear.history()))
-#' xgb.gblinear.history(bst) %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst), type = 'l')
 #' #  Componentwise boosting is known to have similar effect to Lasso regularization.
 #' # Try experimenting with various values of top_k, eta, nrounds,
 #' # as well as different feature_selectors.
@@ -590,37 +587,39 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
 #'               callbacks = list(cb.gblinear.history()))
 #' # coefficients in the CV fold #3
-#' xgb.gblinear.history(bst)[[3]] %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 #'
 #'
 #' #### Multiclass classification:
 #' #
-#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
+#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 1)
 #' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
+#'               lambda = 0.0003, alpha = 0.0003, nthread = 1)
 #' # For the default linear updater 'shotgun' it sometimes is helpful
 #' # to use smaller eta to reduce instability
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
+#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 50, eta = 0.5,
 #'                  callbacks = list(cb.gblinear.history()))
 #' # Will plot the coefficient paths separately for each class:
-#' xgb.gblinear.history(bst, class_index = 0) %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
-#' xgb.gblinear.history(bst, class_index = 1) %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
-#' xgb.gblinear.history(bst, class_index = 2) %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
 #'
 #' # CV:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
 #'               callbacks = list(cb.gblinear.history(FALSE)))
-#' # 1st forld of 1st class
+#' # 1st fold of 1st class
-#' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
 #'
 #' @export
 cb.gblinear.history <- function(sparse = FALSE) {
   coefs <- NULL
 
   init <- function(env) {
-    if (!is.null(env$bst)) { # xgb.train:
+    # xgb.train(): bst will be present
-    } else if (!is.null(env$bst_folds)) { # xgb.cv:
+    # xgb.cv(): bst_folds will be present
-    } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
+    if (is.null(env$bst) && is.null(env$bst_folds)) {
+        stop("Parent frame has neither 'bst' nor 'bst_folds'")
+    }
   }
 
   # convert from list to (sparse) matrix
@@ -642,9 +641,14 @@ cb.gblinear.history <- function(sparse=FALSE) {
     if (!is.null(env$bst)) { # # xgb.train:
       coefs <<- list2mat(coefs)
     } else { # xgb.cv:
-      # first lapply transposes the list
+      # second lapply transposes the list
-      coefs <<- lapply(seq_along(coefs[[1]]), function(i) lapply(coefs, "[[", i)) %>%
+      coefs <<- lapply(
-                lapply(function(x) list2mat(x))
+        X = lapply(
+          X = seq_along(coefs[[1]]),
+          FUN = function(i) lapply(coefs, "[[", i)
+        ),
+        FUN = list2mat
+      )
     }
   }
 
@@ -655,7 +659,7 @@ cb.gblinear.history <- function(sparse=FALSE) {
     } else { # xgb.cv:
       cf <- vector("list", length(env$bst_folds))
       for (i in seq_along(env$bst_folds)) {
-        dmp <- xgb.dump(xgb.handleToBooster(env$bst_folds[[i]]$bst))
+        dmp <- xgb.dump(xgb.handleToBooster(handle = env$bst_folds[[i]]$bst, raw = NULL))
         cf[[i]] <- as.numeric(grep('(booster|bias|weigh)', dmp, invert = TRUE, value = TRUE))
         if (sparse) cf[[i]] <- as(cf[[i]], "sparseVector")
       }

R-package/R/utils.R

@@ -1,6 +1,6 @@
 #
-# This file is for the low level reuseable utility functions
+# This file is for the low level reusable utility functions
-# that are not supposed to be visibe to a user.
+# that are not supposed to be visible to a user.
 #
 
 #
@@ -38,11 +38,11 @@ check.booster.params <- function(params, ...) {
     stop("params must be a list")
 
   # in R interface, allow for '.' instead of '_' in parameter names
-  names(params) <- gsub("\\.", "_", names(params))
+  names(params) <- gsub(".", "_", names(params), fixed = TRUE)
 
   # merge parameters from the params and the dots-expansion
   dot_params <- list(...)
-  names(dot_params) <- gsub("\\.", "_", names(dot_params))
+  names(dot_params) <- gsub(".", "_", names(dot_params), fixed = TRUE)
   if (length(intersect(names(params),
                        names(dot_params))) > 0)
     stop("Same parameters in 'params' and in the call are not allowed. Please check your 'params' list.")
@@ -140,7 +140,7 @@ check.custom.eval <- function(env = parent.frame()) {
 
 
 # Update a booster handle for an iteration with dtrain data
-xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
+xgb.iter.update <- function(booster_handle, dtrain, iter, obj) {
   if (!identical(class(booster_handle), "xgb.Booster.handle")) {
     stop("booster_handle must be of xgb.Booster.handle class")
   }
@@ -163,7 +163,7 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
 # Evaluate one iteration.
 # Returns a named vector of evaluation metrics
 # with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
+xgb.iter.eval <- function(booster_handle, watchlist, iter, feval) {
   if (!identical(class(booster_handle), "xgb.Booster.handle"))
     stop("class of booster_handle must be xgb.Booster.handle")
 
@@ -178,7 +178,8 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
   } else {
     res <- sapply(seq_along(watchlist), function(j) {
       w <- watchlist[[j]]
-      preds <- predict(booster_handle, w, outputmargin = TRUE, ntreelimit = 0) # predict using all trees
+      ## predict using all trees
+      preds <- predict(booster_handle, w, outputmargin = TRUE, iterationrange = c(1, 1))
       eval_res <- feval(preds, w)
       out <- eval_res$value
       names(out) <- paste0(evnames[j], "-", eval_res$metric)
@@ -233,7 +234,7 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
         y <- factor(y)
       }
     }
-    folds <- xgb.createFolds(y, nfold)
+    folds <- xgb.createFolds(y = y, k = nfold)
   } else {
     # make simple non-stratified folds
     kstep <- length(rnd_idx) %/% nfold
@@ -250,8 +251,7 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
 # Creates CV folds stratified by the values of y.
 # It was borrowed from caret::createFolds and simplified
 # by always returning an unnamed list of fold indices.
-xgb.createFolds <- function(y, k = 10)
+xgb.createFolds <- function(y, k) {
-{
   if (is.numeric(y)) {
     ## Group the numeric data based on their magnitudes
     ## and sample within those groups.
@@ -284,7 +284,7 @@ xgb.createFolds <- function(y, k = 10)
     for (i in seq_along(numInClass)) {
       ## create a vector of integers from 1:k as many times as possible without
       ## going over the number of samples in the class. Note that if the number
-      ## of samples in a class is less than k, nothing is producd here.
+      ## of samples in a class is less than k, nothing is produced here.
       seqVector <- rep(seq_len(k), numInClass[i] %/% k)
       ## add enough random integers to get  length(seqVector) == numInClass[i]
       if (numInClass[i] %% k > 0) seqVector <- c(seqVector, sample.int(k, numInClass[i] %% k))

R-package/R/xgb.Booster.R

@@ -1,7 +1,6 @@
 # Construct an internal xgboost Booster and return a handle to it.
 # internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(),
+xgb.Booster.handle <- function(params, cachelist, modelfile, handle) {
-                               modelfile = NULL) {
   if (typeof(cachelist) != "list" ||
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
@@ -12,7 +11,7 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(),
       ## A filename
       handle <- .Call(XGBoosterCreate_R, cachelist)
       modelfile <- path.expand(modelfile)
-      .Call(XGBoosterLoadModel_R, handle, modelfile[1])
+      .Call(XGBoosterLoadModel_R, handle, enc2utf8(modelfile[1]))
       class(handle) <- "xgb.Booster.handle"
       if (length(params) > 0) {
         xgb.parameters(handle) <- params
@@ -20,7 +19,7 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(),
       return(handle)
     } else if (typeof(modelfile) == "raw") {
       ## A memory buffer
-      bst <- xgb.unserialize(modelfile)
+      bst <- xgb.unserialize(modelfile, handle)
       xgb.parameters(bst) <- params
       return (bst)
     } else if (inherits(modelfile, "xgb.Booster")) {
@@ -44,7 +43,7 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(),
 
 # Convert xgb.Booster.handle to xgb.Booster
 # internal utility function
-xgb.handleToBooster <- function(handle, raw = NULL) {
+xgb.handleToBooster <- function(handle, raw) {
   bst <- list(handle = handle, raw = raw)
   class(bst) <- "xgb.Booster"
   return(bst)
@@ -129,7 +128,12 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
     stop("argument type must be xgb.Booster")
 
   if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(modelfile = object$raw)
+    object$handle <- xgb.Booster.handle(
+      params = list(),
+      cachelist = list(),
+      modelfile = object$raw,
+      handle = object$handle
+    )
   } else {
     if (is.null(object$raw) && saveraw) {
       object$raw <- xgb.serialize(object$handle)
@@ -162,14 +166,17 @@ 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}, local data file or \code{xgb.DMatrix}.
+#' @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 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
 #'        sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
 #'        logistic regression would result in predictions for log-odds instead of probabilities.
-#' @param ntreelimit limit the number of model's trees or boosting iterations used in prediction (see Details).
+#' @param ntreelimit Deprecated, use \code{iterationrange} instead.
-#'        It will use all the trees by default (\code{NULL} value).
 #' @param predleaf whether predict leaf index.
 #' @param predcontrib whether to return feature contributions to individual predictions (see Details).
 #' @param approxcontrib whether to use a fast approximation for feature contributions (see Details).
@@ -179,16 +186,19 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #'        or predinteraction flags is TRUE.
 #' @param training whether is the prediction result used for training.  For dart booster,
 #'        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)
+#'        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
+#'        type and shape of prediction are invariant to model type.
+#'
 #' @param ... Parameters passed to \code{predict.xgb.Booster}
 #'
 #' @details
-#' Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
-#' and it is not necessarily equal to the number of trees in a model.
-#' E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-#' But for multiclass classification, while there are multiple trees per iteration,
-#' \code{ntreelimit} limits the number of boosting iterations.
 #'
-#' Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
+#' Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
 #' since gblinear doesn't keep its boosting history.
 #'
 #' One possible practical applications of the \code{predleaf} option is to use the model
@@ -208,8 +218,13 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' Since it quadratically depends on the number of features, it is recommended to perform selection
 #' of the most important features first. See below about the format of the returned results.
 #'
+#' The \code{predict()} method uses as many threads as defined in \code{xgb.Booster} object (all by default).
+#' If you want to change their number, then assign a new number to \code{nthread} using \code{\link{xgb.parameters<-}}.
+#' Note also that converting a matrix to \code{\link{xgb.DMatrix}} uses multiple threads too.
+#'
 #' @return
-#' For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
+#' The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
+#' for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
 #' For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
 #' a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
 #' the \code{reshape} value.
@@ -231,6 +246,13 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 #' such an array.
 #'
+#' When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
+#' normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
+#'
+#' For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
+#' For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
+#' For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
+#'
 #' @seealso
 #' \code{\link{xgb.train}}.
 #'
@@ -253,7 +275,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' # use all trees by default
 #' pred <- predict(bst, test$data)
 #' # use only the 1st tree
-#' pred1 <- predict(bst, test$data, ntreelimit = 1)
+#' pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
 #'
 #' # Predicting tree leafs:
 #' # the result is an nsamples X ntrees matrix
@@ -305,101 +327,159 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' all.equal(pred, pred_labels)
 #' # prediction from using only 5 iterations should result
 #' # in the same error as seen in iteration 5:
-#' pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
+#' pred5 <- predict(bst, as.matrix(iris[, -5]), iterationrange=c(1, 6))
 #' sum(pred5 != lb)/length(lb)
 #'
-#'
-#' ## random forest-like model of 25 trees for binary classification:
-#'
-#' set.seed(11)
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-#'                nthread = 2, nrounds = 1, objective = "binary:logistic",
-#'                num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-#' # Inspect the prediction error vs number of trees:
-#' lb <- test$label
-#' dtest <- xgb.DMatrix(test$data, label=lb)
-#' err <- sapply(1:25, function(n) {
-#'   pred <- predict(bst, dtest, ntreelimit=n)
-#'   sum((pred > 0.5) != lb)/length(lb)
-#' })
-#' plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-#'
 #' @rdname predict.xgb.Booster
 #' @export
 predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE, ntreelimit = NULL,
                                 predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, training = FALSE, ...) {
+                                reshape = FALSE, 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)
+    newdata <- xgb.DMatrix(newdata, missing = missing, nthread = NVL(object$params[["nthread"]], -1))
   if (!is.null(object[["feature_names"]]) &&
       !is.null(colnames(newdata)) &&
       !identical(object[["feature_names"]], colnames(newdata)))
     stop("Feature names stored in `object` and `newdata` are different!")
-  if (is.null(ntreelimit))
+
-    ntreelimit <- NVL(object$best_ntreelimit, 0)
+  if (NVL(object$params[['booster']], '') == 'gblinear' || is.null(ntreelimit))
-  if (NVL(object$params[['booster']], '') == 'gblinear')
     ntreelimit <- 0
-  if (ntreelimit < 0)
-    stop("ntreelimit cannot be negative")
 
-  option <- 0L + 1L * as.logical(outputmargin) + 2L * as.logical(predleaf) + 4L * as.logical(predcontrib) +
+  if (ntreelimit != 0 && is.null(iterationrange)) {
-    8L * as.logical(approxcontrib) + 16L * as.logical(predinteraction)
+    ## only ntreelimit, initialize iteration range
+    iterationrange <- c(0, 0)
+  } else if (ntreelimit == 0 && !is.null(iterationrange)) {
+    ## only iteration range, handle 1-based indexing
+    iterationrange <- c(iterationrange[1] - 1, iterationrange[2] - 1)
+  } else if (ntreelimit != 0 && !is.null(iterationrange)) {
+    ## both are specified, let libgxgboost throw an error
+  } else {
+    ## no limit is supplied, use best
+    if (is.null(object$best_iteration)) {
+      iterationrange <- c(0, 0)
+    } else {
+      ## We don't need to + 1 as R is 1-based index.
+      iterationrange <- c(0, as.integer(object$best_iteration))
+    }
+  }
+  ## Handle the 0 length values.
+  box <- function(val) {
+    if (length(val) == 0) {
+      cval <- vector(, 1)
+      cval[0] <- val
+      return(cval)
+    }
+    return (val)
+  }
 
-  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1],
+  ## We set strict_shape to TRUE then drop the dimensions conditionally
-               as.integer(ntreelimit), as.integer(training))
+  args <- list(
+    training = box(training),
+    strict_shape = box(TRUE),
+    iteration_begin = box(as.integer(iterationrange[1])),
+    iteration_end = box(as.integer(iterationrange[2])),
+    ntree_limit = box(as.integer(ntreelimit)),
+    type = box(as.integer(0))
+  )
+
+  set_type <- function(type) {
+    if (args$type != 0) {
+      stop("One type of prediction at a time.")
+    }
+    return(box(as.integer(type)))
+  }
+  if (outputmargin) {
+    args$type <- set_type(1)
+  }
+  if (predcontrib) {
+    args$type <- set_type(if (approxcontrib) 3 else 2)
+  }
+  if (predinteraction) {
+    args$type <- set_type(if (approxcontrib) 5 else 4)
+  }
+  if (predleaf) {
+    args$type <- set_type(6)
+  }
+
+  predts <- .Call(
+    XGBoosterPredictFromDMatrix_R, object$handle, newdata, jsonlite::toJSON(args, auto_unbox = TRUE)
+  )
+  names(predts) <- c("shape", "results")
+  shape <- predts$shape
+  ret <- predts$results
 
   n_ret <- length(ret)
   n_row <- nrow(newdata)
-  npred_per_case <- n_ret / n_row
+  if (n_row != shape[1]) {
+    stop("Incorrect predict shape.")
+  }
 
-  if (n_ret %% n_row != 0)
+  arr <- array(data = ret, dim = rev(shape))
-    stop("prediction length ", n_ret, " is not multiple of nrows(newdata) ", n_row)
+
+  cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+  n_groups <- shape[2]
+
+  ## Needed regardless of whether strict shape is being used.
+  if (predcontrib) {
+    dimnames(arr) <- list(cnames, NULL, NULL)
+  } else if (predinteraction) {
+    dimnames(arr) <- list(cnames, cnames, NULL, NULL)
+  }
+  if (strict_shape) {
+    return(arr) # strict shape is calculated by libxgboost uniformly.
+  }
 
   if (predleaf) {
-    ret <- if (n_ret == n_row) {
+    ## Predict leaf
-      matrix(ret, ncol = 1)
+    arr <- if (n_ret == n_row) {
+      matrix(arr, ncol = 1)
     } else {
-      matrix(ret, nrow = n_row, byrow = TRUE)
+      matrix(arr, nrow = n_row, byrow = TRUE)
     }
   } else if (predcontrib) {
-    n_col1 <- ncol(newdata) + 1
+    ## Predict contribution
-    n_group <- npred_per_case / n_col1
+    arr <- aperm(a = arr, perm = c(2, 3, 1)) # [group, row, col]
-    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+    arr <- if (n_ret == n_row) {
-    ret <- if (n_ret == n_row) {
+      matrix(arr, ncol =  1, dimnames = list(NULL, cnames))
-      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
+    } else if (n_groups != 1) {
-    } else if (n_group == 1) {
+      ## turns array into list of matrices
-      matrix(ret, nrow = n_row, byrow = TRUE, dimnames = list(NULL, cnames))
+      lapply(seq_len(n_groups), function(g) arr[g, , ])
     } else {
-      arr <- array(ret, c(n_col1, n_group, n_row),
+      ## remove the first axis (group)
-                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2, 3, 1)) # [group, row, col]
+      dn <- dimnames(arr)
-      lapply(seq_len(n_group), function(g) arr[g, , ])
+      matrix(arr[1, , ], nrow = dim(arr)[2], ncol = dim(arr)[3], dimnames = c(dn[2], dn[3]))
     }
   } else if (predinteraction) {
-    n_col1 <- ncol(newdata) + 1
+    ## Predict interaction
-    n_group <- npred_per_case / n_col1^2
+    arr <- aperm(a = arr, perm = c(3, 4, 1, 2)) # [group, row, col, col]
-    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+    arr <- if (n_ret == n_row) {
-    ret <- if (n_ret == n_row) {
+      matrix(arr, ncol = 1, dimnames = list(NULL, cnames))
-      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
+    } else if (n_groups != 1) {
-    } else if (n_group == 1) {
+      ## turns array into list of matrices
-      array(ret, c(n_col1, n_col1, n_row), dimnames = list(cnames, cnames, NULL)) %>% aperm(c(3, 1, 2))
+      lapply(seq_len(n_groups), function(g) arr[g, , , ])
     } else {
-      arr <- array(ret, c(n_col1, n_col1, n_group, n_row),
+      ## remove the first axis (group)
-                   dimnames = list(cnames, cnames, NULL, NULL)) %>% aperm(c(3, 4, 1, 2)) # [group, row, col1, col2]
+      arr <- arr[1, , , , drop = FALSE]
-      lapply(seq_len(n_group), function(g) arr[g, , , ])
+      array(arr, dim = dim(arr)[2:4], dimnames(arr)[2:4])
     }
-  } else if (reshape && npred_per_case > 1) {
+  } else {
-    ret <- matrix(ret, nrow = n_row, byrow = TRUE)
+    ## Normal prediction
+    arr <- if (reshape && n_groups != 1) {
+      matrix(arr, ncol = n_groups, byrow = TRUE)
+    } else {
+      as.vector(ret)
     }
-  return(ret)
+  }
+  return(arr)
 }
 
 #' @rdname predict.xgb.Booster
 #' @export
 predict.xgb.Booster.handle <- function(object, ...) {
 
-  bst <- xgb.handleToBooster(object)
+  bst <- xgb.handleToBooster(handle = object, raw = NULL)
 
   ret <- predict(bst, ...)
   return(ret)
@@ -558,7 +638,7 @@ xgb.attributes <- function(object) {
 #' @export
 xgb.config <- function(object) {
   handle <- xgb.get.handle(object)
-  .Call(XGBoosterSaveJsonConfig_R, handle);
+  .Call(XGBoosterSaveJsonConfig_R, handle)
 }
 
 #' @rdname xgb.config
@@ -600,7 +680,7 @@ xgb.config <- function(object) {
   if (is.null(names(p)) || any(nchar(names(p)) == 0)) {
     stop("parameter names cannot be empty strings")
   }
-  names(p) <- gsub("\\.", "_", names(p))
+  names(p) <- gsub(".", "_", names(p), fixed = TRUE)
   p <- lapply(p, function(x) as.character(x)[1])
   handle <- xgb.get.handle(object)
   for (i in seq_along(p)) {

R-package/R/xgb.DMatrix.R

@@ -1,26 +1,29 @@
 #' Construct xgb.DMatrix object
 #'
 #' Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-#' Supported input file formats are either a libsvm text file or a binary file that was created previously by
+#' 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, or a character
+#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-#'        string representing a filename.
+#'        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 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).
 #'        It is useful when a 0 or some other extreme value represents missing values in data.
 #' @param silent whether to suppress printing an informational message after loading from a file.
+#' @param nthread Number of threads used for creating DMatrix.
 #' @param ... the \code{info} data could be passed directly as parameters, without creating an \code{info} list.
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
-xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
+xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthread = NULL, ...) {
   cnames <- NULL
   if (typeof(data) == "character") {
     if (length(data) > 1)
@@ -29,16 +32,50 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...)
     data <- path.expand(data)
     handle <- .Call(XGDMatrixCreateFromFile_R, data, as.integer(silent))
   } else if (is.matrix(data)) {
-    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing)
+    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))
+    handle <- .Call(
+      XGDMatrixCreateFromCSC_R,
+      data@p,
+      data@i,
+      data@x,
+      nrow(data),
+      missing,
+      as.integer(NVL(nthread, -1))
+    )
     cnames <- colnames(data)
+  } else if (inherits(data, "dgRMatrix")) {
+    handle <- .Call(
+      XGDMatrixCreateFromCSR_R,
+      data@p,
+      data@j,
+      data@x,
+      ncol(data),
+      missing,
+      as.integer(NVL(nthread, -1))
+    )
+    cnames <- colnames(data)
+  } else if (inherits(data, "dsparseVector")) {
+    indptr <- c(0L, as.integer(length(data@i)))
+    ind <- as.integer(data@i) - 1L
+    handle <- .Call(
+      XGDMatrixCreateFromCSR_R,
+      indptr,
+      ind,
+      data@x,
+      length(data),
+      missing,
+      as.integer(NVL(nthread, -1))
+    )
   } else {
     stop("xgb.DMatrix does not support construction from ", typeof(data))
   }
   dmat <- handle
-  attributes(dmat) <- list(.Dimnames = list(NULL, cnames), class = "xgb.DMatrix")
+  attributes(dmat) <- list(class = "xgb.DMatrix")
+  if (!is.null(cnames)) {
+    setinfo(dmat, "feature_name", cnames)
+  }
 
   info <- append(info, list(...))
   for (i in seq_along(info)) {
@@ -51,12 +88,12 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...)
 
 # get dmatrix from data, label
 # internal helper method
-xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
+xgb.get.DMatrix <- function(data, label, missing, weight, nthread) {
   if (inherits(data, "dgCMatrix") || is.matrix(data)) {
     if (is.null(label)) {
       stop("label must be provided when data is a matrix")
     }
-    dtrain <- xgb.DMatrix(data, label = label, missing = missing)
+    dtrain <- xgb.DMatrix(data, label = label, missing = missing, nthread = nthread)
     if (!is.null(weight)) {
       setinfo(dtrain, "weight", weight)
     }
@@ -91,7 +128,7 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 #'
 #' stopifnot(nrow(dtrain) == nrow(train$data))
 #' stopifnot(ncol(dtrain) == ncol(train$data))
@@ -119,7 +156,7 @@ dim.xgb.DMatrix <- function(x) {
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 #' dimnames(dtrain)
 #' colnames(dtrain)
 #' colnames(dtrain) <- make.names(1:ncol(train$data))
@@ -128,7 +165,9 @@ dim.xgb.DMatrix <- function(x) {
 #' @rdname dimnames.xgb.DMatrix
 #' @export
 dimnames.xgb.DMatrix <- function(x) {
-  attr(x, '.Dimnames')
+  fn <- getinfo(x, "feature_name")
+  ## row names is null.
+  list(NULL, fn)
 }
 
 #' @rdname dimnames.xgb.DMatrix
@@ -139,13 +178,13 @@ dimnames.xgb.DMatrix <- function(x) {
   if (!is.null(value[[1L]]))
     stop("xgb.DMatrix does not have rownames")
   if (is.null(value[[2]])) {
-    attr(x, '.Dimnames') <- NULL
+    setinfo(x, "feature_name", NULL)
     return(x)
   }
-  if (ncol(x) != length(value[[2]]))
+  if (ncol(x) != length(value[[2]])) {
-    stop("can't assign ", length(value[[2]]), " colnames to a ",
+    stop("can't assign ", length(value[[2]]), " colnames to a ", ncol(x), " column xgb.DMatrix")
-         ncol(x), " column xgb.DMatrix")
+  }
-  attr(x, '.Dimnames') <- value
+  setinfo(x, "feature_name", value[[2]])
   x
 }
 
@@ -161,9 +200,9 @@ dimnames.xgb.DMatrix <- function(x) {
 #' The \code{name} field can be one of the following:
 #'
 #' \itemize{
-#'     \item \code{label}: label Xgboost learn from ;
+#'     \item \code{label}: label XGBoost learn from ;
 #'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
+#'     \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
 #'     \item \code{nrow}: number of rows of the \code{xgb.DMatrix}.
 #'
 #' }
@@ -172,7 +211,7 @@ dimnames.xgb.DMatrix <- function(x) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -189,11 +228,15 @@ 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')) {
+                     'label_lower_bound', 'label_upper_bound', "feature_type", "feature_name")) {
-    stop("getinfo: name must be one of the following\n",
+    stop(
-         "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound'")
+      "getinfo: name must be one of the following\n",
+      "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound', 'feature_type', 'feature_name'"
+    )
   }
-  if (name != "nrow"){
+  if (name == "feature_name" || name == "feature_type") {
+    ret <- .Call(XGDMatrixGetStrFeatureInfo_R, object, name)
+  } else if (name != "nrow") {
     ret <- .Call(XGDMatrixGetInfo_R, object, name)
   } else {
     ret <- nrow(object)
@@ -216,15 +259,15 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #' The \code{name} field can be one of the following:
 #'
 #' \itemize{
-#'     \item \code{label}: label Xgboost learn from ;
+#'     \item \code{label}: label XGBoost learn from ;
 #'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
+#'     \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
 #'     \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
 #' }
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -271,8 +314,38 @@ 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)
 }
 
 
@@ -289,7 +362,7 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -345,7 +418,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' dtrain
 #' print(dtrain, verbose=TRUE)
@@ -362,7 +435,7 @@ print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
   cat(infos)
   cnames <- colnames(x)
   cat('  colnames:')
-  if (verbose & !is.null(cnames)) {
+  if (verbose && !is.null(cnames)) {
     cat("\n'")
     cat(cnames, sep = "','")
     cat("'")

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

@@ -7,7 +7,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' 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.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+#' \url{https://research.facebook.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))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 #' nrounds = 4
@@ -65,8 +65,12 @@
 #' new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
 #'
 #' # learning with new features
-#' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
+#' new.dtrain <- xgb.DMatrix(
-#' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
+#'   data = new.features.train, label = agaricus.train$label, nthread = 2
+#' )
+#' new.dtest <- xgb.DMatrix(
+#'   data = new.features.test, label = agaricus.test$label, nthread = 2
+#' )
 #' watchlist <- list(train = new.dtrain)
 #' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 #'

R-package/R/xgb.cv.R

@@ -75,9 +75,11 @@
 #' @details
 #' The original sample is randomly partitioned into \code{nfold} equal size subsamples.
 #'
-#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
+#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model,
+#' and the remaining \code{nfold - 1} subsamples are used as training data.
 #'
-#' The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
+#' The cross-validation process is then repeated \code{nrounds} times, with each of the
+#' \code{nfold} subsamples used exactly once as the validation data.
 #'
 #' All observations are used for both training and validation.
 #'
@@ -101,9 +103,7 @@
 #'         parameter or randomly generated.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+#'   \item \code{best_ntreelimit} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
 #'   \item \code{pred} CV prediction values available when \code{prediction} is set.
 #'         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
 #'   \item \code{models} a list of the CV folds' models. It is only available with the explicit
@@ -112,7 +112,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
 #'              max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
@@ -135,9 +135,6 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   check.custom.obj()
   check.custom.eval()
 
-  #if (is.null(params[['eval_metric']]) && is.null(feval))
-  #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
-
   # Check the labels
   if ((inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
       (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
@@ -161,10 +158,6 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
     folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, params)
   }
 
-  # Potential TODO: sequential CV
-  #if (strategy == 'sequential')
-  #  stop('Sequential CV strategy is not yet implemented')
-
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
   print_every_n <- max(as.integer(print_every_n), 1L)
@@ -194,7 +187,13 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # create the booster-folds
   # train_folds
-  dall <- xgb.get.DMatrix(data, label, missing)
+  dall <- xgb.get.DMatrix(
+    data = data,
+    label = label,
+    missing = missing,
+    weight = NULL,
+    nthread = params$nthread
+  )
   bst_folds <- lapply(seq_along(folds), function(k) {
     dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow
@@ -202,7 +201,12 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
        dtrain <- slice(dall, unlist(folds[-k]))
     else
        dtrain <- slice(dall, train_folds[[k]])
-    handle <- xgb.Booster.handle(params, list(dtrain, dtest))
+    handle <- xgb.Booster.handle(
+      params = params,
+      cachelist = list(dtrain, dtest),
+      modelfile = NULL,
+      handle = NULL
+    )
     list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test = dtest), index = folds[[k]])
   })
   rm(dall)
@@ -223,8 +227,18 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
     for (f in cb$pre_iter) f()
 
     msg <- lapply(bst_folds, function(fd) {
-      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
+      xgb.iter.update(
-      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
+        booster_handle = fd$bst,
+        dtrain = fd$dtrain,
+        iter = iteration - 1,
+        obj = obj
+      )
+      xgb.iter.eval(
+        booster_handle = fd$bst,
+        watchlist = fd$watchlist,
+        iter = iteration - 1,
+        feval = feval
+      )
     })
     msg <- simplify2array(msg)
     bst_evaluation <- rowMeans(msg)

R-package/R/xgb.dump.R

@@ -6,8 +6,6 @@
 #' @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.ggplot.R

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

R-package/R/xgb.importance.R

@@ -96,40 +96,48 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
   if (!(is.null(feature_names) || is.character(feature_names)))
     stop("feature_names: Has to be a character vector")
 
-  model_text_dump <- xgb.dump(model = model, with_stats = TRUE)
+  model <- xgb.Booster.complete(model)
-
+  config <- jsonlite::fromJSON(xgb.config(model))
-  # linear model
+  if (config$learner$gradient_booster$name == "gblinear") {
-  if (model_text_dump[2] == "bias:"){
+    args <- list(importance_type = "weight", feature_names = feature_names)
-    weights <- which(model_text_dump == "weight:") %>%
+    results <- .Call(
-               {model_text_dump[(. + 1):length(model_text_dump)]} %>%
+      XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
-               as.numeric
+    )
-
+    names(results) <- c("features", "shape", "weight")
-    num_class <- NVL(model$params$num_class, 1)
+    if (length(results$shape) == 2) {
-    if (is.null(feature_names))
+        n_classes <- results$shape[2]
-      feature_names <- seq(to = length(weights) / num_class) - 1
-    if (length(feature_names) * num_class != length(weights))
-      stop("feature_names length does not match the number of features used in the model")
-
-    result <- if (num_class == 1) {
-      data.table(Feature = feature_names, Weight = weights)[order(-abs(Weight))]
     } else {
-      data.table(Feature = rep(feature_names, each = num_class),
+        n_classes <- 0
-                 Weight = weights,
-                 Class = seq_len(num_class) - 1)[order(Class, -abs(Weight))]
     }
-  } else { # tree model
+    importance <- if (n_classes == 0) {
-      result <- xgb.model.dt.tree(feature_names = feature_names,
+      data.table(Feature = results$features, Weight = results$weight)[order(-abs(Weight))]
-                                  text = model_text_dump,
+    } else {
-                                  trees = trees)[
+      data.table(
-          Feature != "Leaf", .(Gain = sum(Quality),
+        Feature = rep(results$features, each = n_classes), Weight = results$weight, Class = seq_len(n_classes) - 1
-                               Cover = sum(Cover),
+      )[order(Class, -abs(Weight))]
-                               Frequency = .N), by = Feature][
-        , `:=`(Gain = Gain / sum(Gain),
-               Cover = Cover / sum(Cover),
-               Frequency = Frequency / sum(Frequency))][
-          order(Gain, decreasing = TRUE)]
     }
-  result
+  } else {
+    concatenated <- list()
+    output_names <- vector()
+    for (importance_type in c("weight", "total_gain", "total_cover")) {
+      args <- list(importance_type = importance_type, feature_names = feature_names, tree_idx = trees)
+      results <- .Call(
+        XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
+      )
+      names(results) <- c("features", "shape", importance_type)
+      concatenated[
+        switch(importance_type, "weight" = "Frequency", "total_gain" = "Gain", "total_cover" = "Cover")
+      ] <- results[importance_type]
+      output_names <- results$features
+    }
+    importance <- data.table(
+        Feature = output_names,
+        Gain = concatenated$Gain / sum(concatenated$Gain),
+        Cover = concatenated$Cover / sum(concatenated$Cover),
+        Frequency = concatenated$Frequency / sum(concatenated$Frequency)
+    )[order(Gain, decreasing = TRUE)]
+  }
+  importance
 }
 
 # Avoid error messages during CRAN check.

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-internal binary format
+#' The input file is expected to contain a model saved in an xgboost model 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.
@@ -35,12 +35,24 @@ xgb.load <- function(modelfile) {
   if (is.null(modelfile))
     stop("xgb.load: modelfile cannot be NULL")
 
-  handle <- xgb.Booster.handle(modelfile = modelfile)
+  handle <- xgb.Booster.handle(
+    params = list(),
+    cachelist = list(),
+    modelfile = modelfile,
+    handle = NULL
+  )
   # re-use modelfile if it is raw so we do not need to serialize
   if (typeof(modelfile) == "raw") {
-    bst <- xgb.handleToBooster(handle, modelfile)
+    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 = handle, raw = modelfile)
   } else {
-    bst <- xgb.handleToBooster(handle, NULL)
+    bst <- xgb.handleToBooster(handle = handle, raw = NULL)
   }
   bst <- xgb.Booster.complete(bst, saveraw = TRUE)
   return(bst)

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

@@ -3,12 +3,21 @@
 #' 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) {
+xgb.load.raw <- function(buffer, as_booster = FALSE) {
   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)
   }
+}

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

@@ -86,8 +86,7 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
     text <- xgb.dump(model = model, with_stats = TRUE)
   }
 
-  if (length(text) < 2 ||
+  if (length(text) < 2 || !any(grepl('leaf=(\\d+)', text))) {
-      sum(grepl('yes=(\\d+),no=(\\d+)', text)) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
 
@@ -116,16 +115,28 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
                       "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
-  td[isLeaf == FALSE,
+  td[
+    isLeaf == FALSE,
     (branch_cols) := {
       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)
-    }]
+      }
+    }
+  ]
+
   # assign feature_names when available
-  if (!is.null(feature_names)) {
+  is_stump <- function() {
+    return(length(td$Feature) == 1 && is.na(td$Feature))
+  }
+  if (!is.null(feature_names) && !is_stump()) {
     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]]
@@ -134,12 +145,18 @@ 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,
+  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))
-    }]
+      }
+    }
+  ]
 
   # convert some columns to numeric
   numeric_cols <- c("Split", "Quality", "Cover")

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

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

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

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

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

@@ -62,6 +62,9 @@
 #' @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)
 
@@ -75,8 +78,8 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
   while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
     yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
     no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
-    yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
+    yes.nodes.abs.pos <- paste0(yes.row.nodes[, abs.node.position], "_0")
-    no.nodes.abs.pos <- no.row.nodes[, abs.node.position] %>% paste0("_1")
+    no.nodes.abs.pos <- paste0(no.row.nodes[, abs.node.position], "_1")
 
     tree.matrix[ID %in% yes.row.nodes[, Yes], abs.node.position := yes.nodes.abs.pos]
     tree.matrix[ID %in% no.row.nodes[, No], abs.node.position := no.nodes.abs.pos]
@@ -92,19 +95,28 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
   nodes.dt <- tree.matrix[
         , .(Quality = sum(Quality))
         , by = .(abs.node.position, Feature)
-      ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
+      ][, .(Text = paste0(
+              paste0(
+                Feature[seq_len(min(length(Feature), features_keep))],
                 " (",
-                          format(Quality[1:min(length(Quality), features_keep)], digits = 5),
+                format(Quality[seq_len(min(length(Quality), features_keep))], digits = 5),
-                          ")") %>%
+                ")"
-                   paste0(collapse = "\n"))
+              ),
-        , by = abs.node.position]
+              collapse = "\n"
+            )
+          )
+        , by = abs.node.position
+      ]
 
-  edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
+  edges.dt <- data.table::rbindlist(
-    list(tree.matrix[Feature != "Leaf", .(abs.node.position, No)]) %>%
+    l = list(
-    rbindlist() %>%
+      tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)],
-    setnames(c("From", "To")) %>%
+      tree.matrix[Feature != "Leaf", .(abs.node.position, No)]
-    .[, .N, .(From, To)] %>%
+    )
-    .[, N := NULL]
+  )
+  data.table::setnames(edges.dt, c("From", "To"))
+  edges.dt <- edges.dt[, .N, .(From, To)]
+  edges.dt[, N := NULL]
 
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
@@ -120,21 +132,25 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "node",
       attr  = c("color", "fillcolor", "style", "shape", "fontname"),
       value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
+      value = c("DimGray", "1.5", "vee", "Helvetica")
+  )
 
   if (!render) return(invisible(graph))
 

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

@@ -33,7 +33,7 @@
 #' @param col_loess a color to use for the loess curves.
 #' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
 #' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
-#' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
+#' @param plot whether a plot should be drawn. If FALSE, only a list of matrices is returned.
 #' @param ... other parameters passed to \code{plot}.
 #'
 #' @details
@@ -143,7 +143,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       y <- shap_contrib[, f][ord]
       x_lim <- range(x, na.rm = TRUE)
       y_lim <- range(y, na.rm = TRUE)
-      do_na <- plot_NA && any(is.na(x))
+      do_na <- plot_NA && anyNA(x)
       if (do_na) {
         x_range <- diff(x_lim)
         loc_na <- min(x, na.rm = TRUE) + x_range * pos_NA
@@ -157,7 +157,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       plot(x2plot, y, pch = pch, xlab = f, col = col, xlim = x_lim, ylim = y_lim, ylab = ylab, ...)
       grid()
       if (plot_loess) {
-        # compress x to 3 digits, and mean-aggredate y
+        # compress x to 3 digits, and mean-aggregate y
         zz <- data.table(x = signif(x, 3), y)[, .(.N, y = mean(y)), x]
         if (nrow(zz) <= 5) {
           lines(zz$x, zz$y, col = col_loess)
@@ -193,7 +193,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 #' hence allows us to see which features have a negative / positive contribution
 #' on the model prediction, and whether the contribution is different for larger
 #' or smaller values of the feature. We effectively try to replicate the
-#' \code{summary_plot} function from https://github.com/slundberg/shap.
+#' \code{summary_plot} function from https://github.com/shap/shap.
 #'
 #' @inheritParams xgb.plot.shap
 #'
@@ -202,7 +202,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
 #'
 #' @examples # See \code{\link{xgb.plot.shap}}.
 #' @seealso \code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-#'   \url{https://github.com/slundberg/shap}
+#'   \url{https://github.com/shap/shap}
 xgb.plot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
                                   trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
   # Only ggplot implementation is available.
@@ -272,8 +272,8 @@ xgb.shap.data <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       imp <- xgb.importance(model = model, trees = trees, feature_names = colnames(data))
     }
     top_n <- top_n[1]
-    if (top_n < 1 | top_n > 100) stop("top_n: must be an integer within [1, 100]")
+    if (top_n < 1 || top_n > 100) stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[1:min(top_n, NROW(imp))]
+    features <- imp$Feature[seq_len(min(top_n, NROW(imp)))]
   }
   if (is.character(features)) {
     features <- match(features, colnames(data))

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

@@ -34,7 +34,7 @@
 #' The branches that also used for missing values are marked as bold
 #' (as in "carrying extra capacity").
 #'
-#' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
+#' This function uses \href{https://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
 #'
 #' @return
 #'
@@ -98,34 +98,46 @@ 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(dt[Feature != "Leaf", c(ID)] %>% rep(2), dt$ID),
+      from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
       to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-    label = dt[Feature != "Leaf", paste("<", Split)] %>%
+      label = c(
-            c(rep("", nrow(dt[Feature != "Leaf"]))),
+        dt[Feature != "Leaf", paste("<", Split)],
-    style = dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")] %>%
+        rep("", nrow(dt[Feature != "Leaf"]))
-            c(dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]),
+      ),
+      style = c(
+        dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
+        dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
+      ),
       rel   = "leading_to")
+  } else {
+    edges <- NULL
+  }
 
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "node",
       attr  = c("color", "style", "fontname"),
       value = c("DimGray", "filled", "Helvetica")
-      ) %>%
+  )
-    DiagrammeR::add_global_graph_attrs(
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
+      value = c("DimGray", "1.5", "vee", "Helvetica")
+  )
 
   if (!render) return(invisible(graph))
 

R-package/R/xgb.save.R

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

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

@@ -4,6 +4,14 @@
 #' 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')
@@ -17,7 +25,8 @@
 #' pred <- predict(bst, test$data)
 #'
 #' @export
-xgb.save.raw <- function(model) {
+xgb.save.raw <- function(model, raw_format = "deprecated") {
   handle <- xgb.get.handle(model)
-  .Call(XGBoosterModelToRaw_R, handle)
+  args <- list(format = raw_format)
+  .Call(XGBoosterSaveModelToRaw_R, handle, jsonlite::toJSON(args, auto_unbox = TRUE))
 }

R-package/R/xgb.train.R

@@ -18,17 +18,37 @@
 #' 2.1. Parameters for Tree Booster
 #'
 #' \itemize{
-#'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
+#'   \item{ \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1}
-#'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
+#'          when it is added to the current approximation.
+#'          Used to prevent overfitting by making the boosting process more conservative.
+#'          Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model
+#'          more robust to overfitting but slower to compute. Default: 0.3}
+#'   \item{ \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree.
+#'          the larger, the more conservative the algorithm will be.}
 #'   \item \code{max_depth} maximum depth of a tree. Default: 6
-#'   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
+#'   \item{\code{min_child_weight} minimum sum of instance weight (hessian) needed in a child.
-#'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
+#'         If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight,
+#'         then the building process will give up further partitioning.
+#'         In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node.
+#'         The larger, the more conservative the algorithm will be. Default: 1}
+#'   \item{ \code{subsample} subsample ratio of the training instance.
+#'         Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees
+#'         and this will prevent overfitting. It makes computation shorter (because less data to analyse).
+#'         It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1}
 #'   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
 #'   \item \code{lambda} L2 regularization term on weights. Default: 1
 #'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-#'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
+#'   \item{ \code{num_parallel_tree} Experimental parameter. number of trees to grow per round.
-#'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
+#'          Useful to test Random Forest through XGBoost
-#'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
+#'          (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly.
+#'          Default: 1}
+#'   \item{ \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length
+#'          equals to the number of features in the training data.
+#'          \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.}
+#'   \item{ \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions.
+#'        Each item of the list represents one permitted interaction where specified features are allowed to interact with each other.
+#'        Feature index values should start from \code{0} (\code{0} references the first column).
+#'        Leave argument unspecified for no interaction constraints.}
 #' }
 #'
 #' 2.2. Parameters for Linear Booster
@@ -42,29 +62,53 @@
 #' 3. Task Parameters
 #'
 #' \itemize{
-#' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
+#' \item{ \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it.
+#'        The default objective options are below:
 #'   \itemize{
 #'     \item \code{reg:squarederror} Regression with squared loss (Default).
-#'     \item \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
+#'     \item{ \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}.
+#'            All inputs are required to be greater than -1.
+#'            Also, see metric rmsle for possible issue with this objective.}
 #'     \item \code{reg:logistic} logistic regression.
 #'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
 #'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+#'     \item{ \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution.
-#'     \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
+#'            \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).}
-#'     \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
+#'     \item{ \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored).
-#'     \item \code{aft_loss_distribution}: Probabilty Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+#'            Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional
-#'     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
+#'            hazard function \code{h(t) = h0(t) * HR)}.}
-#'     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
+#'     \item{ \code{survival:aft}: Accelerated failure time model for censored survival time data. See
+#'            \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time}
+#'            for details.}
+#'     \item \code{aft_loss_distribution}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+#'     \item{ \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective.
+#'            Class is represented by a number and should be from 0 to \code{num_class - 1}.}
+#'     \item{ \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be
+#'            further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging
+#'            to each class.}
 #'     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
-#'     \item \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
+#'     \item{ \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where
-#'     \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
+#'            \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.}
-#'     \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
+#'     \item{ \code{rank:map}: Use LambdaMART to perform list-wise ranking where
-#'     \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
+#'            \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)}
+#'            is maximized.}
+#'     \item{ \code{reg:gamma}: gamma regression with log-link.
+#'            Output is a mean of gamma distribution.
+#'            It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be
+#'            \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.}
+#'     \item{ \code{reg:tweedie}: Tweedie regression with log-link.
+#'            It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be
+#'            \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.}
+#'   }
 #'  }
 #'   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
-#'   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
+#'   \item{ \code{eval_metric} evaluation metrics for validation data.
+#'          Users can pass a self-defined function to it.
+#'          Default: metric will be assigned according to objective
+#'          (rmse for regression, and error for classification, mean average precision for ranking).
+#'          List is provided in detail section.}
 #' }
 #'
 #' @param data training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
@@ -126,11 +170,11 @@
 #' Parallelization is automatically enabled if \code{OpenMP} is present.
 #' Number of threads can also be manually specified via \code{nthread} parameter.
 #'
-#' The evaluation metric is chosen automatically by Xgboost (according to the objective)
+#' The evaluation metric is chosen automatically by XGBoost (according to the objective)
 #' when the \code{eval_metric} parameter is not provided.
 #' User may set one or several \code{eval_metric} parameters.
 #' Note that when using a customized metric, only this single metric can be used.
-#' The following is the list of built-in metrics for which Xgboost provides optimized implementation:
+#' The following is the list of built-in metrics for which XGBoost provides optimized implementation:
 #'   \itemize{
 #'      \item \code{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
 #'      \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
@@ -141,7 +185,8 @@
 #'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
 #'      \item \code{mae} Mean absolute error
 #'      \item \code{mape} Mean absolute percentage error
-#'      \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+#'      \item{ \code{auc} Area under the curve.
+#'             \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.}
 #'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
 #'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
 #'   }
@@ -171,9 +216,6 @@
 #'         explicitly passed.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
 #'   \item \code{best_score} the best evaluation metric value during early stopping.
 #'         (only available with early stopping).
 #'   \item \code{feature_names} names of the training dataset features
@@ -195,8 +237,8 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #'
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 #' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:
@@ -279,6 +321,10 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     if (is.null(evnames) || any(evnames == ""))
       stop("each element of the watchlist must have a name tag")
   }
+  # Handle multiple evaluation metrics given as a list
+  for (m in params$eval_metric) {
+    params <- c(params, list(eval_metric = m))
+  }
 
   # evaluation printing callback
   params <- c(params)
@@ -317,8 +363,13 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   is_update <- NVL(params[['process_type']], '.') == 'update'
 
   # Construct a booster (either a new one or load from xgb_model)
-  handle <- xgb.Booster.handle(params, append(watchlist, dtrain), xgb_model)
+  handle <- xgb.Booster.handle(
-  bst <- xgb.handleToBooster(handle)
+    params = params,
+    cachelist = append(watchlist, dtrain),
+    modelfile = xgb_model,
+    handle = NULL
+  )
+  bst <- xgb.handleToBooster(handle = handle, raw = NULL)
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
   num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
@@ -344,10 +395,21 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
 
     for (f in cb$pre_iter) f()
 
-    xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
+    xgb.iter.update(
+        booster_handle = bst$handle,
+        dtrain = dtrain,
+        iter = iteration - 1,
+        obj = obj
+    )
 
-    if (length(watchlist) > 0)
+    if (length(watchlist) > 0) {
-      bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
+      bst_evaluation <- xgb.iter.eval(  # nolint: object_usage_linter
+        booster_handle = bst$handle,
+        watchlist = watchlist,
+        iter = iteration - 1,
+        feval = feval
+      )
+    }
 
     xgb.attr(bst$handle, 'niter') <- iteration - 1
 

R-package/R/xgb.unserialize.R

@@ -1,11 +1,21 @@
 #' Load the instance back from \code{\link{xgb.serialize}}
 #'
 #' @param buffer the buffer containing booster instance saved by \code{\link{xgb.serialize}}
+#' @param handle An \code{xgb.Booster.handle} object which will be overwritten with
+#' the new deserialized object. Must be a null handle (e.g. when loading the model through
+#' `readRDS`). If not provided, a new handle will be created.
+#' @return An \code{xgb.Booster.handle} object.
 #'
 #' @export
-xgb.unserialize <- function(buffer) {
+xgb.unserialize <- function(buffer, handle = NULL) {
   cachelist <- list()
+  if (is.null(handle)) {
     handle <- .Call(XGBoosterCreate_R, cachelist)
+  } else {
+    if (!is.null.handle(handle))
+      stop("'handle' is not null/empty. Cannot overwrite existing handle.")
+    .Call(XGBoosterCreateInEmptyObj_R, cachelist, handle)
+  }
   tryCatch(
     .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer),
     error = function(e) {

R-package/R/xgboost.R

@@ -9,8 +9,14 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
                     early_stopping_rounds = NULL, maximize = NULL,
                     save_period = NULL, save_name = "xgboost.model",
                     xgb_model = NULL, callbacks = list(), ...) {
-
+  merged <- check.booster.params(params, ...)
-  dtrain <- xgb.get.DMatrix(data, label, missing, weight)
+  dtrain <- xgb.get.DMatrix(
+    data = data,
+    label = label,
+    missing = missing,
+    weight = weight,
+    nthread = merged$nthread
+  )
 
   watchlist <- list(train = dtrain)
 
@@ -90,7 +96,6 @@ NULL
 #' @importFrom data.table setkey
 #' @importFrom data.table setkeyv
 #' @importFrom data.table setnames
-#' @importFrom magrittr %>%
 #' @importFrom jsonlite fromJSON
 #' @importFrom jsonlite toJSON
 #' @importFrom utils object.size str tail

R-package/README.md

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

R-package/cleanup

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

R-package/configure.ac

@@ -2,10 +2,25 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
+AC_INIT([xgboost],[2.0.0],[],[xgboost],[])
 
-# Use this line to set CC variable to a C compiler
+: ${R_HOME=`R RHOME`}
-AC_PROG_CC
+if test -z "${R_HOME}"; then
+  echo "could not determine R_HOME"
+  exit 1
+fi
+
+CXX17=`"${R_HOME}/bin/R" CMD config CXX17`
+CXX17STD=`"${R_HOME}/bin/R" CMD config CXX17STD`
+CXX="${CXX17} ${CXX17STD}"
+CXXFLAGS=`"${R_HOME}/bin/R" CMD config CXXFLAGS`
+
+CC=`"${R_HOME}/bin/R" CMD config CC`
+CFLAGS=`"${R_HOME}/bin/R" CMD config CFLAGS`
+CPPFLAGS=`"${R_HOME}/bin/R" CMD config CPPFLAGS`
+
+LDFLAGS=`"${R_HOME}/bin/R" CMD config LDFLAGS`
+AC_LANG(C++)
 
 ### Check whether backtrace() is part of libc or the external lib libexecinfo
 AC_MSG_CHECKING([Backtrace lib])
@@ -28,12 +43,19 @@ fi
 
 if test `uname -s` = "Darwin"
 then
-  OPENMP_CXXFLAGS='-Xclang -fopenmp'
+  if command -v brew &> /dev/null
-  OPENMP_LIB='-lomp'
+  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"
   ac_pkg_openmp=no
   AC_MSG_CHECKING([whether OpenMP will work in a package])
   AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
-  ${CC} -o conftest conftest.c ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CXX} -o conftest conftest.cpp ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''

R-package/demo/00Index

@@ -1,6 +1,6 @@
 basic_walkthrough               Basic feature walkthrough
 caret_wrapper                   Use xgboost to train in caret library
-custom_objective                Cutomize loss function, and evaluation metric
+custom_objective                Customize loss function, and evaluation metric
 boost_from_prediction           Boosting from existing prediction
 predict_first_ntree             Predicting using first n trees
 generalized_linear_model        Generalized Linear Model
@@ -8,8 +8,8 @@ cross_validation                Cross validation
 create_sparse_matrix            Create Sparse Matrix
 predict_leaf_indices            Predicting the corresponding leaves
 early_stopping                  Early Stop in training
-poisson_regression              Poisson Regression on count data
+poisson_regression              Poisson regression on count data
-tweedie_regression              Tweddie Regression
+tweedie_regression              Tweedie regression
 gpu_accelerated                 GPU-accelerated tree building algorithms
 interaction_constraints         Interaction constraints among features
 

R-package/demo/README.md

@@ -2,7 +2,7 @@ XGBoost R Feature Walkthrough
 ====
 * [Basic walkthrough of wrappers](basic_walkthrough.R)
 * [Train a xgboost model from caret library](caret_wrapper.R)
-* [Cutomize loss function, and evaluation metric](custom_objective.R)
+* [Customize loss function, and evaluation metric](custom_objective.R)
 * [Boosting from existing prediction](boost_from_prediction.R)
 * [Predicting using first n trees](predict_first_ntree.R)
 * [Generalized Linear Model](generalized_linear_model.R)

R-package/demo/basic_walkthrough.R

@@ -40,7 +40,7 @@ print("Train xgboost with verbose 2, also print information about tree")
 bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
                nthread = 2, objective = "binary:logistic", verbose = 2)
 
-# you can also specify data as file path to a LibSVM format input
+# you can also specify data as file path to a LIBSVM format input
 # since we do not have this file with us, the following line is just for illustration
 # bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nrounds = 2,objective = "binary:logistic")
 
@@ -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)
+bst3 <- xgb.load.raw(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
 print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))

R-package/demo/caret_wrapper.R

@@ -1,5 +1,4 @@
 # install development version of caret library that contains xgboost models
-devtools::install_github("topepo/caret/pkg/caret")
 require(caret)
 require(xgboost)
 require(data.table)
@@ -8,14 +7,23 @@ require(e1071)
 
 # Load Arthritis dataset in memory.
 data(Arthritis)
-# Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
+# Create a copy of the dataset with data.table package
+# (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent
+# and its performance are really good).
 df <- data.table(Arthritis, keep.rownames = FALSE)
 
-# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
+# Let's add some new categorical features to see if it helps.
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
+# Of course these feature are highly correlated to the Age feature.
+# Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features,
+# even in case of highly correlated features.
+# For the first feature we create groups of age by rounding the real age.
+# Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
 df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
+# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old.
+# I choose this value based on nothing.
+# We will see later if simplifying the information based on arbitrary values is a good strategy
+# (I am sure you already have an idea of how well it will work!).
 df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
@@ -28,7 +36,8 @@ fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 2, sear
 # train a xgbTree model using caret::train
 model <- train(factor(Improved) ~ ., data = df, method = "xgbTree", trControl = fitControl)
 
-# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model using xgbLinear
+# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model
+# using xgbLinear
 # model <- train(factor(Improved)~., data = df, method = "xgbLinear", trControl = fitControl)
 
 # See model results

R-package/demo/create_sparse_matrix.R

@@ -2,39 +2,52 @@ require(xgboost)
 require(Matrix)
 require(data.table)
 if (!require(vcd)) {
-  install.packages('vcd') #Available in Cran. Used for its dataset with categorical values.
+  install.packages('vcd') #Available in CRAN. Used for its dataset with categorical values.
   require(vcd)
 }
-# According to its documentation, Xgboost works only on numbers.
+# According to its documentation, XGBoost works only on numbers.
 # Sometimes the dataset we have to work on have categorical data.
-# A categorical variable is one which have a fixed number of values. By example, if for each observation a variable called "Colour" can have only "red", "blue" or "green" as value, it is a categorical variable.
+# A categorical variable is one which have a fixed number of values.
+# By example, if for each observation a variable called "Colour" can have only
+# "red", "blue" or "green" as value, it is a categorical variable.
 #
 # In R, categorical variable is called Factor.
 # Type ?factor in console for more information.
 #
-# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in Xgboost.
+# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix
+# before analyzing it in XGBoost.
 # The method we are going to see is usually called "one hot encoding".
 
 #load Arthritis dataset in memory.
 data(Arthritis)
 
-# create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
+# create a copy of the dataset with data.table package
+# (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent
+# and its performance are really good).
 df <- data.table(Arthritis, keep.rownames = FALSE)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
 print(df)
 
-# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values wich can be ordered, here: None > Some > Marked).
+# 2 columns have factor type, one has ordinal type
+# (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
 cat("Structure of the dataset\n")
 str(df)
 
-# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
+# Let's add some new categorical features to see if it helps.
+# Of course these feature are highly correlated to the Age feature.
+# Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features,
+# even in case of highly correlated features.
 
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
+# For the first feature we create groups of age by rounding the real age.
+# Note that we transform it to factor (categorical data) so the algorithm treat them as independent values.
 df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
+# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old.
+# I choose this value based on nothing.
+# We will see later if simplifying the information based on arbitrary values is a good strategy
+# (I am sure you already have an idea of how well it will work!).
 df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
@@ -48,7 +61,10 @@ print(levels(df[, Treatment]))
 # This method is also called one hot encoding.
 # The purpose is to transform each value of each categorical feature in one binary feature.
 #
-# Let's take, the column Treatment will be replaced by two columns, Placebo, and Treated. Each of them will be binary. For example an observation which had the value Placebo in column Treatment before the transformation will have, after the transformation, the value 1 in the new column Placebo and the value 0 in the new column  Treated.
+# Let's take, the column Treatment will be replaced by two columns, Placebo, and Treated.
+# Each of them will be binary.
+# For example an observation which had the value Placebo in column Treatment before the transformation will have, after the transformation,
+# the value 1 in the new column Placebo and the value 0 in the new column  Treated.
 #
 # Formulae Improved~.-1 used below means transform all categorical features but column Improved to binary values.
 # Column Improved is excluded because it will be our output column, the one we want to predict.
@@ -70,7 +86,10 @@ bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 9,
 
 importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst)
 print(importance)
-# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age. The second most important feature is having received a placebo or not. The sex is third. Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
+# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age.
+# The second most important feature is having received a placebo or not.
+# The sex is third.
+# Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
 
 # Does these result make sense?
 # Let's check some Chi2 between each of these features and the outcome.
@@ -82,8 +101,17 @@ print(chisq.test(df$AgeDiscret, df$Y))
 # Our first simplification of Age gives a Pearson correlation of 8.
 
 print(chisq.test(df$AgeCat, df$Y))
-# The perfectly random split I did between young and old at 30 years old have a low correlation of 2. It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that), but  for the illness we are studying, the age to be vulnerable is not the same. Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
+# The perfectly random split I did between young and old at 30 years old have a low correlation of 2.
+# It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that),
+# but for the illness we are studying, the age to be vulnerable is not the same.
+# Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
 
-# As you can see, in general destroying information by simplifying it won't improve your model. Chi2 just demonstrates that. But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model. The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
+# As you can see, in general destroying information by simplifying it won't improve your model.
+# Chi2 just demonstrates that.
+# But in more complex cases, creating a new feature based on existing one which makes link with the outcome
+# more obvious may help the algorithm and improve the model.
+# The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
 # However it's almost always worse when you add some arbitrary rules.
-# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.
+# Moreover, you can notice that even if we have added some not useful new features highly correlated with
+# other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age.
+# Linear model may not be that strong in these scenario.

R-package/demo/cross_validation.R

@@ -12,7 +12,7 @@ cat('running cross validation\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold = 5, metrics = {'error'})
+xgb.cv(param, dtrain, nrounds, nfold = 5, metrics = 'error')
 
 cat('running cross validation, disable standard deviation display\n')
 # do cross validation, this will print result out as
@@ -22,10 +22,10 @@ xgb.cv(param, dtrain, nrounds, nfold = 5,
        metrics = 'error', showsd = FALSE)
 
 ###
-# you can also do cross validation with cutomized loss function
+# you can also do cross validation with customized loss function
 # See custom_objective.R
 ##
-print ('running cross validation, with cutomsized loss function')
+print ('running cross validation, with customized loss function')
 
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/custom_objective.R

@@ -23,9 +23,9 @@ logregobj <- function(preds, dtrain) {
 
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
+# this may make builtin evaluation metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
+# the builtin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/early_stopping.R

@@ -21,9 +21,9 @@ logregobj <- function(preds, dtrain) {
 }
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
+# this may make builtin evaluation metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
+# the builtin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/interaction_constraints.R

@@ -33,7 +33,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
   }
 
   # Extract nodes with interactions
-  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),
+  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),  # nolint: object_usage_linter
                              c('Feature', paste0('parent_feat_', 1:(input_max_depth - 1))),
                              with = FALSE]
   interaction_trees_split <- split(interaction_trees, seq_len(nrow(interaction_trees)))
@@ -44,7 +44,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
   # Remove non-interactions (same variable)
   interaction_list <- lapply(interaction_list, unique)  # remove same variables
-  interaction_length <- sapply(interaction_list, length)
+  interaction_length <- lengths(interaction_list)
   interaction_list <- interaction_list[interaction_length > 1]
   interaction_list <- unique(lapply(interaction_list, sort))
   return(interaction_list)

R-package/demo/runall.R

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

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

@@ -79,9 +79,9 @@ end_of_table <- empty_lines[empty_lines > start_index][1L]
 
 # Read the contents of the table
 exported_symbols <- objdump_results[(start_index + 1L):end_of_table]
-exported_symbols <- gsub("\t", "", exported_symbols)
+exported_symbols <- gsub("\t", "", exported_symbols, fixed = TRUE)
 exported_symbols <- gsub(".*\\] ", "", exported_symbols)
-exported_symbols <- gsub(" ", "", exported_symbols)
+exported_symbols <- gsub(" ", "", exported_symbols, fixed = TRUE)
 
 # Write R.def file
 writeLines(

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

@@ -38,10 +38,7 @@ The following additional fields are assigned to the model's R object:
 \itemize{
 \item \code{best_score} the evaluation score at the best iteration
 \item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
-\item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
-     It differs from \code{best_iteration} in multiclass or random forest settings.
 }
-
 The Same values are also stored as xgb-attributes:
 \itemize{
 \item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)

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

@@ -8,16 +8,18 @@ during its training.}
 cb.gblinear.history(sparse = FALSE)
 }
 \arguments{
-\item{sparse}{when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
+\item{sparse}{when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
 Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 when using the "thrifty" feature selector with fairly small number of top features
 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
@@ -36,10 +38,9 @@ Callback function expects the following values to be set in its calling frame:
 #
 # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
 # without considering the 2nd order interactions:
-require(magrittr)
 x <- model.matrix(Species ~ .^2, iris)[,-1]
 colnames(x)
-dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
+dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
 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
@@ -57,7 +58,7 @@ matplot(coef_path, type = 'l')
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
                  callbacks = list(cb.gblinear.history()))
-xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst), type = 'l')
 #  Componentwise boosting is known to have similar effect to Lasso regularization.
 # Try experimenting with various values of top_k, eta, nrounds,
 # as well as different feature_selectors.
@@ -66,28 +67,28 @@ xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
               callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
-xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 
 
 #### Multiclass classification:
 #
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 1)
 param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-              lambda = 0.0003, alpha = 0.0003, nthread = 2)
+              lambda = 0.0003, alpha = 0.0003, nthread = 1)
 # For the default linear updater 'shotgun' it sometimes is helpful
 # to use smaller eta to reduce instability
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 50, eta = 0.5,
                  callbacks = list(cb.gblinear.history()))
 # Will plot the coefficient paths separately for each class:
-xgb.gblinear.history(bst, class_index = 0) \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
-xgb.gblinear.history(bst, class_index = 1) \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
-xgb.gblinear.history(bst, class_index = 2) \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
 
 # CV:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
               callbacks = list(cb.gblinear.history(FALSE)))
-# 1st forld of 1st class
+# 1st fold of 1st class
-xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
 
 }
 \seealso{

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)
+dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 
 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)
+dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 dimnames(dtrain)
 colnames(dtrain)
 colnames(dtrain) <- make.names(1:ncol(train$data))

R-package/man/getinfo.Rd

@@ -23,9 +23,9 @@ Get information of an xgb.DMatrix object
 The \code{name} field can be one of the following:
 
 \itemize{
-    \item \code{label}: label Xgboost learn from ;
+    \item \code{label}: label XGBoost learn from ;
     \item \code{weight}: to do a weight rescale ;
-    \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
+    \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
     \item \code{nrow}: number of rows of the \code{xgb.DMatrix}.
 
 }
@@ -34,8 +34,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

R-package/man/normalize.Rd

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

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

@@ -17,6 +17,8 @@
   predinteraction = FALSE,
   reshape = FALSE,
   training = FALSE,
+  iterationrange = NULL,
+  strict_shape = FALSE,
   ...
 )
 
@@ -25,7 +27,11 @@
 \arguments{
 \item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
 
-\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.}
+\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{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).}
@@ -34,8 +40,7 @@ missing values in data (e.g., sometimes 0 or some other extreme value is used).}
 sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
 logistic regression would result in predictions for log-odds instead of probabilities.}
 
-\item{ntreelimit}{limit the number of model's trees or boosting iterations used in prediction (see Details).
+\item{ntreelimit}{Deprecated, use \code{iterationrange} instead.}
-It will use all the trees by default (\code{NULL} value).}
 
 \item{predleaf}{whether predict leaf index.}
 
@@ -52,10 +57,20 @@ or predinteraction flags is TRUE.}
 \item{training}{whether is the prediction result used for training.  For dart booster,
 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)
+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.}
+
+\item{strict_shape}{Default is \code{FALSE}. When it's set to \code{TRUE}, output
+type and shape of prediction are invariant to model type.}
+
 \item{...}{Parameters passed to \code{predict.xgb.Booster}}
 }
 \value{
-For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
+The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
+for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
 For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
 a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
 the \code{reshape} value.
@@ -76,18 +91,19 @@ two dimensions. The "+ 1" columns corresponds to bias. Summing this array along
 produce practically the same result as predict with \code{predcontrib = TRUE}.
 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 such an array.
+
+When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
+normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
+
+For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
+For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
+For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
 }
 \description{
 Predicted values based on either xgboost model or model handle object.
 }
 \details{
-Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
+Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
-and it is not necessarily equal to the number of trees in a model.
-E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-But for multiclass classification, while there are multiple trees per iteration,
-\code{ntreelimit} limits the number of boosting iterations.
-
-Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
 since gblinear doesn't keep its boosting history.
 
 One possible practical applications of the \code{predleaf} option is to use the model
@@ -106,6 +122,10 @@ With \code{predinteraction = TRUE}, SHAP values of contributions of interaction
 are computed. Note that this operation might be rather expensive in terms of compute and memory.
 Since it quadratically depends on the number of features, it is recommended to perform selection
 of the most important features first. See below about the format of the returned results.
+
+The \code{predict()} method uses as many threads as defined in \code{xgb.Booster} object (all by default).
+If you want to change their number, then assign a new number to \code{nthread} using \code{\link{xgb.parameters<-}}.
+Note also that converting a matrix to \code{\link{xgb.DMatrix}} uses multiple threads too.
 }
 \examples{
 ## binary classification:
@@ -120,7 +140,7 @@ bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 # use all trees by default
 pred <- predict(bst, test$data)
 # use only the 1st tree
-pred1 <- predict(bst, test$data, ntreelimit = 1)
+pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
 
 # Predicting tree leafs:
 # the result is an nsamples X ntrees matrix
@@ -172,25 +192,9 @@ str(pred)
 all.equal(pred, pred_labels)
 # prediction from using only 5 iterations should result
 # in the same error as seen in iteration 5:
-pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
+pred5 <- predict(bst, as.matrix(iris[, -5]), iterationrange=c(1, 6))
 sum(pred5 != lb)/length(lb)
 
-
-## random forest-like model of 25 trees for binary classification:
-
-set.seed(11)
-bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-               nthread = 2, nrounds = 1, objective = "binary:logistic",
-               num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-# Inspect the prediction error vs number of trees:
-lb <- test$label
-dtest <- xgb.DMatrix(test$data, label=lb)
-err <- sapply(1:25, function(n) {
-  pred <- predict(bst, dtest, ntreelimit=n)
-  sum((pred > 0.5) != lb)/length(lb)
-})
-plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-
 }
 \references{
 Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}

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

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

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

@@ -19,8 +19,7 @@ Currently it displays dimensions and presence of info-fields and colnames.
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 dtrain
 print(dtrain, verbose=TRUE)

R-package/man/setinfo.Rd

@@ -25,16 +25,15 @@ Set information of an xgb.DMatrix object
 The \code{name} field can be one of the following:
 
 \itemize{
-    \item \code{label}: label Xgboost learn from ;
+    \item \code{label}: label XGBoost learn from ;
     \item \code{weight}: to do a weight rescale ;
-    \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
+    \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
     \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
 }
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

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

@@ -28,8 +28,7 @@ original xgb.DMatrix object
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 dsub <- slice(dtrain, 1:42)
 labels1 <- getinfo(dsub, 'label')

R-package/man/xgb.DMatrix.Rd

@@ -4,11 +4,20 @@
 \alias{xgb.DMatrix}
 \title{Construct xgb.DMatrix object}
 \usage{
-xgb.DMatrix(data, info = list(), missing = NA, silent = FALSE, ...)
+xgb.DMatrix(
+  data,
+  info = list(),
+  missing = NA,
+  silent = FALSE,
+  nthread = NULL,
+  ...
+)
 }
 \arguments{
-\item{data}{a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
+\item{data}{a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-string representing a filename.}
+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{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}
@@ -18,17 +27,18 @@ It is useful when a 0 or some other extreme value represents missing values in d
 
 \item{silent}{whether to suppress printing an informational message after loading from a file.}
 
+\item{nthread}{Number of threads used for creating DMatrix.}
+
 \item{...}{the \code{info} data could be passed directly as parameters, without creating an \code{info} list.}
 }
 \description{
 Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-Supported input file formats are either a libsvm text file or a binary file that was created previously by
+Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
 \code{\link{xgb.DMatrix.save}}).
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')

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

@@ -16,8 +16,7 @@ Save xgb.DMatrix object to binary file
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtrain <- xgb.DMatrix(train$data, label=train$label)
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')

R-package/man/xgb.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.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+\url{https://research.facebook.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 <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 nrounds = 4
@@ -76,8 +76,12 @@ new.features.train <- xgb.create.features(model = bst, agaricus.train$data)
 new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
 
 # learning with new features
-new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
+new.dtrain <- xgb.DMatrix(
-new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
+  data = new.features.train, label = agaricus.train$label, nthread = 2
+)
+new.dtest <- xgb.DMatrix(
+  data = new.features.test, label = agaricus.test$label, nthread = 2
+)
 watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 

R-package/man/xgb.cv.Rd

@@ -135,9 +135,7 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
         parameter or randomly generated.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
-  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+  \item \code{best_ntreelimit} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
-        which could further be used in \code{predict} method
-        (only available with early stopping).
   \item \code{pred} CV prediction values available when \code{prediction} is set.
         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
   \item \code{models} a list of the CV folds' models. It is only available with the explicit
@@ -150,9 +148,11 @@ The cross validation function of xgboost
 \details{
 The original sample is randomly partitioned into \code{nfold} equal size subsamples.
 
-Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
+Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model,
+and the remaining \code{nfold - 1} subsamples are used as training data.
 
-The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
+The cross-validation process is then repeated \code{nrounds} times, with each of the
+\code{nfold} subsamples used exactly once as the validation data.
 
 All observations are used for both training and validation.
 
@@ -160,7 +160,7 @@ Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
              max_depth = 3, eta = 1, objective = "binary:logistic")
 print(cv)

R-package/man/xgb.dump.Rd

@@ -20,8 +20,6 @@ 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-internal binary format
+The input file is expected to contain a model saved in an xgboost model 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

@@ -4,10 +4,12 @@
 \alias{xgb.load.raw}
 \title{Load serialised xgboost model from R's raw vector}
 \usage{
-xgb.load.raw(buffer)
+xgb.load.raw(buffer, as_booster = FALSE)
 }
 \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.plot.importance.Rd

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

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

@@ -87,7 +87,7 @@ more than 5 distinct values.}
 
 \item{which}{whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.}
 
-\item{plot}{whether a plot should be drawn. If FALSE, only a lits of matrices is returned.}
+\item{plot}{whether a plot should be drawn. If FALSE, only a list of matrices is returned.}
 
 \item{...}{other parameters passed to \code{plot}.}
 }

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

@@ -67,12 +67,12 @@ Each point (observation) is coloured based on its feature value. The plot
 hence allows us to see which features have a negative / positive contribution
 on the model prediction, and whether the contribution is different for larger
 or smaller values of the feature. We effectively try to replicate the
-\code{summary_plot} function from https://github.com/slundberg/shap.
+\code{summary_plot} function from https://github.com/shap/shap.
 }
 \examples{
 # See \code{\link{xgb.plot.shap}}.
 }
 \seealso{
 \code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-  \url{https://github.com/slundberg/shap}
+  \url{https://github.com/shap/shap}
 }

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

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

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

@@ -5,10 +5,19 @@
 \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)
+xgb.save.raw(model, raw_format = "deprecated")
 }
 \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

@@ -54,21 +54,43 @@ xgboost(
 
 2. Booster Parameters
 
-2.1. Parameter for Tree Booster
+2.1. Parameters for Tree Booster
 
 \itemize{
-  \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
+  \item{ \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1}
-  \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
+         when it is added to the current approximation.
+         Used to prevent overfitting by making the boosting process more conservative.
+         Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model
+         more robust to overfitting but slower to compute. Default: 0.3}
+  \item{ \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree.
+         the larger, the more conservative the algorithm will be.}
   \item \code{max_depth} maximum depth of a tree. Default: 6
-  \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
+  \item{\code{min_child_weight} minimum sum of instance weight (hessian) needed in a child.
-  \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
+        If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight,
+        then the building process will give up further partitioning.
+        In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node.
+        The larger, the more conservative the algorithm will be. Default: 1}
+  \item{ \code{subsample} subsample ratio of the training instance.
+        Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees
+        and this will prevent overfitting. It makes computation shorter (because less data to analyse).
+        It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1}
   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
-  \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
+  \item \code{lambda} L2 regularization term on weights. Default: 1
-  \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
+  \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-  \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
+  \item{ \code{num_parallel_tree} Experimental parameter. number of trees to grow per round.
+         Useful to test Random Forest through XGBoost
+         (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly.
+         Default: 1}
+  \item{ \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length
+         equals to the number of features in the training data.
+         \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.}
+  \item{ \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions.
+       Each item of the list represents one permitted interaction where specified features are allowed to interact with each other.
+       Feature index values should start from \code{0} (\code{0} references the first column).
+       Leave argument unspecified for no interaction constraints.}
 }
 
-2.2. Parameter for Linear Booster
+2.2. Parameters for Linear Booster
 
 \itemize{
   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -79,29 +101,53 @@ xgboost(
 3. Task Parameters
 
 \itemize{
-\item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
+\item{ \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it.
+       The default objective options are below:
   \itemize{
     \item \code{reg:squarederror} Regression with squared loss (Default).
-    \item \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
+    \item{ \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}.
+           All inputs are required to be greater than -1.
+           Also, see metric rmsle for possible issue with this objective.}
     \item \code{reg:logistic} logistic regression.
     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-    \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+    \item{ \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution.
-    \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
+           \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).}
-    \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
+    \item{ \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored).
-    \item \code{aft_loss_distribution}: Probabilty Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+           Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional
-    \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
+           hazard function \code{h(t) = h0(t) * HR)}.}
-    \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
+    \item{ \code{survival:aft}: Accelerated failure time model for censored survival time data. See
+           \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time}
+           for details.}
+    \item \code{aft_loss_distribution}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
+    \item{ \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective.
+           Class is represented by a number and should be from 0 to \code{num_class - 1}.}
+    \item{ \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be
+           further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging
+           to each class.}
     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
-    \item \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
+    \item{ \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where
-    \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
+           \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.}
-    \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
+    \item{ \code{rank:map}: Use LambdaMART to perform list-wise ranking where
-    \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
+           \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)}
+           is maximized.}
+    \item{ \code{reg:gamma}: gamma regression with log-link.
+           Output is a mean of gamma distribution.
+           It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be
+           \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.}
+    \item{ \code{reg:tweedie}: Tweedie regression with log-link.
+           It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be
+           \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.}
+  }
  }
   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
-  \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
+  \item{ \code{eval_metric} evaluation metrics for validation data.
+         Users can pass a self-defined function to it.
+         Default: metric will be assigned according to objective
+         (rmse for regression, and error for classification, mean average precision for ranking).
+         List is provided in detail section.}
 }}
 
 \item{data}{training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
@@ -185,9 +231,6 @@ An object of class \code{xgb.Booster} with the following elements:
         explicitly passed.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
-  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-        which could further be used in \code{predict} method
-        (only available with early stopping).
   \item \code{best_score} the best evaluation metric value during early stopping.
         (only available with early stopping).
   \item \code{feature_names} names of the training dataset features
@@ -209,11 +252,11 @@ than the \code{xgboost} interface.
 Parallelization is automatically enabled if \code{OpenMP} is present.
 Number of threads can also be manually specified via \code{nthread} parameter.
 
-The evaluation metric is chosen automatically by Xgboost (according to the objective)
+The evaluation metric is chosen automatically by XGBoost (according to the objective)
 when the \code{eval_metric} parameter is not provided.
 User may set one or several \code{eval_metric} parameters.
 Note that when using a customized metric, only this single metric can be used.
-The following is the list of built-in metrics for which Xgboost provides optimized implementation:
+The following is the list of built-in metrics for which XGBoost provides optimized implementation:
   \itemize{
      \item \code{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
      \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
@@ -224,7 +267,8 @@ The following is the list of built-in metrics for which Xgboost provides optimiz
      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
      \item \code{mae} Mean absolute error
      \item \code{mape} Mean absolute percentage error
-     \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+     \item{ \code{auc} Area under the curve.
+            \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.}
      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
   }
@@ -242,8 +286,8 @@ The following callbacks are automatically created when certain parameters are se
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:

R-package/man/xgb.unserialize.Rd

@@ -4,10 +4,17 @@
 \alias{xgb.unserialize}
 \title{Load the instance back from \code{\link{xgb.serialize}}}
 \usage{
-xgb.unserialize(buffer)
+xgb.unserialize(buffer, handle = NULL)
 }
 \arguments{
 \item{buffer}{the buffer containing booster instance saved by \code{\link{xgb.serialize}}}
+
+\item{handle}{An \code{xgb.Booster.handle} object which will be overwritten with
+the new deserialized object. Must be a null handle (e.g. when loading the model through
+`readRDS`). If not provided, a new handle will be created.}
+}
+\value{
+An \code{xgb.Booster.handle} object.
 }
 \description{
 Load the instance back from \code{\link{xgb.serialize}}

R-package/src/Makevars.in

@@ -3,12 +3,11 @@ PKGROOT=../../
 ENABLE_STD_THREAD=1
 # _*_ mode: Makefile; _*_
 
-CXX_STD = CXX14
+CXX_STD = CXX17
 
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\
-           -DDMLC_LOG_CUSTOMIZE=1 -DXGBOOST_CUSTOMIZE_LOGGER=1\
+           -DDMLC_LOG_CUSTOMIZE=1
-           -DRABIT_CUSTOMIZE_MSG_
 
 # disable the use of thread_local for 32 bit windows:
 ifeq ($(R_OSTYPE)$(WIN),windows)
@@ -17,9 +16,94 @@ endif
 $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
-PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ @ENDIAN_FLAG@ -pthread
+PKG_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 ./xgboost_assert.o ./init.o \
+
-         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o \
+OBJECTS= \
-         $(PKGROOT)/rabit/src/engine.o $(PKGROOT)/rabit/src/c_api.o \
+    ./xgboost_R.o \
+    ./xgboost_custom.o \
+    ./init.o \
+    $(PKGROOT)/src/metric/metric.o \
+    $(PKGROOT)/src/metric/elementwise_metric.o \
+    $(PKGROOT)/src/metric/multiclass_metric.o \
+    $(PKGROOT)/src/metric/rank_metric.o \
+    $(PKGROOT)/src/metric/auc.o \
+    $(PKGROOT)/src/metric/survival_metric.o \
+    $(PKGROOT)/src/objective/objective.o \
+    $(PKGROOT)/src/objective/regression_obj.o \
+    $(PKGROOT)/src/objective/multiclass_obj.o \
+    $(PKGROOT)/src/objective/lambdarank_obj.o \
+    $(PKGROOT)/src/objective/hinge.o \
+    $(PKGROOT)/src/objective/aft_obj.o \
+    $(PKGROOT)/src/objective/adaptive.o \
+    $(PKGROOT)/src/objective/init_estimation.o \
+    $(PKGROOT)/src/objective/quantile_obj.o \
+    $(PKGROOT)/src/gbm/gbm.o \
+    $(PKGROOT)/src/gbm/gbtree.o \
+    $(PKGROOT)/src/gbm/gbtree_model.o \
+    $(PKGROOT)/src/gbm/gblinear.o \
+    $(PKGROOT)/src/gbm/gblinear_model.o \
+    $(PKGROOT)/src/data/simple_dmatrix.o \
+    $(PKGROOT)/src/data/data.o \
+    $(PKGROOT)/src/data/sparse_page_raw_format.o \
+    $(PKGROOT)/src/data/ellpack_page.o \
+    $(PKGROOT)/src/data/file_iterator.o \
+    $(PKGROOT)/src/data/gradient_index.o \
+    $(PKGROOT)/src/data/gradient_index_page_source.o \
+    $(PKGROOT)/src/data/gradient_index_format.o \
+    $(PKGROOT)/src/data/sparse_page_dmatrix.o \
+    $(PKGROOT)/src/data/proxy_dmatrix.o \
+    $(PKGROOT)/src/data/iterative_dmatrix.o \
+    $(PKGROOT)/src/predictor/predictor.o \
+    $(PKGROOT)/src/predictor/cpu_predictor.o \
+    $(PKGROOT)/src/predictor/cpu_treeshap.o \
+    $(PKGROOT)/src/tree/constraints.o \
+    $(PKGROOT)/src/tree/param.o \
+    $(PKGROOT)/src/tree/fit_stump.o \
+    $(PKGROOT)/src/tree/tree_model.o \
+    $(PKGROOT)/src/tree/tree_updater.o \
+    $(PKGROOT)/src/tree/multi_target_tree_model.o \
+    $(PKGROOT)/src/tree/updater_approx.o \
+    $(PKGROOT)/src/tree/updater_colmaker.o \
+    $(PKGROOT)/src/tree/updater_prune.o \
+    $(PKGROOT)/src/tree/updater_quantile_hist.o \
+    $(PKGROOT)/src/tree/updater_refresh.o \
+    $(PKGROOT)/src/tree/updater_sync.o \
+    $(PKGROOT)/src/tree/hist/param.o \
+    $(PKGROOT)/src/tree/hist/histogram.o \
+    $(PKGROOT)/src/linear/linear_updater.o \
+    $(PKGROOT)/src/linear/updater_coordinate.o \
+    $(PKGROOT)/src/linear/updater_shotgun.o \
+    $(PKGROOT)/src/learner.o \
+    $(PKGROOT)/src/context.o \
+    $(PKGROOT)/src/logging.o \
+    $(PKGROOT)/src/global_config.o \
+    $(PKGROOT)/src/collective/communicator.o \
+    $(PKGROOT)/src/collective/in_memory_communicator.o \
+    $(PKGROOT)/src/collective/in_memory_handler.o \
+    $(PKGROOT)/src/collective/socket.o \
+    $(PKGROOT)/src/common/charconv.o \
+    $(PKGROOT)/src/common/column_matrix.o \
+    $(PKGROOT)/src/common/common.o \
+    $(PKGROOT)/src/common/error_msg.o \
+    $(PKGROOT)/src/common/hist_util.o \
+    $(PKGROOT)/src/common/host_device_vector.o \
+    $(PKGROOT)/src/common/io.o \
+    $(PKGROOT)/src/common/json.o \
+    $(PKGROOT)/src/common/numeric.o \
+    $(PKGROOT)/src/common/pseudo_huber.o \
+    $(PKGROOT)/src/common/quantile.o \
+    $(PKGROOT)/src/common/random.o \
+    $(PKGROOT)/src/common/stats.o \
+    $(PKGROOT)/src/common/survival_util.o \
+    $(PKGROOT)/src/common/threading_utils.o \
+    $(PKGROOT)/src/common/ranking_utils.o \
+    $(PKGROOT)/src/common/quantile_loss_utils.o \
+    $(PKGROOT)/src/common/timer.o \
+    $(PKGROOT)/src/common/version.o \
+    $(PKGROOT)/src/c_api/c_api.o \
+    $(PKGROOT)/src/c_api/c_api_error.o \
+    $(PKGROOT)/amalgamation/dmlc-minimum0.o \
+    $(PKGROOT)/rabit/src/engine.o \
+    $(PKGROOT)/rabit/src/rabit_c_api.o \
     $(PKGROOT)/rabit/src/allreduce_base.o

R-package/src/Makevars.win

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

R-package/src/init.c

@@ -9,6 +9,7 @@
 #include <Rinternals.h>
 #include <stdlib.h>
 #include <R_ext/Rdynload.h>
+#include <R_ext/Visibility.h>
 
 /* FIXME:
 Check these declarations against the C/Fortran source code.
@@ -17,73 +18,83 @@ Check these declarations against the C/Fortran source code.
 /* .Call calls */
 extern SEXP XGBoosterBoostOneIter_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterCreate_R(SEXP);
+extern SEXP XGBoosterCreateInEmptyObj_R(SEXP, SEXP);
 extern SEXP XGBoosterDumpModel_R(SEXP, SEXP, SEXP, SEXP);
 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 XGBoosterPredictFromDMatrix_R(SEXP, SEXP, SEXP);
-extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSaveModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSetAttr_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSetParam_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterUpdateOneIter_R(SEXP, SEXP, SEXP);
 extern SEXP XGCheckNullPtr_R(SEXP);
-extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSR_R(SEXP, SEXP, SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixCreateFromFile_R(SEXP, SEXP);
-extern SEXP XGDMatrixCreateFromMat_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();
+extern SEXP XGBGetGlobalConfig_R(void);
+extern SEXP XGBoosterFeatureScore_R(SEXP, SEXP);
 
 static const R_CallMethodDef CallEntries[] = {
   {"XGBoosterBoostOneIter_R",     (DL_FUNC) &XGBoosterBoostOneIter_R,     4},
   {"XGBoosterCreate_R",           (DL_FUNC) &XGBoosterCreate_R,           1},
+  {"XGBoosterCreateInEmptyObj_R", (DL_FUNC) &XGBoosterCreateInEmptyObj_R, 2},
   {"XGBoosterDumpModel_R",        (DL_FUNC) &XGBoosterDumpModel_R,        4},
   {"XGBoosterEvalOneIter_R",      (DL_FUNC) &XGBoosterEvalOneIter_R,      4},
   {"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},
+  {"XGBoosterPredictFromDMatrix_R", (DL_FUNC) &XGBoosterPredictFromDMatrix_R, 3},
-  {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          5},
   {"XGBoosterSaveModel_R",        (DL_FUNC) &XGBoosterSaveModel_R,        2},
   {"XGBoosterSetAttr_R",          (DL_FUNC) &XGBoosterSetAttr_R,          3},
   {"XGBoosterSetParam_R",         (DL_FUNC) &XGBoosterSetParam_R,         3},
   {"XGBoosterUpdateOneIter_R",    (DL_FUNC) &XGBoosterUpdateOneIter_R,    3},
   {"XGCheckNullPtr_R",            (DL_FUNC) &XGCheckNullPtr_R,            1},
-  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    4},
+  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    6},
+  {"XGDMatrixCreateFromCSR_R",    (DL_FUNC) &XGDMatrixCreateFromCSR_R,    6},
   {"XGDMatrixCreateFromFile_R",   (DL_FUNC) &XGDMatrixCreateFromFile_R,   2},
-  {"XGDMatrixCreateFromMat_R",    (DL_FUNC) &XGDMatrixCreateFromMat_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},
+  {"XGBoosterFeatureScore_R",     (DL_FUNC) &XGBoosterFeatureScore_R,     2},
   {NULL, NULL, 0}
 };
 
 #if defined(_WIN32)
 __declspec(dllexport)
 #endif  // defined(_WIN32)
-void R_init_xgboost(DllInfo *dll) {
+void attribute_visible R_init_xgboost(DllInfo *dll) {
   R_registerRoutines(dll, NULL, CallEntries, NULL, NULL);
   R_useDynamicSymbols(dll, FALSE);
 }

R-package/src/xgboost-win.def

@@ -0,0 +1,3 @@
+LIBRARY xgboost.dll
+EXPORTS
+ R_init_xgboost

R-package/src/xgboost_R.cc

@@ -1,15 +1,26 @@
-// Copyright (c) 2014 by Contributors
+/**
-#include <dmlc/logging.h>
+ * Copyright 2014-2023 by XGBoost Contributors
-#include <dmlc/omp.h>
+ */
 #include <dmlc/common.h>
+#include <dmlc/omp.h>
 #include <xgboost/c_api.h>
-#include <vector>
+#include <xgboost/context.h>
+#include <xgboost/data.h>
+#include <xgboost/logging.h>
+
+#include <cstdio>
+#include <cstring>
+#include <sstream>
 #include <string>
 #include <utility>
-#include <cstring>
+#include <vector>
-#include <cstdio>
+
-#include <sstream>
+#include "../../src/c_api/c_api_error.h"
-#include "./xgboost_R.h"
+#include "../../src/c_api/c_api_utils.h"  // MakeSparseFromPtr
+#include "../../src/common/threading_utils.h"
+
+#include "./xgboost_R.h"  // Must follow other includes.
+#include "Rinternals.h"
 
 /*!
  * \brief macro to annotate begin of api
@@ -35,14 +46,27 @@
     error(XGBGetLastError());                   \
   }
 
+using dmlc::BeginPtr;
 
-using namespace dmlc;
+xgboost::Context const *BoosterCtx(BoosterHandle handle) {
+  CHECK_HANDLE();
+  auto *learner = static_cast<xgboost::Learner *>(handle);
+  CHECK(learner);
+  return learner->Ctx();
+}
 
-SEXP XGCheckNullPtr_R(SEXP handle) {
+xgboost::Context 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();
+}
+
+XGB_DLL SEXP XGCheckNullPtr_R(SEXP handle) {
   return ScalarLogical(R_ExternalPtrAddr(handle) == NULL);
 }
 
-void _DMatrixFinalizer(SEXP ext) {
+XGB_DLL void _DMatrixFinalizer(SEXP ext) {
   R_API_BEGIN();
   if (R_ExternalPtrAddr(ext) == NULL) return;
   CHECK_CALL(XGDMatrixFree(R_ExternalPtrAddr(ext)));
@@ -50,14 +74,14 @@ void _DMatrixFinalizer(SEXP ext) {
   R_API_END();
 }
 
-SEXP XGBSetGlobalConfig_R(SEXP json_str) {
+XGB_DLL SEXP XGBSetGlobalConfig_R(SEXP json_str) {
   R_API_BEGIN();
   CHECK_CALL(XGBSetGlobalConfig(CHAR(asChar(json_str))));
   R_API_END();
   return R_NilValue;
 }
 
-SEXP XGBGetGlobalConfig_R() {
+XGB_DLL SEXP XGBGetGlobalConfig_R() {
   const char* json_str;
   R_API_BEGIN();
   CHECK_CALL(XGBGetGlobalConfig(&json_str));
@@ -65,7 +89,7 @@ SEXP XGBGetGlobalConfig_R() {
   return mkString(json_str);
 }
 
-SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
+XGB_DLL SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
   SEXP ret;
   R_API_BEGIN();
   DMatrixHandle handle;
@@ -77,8 +101,7 @@ SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
   return ret;
 }
 
-SEXP XGDMatrixCreateFromMat_R(SEXP mat,
+XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
-                              SEXP missing) {
   SEXP ret;
   R_API_BEGIN();
   SEXP dim = getAttrib(mat, R_DimSymbol);
@@ -93,18 +116,32 @@ SEXP XGDMatrixCreateFromMat_R(SEXP mat,
     din = REAL(mat);
   }
   std::vector<float> data(nrow * ncol);
-  dmlc::OMPException exc;
+  xgboost::Context ctx;
-  #pragma omp parallel for schedule(static)
+  ctx.nthread = asInteger(n_threads);
-  for (omp_ulong i = 0; i < nrow; ++i) {
+  std::int32_t threads = ctx.Threads();
-    exc.Run([&]() {
+
+  if (is_int) {
+    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];
+        auto v = iin[i + nrow * j];
+        if (v == NA_INTEGER) {
+          data[i * ncol + j] = std::numeric_limits<float>::quiet_NaN();
+        } else {
+          data[i * ncol + j] = static_cast<float>(v);
+        }
+      }
+    });
+  } else {
+    xgboost::common::ParallelFor(nrow, threads, [&](xgboost::omp_ulong i) {
+      for (size_t j = 0; j < ncol; ++j) {
+        data[i * ncol + j] = din[i + nrow * j];
       }
     });
   }
-  exc.Rethrow();
+
   DMatrixHandle handle;
-  CHECK_CALL(XGDMatrixCreateFromMat(BeginPtr(data), nrow, ncol, asReal(missing), &handle));
+  CHECK_CALL(XGDMatrixCreateFromMat_omp(BeginPtr(data), nrow, ncol,
+                                        asReal(missing), &handle, threads));
   ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
@@ -112,46 +149,85 @@ SEXP XGDMatrixCreateFromMat_R(SEXP mat,
   return ret;
 }
 
-SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
+namespace {
-                              SEXP indices,
+void CreateFromSparse(SEXP indptr, SEXP indices, SEXP data, std::string *indptr_str,
-                              SEXP data,
+                      std::string *indices_str, std::string *data_str) {
-                              SEXP num_row) {
-  SEXP ret;
-  R_API_BEGIN();
   const int *p_indptr = INTEGER(indptr);
   const int *p_indices = INTEGER(indices);
   const double *p_data = REAL(data);
-  size_t nindptr = static_cast<size_t>(length(indptr));
-  size_t ndata = static_cast<size_t>(length(data));
-  size_t nrow = static_cast<size_t>(INTEGER(num_row)[0]);
-  std::vector<size_t> col_ptr_(nindptr);
-  std::vector<unsigned> indices_(ndata);
-  std::vector<float> data_(ndata);
 
-  for (size_t i = 0; i < nindptr; ++i) {
+  auto nindptr = static_cast<std::size_t>(length(indptr));
-    col_ptr_[i] = static_cast<size_t>(p_indptr[i]);
+  auto ndata = static_cast<std::size_t>(length(data));
+  CHECK_EQ(ndata, p_indptr[nindptr - 1]);
+  xgboost::detail::MakeSparseFromPtr(p_indptr, p_indices, p_data, nindptr, indptr_str, indices_str,
+                                     data_str);
 }
-  dmlc::OMPException exc;
+}  // namespace
-  #pragma omp parallel for schedule(static)
+
-  for (int64_t i = 0; i < static_cast<int64_t>(ndata); ++i) {
+XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_row,
-    exc.Run([&]() {
+                                      SEXP missing, SEXP n_threads) {
-      indices_[i] = static_cast<unsigned>(p_indices[i]);
+  SEXP ret;
-      data_[i] = static_cast<float>(p_data[i]);
+  R_API_BEGIN();
-    });
+  std::int32_t threads = asInteger(n_threads);
-  }
+
-  exc.Rethrow();
+  using xgboost::Integer;
+  using xgboost::Json;
+  using xgboost::Object;
+
+  std::string sindptr, sindices, sdata;
+  CreateFromSparse(indptr, indices, data, &sindptr, &sindices, &sdata);
+  auto nrow = static_cast<std::size_t>(INTEGER(num_row)[0]);
+
   DMatrixHandle handle;
-  CHECK_CALL(XGDMatrixCreateFromCSCEx(BeginPtr(col_ptr_), BeginPtr(indices_),
+  Json jconfig{Object{}};
-                                      BeginPtr(data_), nindptr, ndata,
+  // Construct configuration
-                                      nrow, &handle));
+  jconfig["nthread"] = Integer{threads};
+  jconfig["missing"] = xgboost::Number{asReal(missing)};
+  std::string config;
+  Json::Dump(jconfig, &config);
+  CHECK_CALL(XGDMatrixCreateFromCSC(sindptr.c_str(), sindices.c_str(), sdata.c_str(), nrow,
+                                    config.c_str(), &handle));
+
   ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
+
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
   UNPROTECT(1);
   return ret;
 }
 
-SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
+XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_col,
+                                      SEXP missing, SEXP n_threads) {
+  SEXP ret;
+  R_API_BEGIN();
+  std::int32_t threads = asInteger(n_threads);
+
+  using xgboost::Integer;
+  using xgboost::Json;
+  using xgboost::Object;
+
+  std::string sindptr, sindices, sdata;
+  CreateFromSparse(indptr, indices, data, &sindptr, &sindices, &sdata);
+  auto ncol = static_cast<std::size_t>(INTEGER(num_col)[0]);
+
+  DMatrixHandle handle;
+  Json jconfig{Object{}};
+  // Construct configuration
+  jconfig["nthread"] = Integer{threads};
+  jconfig["missing"] = xgboost::Number{asReal(missing)};
+  std::string config;
+  Json::Dump(jconfig, &config);
+  CHECK_CALL(XGDMatrixCreateFromCSR(sindptr.c_str(), sindices.c_str(), sdata.c_str(), ncol,
+                                    config.c_str(), &handle));
+  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();
   int len = length(idxset);
@@ -171,7 +247,7 @@ SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
   return ret;
 }
 
-SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
+XGB_DLL SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixSaveBinary(R_ExternalPtrAddr(handle),
                                  CHAR(asChar(fname)),
@@ -180,49 +256,76 @@ SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
   return R_NilValue;
 }
 
-SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
+XGB_DLL SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
   R_API_BEGIN();
   int len = length(array);
   const char *name = CHAR(asChar(field));
-  dmlc::OMPException exc;
+  auto ctx = DMatrixCtx(R_ExternalPtrAddr(handle));
   if (!strcmp("group", name)) {
     std::vector<unsigned> vec(len);
-    #pragma omp parallel for schedule(static)
+    xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
-    for (int i = 0; i < len; ++i) {
-      exc.Run([&]() {
       vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
     });
-    }
+    CHECK_CALL(
-    exc.Rethrow();
+        XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
-    CHECK_CALL(XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle),
-                                    CHAR(asChar(field)),
-                                    BeginPtr(vec), len));
   } else {
     std::vector<float> vec(len);
-    #pragma omp parallel for schedule(static)
+    xgboost::common::ParallelFor(len, ctx->Threads(),
-    for (int i = 0; i < len; ++i) {
+                                 [&](xgboost::omp_ulong i) { vec[i] = REAL(array)[i]; });
-      exc.Run([&]() {
+    CHECK_CALL(
-        vec[i] = REAL(array)[i];
+        XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
-      });
-    }
-    exc.Rethrow();
-    CHECK_CALL(XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle),
-                                     CHAR(asChar(field)),
-                                     BeginPtr(vec), len));
   }
   R_API_END();
   return R_NilValue;
 }
 
-SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
+XGB_DLL SEXP XGDMatrixSetStrFeatureInfo_R(SEXP handle, SEXP field, SEXP array) {
+  R_API_BEGIN();
+  size_t len{0};
+  if (!isNull(array)) {
+    len = length(array);
+  }
+
+  const char *name = CHAR(asChar(field));
+  std::vector<std::string> str_info;
+  for (size_t i = 0; i < len; ++i) {
+    str_info.emplace_back(CHAR(asChar(VECTOR_ELT(array, i))));
+  }
+  std::vector<char const*> vec(len);
+  std::transform(str_info.cbegin(), str_info.cend(), vec.begin(),
+                 [](std::string const &str) { return str.c_str(); });
+  CHECK_CALL(XGDMatrixSetStrFeatureInfo(R_ExternalPtrAddr(handle), name, vec.data(), len));
+  R_API_END();
+  return R_NilValue;
+}
+
+XGB_DLL SEXP XGDMatrixGetStrFeatureInfo_R(SEXP handle, SEXP field) {
+  SEXP ret;
+  R_API_BEGIN();
+  char const **out_features{nullptr};
+  bst_ulong len{0};
+  const char *name = CHAR(asChar(field));
+  XGDMatrixGetStrFeatureInfo(R_ExternalPtrAddr(handle), name, &len, &out_features);
+
+  if (len > 0) {
+    ret = PROTECT(allocVector(STRSXP, len));
+    for (size_t i = 0; i < len; ++i) {
+      SET_STRING_ELT(ret, i, mkChar(out_features[i]));
+    }
+  } else {
+    ret = PROTECT(R_NilValue);
+  }
+  R_API_END();
+  UNPROTECT(1);
+  return ret;
+}
+
+XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong olen;
   const float *res;
-  CHECK_CALL(XGDMatrixGetFloatInfo(R_ExternalPtrAddr(handle),
+  CHECK_CALL(XGDMatrixGetFloatInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), &olen, &res));
-                                   CHAR(asChar(field)),
-                                 &olen,
-                                 &res));
   ret = PROTECT(allocVector(REALSXP, olen));
   for (size_t i = 0; i < olen; ++i) {
     REAL(ret)[i] = res[i];
@@ -232,7 +335,7 @@ SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   return ret;
 }
 
-SEXP XGDMatrixNumRow_R(SEXP handle) {
+XGB_DLL SEXP XGDMatrixNumRow_R(SEXP handle) {
   bst_ulong nrow;
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixNumRow(R_ExternalPtrAddr(handle), &nrow));
@@ -240,7 +343,7 @@ SEXP XGDMatrixNumRow_R(SEXP handle) {
   return ScalarInteger(static_cast<int>(nrow));
 }
 
-SEXP XGDMatrixNumCol_R(SEXP handle) {
+XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle) {
   bst_ulong ncol;
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixNumCol(R_ExternalPtrAddr(handle), &ncol));
@@ -255,7 +358,7 @@ void _BoosterFinalizer(SEXP ext) {
   R_ClearExternalPtr(ext);
 }
 
-SEXP XGBoosterCreate_R(SEXP dmats) {
+XGB_DLL SEXP XGBoosterCreate_R(SEXP dmats) {
   SEXP ret;
   R_API_BEGIN();
   int len = length(dmats);
@@ -272,7 +375,22 @@ SEXP XGBoosterCreate_R(SEXP dmats) {
   return ret;
 }
 
-SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
+XGB_DLL SEXP XGBoosterCreateInEmptyObj_R(SEXP dmats, SEXP R_handle) {
+  R_API_BEGIN();
+  int len = length(dmats);
+  std::vector<void*> dvec;
+  for (int i = 0; i < len; ++i) {
+    dvec.push_back(R_ExternalPtrAddr(VECTOR_ELT(dmats, i)));
+  }
+  BoosterHandle handle;
+  CHECK_CALL(XGBoosterCreate(BeginPtr(dvec), dvec.size(), &handle));
+  R_SetExternalPtrAddr(R_handle, handle);
+  R_RegisterCFinalizerEx(R_handle, _BoosterFinalizer, TRUE);
+  R_API_END();
+  return R_NilValue;
+}
+
+XGB_DLL SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterSetParam(R_ExternalPtrAddr(handle),
                                CHAR(asChar(name)),
@@ -281,7 +399,7 @@ SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
   return R_NilValue;
 }
 
-SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
+XGB_DLL SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterUpdateOneIter(R_ExternalPtrAddr(handle),
                                   asInteger(iter),
@@ -290,21 +408,17 @@ SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
   return R_NilValue;
 }
 
-SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP hess) {
+XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP hess) {
   R_API_BEGIN();
   CHECK_EQ(length(grad), length(hess))
       << "gradient and hess must have same length";
   int len = length(grad);
   std::vector<float> tgrad(len), thess(len);
-  dmlc::OMPException exc;
+  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  #pragma omp parallel for schedule(static)
+  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong j) {
-  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),
@@ -313,7 +427,7 @@ SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP hess) {
   return R_NilValue;
 }
 
-SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
+XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
   const char *ret;
   R_API_BEGIN();
   CHECK_EQ(length(dmats), length(evnames))
@@ -338,57 +452,59 @@ SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
   return mkString(ret);
 }
 
-SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
+XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_config)  {
-                        SEXP ntree_limit, SEXP training) {
+  SEXP r_out_shape;
-  SEXP ret;
+  SEXP r_out_result;
+  SEXP r_out;
+
   R_API_BEGIN();
-  bst_ulong olen;
+  char const *c_json_config = CHAR(asChar(json_config));
-  const float *res;
+
-  CHECK_CALL(XGBoosterPredict(R_ExternalPtrAddr(handle),
+  bst_ulong out_dim;
-                              R_ExternalPtrAddr(dmat),
+  bst_ulong const *out_shape;
-                              asInteger(option_mask),
+  float const *out_result;
-                              asInteger(ntree_limit),
+  CHECK_CALL(XGBoosterPredictFromDMatrix(R_ExternalPtrAddr(handle),
-                              asInteger(training),
+                                         R_ExternalPtrAddr(dmat), c_json_config,
-                              &olen, &res));
+                                         &out_shape, &out_dim, &out_result));
-  ret = PROTECT(allocVector(REALSXP, olen));
+
-  for (size_t i = 0; i < olen; ++i) {
+  r_out_shape = PROTECT(allocVector(INTSXP, out_dim));
-    REAL(ret)[i] = res[i];
+  size_t len = 1;
+  for (size_t i = 0; i < out_dim; ++i) {
+    INTEGER(r_out_shape)[i] = out_shape[i];
+    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) {
+    REAL(r_out_result)[i] = out_result[i];
+  });
+
+  r_out = PROTECT(allocVector(VECSXP, 2));
+
+  SET_VECTOR_ELT(r_out, 0, r_out_shape);
+  SET_VECTOR_ELT(r_out, 1, r_out_result);
+
   R_API_END();
-  UNPROTECT(1);
+  UNPROTECT(3);
-  return ret;
+
+  return r_out;
 }
 
-SEXP XGBoosterLoadModel_R(SEXP handle, SEXP fname) {
+XGB_DLL SEXP XGBoosterLoadModel_R(SEXP handle, SEXP fname) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadModel(R_ExternalPtrAddr(handle), CHAR(asChar(fname))));
   R_API_END();
   return R_NilValue;
 }
 
-SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
+XGB_DLL SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterSaveModel(R_ExternalPtrAddr(handle), CHAR(asChar(fname))));
   R_API_END();
   return R_NilValue;
 }
 
-SEXP XGBoosterModelToRaw_R(SEXP handle) {
+XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
-  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;
-}
-
-SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadModelFromBuffer(R_ExternalPtrAddr(handle),
                                           RAW(raw),
@@ -397,7 +513,23 @@ SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   return R_NilValue;
 }
 
-SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
+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();
   bst_ulong len {0};
@@ -408,14 +540,14 @@ SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
   return mkString(ret);
 }
 
-SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
+XGB_DLL SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadJsonConfig(R_ExternalPtrAddr(handle), CHAR(asChar(value))));
   R_API_END();
   return R_NilValue;
 }
 
-SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
+XGB_DLL SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong out_len;
@@ -430,7 +562,7 @@ SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
   return ret;
 }
 
-SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
+XGB_DLL SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterUnserializeFromBuffer(R_ExternalPtrAddr(handle),
                                  RAW(raw),
@@ -439,7 +571,7 @@ SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
   return R_NilValue;
 }
 
-SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_format) {
+XGB_DLL SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_format) {
   SEXP out;
   R_API_BEGIN();
   bst_ulong olen;
@@ -476,7 +608,7 @@ SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_for
   return out;
 }
 
-SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
+XGB_DLL SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
   SEXP out;
   R_API_BEGIN();
   int success;
@@ -496,7 +628,7 @@ SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
   return out;
 }
 
-SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
+XGB_DLL SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
   R_API_BEGIN();
   const char *v = isNull(val) ? nullptr : CHAR(asChar(val));
   CHECK_CALL(XGBoosterSetAttr(R_ExternalPtrAddr(handle),
@@ -505,7 +637,7 @@ SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
   return R_NilValue;
 }
 
-SEXP XGBoosterGetAttrNames_R(SEXP handle) {
+XGB_DLL SEXP XGBoosterGetAttrNames_R(SEXP handle) {
   SEXP out;
   R_API_BEGIN();
   bst_ulong len;
@@ -524,3 +656,50 @@ SEXP XGBoosterGetAttrNames_R(SEXP handle) {
   UNPROTECT(1);
   return out;
 }
+
+XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config) {
+  SEXP out_features_sexp;
+  SEXP out_scores_sexp;
+  SEXP out_shape_sexp;
+  SEXP r_out;
+
+  R_API_BEGIN();
+  char const *c_json_config = CHAR(asChar(json_config));
+  bst_ulong out_n_features;
+  char const **out_features;
+
+  bst_ulong out_dim;
+  bst_ulong const *out_shape;
+  float const *out_scores;
+
+  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) {
+    INTEGER(out_shape_sexp)[i] = out_shape[i];
+    len *= out_shape[i];
+  }
+
+  out_scores_sexp = PROTECT(allocVector(REALSXP, len));
+  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
+  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong 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) {
+    SET_STRING_ELT(out_features_sexp, i, mkChar(out_features[i]));
+  }
+
+  r_out = PROTECT(allocVector(VECSXP, 3));
+  SET_VECTOR_ELT(r_out, 0, out_features_sexp);
+  SET_VECTOR_ELT(r_out, 1, out_shape_sexp);
+  SET_VECTOR_ELT(r_out, 2, out_scores_sexp);
+
+  R_API_END();
+  UNPROTECT(4);
+
+  return r_out;
+}

R-package/src/xgboost_R.h

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2014 (c) by Contributors
+ * Copyright 2014-2022 by XGBoost Contributors
  * \file xgboost_R.h
  * \author Tianqi Chen
  * \brief R wrapper of xgboost
@@ -47,22 +47,37 @@ XGB_DLL SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent);
  * This assumes the matrix is stored in column major format
  * \param data R Matrix object
  * \param missing which value to represent missing value
+ * \param n_threads Number of threads used to construct DMatrix from dense matrix.
  * \return created dmatrix
  */
 XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat,
-                                      SEXP missing);
+                                      SEXP missing,
+                                      SEXP n_threads);
 /*!
  * \brief create a matrix content from CSC format
  * \param indptr pointer to column headers
  * \param indices row indices
  * \param data content of the data
  * \param num_row numer of rows (when it's set to 0, then guess from data)
+ * \param missing which value to represent missing value
+ * \param n_threads Number of threads used to construct DMatrix from csc matrix.
  * \return created dmatrix
  */
-XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
+XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_row,
-                                      SEXP indices,
+                                      SEXP missing, SEXP n_threads);
-                                      SEXP data,
+
-                                      SEXP num_row);
+/*!
+ * \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 missing which value to represent missing value
+ * \param n_threads Number of threads used to construct DMatrix from csr matrix.
+ * \return created dmatrix
+ */
+XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_col,
+                                      SEXP missing, SEXP n_threads);
 
 /*!
  * \brief create a new dmatrix from sliced content of existing matrix
@@ -116,6 +131,14 @@ XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle);
  */
 XGB_DLL SEXP XGBoosterCreate_R(SEXP dmats);
 
+
+/*!
+ * \brief create xgboost learner, saving the pointer into an existing R object
+ * \param dmats a list of dmatrix handles that will be cached
+ * \param R_handle a clean R external pointer (not holding any object)
+ */
+XGB_DLL SEXP XGBoosterCreateInEmptyObj_R(SEXP dmats, SEXP R_handle);
+
 /*!
  * \brief set parameters
  * \param handle handle
@@ -156,15 +179,14 @@ XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP h
 XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames);
 
 /*!
- * \brief make prediction based on dmat
+ * \brief Run prediction on DMatrix, replacing `XGBoosterPredict_R`
  * \param handle handle
  * \param dmat data matrix
- * \param option_mask output_margin:1 predict_leaf:2
+ * \param json_config See `XGBoosterPredictFromDMatrix` in xgboost c_api.h
- * \param ntree_limit limit number of trees used in prediction
+ *
- * \param training Whether the prediction value is used for training.
+ * \return A list containing 2 vectors, first one for shape while second one for prediction result.
  */
-XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
+XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_config);
-                                SEXP ntree_limit, SEXP training);
 /*!
  * \brief load model from existing file
  * \param handle handle
@@ -189,11 +211,21 @@ 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
- * \return raw array
+ * \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
  */
-XGB_DLL SEXP XGBoosterModelToRaw_R(SEXP handle);
+XGB_DLL SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP json_config);
 
 /*!
  * \brief Save internal parameters as a JSON string
@@ -257,4 +289,12 @@ XGB_DLL SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val);
  */
 XGB_DLL SEXP XGBoosterGetAttrNames_R(SEXP handle);
 
+/*!
+ * \brief Get feature scores from the model.
+ * \param json_config See `XGBoosterFeatureScore` in xgboost c_api.h
+ * \return A vector with the first element as feature names, second element as shape of
+ *         feature scores and thrid element as feature scores.
+ */
+XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config);
+
 #endif  // XGBOOST_WRAPPER_R_H_ // NOLINT(*)

R-package/src/xgboost_assert.c

@@ -1,26 +0,0 @@
-// 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/install_deps.R

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

R-package/tests/helper_scripts/run_lint.R

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

R-package/tests/testthat/test_basic.R

@@ -1,5 +1,3 @@
-require(xgboost)
-
 context("basic functions")
 
 data(agaricus.train, package = 'xgboost')
@@ -34,6 +32,10 @@ test_that("train and predict binary classification", {
   err_pred1 <- sum((pred1 > 0.5) != train$label) / length(train$label)
   err_log <- bst$evaluation_log[1, train_error]
   expect_lt(abs(err_pred1 - err_log), 10e-6)
+
+  pred2 <- predict(bst, train$data, iterationrange = c(1, 2))
+  expect_length(pred1, 6513)
+  expect_equal(pred1, pred2)
 })
 
 test_that("parameter validation works", {
@@ -83,9 +85,18 @@ test_that("dart prediction works", {
     rnorm(100)
 
   set.seed(1994)
-  booster_by_xgboost <- xgboost(data = d, label = y, max_depth = 2, booster = "dart",
+  booster_by_xgboost <- xgboost(
-                                rate_drop = 0.5, one_drop = TRUE,
+    data = d,
-                                eta = 1, nthread = 2, nrounds = nrounds, objective = "reg:squarederror")
+    label = y,
+    max_depth = 2,
+    booster = "dart",
+    rate_drop = 0.5,
+    one_drop = TRUE,
+    eta = 1,
+    nthread = 2,
+    nrounds = nrounds,
+    objective = "reg:squarederror"
+  )
   pred_by_xgboost_0 <- predict(booster_by_xgboost, newdata = d, ntreelimit = 0)
   pred_by_xgboost_1 <- predict(booster_by_xgboost, newdata = d, ntreelimit = nrounds)
   expect_true(all(matrix(pred_by_xgboost_0, byrow = TRUE) == matrix(pred_by_xgboost_1, byrow = TRUE)))
@@ -95,14 +106,14 @@ test_that("dart prediction works", {
 
   set.seed(1994)
   dtrain <- xgb.DMatrix(data = d, info = list(label = y))
-  booster_by_train <- xgb.train(params = list(
+  booster_by_train <- xgb.train(
+    params = list(
       booster = "dart",
       max_depth = 2,
       eta = 1,
       rate_drop = 0.5,
       one_drop = TRUE,
       nthread = 1,
-                                    tree_method = "exact",
       objective = "reg:squarederror"
     ),
     data = dtrain,
@@ -143,6 +154,24 @@ test_that("train and predict softprob", {
   pred_labels <- max.col(mpred) - 1
   err <- sum(pred_labels != lb) / length(lb)
   expect_equal(bst$evaluation_log[1, train_merror], err, tolerance = 5e-6)
+
+  mpred1 <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE, iterationrange = c(1, 2))
+  expect_equal(mpred, mpred1)
+
+  d <- cbind(
+    x1 = rnorm(100),
+    x2 = rnorm(100),
+    x3 = rnorm(100)
+  )
+  y <- sample.int(10, 100, replace = TRUE) - 1
+  dtrain <- xgb.DMatrix(data = d, info = list(label = y))
+  booster <- xgb.train(
+    params = list(tree_method = "hist"), data = dtrain, nrounds = 4, num_class = 10,
+    objective = "multi:softprob"
+  )
+  predt <- predict(booster, as.matrix(d), reshape = TRUE, strict_shape = FALSE)
+  expect_equal(ncol(predt), 10)
+  expect_equal(rowSums(predt), rep(1, 100), tolerance = 1e-7)
 })
 
 test_that("train and predict softmax", {
@@ -182,10 +211,8 @@ test_that("train and predict RF", {
   pred_err_20 <- sum((pred > 0.5) != lb) / length(lb)
   expect_equal(pred_err_20, pred_err)
 
-  #pred <- predict(bst, train$data, ntreelimit = 1)
+  pred1 <- predict(bst, train$data, iterationrange = c(1, 2))
-  #pred_err_1 <- sum((pred > 0.5) != lb)/length(lb)
+  expect_equal(pred, pred1)
-  #expect_lt(pred_err, pred_err_1)
-  #expect_lt(pred_err, 0.08)
 })
 
 test_that("train and predict RF with softprob", {
@@ -220,6 +247,14 @@ test_that("use of multiple eval metrics works", {
   expect_false(is.null(bst$evaluation_log))
   expect_equal(dim(bst$evaluation_log), c(2, 4))
   expect_equal(colnames(bst$evaluation_log), c("iter", "train_error", "train_auc", "train_logloss"))
+  expect_output(
+    bst2 <- xgboost(data = train$data, label = train$label, max_depth = 2,
+                    eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic",
+                    eval_metric = list("error", "auc", "logloss"))
+  , "train-error.*train-auc.*train-logloss")
+  expect_false(is.null(bst2$evaluation_log))
+  expect_equal(dim(bst2$evaluation_log), c(2, 4))
+  expect_equal(colnames(bst2$evaluation_log), c("iter", "train_error", "train_auc", "train_logloss"))
 })
 
 
@@ -331,7 +366,7 @@ test_that("train and predict with non-strict classes", {
   expect_error(pr <- predict(bst, train_dense), regexp = NA)
   expect_equal(pr0, pr)
 
-  # when someone inhertis from xgb.Booster, it should still be possible to use it as xgb.Booster
+  # when someone inherits from xgb.Booster, it should still be possible to use it as xgb.Booster
   class(bst) <- c('super.Booster', 'xgb.Booster')
   expect_error(pr <- predict(bst, train_dense), regexp = NA)
   expect_equal(pr0, pr)
@@ -346,7 +381,7 @@ test_that("max_delta_step works", {
   bst1 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1)
   # model with restricted max_delta_step
   bst2 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1, max_delta_step = 1)
-  # the no-restriction model is expected to have consistently lower loss during the initial interations
+  # the no-restriction model is expected to have consistently lower loss during the initial iterations
   expect_true(all(bst1$evaluation_log$train_logloss < bst2$evaluation_log$train_logloss))
   expect_lt(mean(bst1$evaluation_log$train_logloss) / mean(bst2$evaluation_log$train_logloss), 0.8)
 })
@@ -373,7 +408,7 @@ test_that("colsample_bytree works", {
   xgb.importance(model = bst)
   # If colsample_bytree works properly, a variety of features should be used
   # in the 100 trees
-  expect_gte(nrow(xgb.importance(model = bst)), 30)
+  expect_gte(nrow(xgb.importance(model = bst)), 28)
 })
 
 test_that("Configuration works", {
@@ -383,5 +418,74 @@ test_that("Configuration works", {
   config <- xgb.config(bst)
   xgb.config(bst) <- config
   reloaded_config <- xgb.config(bst)
-  expect_equal(config, reloaded_config);
+  expect_equal(config, reloaded_config)
+})
+
+test_that("strict_shape works", {
+  n_rounds <- 2
+
+  test_strict_shape <- function(bst, X, n_groups) {
+    predt <- predict(bst, X, strict_shape = TRUE)
+    margin <- predict(bst, X, outputmargin = TRUE, strict_shape = TRUE)
+    contri <- predict(bst, X, predcontrib = TRUE, strict_shape = TRUE)
+    interact <- predict(bst, X, predinteraction = TRUE, strict_shape = TRUE)
+    leaf <- predict(bst, X, predleaf = TRUE, strict_shape = TRUE)
+
+    n_rows <- nrow(X)
+    n_cols <- ncol(X)
+
+    expect_equal(dim(predt), c(n_groups, n_rows))
+    expect_equal(dim(margin), c(n_groups, n_rows))
+    expect_equal(dim(contri), c(n_cols + 1, n_groups, n_rows))
+    expect_equal(dim(interact), c(n_cols + 1, n_cols + 1, n_groups, n_rows))
+    expect_equal(dim(leaf), c(1, n_groups, n_rounds, n_rows))
+
+    if (n_groups != 1) {
+      for (g in seq_len(n_groups)) {
+        expect_lt(max(abs(colSums(contri[, g, ]) - margin[g, ])), 1e-5)
+      }
+    }
+  }
+
+  test_iris <- function() {
+    y <- as.numeric(iris$Species) - 1
+    X <- as.matrix(iris[, -5])
+
+    bst <- xgboost(data = X, label = y,
+                   max_depth = 2, nrounds = n_rounds,
+                   objective = "multi:softprob", num_class = 3, eval_metric = "merror")
+
+    test_strict_shape(bst, X, 3)
+  }
+
+
+  test_agaricus <- function() {
+    data(agaricus.train, package = 'xgboost')
+    X <- agaricus.train$data
+    y <- agaricus.train$label
+
+    bst <- xgboost(data = X, label = y, max_depth = 2,
+                   nrounds = n_rounds, objective = "binary:logistic",
+                   eval_metric = 'error', eval_metric = 'auc', eval_metric = "logloss")
+
+    test_strict_shape(bst, X, 1)
+  }
+
+  test_iris()
+  test_agaricus()
+})
+
+test_that("'predict' accepts CSR data", {
+  X <- agaricus.train$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)
 })