[jvm-packages] update version of 1.1.0 branch (#6435)

* [CI] Throttle Jenkins CI

* Don't use Jenkins master instance

.clang-format

@@ -1,214 +0,0 @@
----
-Language:        Cpp
-# BasedOnStyle:  Google
-AccessModifierOffset: -1
-AlignAfterOpenBracket: Align
-AlignArrayOfStructures: None
-AlignConsecutiveMacros: None
-AlignConsecutiveAssignments: None
-AlignConsecutiveBitFields: None
-AlignConsecutiveDeclarations: None
-AlignEscapedNewlines: Left
-AlignOperands:   Align
-AlignTrailingComments: true
-AllowAllArgumentsOnNextLine: true
-AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortEnumsOnASingleLine: true
-AllowShortBlocksOnASingleLine: Never
-AllowShortCaseLabelsOnASingleLine: false
-AllowShortFunctionsOnASingleLine: All
-AllowShortLambdasOnASingleLine: Inline
-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-use-nodiscard,-modernize-concat-nested-namespaces,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
+Checks: 'modernize-*,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
 CheckOptions:
   - { key: readability-identifier-naming.ClassCase,                 value: CamelCase  }
   - { key: readability-identifier-naming.StructCase,                value: CamelCase  }

.gitattributes

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

.github/FUNDING.yml

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

.github/dependabot.yml

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

.github/workflows/i386.yml

@@ -1,43 +0,0 @@
-name: XGBoost-i386-test
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build-32bit:
-    name: Build 32-bit
-    runs-on: ubuntu-latest
-    services:
-      registry:
-        image: registry:2
-        ports:
-          - 5000:5000
-    steps:
-    - uses: actions/checkout@v2.5.0
-      with:
-        submodules: 'true'
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
-      with:
-        driver-opts: network=host
-    - name: Build and push container
-      uses: docker/build-push-action@v5
-      with:
-        context: .
-        file: tests/ci_build/Dockerfile.i386
-        push: true
-        tags: localhost:5000/xgboost/build-32bit:latest
-        cache-from: type=gha
-        cache-to: type=gha,mode=max
-    - name: Build XGBoost
-      run: |
-        docker run --rm -v $PWD:/workspace -w /workspace \
-          -e CXXFLAGS='-Wno-error=overloaded-virtual -Wno-error=maybe-uninitialized -Wno-error=redundant-move' \
-          localhost:5000/xgboost/build-32bit:latest \
-          tests/ci_build/build_via_cmake.sh

.github/workflows/jvm_tests.yml

@@ -1,111 +0,0 @@
-name: XGBoost-JVM-Tests
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-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@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
-      with:
-        submodules: 'true'
-
-    - uses: mamba-org/setup-micromamba@422500192359a097648154e8db4e39bdb6c6eed7  # v1.8.1
-      with:
-        micromamba-version: '1.5.6-0'
-        environment-name: jvm_tests
-        create-args: >-
-          python=3.10
-          awscli
-        cache-downloads: true
-        cache-environment: true
-        init-shell: bash powershell
-
-    - name: Cache Maven packages
-      uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2  # v4.0.0
-      with:
-        path: ~/.m2
-        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-
-    - name: Build xgboost4j.dll
-      run: |
-        mkdir build
-        cd build
-        cmake .. -G"Visual Studio 17 2022" -A x64 -DJVM_BINDINGS=ON
-        cmake --build . --config Release
-      if: matrix.os == 'windows-latest'
-
-    - name: Test XGBoost4J (Core)
-      run: |
-        cd jvm-packages
-        mvn test -B -pl :xgboost4j_2.12
-
-    - name: Extract branch name
-      shell: bash
-      run: |
-        echo "branch=${GITHUB_REF#refs/heads/}" >> "$GITHUB_OUTPUT"
-      id: extract_branch
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        (matrix.os == 'windows-latest' || matrix.os == 'macos-11')
-
-    - name: Publish artifact xgboost4j.dll to S3
-      run: |
-        cd lib/
-        Rename-Item -Path xgboost4j.dll -NewName xgboost4j_${{ github.sha }}.dll
-        dir
-        python -m awscli s3 cp xgboost4j_${{ github.sha }}.dll s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/libxgboost4j/ --acl public-read --region us-west-2
-      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: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-    - name: Publish artifact libxgboost4j.dylib to S3
-      shell: bash -l {0}
-      run: |
-        cd lib/
-        mv -v libxgboost4j.dylib libxgboost4j_${{ github.sha }}.dylib
-        ls
-        python -m awscli s3 cp libxgboost4j_${{ github.sha }}.dylib s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/libxgboost4j/ --acl public-read --region us-west-2
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'macos-11'
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-
-    - name: Test XGBoost4J (Core, Spark, Examples)
-      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

@@ -1,191 +0,0 @@
-# This is a basic workflow to help you get started with Actions
-
-name: XGBoost-CI
-
-# Controls when the action will run. Triggers the workflow on push or pull request
-# events but only for the master branch
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
-jobs:
-  gtest-cpu:
-    name: Test Google C++ test (CPU)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [macos-11]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        brew install ninja libomp
-    - name: Build gtest binary
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DGOOGLE_TEST=ON -DUSE_OPENMP=ON -DUSE_DMLC_GTEST=ON -GNinja -DBUILD_DEPRECATED_CLI=ON
-        ninja -v
-    - name: Run gtest binary
-      run: |
-        cd build
-        ./testxgboost
-        ctest -R TestXGBoostCLI --extra-verbose
-
-  gtest-cpu-nonomp:
-    name: Test Google C++ unittest (CPU Non-OMP)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -GNinja -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON -DUSE_OPENMP=OFF -DBUILD_DEPRECATED_CLI=ON
-        ninja -v
-    - name: Run gtest binary
-      run: |
-        cd build
-        ctest --extra-verbose
-
-  gtest-cpu-sycl:
-    name: Test Google C++ unittest (CPU SYCL)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: linux_sycl_test
-        environment-file: tests/ci_build/conda_env/linux_sycl_test.yml
-
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON -DPLUGIN_SYCL=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX
-        make -j$(nproc)
-    - name: Run gtest binary for SYCL
-      run: |
-        cd build
-        ./testxgboost --gtest_filter=Sycl*
-    - name: Run gtest binary for non SYCL
-      run: |
-        cd build
-        ./testxgboost --gtest_filter=-Sycl*
-
-  c-api-demo:
-    name: Test installing XGBoost lib + building the C API demo
-    runs-on: ${{ matrix.os }}
-    defaults:
-      run:
-        shell: bash -l {0}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: cpp_test
-        environment-file: tests/ci_build/conda_env/cpp_test.yml
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-
-    - name: Build and install XGBoost static library
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-        ninja -v install
-        cd -
-    - name: Build and run C API demo with static
-      run: |
-        pushd .
-        cd demo/c-api/
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v
-        ctest
-        cd ..
-        rm -rf ./build
-        popd
-
-    - name: Build and install XGBoost shared library
-      run: |
-        cd build
-        cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-        ninja -v install
-        cd -
-    - name: Build and run C API demo with shared
-      run: |
-        pushd .
-        cd demo/c-api/
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v
-        ctest
-        popd
-        ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
-        ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
-
-  cpp-lint:
-    runs-on: ubuntu-latest
-    name: Code linting for C++
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools cmakelint cpplint pylint
-    - name: Run lint
-      run: |
-        python3 tests/ci_build/lint_cpp.py
-        sh ./tests/ci_build/lint_cmake.sh

.github/workflows/python_tests.yml

@@ -1,343 +0,0 @@
-name: XGBoost-Python-Tests
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-defaults:
-  run:
-    shell: bash -l {0}
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-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 -DBUILD_DEPRECATED_CLI=ON
-        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 -DBUILD_DEPRECATED_CLI=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 -DBUILD_DEPRECATED_CLI=ON
-        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-sycl-tests-on-ubuntu:
-    name: Test XGBoost Python package with SYCL on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 90
-    strategy:
-      matrix:
-        config:
-          - {os: ubuntu-latest, python-version: "3.8"}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
-      with:
-        cache-downloads: true
-        cache-env: true
-        environment-name: linux_sycl_test
-        environment-file: tests/ci_build/conda_env/linux_sycl_test.yml
-
-    - name: Display Conda env
-      run: |
-        conda info
-        conda list
-    - name: Build XGBoost on Ubuntu
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DPLUGIN_SYCL=ON -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        make -j$(nproc)
-    - 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-sycl/
-
-
-  python-system-installation-on-ubuntu:
-    name: Test XGBoost Python package System Installation on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          submodules: 'true'
-
-      - name: Set up Python 3.8
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
-        with:
-          python-version: 3.8
-
-      - name: Install ninja
-        run: |
-          sudo apt-get update && sudo apt-get install -y ninja-build
-
-      - name: Build XGBoost on Ubuntu
-        run: |
-          mkdir build
-          cd build
-          cmake .. -GNinja
-          ninja
-
-      - name: Copy lib to system lib
-        run: |
-          cp lib/* "$(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

@@ -1,45 +0,0 @@
-name: XGBoost-Python-Wheels
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-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@a12a3943b4bdde767164f792f33f40b04645d846 # v3.0.0
-      with:
-        submodules: 'true'
-    - name: Setup Python
-      uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
-      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

@@ -1,44 +0,0 @@
-# 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
-
-on:
-  pull_request_review_comment:
-    types: [created]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  test-R-noLD:
-    if: github.event.comment.body == '/gha run r-nold-test' && contains('OWNER,MEMBER,COLLABORATOR', github.event.comment.author_association)
-    timeout-minutes: 120
-    runs-on: ubuntu-latest
-    container:
-      image: rhub/debian-gcc-devel-nold
-    steps:
-    - name: Install git and system packages
-      shell: bash
-      run: |
-        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
-
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - name: Install dependencies
-      shell: bash -l {0}
-      run: |
-        /tmp/R-devel/bin/Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
-
-    - name: Run R tests
-      shell: bash
-      run: |
-        cd R-package && \
-        /tmp/R-devel/bin/R CMD INSTALL . && \
-        /tmp/R-devel/bin/R -q -e "library(testthat); setwd('tests'); source('testthat.R')"

.github/workflows/r_tests.yml

@@ -1,150 +0,0 @@
-name: XGBoost-R-Tests
-
-on: [push, pull_request]
-
-env:
-  GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  lintr:
-    runs-on: ${{ matrix.config.os }}
-    name: Run R linters on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-    strategy:
-      matrix:
-        config:
-          - {os: ubuntu-latest, r: 'release'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@e40ad904310fc92e96951c1b0d64f3de6cbe9e14 # v2.6.5
-      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-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        source("./R-package/tests/helper_scripts/install_deps.R")
-
-    - name: Run lintr
-      run: |
-        MAKEFLAGS="-j$(nproc)" R CMD INSTALL R-package/
-        Rscript tests/ci_build/lint_r.R $(pwd)
-
-  test-Rpkg:
-    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-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: ubuntu-latest, r: 'release', compiler: 'none', build: 'cmake'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - name: Install system dependencies
-      run: |
-        sudo apt update
-        sudo apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev
-      if: matrix.config.os == 'ubuntu-latest'
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@e40ad904310fc92e96951c1b0d64f3de6cbe9e14 # v2.6.5
-      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-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5.0.0
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-
-    - uses: r-lib/actions/setup-tinytex@v2
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        source("./R-package/tests/helper_scripts/install_deps.R")
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool="${{ matrix.config.build }}" --task=check
-      if: matrix.config.compiler != 'none'
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --build-tool="${{ matrix.config.build }}" --task=check
-      if: matrix.config.compiler == 'none'
-
-  test-R-on-Debian:
-    name: Test R package on Debian
-    runs-on: ubuntu-latest
-    container:
-      image: rhub/debian-gcc-release
-
-    steps:
-    - name: Install system dependencies
-      run: |
-        # Must run before checkout to have the latest git installed.
-        # No need to add pandoc, the container has it figured out.
-        apt update && apt install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libglpk-dev libxml2-dev libharfbuzz-dev libfribidi-dev git -y
-
-    - name: Trust git cloning project sources
-      run: |
-        git config --global --add safe.directory "${GITHUB_WORKSPACE}"
-
-    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
-      with:
-        submodules: 'true'
-
-    - name: Install dependencies
-      shell: bash -l {0}
-      run: |
-        Rscript -e "source('./R-package/tests/helper_scripts/install_deps.R')"
-
-    - name: Test R
-      shell: bash -l {0}
-      run: |
-        python3 tests/ci_build/test_r_package.py --r=/usr/bin/R --build-tool=autotools --task=check
-
-    - 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=/usr/bin/R --task=doc

.github/workflows/scorecards.yml

@@ -1,54 +0,0 @@
-name: Scorecards supply-chain security
-on:
-  # Only the default branch is supported.
-  branch_protection_rule:
-  schedule:
-    - cron: '17 2 * * 6'
-  push:
-    branches: [ "master" ]
-
-# Declare default permissions as read only.
-permissions: read-all
-
-jobs:
-  analysis:
-    name: Scorecards analysis
-    runs-on: ubuntu-latest
-    permissions:
-      # Needed to upload the results to code-scanning dashboard.
-      security-events: write
-      # Used to receive a badge.
-      id-token: write
-
-    steps:
-      - name: "Checkout code"
-        uses: actions/checkout@a12a3943b4bdde767164f792f33f40b04645d846 # v3.0.0
-        with:
-          persist-credentials: false
-
-      - name: "Run analysis"
-        uses: ossf/scorecard-action@0864cf19026789058feabb7e87baa5f140aac736 # v2.3.1
-        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@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4.3.1
-        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@83a02f7883b12e0e4e1a146174f5e2292a01e601 # v2.16.4
-        with:
-          sarif_file: results.sarif

.github/workflows/update_rapids.yml

@@ -1,44 +0,0 @@
-name: update-rapids
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 20 * * 1"  # Run once weekly
-
-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@v6
-      if: github.ref == 'refs/heads/master'
-      with:
-        add-paths: |
-          tests/buildkite
-        branch: create-pull-request/update-rapids
-        base: master
-        title: "[CI] Update RAPIDS to latest stable"
-        commit-message: "[CI] Update RAPIDS to latest stable"
-      

.gitignore

@@ -48,13 +48,9 @@ Debug
 *.Rproj
 ./xgboost.mpi
 ./xgboost.mock
-*.bak
 #.Rbuildignore
 R-package.Rproj
 *.cache*
-.mypy_cache/
-doxygen
-
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -66,7 +62,6 @@ nb-configuration*
 # Eclipse
 .project
 .cproject
-.classpath
 .pydevproject
 .settings/
 build
@@ -75,7 +70,6 @@ build
 build_plugin
 recommonmark/
 tags
-TAGS
 *.class
 target
 *.swp
@@ -98,13 +92,9 @@ metastore_db
 # files from R-package source install
 **/config.status
 R-package/src/Makevars
-*.lib
 
-# Visual Studio
-.vs/
-CMakeSettings.json
-*.ilk
-*.pdb
+# Visual Studio Code
+/.vscode/
 
 # IntelliJ/CLion
 .idea
@@ -112,43 +102,4 @@ CMakeSettings.json
 /cmake-build-debug/
 
 # GDB
-.gdb_history
-
-# Python joblib.Memory used in pytest.
-cachedir/
-
-# Files from local Dask work
-dask-worker-space/
-
-# Jupyter notebook checkpoints
-.ipynb_checkpoints/
-
-# credentials and key material
-config
-credentials
-credentials.csv
-*.env
-*.pem
-*.pub
-*.rdp
-*_rsa
-
-# Visual Studio code + extensions
-.vscode
-.metals
-.bloop
-
-# python tests
-demo/**/*.txt
-*.dmatrix
-.hypothesis
-__MACOSX/
-model*.json
-
-# R tests
-*.htm
-*.html
-*.libsvm
-*.rds
-Rplots.pdf
-*.zip
+.gdb_history

.gitmodules

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

.readthedocs.yaml

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

.travis.yml

@@ -0,0 +1,79 @@
+# disable sudo for container build.
+sudo: required
+
+# Enabling test OS X
+os:
+  - linux
+  - osx
+
+osx_image: xcode10.1
+dist: bionic
+
+# Use Build Matrix to do lint and build seperately
+env:
+  matrix:
+    # python package test
+    - TASK=python_test
+    # test installation of Python source distribution
+    - TASK=python_sdist_test
+    # java package test
+    - TASK=java_test
+    # cmake test
+    - TASK=cmake_test
+
+  global:
+    - secure: "PR16i9F8QtNwn99C5NDp8nptAS+97xwDtXEJJfEiEVhxPaaRkOp0MPWhogCaK0Eclxk1TqkgWbdXFknwGycX620AzZWa/A1K3gAs+GrpzqhnPMuoBJ0Z9qxXTbSJvCyvMbYwVrjaxc/zWqdMU8waWz8A7iqKGKs/SqbQ3rO6v7c="
+    - secure: "dAGAjBokqm/0nVoLMofQni/fWIBcYSmdq4XvCBX1ZAMDsWnuOfz/4XCY6h2lEI1rVHZQ+UdZkc9PioOHGPZh5BnvE49/xVVWr9c4/61lrDOlkD01ZjSAeoV0fAZq+93V/wPl4QV+MM+Sem9hNNzFSbN5VsQLAiWCSapWsLdKzqA="
+
+matrix:
+  exclude:
+    - os: linux
+      env: TASK=python_test
+    - os: linux
+      env: TASK=java_test
+    - os: linux
+      env: TASK=cmake_test
+
+# dependent brew packages
+addons:
+  homebrew:
+    packages:
+      - cmake
+      - libomp
+      - graphviz
+      - openssl
+      - libgit2
+      - wget
+      - r
+    update: true
+
+before_install:
+  - source tests/travis/travis_setup_env.sh
+  - if [ "${TASK}" != "python_sdist_test" ]; then export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package; fi
+  - 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

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

CMakeLists.txt

@@ -1,110 +1,53 @@
-cmake_minimum_required(VERSION 3.18 FATAL_ERROR)
-
-if(PLUGIN_SYCL)
-  set(CMAKE_CXX_COMPILER  "g++")
-  set(CMAKE_C_COMPILER  "gcc")
-  string(REPLACE " -isystem ${CONDA_PREFIX}/include" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
-endif()
-
-project(xgboost LANGUAGES CXX C VERSION 2.1.0)
+cmake_minimum_required(VERSION 3.13)
+project(xgboost LANGUAGES CXX C VERSION 1.1.1)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
+cmake_policy(SET CMP0022 NEW)
+cmake_policy(SET CMP0079 NEW)
+cmake_policy(SET CMP0063 NEW)
 
-# These policies are already set from 3.18 but we still need to set the policy
-# default variables here for lower minimum versions in the submodules
-set(CMAKE_POLICY_DEFAULT_CMP0063 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0069 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0076 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0079 NEW)
+if ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
+  cmake_policy(SET CMP0077 NEW)
+endif ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
 
 message(STATUS "CMake version ${CMAKE_VERSION}")
 
-# Check compiler versions
-# Use recent compilers to ensure that std::filesystem is available
-if(MSVC)
-  if(MSVC_VERSION LESS 1920)
-    message(FATAL_ERROR "Need Visual Studio 2019 or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "8.1")
-    message(FATAL_ERROR "Need GCC 8.1 or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "11.0")
-    message(FATAL_ERROR "Need Xcode 11.0 (AppleClang 11.0) or newer to build XGBoost")
-  endif()
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS "9.0")
-    message(FATAL_ERROR "Need Clang 9.0 or newer to build XGBoost")
-  endif()
+if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 5.0)
+  message(FATAL_ERROR "GCC version must be at least 5.0!")
 endif()
 
-include(${xgboost_SOURCE_DIR}/cmake/PrefetchIntrinsics.cmake)
+include(${xgboost_SOURCE_DIR}/cmake/FindPrefetchIntrinsics.cmake)
 find_prefetch_intrinsics()
 include(${xgboost_SOURCE_DIR}/cmake/Version.cmake)
 write_version()
 set_default_configuration_release()
 
 #-- Options
-include(CMakeDependentOption)
-
-## User options
 option(BUILD_C_DOC "Build documentation for C APIs using Doxygen." OFF)
 option(USE_OPENMP "Build with OpenMP support." ON)
 option(BUILD_STATIC_LIB "Build static library" OFF)
-option(BUILD_DEPRECATED_CLI "Build the deprecated command line interface" OFF)
-option(FORCE_SHARED_CRT "Build with dynamic CRT on Windows (/MD)" OFF)
 ## Bindings
 option(JVM_BINDINGS "Build JVM bindings" OFF)
 option(R_LIB "Build shared library for R package" OFF)
 ## Dev
 option(USE_DEBUG_OUTPUT "Dump internal training results like gradients and predictions to stdout.
 Should only be used for debugging." OFF)
-option(FORCE_COLORED_OUTPUT "Force colored output from compilers, useful when ninja is used instead of make." OFF)
-option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC/Clang" OFF)
-option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
 option(GOOGLE_TEST "Build google tests" OFF)
 option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
-option(USE_DEVICE_DEBUG "Generate CUDA/HIP device debug info." OFF)
 option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
 set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
 option(RABIT_MOCK "Build rabit with mock" OFF)
 option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
-option(KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR "Output build artifacts in CMake binary dir" OFF)
 ## CUDA
 option(USE_CUDA  "Build with GPU acceleration" OFF)
-option(USE_PER_THREAD_DEFAULT_STREAM "Build with per-thread default stream" ON)
 option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
-# This is specifically designed for PyPI binary release and should be disabled for most of the cases.
-option(USE_DLOPEN_NCCL "Whether to load nccl dynamically." OFF)
 option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
-
-if(USE_CUDA)
-  if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES AND NOT DEFINED ENV{CUDAARCHS})
-    set(GPU_COMPUTE_VER "" CACHE STRING
-      "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
-  else()
-    # Clear any cached values from previous runs
-    unset(GPU_COMPUTE_VER)
-    unset(GPU_COMPUTE_VER CACHE)
-  endif()
-endif()
-
-# CUDA device LTO was introduced in CMake v3.25 and requires host LTO to also be enabled but can still
-# be explicitly disabled allowing for LTO on host only, host and device, or neither, but device-only LTO
-# is not a supproted configuration
-cmake_dependent_option(USE_CUDA_LTO
-  "Enable link-time optimization for CUDA device code"
-  "${CMAKE_INTERPROCEDURAL_OPTIMIZATION}"
-  "CMAKE_VERSION VERSION_GREATER_EQUAL 3.25;USE_CUDA;CMAKE_INTERPROCEDURAL_OPTIMIZATION"
-  OFF)
-## HIP
-option(USE_HIP  "Build with GPU acceleration" OFF)
-option(USE_RCCL "Build with RCCL to enable distributed GPU support." OFF)
-# This is specifically designed for PyPI binary release and should be disabled for most of the cases.
-option(USE_DLOPEN_RCCL "Whether to load nccl dynamically." OFF)
-option(BUILD_WITH_SHARED_RCCL "Build with shared RCCL library." OFF)
+set(GPU_COMPUTE_VER "" CACHE STRING
+  "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
+## Copied From dmlc
+option(USE_HDFS "Build with HDFS support" OFF)
+option(USE_AZURE "Build with AZURE support" OFF)
+option(USE_S3 "Build with S3 support" OFF)
 ## Sanitizers
 option(USE_SANITIZER "Use santizer flags" OFF)
 option(SANITIZER_PATH "Path to sanitizes.")
@@ -112,372 +55,173 @@ 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_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_SYCL "SYCL plugin" OFF)
+option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
+option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
 option(ADD_PKGCONFIG "Add xgboost.pc into system." ON)
 
 #-- Checks for building XGBoost
-if(USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
+if (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
   message(SEND_ERROR "Do not enable `USE_DEBUG_OUTPUT' with release build.")
-endif()
-if(USE_NCCL AND NOT (USE_CUDA))
+endif (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
+if (USE_NCCL AND NOT (USE_CUDA))
   message(SEND_ERROR "`USE_NCCL` must be enabled with `USE_CUDA` flag.")
-endif()
-if(USE_DEVICE_DEBUG AND NOT (USE_CUDA))
-  message(SEND_ERROR "`USE_DEVICE_DEBUG` must be enabled with `USE_CUDA` flag.")
-endif()
-if(BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
+endif (USE_NCCL AND NOT (USE_CUDA))
+if (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
   message(SEND_ERROR "Build XGBoost with -DUSE_NCCL=ON to enable BUILD_WITH_SHARED_NCCL.")
-endif()
-if(USE_DLOPEN_NCCL AND (NOT USE_NCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_NCCL=ON to enable USE_DLOPEN_NCCL.")
-endif()
-if(USE_DLOPEN_NCCL AND (NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux")))
-  message(SEND_ERROR "`USE_DLOPEN_NCCL` supports only Linux at the moment.")
-endif()
-if(USE_RCCL AND NOT (USE_HIP))
-    message(SEND_ERROR "`USE_RCCL` must be enabled with `USE_HIP` flag.")
-endif()
-if(BUILD_WITH_SHARED_RCCL AND (NOT USE_RCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_RCCL=ON to enable BUILD_WITH_SHARED_RCCL.")
-endif()
-if(USE_DLOPEN_RCCL AND (NOT USE_RCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_RCCL=ON to enable USE_DLOPEN_RCCL.")
-endif()
-if(USE_DLOPEN_RCCL AND (NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux")))
-  message(SEND_ERROR "`USE_DLOPEN_RCCL` supports only Linux at the moment.")
-endif()
-if(JVM_BINDINGS AND R_LIB)
+endif (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
+if (JVM_BINDINGS AND R_LIB)
   message(SEND_ERROR "`R_LIB' is not compatible with `JVM_BINDINGS' as they both have customized configurations.")
-endif()
-if(R_LIB AND GOOGLE_TEST)
-  message(
-    WARNING
-    "Some C++ tests will fail with `R_LIB` enabled, as R package redirects some functions to R runtime implementation."
-  )
-endif()
-if(PLUGIN_RMM AND NOT (USE_CUDA))
-  message(SEND_ERROR "`PLUGIN_RMM` must be enabled with `USE_CUDA` flag.")
-endif()
-if(PLUGIN_RMM AND NOT ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") OR (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with GCC or Clang compiler.")
-endif()
-if(PLUGIN_RMM AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with Linux.")
-endif()
-if(ENABLE_ALL_WARNINGS)
-  if((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-    message(SEND_ERROR "ENABLE_ALL_WARNINGS is only available for Clang and GCC.")
-  endif()
-endif()
-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()
-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()
-
-#-- Removed options
-if(USE_AVX)
-  message(SEND_ERROR  "The option `USE_AVX` is deprecated as experimental AVX features have been removed from XGBoost.")
-endif()
-if(PLUGIN_LZ4)
-  message(SEND_ERROR  "The option `PLUGIN_LZ4` is removed from XGBoost.")
-endif()
-if(RABIT_BUILD_MPI)
-  message(SEND_ERROR "The option `RABIT_BUILD_MPI` has been removed from XGBoost.")
-endif()
-if(USE_S3)
-  message(SEND_ERROR "The option `USE_S3` has been removed from XGBoost")
-endif()
-if(USE_AZURE)
-  message(SEND_ERROR "The option `USE_AZURE` has been removed from XGBoost")
-endif()
-if(USE_HDFS)
-  message(SEND_ERROR "The option `USE_HDFS` has been removed from XGBoost")
-endif()
-if(PLUGIN_DENSE_PARSER)
-  message(SEND_ERROR "The option `PLUGIN_DENSE_PARSER` has been removed from XGBoost.")
-endif()
+endif (JVM_BINDINGS AND R_LIB)
+if (R_LIB AND GOOGLE_TEST)
+  message(WARNING "Some C++ unittests will fail with `R_LIB` enabled,
+ as R package redirects some functions to R runtime implementation.")
+endif (R_LIB AND GOOGLE_TEST)
+if (USE_AVX)
+  message(SEND_ERROR  "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from XGBoost.")
+endif (USE_AVX)
 
 #-- Sanitizer
-if(USE_SANITIZER)
+if (USE_SANITIZER)
   include(cmake/Sanitizer.cmake)
   enable_sanitizers("${ENABLED_SANITIZERS}")
-endif()
+endif (USE_SANITIZER)
 
-if(USE_CUDA)
-  set(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
+if (USE_CUDA)
+  SET(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
   # `export CXX=' is ignored by CMake CUDA.
-  if(NOT DEFINED CMAKE_CUDA_HOST_COMPILER AND NOT DEFINED ENV{CUDAHOSTCXX})
-    set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER} CACHE FILEPATH
-      "The compiler executable to use when compiling host code for CUDA or HIP language files.")
-    mark_as_advanced(CMAKE_CUDA_HOST_COMPILER)
-    message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
-  endif()
-
-  if(NOT DEFINED CMAKE_CUDA_RUNTIME_LIBRARY)
-    set(CMAKE_CUDA_RUNTIME_LIBRARY Static)
-  endif()
+  set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
+  message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
 
   enable_language(CUDA)
-  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 11.0)
-    message(FATAL_ERROR "CUDA version must be at least 11.0!")
-  endif()
-  if(DEFINED GPU_COMPUTE_VER)
-    compute_cmake_cuda_archs("${GPU_COMPUTE_VER}")
-  endif()
-  add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
-
-  find_package(CUDAToolkit REQUIRED)
-endif()
-
-if (USE_HIP)
-  set(USE_OPENMP ON CACHE BOOL "HIP requires OpenMP" FORCE)
-  # `export CXX=' is ignored by CMake HIP.
-  set(CMAKE_HIP_HOST_COMPILER ${CMAKE_CXX_COMPILER})
-  message(STATUS "Configured HIP host compiler: ${CMAKE_HIP_HOST_COMPILER}")
-
-  enable_language(HIP)
-  find_package(hip REQUIRED)
-  find_package(rocthrust REQUIRED)
-  find_package(hipcub REQUIRED)
-
-  set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} -I${HIP_INCLUDE_DIRS}")
-  set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} -Wunused-result -w")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__HIP_PLATFORM_AMD__")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -I${HIP_INCLUDE_DIRS}")
-  #set(CMAKE_HIP_SEPARABLE_COMPILATION ON)
-  add_subdirectory(${PROJECT_SOURCE_DIR}/rocgputreeshap)
-endif (USE_HIP)
-
-if(FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
-    ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
-      (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-color=always")
-endif()
+  set(GEN_CODE "")
+  format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
+  message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
+endif (USE_CUDA)
 
 find_package(Threads REQUIRED)
 
-if(USE_OPENMP)
-  if(APPLE)
-    find_package(OpenMP)
-    if(NOT OpenMP_FOUND)
-      # Try again with extra path info; required for libomp 15+ from Homebrew
-      execute_process(COMMAND brew --prefix libomp
-                      OUTPUT_VARIABLE HOMEBREW_LIBOMP_PREFIX
-                      OUTPUT_STRIP_TRAILING_WHITESPACE)
-      set(OpenMP_C_FLAGS
-        "-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include")
-      set(OpenMP_CXX_FLAGS
-        "-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include")
-      set(OpenMP_C_LIB_NAMES omp)
-      set(OpenMP_CXX_LIB_NAMES omp)
-      set(OpenMP_omp_LIBRARY ${HOMEBREW_LIBOMP_PREFIX}/lib/libomp.dylib)
-      find_package(OpenMP REQUIRED)
-    endif()
-  else()
-    find_package(OpenMP REQUIRED)
-  endif()
-endif()
-#Add for IBM i
-if(${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()
-
-if (USE_RCCL)
-  find_package(rccl REQUIRED)
-endif (USE_RCCL)
+if (USE_OPENMP)
+  if (APPLE)
+    # Require CMake 3.16+ on Mac OSX, as previous versions of CMake had trouble locating
+    # OpenMP on Mac. See https://github.com/dmlc/xgboost/pull/5146#issuecomment-568312706
+    cmake_minimum_required(VERSION 3.16)
+  endif (APPLE)
+  find_package(OpenMP REQUIRED)
+endif (USE_OPENMP)
 
 # dmlc-core
 msvc_use_static_runtime()
-if(FORCE_SHARED_CRT)
-  set(DMLC_FORCE_SHARED_CRT ON)
-endif()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-
-if(MSVC)
-  if(TARGET dmlc_unit_tests)
-    target_compile_options(
-        dmlc_unit_tests PRIVATE
-        -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE
-    )
-  endif()
-endif()
+set_target_properties(dmlc PROPERTIES
+  CXX_STANDARD 11
+  CXX_STANDARD_REQUIRED ON
+  POSITION_INDEPENDENT_CODE ON)
+list(APPEND LINKED_LIBRARIES_PRIVATE dmlc)
 
 # rabit
+set(RABIT_BUILD_DMLC OFF)
+set(DMLC_ROOT ${xgboost_SOURCE_DIR}/dmlc-core)
+set(RABIT_WITH_R_LIB ${R_LIB})
 add_subdirectory(rabit)
 
-# core xgboost
-add_subdirectory(${xgboost_SOURCE_DIR}/src)
-target_link_libraries(objxgboost PUBLIC dmlc)
-
-# Link -lstdc++fs for GCC 8.x
-if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "9.0")
-  target_link_libraries(objxgboost PUBLIC stdc++fs)
-endif()
+if (RABIT_MOCK)
+  list(APPEND LINKED_LIBRARIES_PRIVATE rabit_mock_static)
+else()
+  list(APPEND LINKED_LIBRARIES_PRIVATE rabit)
+endif(RABIT_MOCK)
+foreach(lib rabit rabit_base rabit_empty rabit_mock rabit_mock_static)
+  # Explicitly link dmlc to rabit, so that configured header (build_config.h)
+  # from dmlc is correctly applied to rabit.
+  if (TARGET ${lib})
+    target_link_libraries(${lib} dmlc ${CMAKE_THREAD_LIBS_INIT})
+    if (HIDE_CXX_SYMBOLS)  # Hide all C++ symbols from Rabit
+      set_target_properties(${lib} PROPERTIES CXX_VISIBILITY_PRESET hidden)
+    endif (HIDE_CXX_SYMBOLS)
+  endif (TARGET ${lib})
+endforeach()
 
 # Exports some R specific definitions and objects
-if(R_LIB)
+if (R_LIB)
   add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
-endif()
+endif (R_LIB)
 
-# This creates its own shared library `xgboost4j'.
-if(JVM_BINDINGS)
-  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
-endif()
-
-# Plugin
+# core xgboost
+list(APPEND LINKED_LIBRARIES_PRIVATE Threads::Threads ${CMAKE_THREAD_LIBS_INIT})
 add_subdirectory(${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 "${rmm_link_libs}")
-  get_target_property(rmm_link_libs rmm::rmm INTERFACE_LINK_LIBRARIES)
-endif()
-
-if(PLUGIN_SYCL)
-  set(CMAKE_CXX_LINK_EXECUTABLE
-      "icpx <FLAGS> <CMAKE_CXX_LINK_FLAGS> -qopenmp <LINK_FLAGS> <OBJECTS> -o <TARGET> <LINK_LIBRARIES>")
-  set(CMAKE_CXX_CREATE_SHARED_LIBRARY
-      "icpx <CMAKE_SHARED_LIBRARY_CXX_FLAGS> -qopenmp <LANGUAGE_COMPILE_FLAGS> \
-      <CMAKE_SHARED_LIBRARY_CREATE_CXX_FLAGS> <SONAME_FLAG>,<TARGET_SONAME> \
-      -o <TARGET> <OBJECTS> <LINK_LIBRARIES>")
-endif()
+add_subdirectory(${xgboost_SOURCE_DIR}/src)
+target_link_libraries(objxgboost PUBLIC dmlc)
+set(XGBOOST_OBJ_SOURCES "${XGBOOST_OBJ_SOURCES};$<TARGET_OBJECTS:objxgboost>")
 
 #-- library
-if(BUILD_STATIC_LIB)
-  add_library(xgboost STATIC)
-else()
-  add_library(xgboost SHARED)
-endif()
-target_link_libraries(xgboost PRIVATE objxgboost)
+if (BUILD_STATIC_LIB)
+  add_library(xgboost STATIC ${XGBOOST_OBJ_SOURCES})
+else (BUILD_STATIC_LIB)
+  add_library(xgboost SHARED ${XGBOOST_OBJ_SOURCES})
+endif (BUILD_STATIC_LIB)
+
+#-- Hide all C++ symbols
+if (HIDE_CXX_SYMBOLS)
+  set_target_properties(objxgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
+  set_target_properties(xgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
+endif (HIDE_CXX_SYMBOLS)
+
 target_include_directories(xgboost
   INTERFACE
-  $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
+  $<INSTALL_INTERFACE:${CMAKE_INSTALL_PREFIX}/include>
   $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
+target_link_libraries(xgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
+
+# This creates its own shared library `xgboost4j'.
+if (JVM_BINDINGS)
+  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
+endif (JVM_BINDINGS)
 #-- End shared library
 
 #-- CLI for xgboost
-if(BUILD_DEPRECATED_CLI)
-  add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
-  target_link_libraries(runxgboost PRIVATE objxgboost)
-  target_include_directories(runxgboost
-    PRIVATE
-    ${xgboost_SOURCE_DIR}/include
-    ${xgboost_SOURCE_DIR}/dmlc-core/include
-    ${xgboost_SOURCE_DIR}/rabit/include
-  )
-  set_target_properties(runxgboost PROPERTIES OUTPUT_NAME xgboost)
-  xgboost_target_properties(runxgboost)
-  xgboost_target_link_libraries(runxgboost)
-  xgboost_target_defs(runxgboost)
+add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc ${XGBOOST_OBJ_SOURCES})
 
-  if(KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR)
-    set_output_directory(runxgboost ${xgboost_BINARY_DIR})
-  else()
-    set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
-  endif()
-endif()
+target_include_directories(runxgboost
+  PRIVATE
+  ${xgboost_SOURCE_DIR}/include
+  ${xgboost_SOURCE_DIR}/dmlc-core/include
+  ${xgboost_SOURCE_DIR}/rabit/include)
+target_link_libraries(runxgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
+set_target_properties(
+  runxgboost PROPERTIES
+  OUTPUT_NAME xgboost
+  CXX_STANDARD 11
+  CXX_STANDARD_REQUIRED ON)
 #-- End CLI for xgboost
 
-# Common setup for all targets
-foreach(target xgboost objxgboost dmlc)
-  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()
-
-if(KEEP_BUILD_ARTIFACTS_IN_BINARY_DIR)
-  set_output_directory(xgboost ${xgboost_BINARY_DIR}/lib)
-else()
-  set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
-endif()
-
+set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
+set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
 # Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
-if(BUILD_DEPRECATED_CLI)
-  add_dependencies(xgboost runxgboost)
-endif()
+add_dependencies(xgboost runxgboost)
 
 #-- Installing XGBoost
-if(R_LIB)
-  include(cmake/RPackageInstallTargetSetup.cmake)
+if (R_LIB)
   set_target_properties(xgboost PROPERTIES PREFIX "")
-  if(APPLE)
+  if (APPLE)
     set_target_properties(xgboost PROPERTIES SUFFIX ".so")
-  endif()
-  setup_rpackage_install_target(xgboost "${CMAKE_CURRENT_BINARY_DIR}/R-package-install")
+  endif (APPLE)
+  setup_rpackage_install_target(xgboost ${CMAKE_CURRENT_BINARY_DIR})
   set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
-endif()
-if(MINGW)
+endif (R_LIB)
+if (MINGW)
   set_target_properties(xgboost PROPERTIES PREFIX "")
-endif()
+endif (MINGW)
 
-if(BUILD_C_DOC)
+if (BUILD_C_DOC)
   include(cmake/Doc.cmake)
   run_doxygen()
-endif()
-
-include(CPack)
+endif (BUILD_C_DOC)
 
 include(GNUInstallDirs)
 # Install all headers.  Please note that currently the C++ headers does not form an "API".
 install(DIRECTORY ${xgboost_SOURCE_DIR}/include/xgboost
   DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
 
-# Install libraries. If `xgboost` is a static lib, specify `objxgboost` also, to avoid the
-# following error:
-#
-#  > install(EXPORT ...) includes target "xgboost" which requires target "objxgboost" that is not
-#  > in any export set.
-#
-# https://github.com/dmlc/xgboost/issues/6085
-if(BUILD_STATIC_LIB)
-  if(BUILD_DEPRECATED_CLI)
-    set(INSTALL_TARGETS xgboost runxgboost objxgboost dmlc)
-  else()
-    set(INSTALL_TARGETS xgboost objxgboost dmlc)
-  endif()
-else()
-  if(BUILD_DEPRECATED_CLI)
-    set(INSTALL_TARGETS xgboost runxgboost)
-  else()
-    set(INSTALL_TARGETS xgboost)
-  endif()
-endif()
-
-install(TARGETS ${INSTALL_TARGETS}
+install(TARGETS xgboost runxgboost
   EXPORT XGBoostTargets
   ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
   LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
@@ -499,41 +243,33 @@ write_basic_package_version_file(
   COMPATIBILITY AnyNewerVersion)
 install(
   FILES
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
+  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
   ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
   DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
 
 #-- Test
-if(GOOGLE_TEST)
+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
     ${xgboost_BINARY_DIR}/tests/cli/machine.conf
     @ONLY)
-  if(BUILD_DEPRECATED_CLI)
-    add_test(
-      NAME TestXGBoostCLI
-      COMMAND runxgboost ${xgboost_BINARY_DIR}/tests/cli/machine.conf
-      WORKING_DIRECTORY ${xgboost_BINARY_DIR})
-    set_tests_properties(TestXGBoostCLI
-      PROPERTIES
-      PASS_REGULAR_EXPRESSION ".*test-rmse:0.087.*")
-  endif()
-endif()
+  add_test(
+    NAME TestXGBoostCLI
+    COMMAND runxgboost ${xgboost_BINARY_DIR}/tests/cli/machine.conf
+    WORKING_DIRECTORY ${xgboost_BINARY_DIR})
+  set_tests_properties(TestXGBoostCLI
+    PROPERTIES
+    PASS_REGULAR_EXPRESSION ".*test-rmse:0.087.*")
+endif (GOOGLE_TEST)
 
 # For MSVC: Call msvc_use_static_runtime() once again to completely
 # replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
@@ -541,10 +277,10 @@ endif()
 msvc_use_static_runtime()
 
 # Add xgboost.pc
-if(ADD_PKGCONFIG)
+if (ADD_PKGCONFIG)
   configure_file(${xgboost_SOURCE_DIR}/cmake/xgboost.pc.in ${xgboost_BINARY_DIR}/xgboost.pc @ONLY)
 
   install(
     FILES ${xgboost_BINARY_DIR}/xgboost.pc
     DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
-endif()
+endif (ADD_PKGCONFIG)

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), Red Hat
-  - Yuan is a principal software engineer at Red Hat. He contributed mostly in R and Python packages.
+* [Yuan Tang](https://github.com/terrytangyuan), Ant Financial
+  - Yuan is a software engineer in Ant Financial. He contributed mostly in R and Python packages.
 * [Nan Zhu](https://github.com/CodingCat), Uber
   - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
 * [Jiaming Yuan](https://github.com/trivialfis)
@@ -37,13 +37,11 @@ Committers are people who have made substantial contribution to the project and
   - Sergei is a software engineer in Criteo. He contributed mostly in JVM packages.
 * [Scott Lundberg](http://scottlundberg.com/), University of Washington
   - Scott is a Ph.D. student at University of Washington. He is the creator of SHAP, a unified approach to explain the output of machine learning models such as decision tree ensembles. He also helps maintain the XGBoost Julia package.
-* [Egor Smirnov](https://github.com/SmirnovEgorRu), Intel
-  - Egor has led a major effort to improve the performance of XGBoost on multi-core CPUs.
 
 
 Become a Committer
 ------------------
-XGBoost is a open source project and we are actively looking for new committers who are willing to help maintaining and lead the project.
+XGBoost is a opensource project and we are actively looking for new committers who are willing to help maintaining and lead the project.
 Committers comes from contributors who:
 * Made substantial contribution to the project.
 * Willing to spent time on maintaining and lead the project.
@@ -59,7 +57,7 @@ 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 +89,7 @@ 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

@@ -0,0 +1,422 @@
+#!/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'
+
+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 {
+          checkoutSrcs()
+          commit_id = "${GIT_COMMIT}"
+        }
+        sh 'python3 tests/jenkins_get_approval.py'
+        stash name: 'srcs'
+        milestone ordinal: 1
+      }
+    }
+    stage('Jenkins Linux: Formatting Check') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'clang-tidy': { ClangTidy() },
+            'sphinx-doc': { SphinxDoc() },
+            'doxygen': { Doxygen() }
+          ])
+        }
+        milestone ordinal: 2
+      }
+    }
+    stage('Jenkins Linux: Build') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'build-cpu': { BuildCPU() },
+            'build-cpu-rabit-mock': { BuildCPUMock() },
+            'build-cpu-non-omp': { BuildCPUNonOmp() },
+            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
+            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
+            'build-jvm-doc': { BuildJVMDoc() }
+          ])
+        }
+        milestone ordinal: 3
+      }
+    }
+    stage('Jenkins Linux: Test') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'test-python-cpu': { TestPythonCPU() },
+            'test-python-gpu-cuda9.0': { TestPythonGPU(cuda_version: '9.0') },
+            'test-python-gpu-cuda10.0': { TestPythonGPU(cuda_version: '10.0') },
+            'test-python-gpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1') },
+            'test-python-mgpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1', multi_gpu: true) },
+            'test-cpp-gpu': { TestCppGPU(cuda_version: '10.1') },
+            'test-cpp-mgpu': { TestCppGPU(cuda_version: '10.1', multi_gpu: true) },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '2.4.3') },
+            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
+            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
+            'test-r-3.5.3': { TestR(use_r35: true) }
+          ])
+        }
+        milestone ordinal: 4
+      }
+    }
+    stage('Jenkins Linux: Deploy') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '2.4.3') }
+          ])
+        }
+        milestone ordinal: 5
+      }
+    }
+  }
+}
+
+// check out source code from git
+def checkoutSrcs() {
+  retry(5) {
+    try {
+      timeout(time: 2, unit: 'MINUTES') {
+        checkout scm
+        sh 'git submodule update --init'
+      }
+    } catch (exc) {
+      deleteDir()
+      error "Failed to fetch source codes"
+    }
+  }
+}
+
+def ClangTidy() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running clang-tidy job..."
+    def container_type = "clang_tidy"
+    def docker_binary = "docker"
+    def dockerArgs = "--build-arg CUDA_VERSION=10.1"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
+    """
+    deleteDir()
+  }
+}
+
+def Lint() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running lint..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} make lint
+    """
+    deleteDir()
+  }
+}
+
+def SphinxDoc() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running sphinx-doc..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
+    sh """#!/bin/bash
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} make -C doc html
+    """
+    deleteDir()
+  }
+}
+
+def Doxygen() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running doxygen..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
+    """
+    echo 'Uploading doc...'
+    s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
+    deleteDir()
+  }
+}
+
+def BuildCPU() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} rm -fv dmlc-core/include/dmlc/build_config_default.h
+      # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
+      # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
+      # See discussion at https://github.com/dmlc/xgboost/issues/5510
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh
+    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    """
+    // Sanitizer test
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
+      -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    """
+
+    stash name: 'xgboost_cli', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCPUMock() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU with rabit mock"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_mock_cmake.sh
+    """
+    echo 'Stashing rabit C++ test executable (xgboost)...'
+    stash name: 'xgboost_rabit_tests', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCPUNonOmp() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU without OpenMP"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_OPENMP=OFF
+    """
+    echo "Running Non-OpenMP C++ test..."
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    """
+    deleteDir()
+  }
+}
+
+def BuildCUDA(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build with CUDA ${args.cuda_version}"
+    def container_type = "gpu_build"
+    def docker_binary = "docker"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOLS=ON
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
+    """
+    // Stash wheel for CUDA 10.0 target
+    if (args.cuda_version == '10.0') {
+      echo 'Stashing Python wheel...'
+      stash name: 'xgboost_whl_cuda10', includes: 'python-package/dist/*.whl'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+      echo 'Stashing C++ test executable (testxgboost)...'
+      stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost'
+    }
+    deleteDir()
+  }
+}
+
+def BuildJVMPackages(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}"
+    def container_type = "jvm"
+    def docker_binary = "docker"
+    // Use only 4 CPU cores
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
+    """
+    echo 'Stashing XGBoost4J JAR...'
+    stash name: 'xgboost4j_jar', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
+    deleteDir()
+  }
+}
+
+def BuildJVMDoc() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Building JVM doc..."
+    def container_type = "jvm"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
+    """
+    echo 'Uploading doc...'
+    s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
+    deleteDir()
+  }
+}
+
+def TestPythonCPU() {
+  node('linux && cpu') {
+    unstash name: 'xgboost_whl_cuda10'
+    unstash name: 'srcs'
+    unstash name: 'xgboost_cli'
+    echo "Test Python CPU"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-py35
+    """
+    deleteDir()
+  }
+}
+
+def TestPythonGPU(args) {
+  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
+  node(nodeReq) {
+    unstash name: 'xgboost_whl_cuda10'
+    unstash name: 'srcs'
+    echo "Test Python GPU: CUDA ${args.cuda_version}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
+    if (args.multi_gpu) {
+      echo "Using multiple GPUs"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
+      """
+    } else {
+      echo "Using a single GPU"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
+      """
+    }
+    deleteDir()
+  }
+}
+
+def TestCppRabit() {
+  node(nodeReq) {
+    unstash name: 'xgboost_rabit_tests'
+    unstash name: 'srcs'
+    echo "Test C++, rabit mock on"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/runxgb.sh xgboost tests/ci_build/approx.conf.in
+    """
+    deleteDir()
+  }
+}
+
+def TestCppGPU(args) {
+  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
+  node(nodeReq) {
+    unstash name: 'xgboost_cpp_tests'
+    unstash name: 'srcs'
+    echo "Test C++, CUDA ${args.cuda_version}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
+    if (args.multi_gpu) {
+      echo "Using multiple GPUs"
+      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=*.MGPU_*"
+    } else {
+      echo "Using a single GPU"
+      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=-*.MGPU_*"
+    }
+    deleteDir()
+  }
+}
+
+def CrossTestJVMwithJDK(args) {
+  node('linux && cpu') {
+    unstash name: 'xgboost4j_jar'
+    unstash name: 'srcs'
+    if (args.spark_version != null) {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
+    } else {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
+    }
+    def container_type = "jvm_cross"
+    def docker_binary = "docker"
+    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
+    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
+    // Run integration tests only when spark_version is given
+    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
+    """
+    deleteDir()
+  }
+}
+
+def TestR(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Test R package"
+    def container_type = "rproject"
+    def docker_binary = "docker"
+    def use_r35_flag = (args.use_r35) ? "1" : "0"
+    def docker_args = "--build-arg USE_R35=${use_r35_flag}"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_test_rpkg.sh || tests/ci_build/print_r_stacktrace.sh
+    """
+    deleteDir()
+  }
+}
+
+def DeployJVMPackages(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Deploying to xgboost-maven-repo S3 repo...'
+      def container_type = "jvm"
+      def docker_binary = "docker"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      """
+    }
+    deleteDir()
+  }
+}

Jenkinsfile-win64

@@ -0,0 +1,150 @@
+#!/usr/bin/groovy
+// -*- mode: groovy -*-
+
+/* Jenkins pipeline for Windows AMD64 target */
+
+import groovy.transform.Field
+
+@Field
+def commit_id   // necessary to pass a variable from one stage to another
+
+pipeline {
+  agent none
+  // Build stages
+  stages {
+    stage('Jenkins Win64: Initialize') {
+      agent { label 'job_initializer' }
+      steps {
+        script {
+          checkoutSrcs()
+          commit_id = "${GIT_COMMIT}"
+        }
+        sh 'python3 tests/jenkins_get_approval.py'
+        stash name: 'srcs'
+        milestone ordinal: 1
+      }
+    }
+    stage('Jenkins Win64: Build') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'build-win64-cuda10.0': { BuildWin64() }
+          ])
+        }
+        milestone ordinal: 2
+      }
+    }
+    stage('Jenkins Win64: Test') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'test-win64-cpu': { TestWin64CPU() },
+            'test-win64-gpu-cuda10.1': { TestWin64GPU(cuda_target: 'cuda10_1') }
+          ])
+        }
+        milestone ordinal: 3
+      }
+    }
+  }
+}
+
+// check out source code from git
+def checkoutSrcs() {
+  retry(5) {
+    try {
+      timeout(time: 2, unit: 'MINUTES') {
+        checkout scm
+        sh 'git submodule update --init'
+      }
+    } catch (exc) {
+      deleteDir()
+      error "Failed to fetch source codes"
+    }
+  }
+}
+
+def BuildWin64() {
+  node('win64 && build && cuda10') {
+    unstash name: 'srcs'
+    echo "Building XGBoost for Windows AMD64 target..."
+    bat "nvcc --version"
+    bat """
+    mkdir build
+    cd build
+    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
+    """
+    bat """
+    cd build
+    "C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Community\\MSBuild\\15.0\\Bin\\MSBuild.exe" xgboost.sln /m /p:Configuration=Release /nodeReuse:false
+    """
+    bat """
+    cd python-package
+    conda activate && python setup.py bdist_wheel --universal && for /R %%i in (dist\\*.whl) DO python ../tests/ci_build/rename_whl.py "%%i" ${commit_id} win_amd64
+    """
+    echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
+    bat """
+    cd python-package\\dist
+    COPY /B ..\\..\\tests\\ci_build\\insert_vcomp140.py
+    conda activate && python insert_vcomp140.py *.whl
+    """
+    echo 'Stashing Python wheel...'
+    stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
+    path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+    s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    echo 'Stashing C++ test executable (testxgboost)...'
+    stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
+    stash name: 'xgboost_cli', includes: 'xgboost.exe'
+    deleteDir()
+  }
+}
+
+def TestWin64CPU() {
+  node('win64 && cpu') {
+    unstash name: 'srcs'
+    unstash name: 'xgboost_whl'
+    unstash name: 'xgboost_cli'
+    echo "Test Win64 CPU"
+    echo "Installing Python wheel..."
+    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
+    bat """
+    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
+    """
+    echo "Installing Python dependencies..."
+    bat """
+     conda activate && conda upgrade scikit-learn pandas numpy
+    """
+    echo "Running Python tests..."
+    bat "conda activate && python -m pytest -v -s --fulltrace tests\\python"
+    bat "conda activate && python -m pip uninstall -y xgboost"
+    deleteDir()
+  }
+}
+
+def TestWin64GPU(args) {
+  node("win64 && gpu && ${args.cuda_target}") {
+    unstash name: 'srcs'
+    unstash name: 'xgboost_whl'
+    unstash name: 'xgboost_cpp_tests'
+    echo "Test Win64 GPU (${args.cuda_target})"
+    bat "nvcc --version"
+    echo "Running C++ tests..."
+    bat "build\\testxgboost.exe"
+    echo "Installing Python wheel..."
+    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
+    bat """
+    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
+    """
+    echo "Installing Python dependencies..."
+    bat """
+     conda activate && conda upgrade scikit-learn pandas numpy && python -m pip uninstall -y cupy-cuda100 cupy-cuda101 cupy-cuda102
+    """
+    echo "Running Python tests..."
+    bat """
+    conda activate && python -m pytest -v -s --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
+    """
+    bat "conda activate && python -m pip uninstall -y xgboost"
+    deleteDir()
+  }
+}

Makefile

@@ -0,0 +1,147 @@
+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++11 -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
+
+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
+	rm xgboost/remove_warning_suppression_pragma.sh
+
+Rbuild: Rpack
+	R CMD build --no-build-vignettes xgboost
+	rm -rf xgboost
+
+Rcheck: Rbuild
+	R CMD check xgboost*.tar.gz
+
+-include build/*.d
+-include build/*/*.d

R-package/.Rbuildignore

@@ -4,5 +4,3 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
 README.md
-^doc$
-^Meta$

R-package/CMakeLists.txt

@@ -1,64 +1,38 @@
 find_package(LibR REQUIRED)
 message(STATUS "LIBR_CORE_LIBRARY " ${LIBR_CORE_LIBRARY})
 
-file(
-  GLOB_RECURSE R_SOURCES
+file(GLOB_RECURSE R_SOURCES
   ${CMAKE_CURRENT_LIST_DIR}/src/*.cc
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.c
-)
-
+  ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
 # Use object library to expose symbols
 add_library(xgboost-r OBJECT ${R_SOURCES})
 
-if(ENABLE_ALL_WARNINGS)
-  target_compile_options(xgboost-r PRIVATE -Wall -Wextra)
-endif()
-
-if(MSVC)
-  # https://github.com/microsoft/LightGBM/pull/6061
-  # MSVC doesn't work with anonymous types in structs. (R complex)
-  #
-  # syntax error: missing ';' before identifier 'private_data_c'
-  #
-  target_compile_definitions(xgboost-r PRIVATE -DR_LEGACY_RCOMPLEX)
-endif()
-
-target_compile_definitions(
-  xgboost-r PUBLIC
+set(R_DEFINITIONS
   -DXGBOOST_STRICT_R_MODE=1
+  -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
   -DDMLC_LOG_BEFORE_THROW=0
   -DDMLC_DISABLE_STDIN=1
   -DDMLC_LOG_CUSTOMIZE=1
-  -DRABIT_STRICT_CXX98_
-)
-
-target_include_directories(
-  xgboost-r PRIVATE
+  -DRABIT_CUSTOMIZE_MSG_
+  -DRABIT_STRICT_CXX98_)
+target_compile_definitions(xgboost-r
+  PRIVATE ${R_DEFINITIONS})
+target_include_directories(xgboost-r
+  PRIVATE
   ${LIBR_INCLUDE_DIRS}
   ${PROJECT_SOURCE_DIR}/include
   ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include
-)
-
-target_link_libraries(xgboost-r PUBLIC ${LIBR_CORE_LIBRARY})
-
-if(USE_OPENMP)
-  find_package(OpenMP REQUIRED)
-  target_link_libraries(xgboost-r PUBLIC OpenMP::OpenMP_CXX OpenMP::OpenMP_C)
-endif()
-
+  ${PROJECT_SOURCE_DIR}/rabit/include)
 set_target_properties(
   xgboost-r PROPERTIES
-  CXX_STANDARD 17
+  CXX_STANDARD 11
   CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON
-)
+  POSITION_INDEPENDENT_CODE ON)
 
-# Get compilation and link flags of xgboost-r and propagate to objxgboost
-target_link_libraries(objxgboost PUBLIC xgboost-r)
+set(XGBOOST_DEFINITIONS "${XGBOOST_DEFINITIONS};${R_DEFINITIONS}" PARENT_SCOPE)
+set(XGBOOST_OBJ_SOURCES $<TARGET_OBJECTS:xgboost-r> PARENT_SCOPE)
+set(LINKED_LIBRARIES_PRIVATE ${LINKED_LIBRARIES_PRIVATE} ${LIBR_CORE_LIBRARY} PARENT_SCOPE)
 
-# Add all objects of xgboost-r to objxgboost
-target_sources(objxgboost INTERFACE $<TARGET_OBJECTS:xgboost-r>)
-
-set(LIBR_HOME "${LIBR_HOME}" PARENT_SCOPE)
-set(LIBR_EXECUTABLE "${LIBR_EXECUTABLE}" PARENT_SCOPE)
+if (USE_OPENMP)
+  target_link_libraries(xgboost-r PRIVATE OpenMP::OpenMP_CXX)
+endif ()

R-package/DESCRIPTION

@@ -1,12 +1,12 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 2.1.0.0
-Date: 2023-08-19
+Version: 1.1.1.1
+Date: 2020-02-21
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut"),
+  person("Tong", "He", role = c("aut", "cre"),
          email = "hetong007@gmail.com"),
   person("Michael", "Benesty", role = c("aut"),
          email = "michael@benesty.fr"),
@@ -26,17 +26,14 @@ 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
-    model solver and tree learning algorithms. The package can automatically
-    do parallel computation on a single machine which could be more than 10
+    This package is its R interface. The package includes efficient linear 
+    model solver and tree learning algorithms. The package can automatically 
+    do parallel computation on a single machine which could be more than 10 
     times faster than existing gradient boosting packages. It supports
     various objective functions, including regression, classification and ranking.
     The package is made to be extensible, so that users are also allowed to define
@@ -54,18 +51,17 @@ Suggests:
     Ckmeans.1d.dp (>= 3.3.1),
     vcd (>= 1.3),
     testthat,
+    lintr,
     igraph (>= 1.0.1),
-    float,
-    titanic,
-    RhpcBLASctl
+    jsonlite,
+    float
 Depends:
-    R (>= 4.3.0)
+    R (>= 3.3.0)
 Imports:
     Matrix (>= 1.1-0),
     methods,
     data.table (>= 1.9.6),
-    jsonlite (>= 1.0)
-Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
-Encoding: UTF-8
-SystemRequirements: GNU make, C++17
+    magrittr (>= 1.5),
+    stringi (>= 0.5.2)
+RoxygenNote: 7.1.0
+SystemRequirements: GNU make, C++11

R-package/LICENSE

@@ -1,9 +1,9 @@
-Copyright (c) 2014-2023, Tianqi Chen and XBGoost Contributors
+Copyright (c) 2014 by Tianqi Chen and Contributors 
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at
-
+    
    http://www.apache.org/licenses/LICENSE-2.0
 
 Unless required by applicable law or agreed to in writing, software

R-package/NAMESPACE

@@ -1,61 +1,44 @@
 # Generated by roxygen2: do not edit by hand
 
-S3method("[",xgb.Booster)
 S3method("[",xgb.DMatrix)
 S3method("dimnames<-",xgb.DMatrix)
-S3method(coef,xgb.Booster)
 S3method(dim,xgb.DMatrix)
 S3method(dimnames,xgb.DMatrix)
-S3method(getinfo,xgb.Booster)
 S3method(getinfo,xgb.DMatrix)
-S3method(length,xgb.Booster)
 S3method(predict,xgb.Booster)
+S3method(predict,xgb.Booster.handle)
 S3method(print,xgb.Booster)
 S3method(print,xgb.DMatrix)
 S3method(print,xgb.cv.synchronous)
-S3method(setinfo,xgb.Booster)
 S3method(setinfo,xgb.DMatrix)
-S3method(variable.names,xgb.Booster)
+S3method(slice,xgb.DMatrix)
 export("xgb.attr<-")
 export("xgb.attributes<-")
 export("xgb.config<-")
 export("xgb.parameters<-")
+export(cb.cv.predict)
+export(cb.early.stop)
+export(cb.evaluation.log)
+export(cb.gblinear.history)
+export(cb.print.evaluation)
+export(cb.reset.parameters)
+export(cb.save.model)
 export(getinfo)
 export(setinfo)
-export(xgb.Callback)
+export(slice)
+export(xgb.Booster.complete)
 export(xgb.DMatrix)
-export(xgb.DMatrix.hasinfo)
 export(xgb.DMatrix.save)
-export(xgb.DataBatch)
-export(xgb.DataIter)
-export(xgb.ExternalDMatrix)
-export(xgb.QuantileDMatrix)
-export(xgb.QuantileDMatrix.from_iterator)
 export(xgb.attr)
 export(xgb.attributes)
-export(xgb.cb.cv.predict)
-export(xgb.cb.early.stop)
-export(xgb.cb.evaluation.log)
-export(xgb.cb.gblinear.history)
-export(xgb.cb.print.evaluation)
-export(xgb.cb.reset.parameters)
-export(xgb.cb.save.model)
 export(xgb.config)
-export(xgb.copy.Booster)
 export(xgb.create.features)
 export(xgb.cv)
 export(xgb.dump)
 export(xgb.gblinear.history)
-export(xgb.get.DMatrix.data)
-export(xgb.get.DMatrix.num.non.missing)
-export(xgb.get.DMatrix.qcut)
-export(xgb.get.config)
-export(xgb.get.num.boosted.rounds)
 export(xgb.ggplot.deepness)
 export(xgb.ggplot.importance)
-export(xgb.ggplot.shap.summary)
 export(xgb.importance)
-export(xgb.is.same.Booster)
 export(xgb.load)
 export(xgb.load.raw)
 export(xgb.model.dt.tree)
@@ -63,20 +46,21 @@ export(xgb.plot.deepness)
 export(xgb.plot.importance)
 export(xgb.plot.multi.trees)
 export(xgb.plot.shap)
-export(xgb.plot.shap.summary)
 export(xgb.plot.tree)
 export(xgb.save)
 export(xgb.save.raw)
-export(xgb.set.config)
-export(xgb.slice.Booster)
-export(xgb.slice.DMatrix)
+export(xgb.serialize)
 export(xgb.train)
+export(xgb.unserialize)
 export(xgboost)
 import(methods)
-importClassesFrom(Matrix,CsparseMatrix)
 importClassesFrom(Matrix,dgCMatrix)
-importClassesFrom(Matrix,dgRMatrix)
+importClassesFrom(Matrix,dgeMatrix)
+importFrom(Matrix,colSums)
 importFrom(Matrix,sparse.model.matrix)
+importFrom(Matrix,sparseMatrix)
+importFrom(Matrix,sparseVector)
+importFrom(Matrix,t)
 importFrom(data.table,":=")
 importFrom(data.table,as.data.table)
 importFrom(data.table,data.table)
@@ -92,14 +76,14 @@ importFrom(graphics,lines)
 importFrom(graphics,par)
 importFrom(graphics,points)
 importFrom(graphics,title)
-importFrom(jsonlite,fromJSON)
-importFrom(jsonlite,toJSON)
-importFrom(methods,new)
-importFrom(stats,coef)
+importFrom(magrittr,"%>%")
 importFrom(stats,median)
 importFrom(stats,predict)
-importFrom(stats,sd)
-importFrom(stats,variable.names)
+importFrom(stringi,stri_detect_regex)
+importFrom(stringi,stri_match_first_regex)
+importFrom(stringi,stri_replace_all_regex)
+importFrom(stringi,stri_replace_first_regex)
+importFrom(stringi,stri_split_regex)
 importFrom(utils,head)
 importFrom(utils,object.size)
 importFrom(utils,str)

R-package/R/utils.R

@@ -1,6 +1,6 @@
 #
-# This file is for the low level reusable utility functions
-# that are not supposed to be visible to a user.
+# This file is for the low level reuseable utility functions
+# that are not supposed to be visibe to a user.
 #
 
 #
@@ -20,17 +20,6 @@ NVL <- function(x, val) {
   stop("typeof(x) == ", typeof(x), " is not supported by NVL")
 }
 
-# List of classification and ranking objectives
-.CLASSIFICATION_OBJECTIVES <- function() {
-  return(c('binary:logistic', 'binary:logitraw', 'binary:hinge', 'multi:softmax',
-           'multi:softprob', 'rank:pairwise', 'rank:ndcg', 'rank:map'))
-}
-
-.RANKING_OBJECTIVES <- function() {
-  return(c('binary:logistic', 'binary:logitraw', 'binary:hinge', 'multi:softmax',
-           'multi:softprob'))
-}
-
 
 #
 # Low-level functions for boosting --------------------------------------------
@@ -43,11 +32,11 @@ check.booster.params <- function(params, ...) {
     stop("params must be a list")
 
   # in R interface, allow for '.' instead of '_' in parameter names
-  names(params) <- gsub(".", "_", names(params), fixed = TRUE)
+  names(params) <- gsub("\\.", "_", names(params))
 
   # merge parameters from the params and the dots-expansion
   dot_params <- list(...)
-  names(dot_params) <- gsub(".", "_", names(dot_params), fixed = TRUE)
+  names(dot_params) <- gsub("\\.", "_", names(dot_params))
   if (length(intersect(names(params),
                        names(dot_params))) > 0)
     stop("Same parameters in 'params' and in the call are not allowed. Please check your 'params' list.")
@@ -80,31 +69,23 @@ check.booster.params <- function(params, ...) {
 
   if (!is.null(params[['monotone_constraints']]) &&
       typeof(params[['monotone_constraints']]) != "character") {
-        vec2str <- paste(params[['monotone_constraints']], collapse = ',')
-        vec2str <- paste0('(', vec2str, ')')
-        params[['monotone_constraints']] <- vec2str
+        vec2str = paste(params[['monotone_constraints']], collapse = ',')
+        vec2str = paste0('(', vec2str, ')')
+        params[['monotone_constraints']] = vec2str
   }
 
   # interaction constraints parser (convert from list of column indices to string)
   if (!is.null(params[['interaction_constraints']]) &&
-      typeof(params[['interaction_constraints']]) != "character") {
+      typeof(params[['interaction_constraints']]) != "character"){
     # check input class
-    if (!identical(class(params[['interaction_constraints']]), 'list')) stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric', 'integer'))) {
+    if (!identical(class(params[['interaction_constraints']]),'list')) stop('interaction_constraints should be class list')
+    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric','integer'))) {
       stop('interaction_constraints should be a list of numeric/integer vectors')
     }
 
     # recast parameter as string
-    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse = ','), ']'))
-    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse = ','), ']')
-  }
-
-  # for evaluation metrics, should generate multiple entries per metric
-  if (NROW(params[['eval_metric']]) > 1) {
-    eval_metrics <- as.list(params[["eval_metric"]])
-    names(eval_metrics) <- rep("eval_metric", length(eval_metrics))
-    params_without_ev_metrics <- within(params, rm("eval_metric"))
-    params <- c(params_without_ev_metrics, eval_metrics)
+    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse=','), ']'))
+    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse=','), ']')
   }
   return(params)
 }
@@ -147,49 +128,26 @@ check.custom.eval <- function(env = parent.frame()) {
   if (!is.null(env$feval) &&
       is.null(env$maximize) && (
         !is.null(env$early_stopping_rounds) ||
-        has.callbacks(env$callbacks, "early_stop")))
+        has.callbacks(env$callbacks, 'cb.early.stop')))
     stop("Please set 'maximize' to indicate whether the evaluation metric needs to be maximized or not")
 }
 
 
 # Update a booster handle for an iteration with dtrain data
-xgb.iter.update <- function(bst, dtrain, iter, obj) {
+xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
+  if (!identical(class(booster_handle), "xgb.Booster.handle")) {
+    stop("booster_handle must be of xgb.Booster.handle class")
+  }
   if (!inherits(dtrain, "xgb.DMatrix")) {
     stop("dtrain must be of xgb.DMatrix class")
   }
-  handle <- xgb.get.handle(bst)
 
   if (is.null(obj)) {
-    .Call(XGBoosterUpdateOneIter_R, handle, as.integer(iter), dtrain)
+    .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
   } else {
-    pred <- predict(
-      bst,
-      dtrain,
-      outputmargin = TRUE,
-      training = TRUE,
-      reshape = TRUE
-    )
+    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE)
     gpair <- obj(pred, dtrain)
-    n_samples <- dim(dtrain)[1]
-    grad <- gpair$grad
-    hess <- gpair$hess
-
-    if ((is.matrix(grad) && dim(grad)[1] != n_samples) ||
-        (is.vector(grad) && length(grad) != n_samples) ||
-        (is.vector(grad) != is.vector(hess))) {
-      warning(paste(
-        "Since 2.1.0, the shape of the gradient and hessian is required to be ",
-        "(n_samples, n_targets) or (n_samples, n_classes). Will reshape assuming ",
-        "column-major order.",
-        sep = ""
-      ))
-      grad <- matrix(grad, nrow = n_samples)
-      hess <- matrix(hess, nrow = n_samples)
-    }
-
-    .Call(
-      XGBoosterTrainOneIter_R, handle, dtrain, iter, grad, hess
-    )
+    .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
   }
   return(TRUE)
 }
@@ -198,22 +156,23 @@ xgb.iter.update <- function(bst, dtrain, iter, obj) {
 # Evaluate one iteration.
 # Returns a named vector of evaluation metrics
 # with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(bst, evals, iter, feval) {
-  handle <- xgb.get.handle(bst)
+xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
+  if (!identical(class(booster_handle), "xgb.Booster.handle"))
+    stop("class of booster_handle must be xgb.Booster.handle")
 
-  if (length(evals) == 0)
+  if (length(watchlist) == 0)
     return(NULL)
 
-  evnames <- names(evals)
+  evnames <- names(watchlist)
   if (is.null(feval)) {
-    msg <- .Call(XGBoosterEvalOneIter_R, handle, as.integer(iter), evals, as.list(evnames))
-    mat <- matrix(strsplit(msg, '\\s+|:')[[1]][-1], nrow = 2)
-    res <- structure(as.numeric(mat[2, ]), names = mat[1, ])
+    msg <- .Call(XGBoosterEvalOneIter_R, booster_handle, as.integer(iter), watchlist, as.list(evnames))
+    msg <- stri_split_regex(msg, '(\\s+|:|\\s+)')[[1]][-1]
+    res <- as.numeric(msg[c(FALSE,TRUE)]) # even indices are the values
+    names(res) <- msg[c(TRUE,FALSE)]      # odds are the names
   } else {
-    res <- sapply(seq_along(evals), function(j) {
-      w <- evals[[j]]
-      ## predict using all trees
-      preds <- predict(bst, w, outputmargin = TRUE, iterationrange = "all")
+    res <- sapply(seq_along(watchlist), function(j) {
+      w <- watchlist[[j]]
+      preds <- predict(booster_handle, w) # predict using all trees
       eval_res <- feval(preds, w)
       out <- eval_res$value
       names(out) <- paste0(evnames[j], "-", eval_res$metric)
@@ -228,57 +187,40 @@ xgb.iter.eval <- function(bst, evals, iter, feval) {
 # Helper functions for cross validation ---------------------------------------
 #
 
-# Possibly convert the labels into factors, depending on the objective.
-# The labels are converted into factors only when the given objective refers to the classification
-# or ranking tasks.
-convert.labels <- function(labels, objective_name) {
-  if (objective_name %in% .CLASSIFICATION_OBJECTIVES()) {
-    return(as.factor(labels))
-  } else {
-    return(labels)
-  }
-}
-
 # Generates random (stratified if needed) CV folds
-generate.cv.folds <- function(nfold, nrows, stratified, label, group, params) {
-  if (NROW(group)) {
-    if (stratified) {
-      warning(
-        paste0(
-          "Stratified splitting is not supported when using 'group' attribute.",
-          " Will use unstratified splitting."
-        )
-      )
-    }
-    return(generate.group.folds(nfold, group))
-  }
-  objective <- params$objective
-  if (!is.character(objective)) {
-    warning("Will use unstratified splitting (custom objective used)")
-    stratified <- FALSE
-  }
-  # cannot stratify if label is NULL
-  if (stratified && is.null(label)) {
-    warning("Will use unstratified splitting (no 'labels' available)")
-    stratified <- FALSE
-  }
+generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
 
   # cannot do it for rank
-  if (is.character(objective) && strtrim(objective, 5) == 'rank:') {
-    stop("\n\tAutomatic generation of CV-folds is not implemented for ranking without 'group' field!\n",
+  if (exists('objective', where = params) &&
+      is.character(params$objective) &&
+      strtrim(params$objective, 5) == 'rank:') {
+    stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
          "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
   }
   # shuffle
   rnd_idx <- sample.int(nrows)
-  if (stratified && length(label) == length(rnd_idx)) {
+  if (stratified &&
+      length(label) == length(rnd_idx)) {
     y <- label[rnd_idx]
+    # WARNING: some heuristic logic is employed to identify classification setting!
     #  - For classification, need to convert y labels to factor before making the folds,
     #    and then do stratification by factor levels.
     #  - For regression, leave y numeric and do stratification by quantiles.
-    if (is.character(objective)) {
-      y <- convert.labels(y, objective)
+    if (exists('objective', where = params) &&
+        is.character(params$objective)) {
+      # If 'objective' provided in params, assume that y is a classification label
+      # unless objective is reg:squarederror
+      if (params$objective != 'reg:squarederror')
+        y <- factor(y)
+    } else {
+      # If no 'objective' given in params, it means that user either wants to
+      # use the default 'reg:squarederror' objective or has provided a custom
+      # obj function.  Here, assume classification setting when y has 5 or less
+      # unique values:
+      if (length(unique(y)) <= 5)
+        y <- factor(y)
     }
-    folds <- xgb.createFolds(y = y, k = nfold)
+    folds <- xgb.createFolds(y, nfold)
   } else {
     # make simple non-stratified folds
     kstep <- length(rnd_idx) %/% nfold
@@ -292,33 +234,11 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, group, params) {
   return(folds)
 }
 
-generate.group.folds <- function(nfold, group) {
-  ngroups <- length(group) - 1
-  if (ngroups < nfold) {
-    stop("DMatrix has fewer groups than folds.")
-  }
-  seq_groups <- seq_len(ngroups)
-  indices <- lapply(seq_groups, function(gr) seq(group[gr] + 1, group[gr + 1]))
-  assignments <- base::split(seq_groups, as.integer(seq_groups %% nfold))
-  assignments <- unname(assignments)
-
-  out <- vector("list", nfold)
-  randomized_groups <- sample(ngroups)
-  for (idx in seq_len(nfold)) {
-    groups_idx_test <- randomized_groups[assignments[[idx]]]
-    groups_test <- indices[groups_idx_test]
-    idx_test <- unlist(groups_test)
-    attributes(idx_test)$group_test <- lengths(groups_test)
-    attributes(idx_test)$group_train <- lengths(indices[-groups_idx_test])
-    out[[idx]] <- idx_test
-  }
-  return(out)
-}
-
 # Creates CV folds stratified by the values of y.
 # It was borrowed from caret::createFolds and simplified
 # by always returning an unnamed list of fold indices.
-xgb.createFolds <- function(y, k) {
+xgb.createFolds <- function(y, k = 10)
+{
   if (is.numeric(y)) {
     ## Group the numeric data based on their magnitudes
     ## and sample within those groups.
@@ -351,7 +271,7 @@ xgb.createFolds <- function(y, k) {
     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 produced here.
+      ## of samples in a class is less than k, nothing is producd 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))
@@ -387,100 +307,6 @@ xgb.createFolds <- function(y, k) {
 #' @name xgboost-deprecated
 NULL
 
-#' @title Model Serialization and Compatibility
-#' @description
-#'
-#' When it comes to serializing XGBoost models, it's possible to use R serializers such as
-#' \link{save} or \link{saveRDS} to serialize an XGBoost R model, but XGBoost also provides
-#' its own serializers with better compatibility guarantees, which allow loading
-#' said models in other language bindings of XGBoost.
-#'
-#' Note that an `xgb.Booster` object, outside of its core components, might also keep:\itemize{
-#' \item Additional model configuration (accessible through \link{xgb.config}),
-#' which includes model fitting parameters like `max_depth` and runtime parameters like `nthread`.
-#' These are not necessarily useful for prediction/importance/plotting.
-#' \item Additional R-specific attributes  - e.g. results of callbacks, such as evaluation logs,
-#' which are kept as a `data.table` object, accessible through `attributes(model)$evaluation_log`
-#' if present.
-#' }
-#'
-#' The first one (configurations) does not have the same compatibility guarantees as
-#' the model itself, including attributes that are set and accessed through \link{xgb.attributes} - that is, such configuration
-#' might be lost after loading the booster in a different XGBoost version, regardless of the
-#' serializer that was used. These are saved when using \link{saveRDS}, but will be discarded
-#' if loaded into an incompatible XGBoost version. They are not saved when using XGBoost's
-#' serializers from its public interface including \link{xgb.save} and \link{xgb.save.raw}.
-#'
-#' The second ones (R attributes) are not part of the standard XGBoost model structure, and thus are
-#' not saved when using XGBoost's own serializers. These attributes are only used for informational
-#' purposes, such as keeping track of evaluation metrics as the model was fit, or saving the R
-#' call that produced the model, but are otherwise not used for prediction / importance / plotting / etc.
-#' These R attributes are only preserved when using R's serializers.
-#'
-#' Note that XGBoost models in R starting from version `2.1.0` and onwards, and XGBoost models
-#' before version `2.1.0`; have a very different R object structure and are incompatible with
-#' each other. Hence, models that were saved with R serializers live `saveRDS` or `save` before
-#' version `2.1.0` will not work with latter `xgboost` versions and vice versa. Be aware that
-#' the structure of R model objects could in theory change again in the future, so XGBoost's serializers
-#' should be preferred for long-term storage.
-#'
-#' Furthermore, note that using the package `qs` for serialization will require version 0.26 or
-#' higher of said package, and will have the same compatibility restrictions as R serializers.
-#'
-#' @details
-#' Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-#' the JSON format by specifying the JSON extension. To read the model back, use
-#' \code{\link{xgb.load}}.
-#'
-#' Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-#' in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-#' re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-#' The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-#' as part of another R object.
-#'
-#' Use \link{saveRDS} if you require the R-specific attributes that a booster might have, such
-#' as evaluation logs, but note that future compatibility of such objects is outside XGBoost's
-#' control as it relies on R's serialization format (see e.g. the details section in
-#' \link{serialize} and \link{save} from base R).
-#'
-#' For more details and explanation about model persistence and archival, consult the page
-#' \url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' bst <- xgb.train(data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
-#'                  max_depth = 2, eta = 1, nthread = 2, nrounds = 2,
-#'                  objective = "binary:logistic")
-#'
-#' # Save as a stand-alone file; load it with xgb.load()
-#' fname <- file.path(tempdir(), "xgb_model.ubj")
-#' xgb.save(bst, fname)
-#' bst2 <- xgb.load(fname)
-#'
-#' # Save as a stand-alone file (JSON); load it with xgb.load()
-#' fname <- file.path(tempdir(), "xgb_model.json")
-#' xgb.save(bst, fname)
-#' bst2 <- xgb.load(fname)
-#'
-#' # Save as a raw byte vector; load it with xgb.load.raw()
-#' xgb_bytes <- xgb.save.raw(bst)
-#' bst2 <- xgb.load.raw(xgb_bytes)
-#'
-#' # Persist XGBoost model as part of another R object
-#' obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-#' # Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-#' # xgb.Booster directly. What's being persisted is the future-proof byte representation
-#' # as given by xgb.save.raw().
-#' fname <- file.path(tempdir(), "my_object.Rds")
-#' saveRDS(obj, fname)
-#' # Read back the R object
-#' obj2 <- readRDS(fname)
-#' # Re-construct xgb.Booster object from the bytes
-#' bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-#'
-#' @name a-compatibility-note-for-saveRDS-save
-NULL
-
 # Lookup table for the deprecated parameters bookkeeping
 depr_par_lut <- matrix(c(
   'print.every.n', 'print_every_n',
@@ -489,11 +315,10 @@ depr_par_lut <- matrix(c(
   'with.stats', 'with_stats',
   'numberOfClusters', 'n_clusters',
   'features.keep', 'features_keep',
-  'plot.height', 'plot_height',
-  'plot.width', 'plot_width',
+  'plot.height','plot_height',
+  'plot.width','plot_width',
   'n_first_tree', 'trees',
-  'dummy', 'DUMMY',
-  'watchlist', 'evals'
+  'dummy', 'DUMMY'
 ), ncol = 2, byrow = TRUE)
 colnames(depr_par_lut) <- c('old', 'new')
 
@@ -504,20 +329,20 @@ colnames(depr_par_lut) <- c('old', 'new')
 check.deprecation <- function(..., env = parent.frame()) {
   pars <- list(...)
   # exact and partial matches
-  all_match <- pmatch(names(pars), depr_par_lut[, 1])
+  all_match <- pmatch(names(pars), depr_par_lut[,1])
   # indices of matched pars' names
   idx_pars <- which(!is.na(all_match))
   if (length(idx_pars) == 0) return()
   # indices of matched LUT rows
   idx_lut <- all_match[idx_pars]
   # which of idx_lut were the exact matches?
-  ex_match <- depr_par_lut[idx_lut, 1] %in% names(pars)
+  ex_match <- depr_par_lut[idx_lut,1] %in% names(pars)
   for (i in seq_along(idx_pars)) {
     pars_par <- names(pars)[idx_pars[i]]
     old_par <- depr_par_lut[idx_lut[i], 1]
     new_par <- depr_par_lut[idx_lut[i], 2]
     if (!ex_match[i]) {
-      warning("'", pars_par, "' was partially matched to '", old_par, "'")
+      warning("'", pars_par, "' was partially matched to '", old_par,"'")
     }
     .Deprecated(new_par, old = old_par, package = 'xgboost')
     if (new_par != 'NULL') {

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

@@ -1,25 +1,24 @@
 #' Save xgb.DMatrix object to binary file
-#'
+#' 
 #' Save xgb.DMatrix object to binary file
-#'
+#' 
 #' @param dmatrix the \code{xgb.DMatrix} object
 #' @param fname the name of the file to write.
-#'
+#' 
 #' @examples
-#' \dontshow{RhpcBLASctl::omp_set_num_threads(1)}
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-#' fname <- file.path(tempdir(), "xgb.DMatrix.data")
-#' xgb.DMatrix.save(dtrain, fname)
-#' dtrain <- xgb.DMatrix(fname)
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
+#' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
+#' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
 xgb.DMatrix.save <- function(dmatrix, fname) {
   if (typeof(fname) != "character")
     stop("fname must be character")
   if (!inherits(dmatrix, "xgb.DMatrix"))
     stop("dmatrix must be xgb.DMatrix")
-
-  fname <- path.expand(fname)
+  
   .Call(XGDMatrixSaveBinary_R, dmatrix, fname[1], 0L)
   return(TRUE)
 }

R-package/R/xgb.config.R

@@ -1,45 +0,0 @@
-#' Global configuration consists of a collection of parameters that can be applied in the global
-#' scope. See \url{https://xgboost.readthedocs.io/en/stable/parameter.html} for the full list of
-#' parameters supported in the global configuration. Use \code{xgb.set.config} to update the
-#' values of one or more global-scope parameters. Use \code{xgb.get.config} to fetch the current
-#' values of all global-scope parameters (listed in
-#' \url{https://xgboost.readthedocs.io/en/stable/parameter.html}).
-#' @details
-#' Note that serialization-related functions might use a globally-configured number of threads,
-#' which is managed by the system's OpenMP (OMP) configuration instead. Typically, XGBoost methods
-#' accept an `nthreads` parameter, but some methods like `readRDS` might get executed before such
-#' parameter can be supplied.
-#'
-#' The number of OMP threads can in turn be configured for example through an environment variable
-#' `OMP_NUM_THREADS` (needs to be set before R is started), or through `RhpcBLASctl::omp_set_num_threads`.
-#' @rdname xgbConfig
-#' @title Set and get global configuration
-#' @name xgb.set.config, xgb.get.config
-#' @export xgb.set.config xgb.get.config
-#' @param ... List of parameters to be set, as keyword arguments
-#' @return
-#' \code{xgb.set.config} returns \code{TRUE} to signal success. \code{xgb.get.config} returns
-#' a list containing all global-scope parameters and their values.
-#'
-#' @examples
-#' # Set verbosity level to silent (0)
-#' xgb.set.config(verbosity = 0)
-#' # Now global verbosity level is 0
-#' config <- xgb.get.config()
-#' print(config$verbosity)
-#' # Set verbosity level to warning (1)
-#' xgb.set.config(verbosity = 1)
-#' # Now global verbosity level is 1
-#' config <- xgb.get.config()
-#' print(config$verbosity)
-xgb.set.config <- function(...) {
-  new_config <- list(...)
-  .Call(XGBSetGlobalConfig_R, jsonlite::toJSON(new_config, auto_unbox = TRUE))
-  return(TRUE)
-}
-
-#' @rdname xgbConfig
-xgb.get.config <- function() {
-  config <- .Call(XGBGetGlobalConfig_R)
-  return(jsonlite::fromJSON(config))
-}

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

@@ -1,90 +1,87 @@
 #' Create new features from a previously learned model
-#'
+#' 
 #' May improve the learning by adding new features to the training data based on the decision trees from a previously learned model.
-#'
+#' 
 #' @param model decision tree boosting model learned on the original data
 #' @param data original data (usually provided as a \code{dgCMatrix} matrix)
 #' @param ... currently not used
-#'
+#' 
 #' @return \code{dgCMatrix} matrix including both the original data and the new features.
 #'
-#' @details
+#' @details 
 #' This is the function inspired from the paragraph 3.1 of the paper:
-#'
+#' 
 #' \strong{Practical Lessons from Predicting Clicks on Ads at Facebook}
-#'
-#' \emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers,
+#' 
+#' \emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, 
 #' Joaquin Quinonero Candela)}
-#'
+#'  
 #' International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
-#'
-#' \url{https://research.facebook.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
-#'
+#' 
+#' \url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+#' 
 #' Extract explaining the method:
-#'
+#' 
 #' "We found that boosted decision trees are a powerful and very
 #' convenient way to implement non-linear and tuple transformations
 #' of the kind we just described. We treat each individual
 #' tree as a categorical feature that takes as value the
-#' index of the leaf an instance ends up falling in. We use
-#' 1-of-K coding of this type of features.
-#'
-#' For example, consider the boosted tree model in Figure 1 with 2 subtrees,
+#' index of the leaf an instance ends up falling in. We use 
+#' 1-of-K coding of this type of features. 
+#' 
+#' For example, consider the boosted tree model in Figure 1 with 2 subtrees, 
 #' where the first subtree has 3 leafs and the second 2 leafs. If an
 #' instance ends up in leaf 2 in the first subtree and leaf 1 in
 #' second subtree, the overall input to the linear classifier will
 #' be the binary vector \code{[0, 1, 0, 1, 0]}, where the first 3 entries
 #' correspond to the leaves of the first subtree and last 2 to
 #' those of the second subtree.
-#'
+#' 
 #' [...]
-#'
+#' 
 #' We can understand boosted decision tree
 #' based transformation as a supervised feature encoding that
 #' converts a real-valued vector into a compact binary-valued
 #' vector. A traversal from root node to a leaf node represents
 #' a rule on certain features."
-#'
+#' 
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
+#' dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 #'
-#' param <- list(max_depth=2, eta=1, objective='binary:logistic')
+#' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 #' nrounds = 4
 #'
 #' bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
-#'
+#' 
 #' # Model accuracy without new features
 #' accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
 #'                    length(agaricus.test$label)
-#'
+#' 
 #' # Convert previous features to one hot encoding
 #' new.features.train <- xgb.create.features(model = bst, agaricus.train$data)
 #' new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
-#'
+#' 
 #' # learning with new features
-#' new.dtrain <- xgb.DMatrix(
-#'   data = new.features.train, label = agaricus.train$label, nthread = 2
-#' )
-#' new.dtest <- xgb.DMatrix(
-#'   data = new.features.test, label = agaricus.test$label, nthread = 2
-#' )
+#' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
+#' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
+#' watchlist <- list(train = new.dtrain)
 #' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
-#'
+#' 
 #' # Model accuracy with new features
 #' accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /
 #'                   length(agaricus.test$label)
-#'
+#' 
 #' # Here the accuracy was already good and is now perfect.
 #' cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
 #'           accuracy.after, "!\n"))
-#'
+#' 
 #' @export
-xgb.create.features <- function(model, data, ...) {
+xgb.create.features <- function(model, data, ...){
   check.deprecation(...)
   pred_with_leaf <- predict(model, data, predleaf = TRUE)
   cols <- lapply(as.data.frame(pred_with_leaf), factor)
-  cbind(data, sparse.model.matrix(~ . -1, cols)) # nolint
+  cbind(data, sparse.model.matrix( ~ . -1, cols))
 }

R-package/R/xgb.cv.R

@@ -1,16 +1,13 @@
 #' Cross Validation
 #'
-#' The cross validation function of xgboost.
+#' The cross validation function of xgboost
 #'
-#' @param params the list of parameters. The complete list of parameters is
-#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @param params the list of parameters. Commonly used ones are:
 #' \itemize{
 #'   \item \code{objective} objective function, common ones are
 #'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss.
-#'     \item \code{binary:logistic} logistic regression for classification.
-#'     \item See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
+#'     \item \code{reg:squarederror} Regression with squared loss
+#'     \item \code{binary:logistic} logistic regression for classification
 #'   }
 #'   \item \code{eta} step size of each boosting step
 #'   \item \code{max_depth} maximum depth of the tree
@@ -19,19 +16,15 @@
 #'
 #'   See \code{\link{xgb.train}} for further details.
 #'   See also demo/ for walkthrough example in R.
-#'
-#' Note that, while `params` accepts a `seed` entry and will use such parameter for model training if
-#' supplied, this seed is not used for creation of train-test splits, which instead rely on R's own RNG
-#' system - thus, for reproducible results, one needs to call the `set.seed` function beforehand.
-#' @param data An `xgb.DMatrix` object, with corresponding fields like `label` or bounds as required
-#'        for model training by the objective.
-#'
-#'        Note that only the basic `xgb.DMatrix` class is supported - variants such as `xgb.QuantileDMatrix`
-#'        or `xgb.ExternalDMatrix` are not supported here.
+#' @param data takes an \code{xgb.DMatrix}, \code{matrix}, or \code{dgCMatrix} as the input.
 #' @param nrounds the max number of iterations
 #' @param nfold the original dataset is randomly partitioned into \code{nfold} equal size subsamples.
+#' @param label vector of response values. Should be provided only when data is an R-matrix.
+#' @param missing is only used when input is a dense matrix. By default is set to NA, which means
+#'        that NA values should be considered as 'missing' by the algorithm.
+#'        Sometimes, 0 or other extreme value might be used to represent missing values.
 #' @param prediction A logical value indicating whether to return the test fold predictions
-#'        from each CV model. This parameter engages the \code{\link{xgb.cb.cv.predict}} callback.
+#'        from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callback.
 #' @param showsd \code{boolean}, whether to show standard deviation of cross validation
 #' @param metrics, list of evaluation metrics to be used in cross validation,
 #'   when it is not specified, the evaluation metric is chosen according to objective function.
@@ -40,8 +33,6 @@
 #'   \item \code{error} binary classification error rate
 #'   \item \code{rmse} Rooted mean square error
 #'   \item \code{logloss} negative log-likelihood function
-#'   \item \code{mae} Mean absolute error
-#'   \item \code{mape} Mean absolute percentage error
 #'   \item \code{auc} Area under curve
 #'   \item \code{aucpr} Area under PR curve
 #'   \item \code{merror} Exact matching error, used to evaluate multi-class classification
@@ -51,44 +42,27 @@
 #' @param feval customized evaluation function. Returns
 #'        \code{list(metric='metric-name', value='metric-value')} with given
 #'        prediction and dtrain.
-#' @param stratified A \code{boolean} indicating whether sampling of folds should be stratified
-#'        by the values of outcome labels. For real-valued labels in regression objectives,
-#'        stratification will be done by discretizing the labels into up to 5 buckets beforehand.
-#'
-#'        If passing "auto", will be set to `TRUE` if the objective in `params` is a classification
-#'        objective (from XGBoost's built-in objectives, doesn't apply to custom ones), and to
-#'        `FALSE` otherwise.
-#'
-#'        This parameter is ignored when `data` has a `group` field - in such case, the splitting
-#'        will be based on whole groups (note that this might make the folds have different sizes).
-#'
-#'        Value `TRUE` here is \bold{not} supported for custom objectives.
+#' @param stratified a \code{boolean} indicating whether sampling of folds should be stratified
+#'        by the values of outcome labels.
 #' @param folds \code{list} provides a possibility to use a list of pre-defined CV folds
 #'        (each element must be a vector of test fold's indices). When folds are supplied,
 #'        the \code{nfold} and \code{stratified} parameters are ignored.
-#'
-#'        If `data` has a `group` field and the objective requires this field, each fold (list element)
-#'        must additionally have two attributes (retrievable through \link{attributes}) named `group_test`
-#'        and `group_train`, which should hold the `group` to assign through \link{setinfo.xgb.DMatrix} to
-#'        the resulting DMatrices.
 #' @param train_folds \code{list} list specifying which indicies to use for training. If \code{NULL}
 #'        (the default) all indices not specified in \code{folds} will be used for training.
-#'
-#'        This is not supported when `data` has `group` field.
 #' @param verbose \code{boolean}, print the statistics during the process
 #' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
 #'        Default is 1 which means all messages are printed. This parameter is passed to the
-#'        \code{\link{xgb.cb.print.evaluation}} callback.
+#'        \code{\link{cb.print.evaluation}} callback.
 #' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
 #'        If set to an integer \code{k}, training with a validation set will stop if the performance
 #'        doesn't improve for \code{k} rounds.
-#'        Setting this parameter engages the \code{\link{xgb.cb.early.stop}} callback.
+#'        Setting this parameter engages the \code{\link{cb.early.stop}} callback.
 #' @param maximize If \code{feval} and \code{early_stopping_rounds} are set,
 #'        then this parameter must be set as well.
 #'        When it is \code{TRUE}, it means the larger the evaluation score the better.
-#'        This parameter is passed to the \code{\link{xgb.cb.early.stop}} callback.
+#'        This parameter is passed to the \code{\link{cb.early.stop}} callback.
 #' @param callbacks a list of callback functions to perform various task during boosting.
-#'        See \code{\link{xgb.Callback}}. Some of the callbacks are automatically created depending on the
+#'        See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
 #'        parameters' values. User can provide either existing or their own callback methods in order
 #'        to customize the training process.
 #' @param ... other parameters to pass to \code{params}.
@@ -96,60 +70,57 @@
 #' @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.
 #'
-#' Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
+#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
 #'
 #' @return
 #' An object of class \code{xgb.cv.synchronous} with the following elements:
 #' \itemize{
 #'   \item \code{call} a function call.
 #'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not
-#'         capture parameters changed by the \code{\link{xgb.cb.reset.parameters}} callback.
+#'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
+#'   \item \code{callbacks} callback functions that were either automatically assigned or
+#'         explicitly passed.
 #'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
 #'         first column corresponding to iteration number and the rest corresponding to the
 #'         CV-based evaluation means and standard deviations for the training and test CV-sets.
-#'         It is created by the \code{\link{xgb.cb.evaluation.log}} callback.
+#'         It is created by the \code{\link{cb.evaluation.log}} callback.
 #'   \item \code{niter} number of boosting iterations.
 #'   \item \code{nfeatures} number of features in training data.
 #'   \item \code{folds} the list of CV folds' indices - either those passed through the \code{folds}
 #'         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,
+#'         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
+#'         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
 #' }
 #'
-#' Plus other potential elements that are the result of callbacks, such as a list `cv_predict` with
-#' a sub-element `pred` when passing `prediction = TRUE`, which is added by the \link{xgb.cb.cv.predict}
-#' callback (note that one can also pass it manually under `callbacks` with different settings,
-#' such as saving also the models created during cross validation); or a list `early_stop` which
-#' will contain elements such as `best_iteration` when using the early stopping callback (\link{xgb.cb.early.stop}).
-#'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-#'              max_depth = 3, eta = 1, objective = "binary:logistic")
+#'                   max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
 #' print(cv, verbose=TRUE)
 #'
 #' @export
-xgb.cv <- function(params = list(), data, nrounds, nfold,
-                   prediction = FALSE, showsd = TRUE, metrics = list(),
-                   obj = NULL, feval = NULL, stratified = "auto", folds = NULL, train_folds = NULL,
-                   verbose = TRUE, print_every_n = 1L,
+xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NA,
+                   prediction = FALSE, showsd = TRUE, metrics=list(),
+                   obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, train_folds = NULL,
+                   verbose = TRUE, print_every_n=1L,
                    early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...) {
 
   check.deprecation(...)
-  stopifnot(inherits(data, "xgb.DMatrix"))
-  if (inherits(data, "xgb.DMatrix") && .Call(XGCheckNullPtr_R, data)) {
-    stop("'data' is an invalid 'xgb.DMatrix' object. Must be constructed again.")
-  }
 
   params <- check.booster.params(params, ...)
   # TODO: should we deprecate the redundant 'metrics' parameter?
@@ -159,166 +130,121 @@ xgb.cv <- function(params = list(), data, nrounds, nfold,
   check.custom.obj()
   check.custom.eval()
 
-  if (stratified == "auto") {
-    if (is.character(params$objective)) {
-      stratified <- (
-        (params$objective %in% .CLASSIFICATION_OBJECTIVES())
-        && !(params$objective %in% .RANKING_OBJECTIVES())
-      )
-    } else {
-      stratified <- FALSE
-    }
-  }
+  #if (is.null(params[['eval_metric']]) && is.null(feval))
+  #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
 
-  # Check the labels and groups
-  cv_label <- getinfo(data, "label")
-  cv_group <- getinfo(data, "group")
-  if (!is.null(train_folds) && NROW(cv_group)) {
-    stop("'train_folds' is not supported for DMatrix object with 'group' field.")
+  # Check the labels
+  if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
+       (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
+    stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
+  } else if (inherits(data, 'xgb.DMatrix')) {
+    if (!is.null(label))
+      warning("xgb.cv: label will be ignored, since data is of type xgb.DMatrix")
+    cv_label = getinfo(data, 'label')
+  } else {
+    cv_label = label
   }
 
   # CV folds
-  if (!is.null(folds)) {
-    if (!is.list(folds) || length(folds) < 2)
+  if(!is.null(folds)) {
+    if(!is.list(folds) || length(folds) < 2)
       stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
     nfold <- length(folds)
   } else {
     if (nfold <= 1)
       stop("'nfold' must be > 1")
-    folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, cv_group, params)
+    folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, params)
   }
 
-  # Callbacks
-  tmp <- .process.callbacks(callbacks, is_cv = TRUE)
-  callbacks <- tmp$callbacks
-  cb_names <- tmp$cb_names
-  rm(tmp)
+  # Potential TODO: sequential CV
+  #if (strategy == 'sequential')
+  #  stop('Sequential CV strategy is not yet implemented')
 
-  # Early stopping callback
-  if (!is.null(early_stopping_rounds) && !("early_stop" %in% cb_names)) {
-    callbacks <- add.callback(
-      callbacks,
-      xgb.cb.early.stop(
-        early_stopping_rounds,
-        maximize = maximize,
-        verbose = verbose
-      ),
-      as_first_elt = TRUE
-    )
-  }
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
-  print_every_n <- max(as.integer(print_every_n), 1L)
-  if (verbose && !("print_evaluation" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.print.evaluation(print_every_n, showsd = showsd))
+  print_every_n <- max( as.integer(print_every_n), 1L)
+  if (!has.callbacks(callbacks, 'cb.print.evaluation') && verbose) {
+    callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n, showsd = showsd))
   }
   # evaluation log callback: always is on in CV
-  if (!("evaluation_log" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.evaluation.log())
+  evaluation_log <- list()
+  if (!has.callbacks(callbacks, 'cb.evaluation.log')) {
+    callbacks <- add.cb(callbacks, cb.evaluation.log())
+  }
+  # Early stopping callback
+  stop_condition <- FALSE
+  if (!is.null(early_stopping_rounds) &&
+      !has.callbacks(callbacks, 'cb.early.stop')) {
+    callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
+                                                 maximize = maximize, verbose = verbose))
   }
   # CV-predictions callback
-  if (prediction && !("cv_predict" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.cv.predict(save_models = FALSE))
+  if (prediction &&
+      !has.callbacks(callbacks, 'cb.cv.predict')) {
+    callbacks <- add.cb(callbacks, cb.cv.predict(save_models = FALSE))
   }
+  # Sort the callbacks into categories
+  cb <- categorize.callbacks(callbacks)
+
 
   # create the booster-folds
   # train_folds
-  dall <- data
+  dall <- xgb.get.DMatrix(data, label, missing)
   bst_folds <- lapply(seq_along(folds), function(k) {
-    dtest <- xgb.slice.DMatrix(dall, folds[[k]], allow_groups = TRUE)
+    dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow
-    if (is.null(train_folds))
-       dtrain <- xgb.slice.DMatrix(dall, unlist(folds[-k]), allow_groups = TRUE)
+    if(is.null(train_folds))
+       dtrain <- slice(dall, unlist(folds[-k]))
     else
-       dtrain <- xgb.slice.DMatrix(dall, train_folds[[k]], allow_groups = TRUE)
-    if (!is.null(attributes(folds[[k]])$group_test)) {
-      setinfo(dtest, "group", attributes(folds[[k]])$group_test)
-      setinfo(dtrain, "group", attributes(folds[[k]])$group_train)
-    }
-    bst <- xgb.Booster(
-      params = params,
-      cachelist = list(dtrain, dtest),
-      modelfile = NULL
-    )
-    bst <- bst$bst
-    list(dtrain = dtrain, bst = bst, evals = list(train = dtrain, test = dtest), index = folds[[k]])
+       dtrain <- slice(dall, train_folds[[k]])
+    handle <- xgb.Booster.handle(params, list(dtrain, dtest))
+    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test=dtest), index = folds[[k]])
   })
+  rm(dall)
+  # a "basket" to collect some results from callbacks
+  basket <- list()
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1) # nolint
+  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
+  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
 
   # those are fixed for CV (no training continuation)
   begin_iteration <- 1
   end_iteration <- nrounds
 
-  .execute.cb.before.training(
-    callbacks,
-    bst_folds,
-    dall,
-    NULL,
-    begin_iteration,
-    end_iteration
-  )
-
   # synchronous CV boosting: run CV folds' models within each iteration
   for (iteration in begin_iteration:end_iteration) {
 
-    .execute.cb.before.iter(
-      callbacks,
-      bst_folds,
-      dall,
-      NULL,
-      iteration
-    )
+    for (f in cb$pre_iter) f()
 
     msg <- lapply(bst_folds, function(fd) {
-      xgb.iter.update(
-        bst = fd$bst,
-        dtrain = fd$dtrain,
-        iter = iteration - 1,
-        obj = obj
-      )
-      xgb.iter.eval(
-        bst = fd$bst,
-        evals = fd$evals,
-        iter = iteration - 1,
-        feval = feval
-      )
+      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
+      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
     })
     msg <- simplify2array(msg)
+    bst_evaluation <- rowMeans(msg)
+    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
 
-    should_stop <- .execute.cb.after.iter(
-      callbacks,
-      bst_folds,
-      dall,
-      NULL,
-      iteration,
-      msg
-    )
+    for (f in cb$post_iter) f()
 
-    if (should_stop) break
+    if (stop_condition) break
   }
-  cb_outputs <- .execute.cb.after.training(
-    callbacks,
-    bst_folds,
-    dall,
-    NULL,
-    iteration,
-    msg
-  )
+  for (f in cb$finalize) f(finalize = TRUE)
 
   # the CV result
   ret <- list(
     call = match.call(),
     params = params,
-    niter = iteration,
-    nfeatures = ncol(dall),
+    callbacks = callbacks,
+    evaluation_log = evaluation_log,
+    niter = end_iteration,
+    nfeatures = ncol(data),
     folds = folds
   )
-  ret <- c(ret, cb_outputs)
+  ret <- c(ret, basket)
 
   class(ret) <- 'xgb.cv.synchronous'
-  return(invisible(ret))
+  invisible(ret)
 }
 
 
@@ -338,8 +264,8 @@ xgb.cv <- function(params = list(), data, nrounds, nfold,
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' cv <- xgb.cv(data = xgb.DMatrix(train$data, label = train$label), nfold = 5, max_depth = 2,
-#'              eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+#' cv <- xgb.cv(data = train$data, label = train$label, nfold = 5, max_depth = 2,
+#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' print(cv)
 #' print(cv, verbose=TRUE)
 #'
@@ -356,21 +282,28 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
     }
     if (!is.null(x$params)) {
       cat('params (as set within xgb.cv):\n')
-      cat('  ',
-          paste(names(x$params),
-                paste0('"', unlist(x$params), '"'),
-                sep = ' = ', collapse = ', '), '\n', sep = '')
+      cat( '  ',
+           paste(names(x$params),
+                 paste0('"', unlist(x$params), '"'),
+                 sep = ' = ', collapse = ', '), '\n', sep = '')
+    }
+    if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
+      cat('callbacks:\n')
+      lapply(callback.calls(x$callbacks), function(x) {
+        cat('  ')
+        print(x)
+      })
     }
 
-    for (n in c('niter', 'best_iteration')) {
-      if (is.null(x$early_stop[[n]]))
+    for (n in c('niter', 'best_iteration', 'best_ntreelimit')) {
+      if (is.null(x[[n]]))
         next
-      cat(n, ': ', x$early_stop[[n]], '\n', sep = '')
+      cat(n, ': ', x[[n]], '\n', sep = '')
     }
 
-    if (!is.null(x$cv_predict$pred)) {
+    if (!is.null(x$pred)) {
       cat('pred:\n')
-      str(x$cv_predict$pred)
+      str(x$pred)
     }
   }
 
@@ -378,9 +311,9 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
     cat('evaluation_log:\n')
   print(x$evaluation_log, row.names = FALSE, ...)
 
-  if (!is.null(x$early_stop$best_iteration)) {
+  if (!is.null(x$best_iteration)) {
     cat('Best iteration:\n')
-    print(x$evaluation_log[x$early_stop$best_iteration], row.names = FALSE, ...)
+    print(x$evaluation_log[x$best_iteration], row.names = FALSE, ...)
   }
   invisible(x)
 }

R-package/R/xgb.dump.R

@@ -1,22 +1,21 @@
 #' Dump an xgboost model in text format.
-#'
+#' 
 #' Dump an xgboost model in text format.
-#'
+#' 
 #' @param model the model object.
-#' @param fname the name of the text file where to save the model text dump.
+#' @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}
+#'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt} 
 #'        for example Format.
 #' @param with_stats whether to dump some additional statistics about the splits.
 #'        When this option is on, the model dump contains two additional values:
 #'        gain is the approximate loss function gain we get in each split;
 #'        cover is the sum of second order gradient in each node.
-#' @param dump_format either 'text', 'json', or 'dot' (graphviz) format could be specified.
-#'
-#' Format 'dot' for a single tree can be passed directly to packages that consume this format
-#' for graph visualization, such as function [DiagrammeR::grViz()]
+#' @param dump_format either 'text' or 'json' format could be specified.
 #' @param ... currently not used
 #'
 #' @return
@@ -24,30 +23,25 @@
 #' as a \code{character} vector. Otherwise it will return \code{TRUE}.
 #'
 #' @examples
-#' \dontshow{RhpcBLASctl::omp_set_num_threads(1)}
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
 #' dump_path = file.path(tempdir(), 'model.dump')
 #' xgb.dump(bst, dump_path, with_stats = TRUE)
-#'
+#' 
 #' # print the model without saving it to a file
 #' print(xgb.dump(bst, with_stats = TRUE))
-#'
+#' 
 #' # print in JSON format:
 #' cat(xgb.dump(bst, with_stats = TRUE, dump_format='json'))
-#'
-#' # plot first tree leveraging the 'dot' format
-#' if (requireNamespace('DiagrammeR', quietly = TRUE)) {
-#'   DiagrammeR::grViz(xgb.dump(bst, dump_format = "dot")[[1L]])
-#' }
+#' 
 #' @export
-xgb.dump <- function(model, fname = NULL, fmap = "", with_stats = FALSE,
-                     dump_format = c("text", "json", "dot"), ...) {
+xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
+                     dump_format = c("text", "json"), ...) {
   check.deprecation(...)
   dump_format <- match.arg(dump_format)
   if (!inherits(model, "xgb.Booster"))
@@ -56,30 +50,22 @@ xgb.dump <- function(model, fname = NULL, fmap = "", with_stats = FALSE,
     stop("fname: argument must be a character string (when provided)")
   if (!(is.null(fmap) || is.character(fmap)))
     stop("fmap: argument must be a character string (when provided)")
+  
+  model <- xgb.Booster.complete(model)
+  model_dump <- .Call(XGBoosterDumpModel_R, model$handle, NVL(fmap, "")[1], as.integer(with_stats),
+                      as.character(dump_format))
 
-  model_dump <- .Call(
-    XGBoosterDumpModel_R,
-    xgb.get.handle(model),
-    NVL(fmap, "")[1],
-    as.integer(with_stats),
-    as.character(dump_format)
-  )
-  if (dump_format == "dot") {
-    return(sapply(model_dump, function(x) gsub("^booster\\[\\d+\\]\\n", "\\1", x)))
-  }
-
-  if (is.null(fname))
-    model_dump <- gsub('\t', '', model_dump, fixed = TRUE)
-
+  if (is.null(fname)) 
+    model_dump <- stri_replace_all_regex(model_dump, '\t', '')
+  
   if (dump_format == "text")
-    model_dump <- unlist(strsplit(model_dump, '\n', fixed = TRUE))
-
+    model_dump <- unlist(stri_split_regex(model_dump, '\n'))
+  
   model_dump <- grep('^\\s*$', model_dump, invert = TRUE, value = TRUE)
-
+  
   if (is.null(fname)) {
     return(model_dump)
   } else {
-    fname <- path.expand(fname)
     writeLines(model_dump, fname[1])
     return(TRUE)
   }

R-package/R/xgb.ggplot.R

@@ -3,9 +3,9 @@
 
 #' @rdname xgb.plot.importance
 #' @export
-xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
-                                  rel_to_first = FALSE, n_clusters = seq_len(10), ...) {
-
+xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL, 
+                                  rel_to_first = FALSE, n_clusters = c(1:10), ...) {
+  
   importance_matrix <- xgb.plot.importance(importance_matrix, top_n = top_n, measure = measure,
                                            rel_to_first = rel_to_first, plot = FALSE, ...)
   if (!requireNamespace("ggplot2", quietly = TRUE)) {
@@ -14,21 +14,21 @@ xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measur
   if (!requireNamespace("Ckmeans.1d.dp", quietly = TRUE)) {
     stop("Ckmeans.1d.dp package is required", call. = FALSE)
   }
-
+  
   clusters <- suppressWarnings(
     Ckmeans.1d.dp::Ckmeans.1d.dp(importance_matrix$Importance, n_clusters)
   )
   importance_matrix[, Cluster := as.character(clusters$cluster)]
 
   plot <-
-    ggplot2::ggplot(importance_matrix,
+    ggplot2::ggplot(importance_matrix, 
                     ggplot2::aes(x = factor(Feature, levels = rev(Feature)), y = Importance, width = 0.5),
-                    environment = environment()) +
-    ggplot2::geom_bar(ggplot2::aes(fill = Cluster), stat = "identity", position = "identity") +
-    ggplot2::coord_flip() +
-    ggplot2::xlab("Features") +
-    ggplot2::ggtitle("Feature importance") +
-    ggplot2::theme(plot.title = ggplot2::element_text(lineheight = .9, face = "bold"),
+                    environment = environment()) + 
+    ggplot2::geom_bar(ggplot2::aes(fill = Cluster), stat = "identity", position = "identity") + 
+    ggplot2::coord_flip() + 
+    ggplot2::xlab("Features") + 
+    ggplot2::ggtitle("Feature importance") + 
+    ggplot2::theme(plot.title = ggplot2::element_text(lineheight = .9, face = "bold"), 
                    panel.grid.major.y = ggplot2::element_blank())
   return(plot)
 }
@@ -42,7 +42,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     stop("ggplot2 package is required for plotting the graph deepness.", call. = FALSE)
 
   which <- match.arg(which)
-
+  
   dt_depths <- xgb.plot.deepness(model = model, plot = FALSE)
   dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
   setkey(dt_summaries, 'Depth')
@@ -60,30 +60,30 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
         axis.ticks = ggplot2::element_blank(),
         axis.text.x = ggplot2::element_blank()
       )
-
-    p2 <-
+  
+    p2 <- 
       ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") +
+      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") + 
       ggplot2::xlab("Leaf depth") +
       ggplot2::ylab("Weighted cover")
-
+  
     multiplot(p1, p2, cols = 1)
     return(invisible(list(p1, p2)))
-
+    
   } else if (which == "max.depth") {
     p <-
       ggplot2::ggplot(dt_depths[, max(Depth), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
+                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Max tree leaf depth")
     return(p)
-
+    
   } else if (which == "med.depth") {
     p <-
       ggplot2::ggplot(dt_depths[, median(as.numeric(Depth)), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
+                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median tree leaf depth")
     return(p)
@@ -92,103 +92,24 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     p <-
       ggplot2::ggplot(dt_depths[, median(abs(Weight)), Tree]) +
       ggplot2::geom_point(ggplot2::aes(x = Tree, y = V1),
-                          alpha = 0.4, size = 3, stroke = 0) +
+                          alpha=0.4, size=3, stroke=0) + 
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median absolute leaf weight")
     return(p)
   }
 }
 
-#' @rdname xgb.plot.shap.summary
-#' @export
-xgb.ggplot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
-                                    trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 10000  # 10,000 samples per feature.
-  )
-  p_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
-  # Reverse factor levels so that the first level is at the top of the plot
-  p_data[, "feature" := factor(feature, rev(levels(feature)))]
-  p <- ggplot2::ggplot(p_data, ggplot2::aes(x = feature, y = p_data$shap_value, colour = p_data$feature_value)) +
-    ggplot2::geom_jitter(alpha = 0.5, width = 0.1) +
-    ggplot2::scale_colour_viridis_c(limits = c(-3, 3), option = "plasma", direction = -1) +
-    ggplot2::geom_abline(slope = 0, intercept = 0, colour = "darkgrey") +
-    ggplot2::coord_flip()
-
-  p
-}
-
-#' Combine feature values and SHAP values
-#'
-#' Internal function used to combine and melt feature values and SHAP contributions
-#' as required for ggplot functions related to SHAP.
-#'
-#' @param data_list The result of `xgb.shap.data()`.
-#' @param normalize Whether to standardize feature values to mean 0 and
-#'   standard deviation 1. This is useful for comparing multiple features on the same
-#'   plot. Default is \code{FALSE}.
-#'
-#' @return A `data.table` containing the observation ID, the feature name, the
-#'   feature value (normalized if specified), and the SHAP contribution value.
-#' @noRd
-#' @keywords internal
-prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-
-  data <- data.table::as.data.table(as.matrix(data))
-  if (normalize) {
-    data[, (names(data)) := lapply(.SD, normalize)]
-  }
-  data[, "id" := seq_len(nrow(data))]
-  data_m <- data.table::melt.data.table(data, id.vars = "id", variable.name = "feature", value.name = "feature_value")
-
-  shap_contrib <- data.table::as.data.table(as.matrix(shap_contrib))
-  shap_contrib[, "id" := seq_len(nrow(shap_contrib))]
-  shap_contrib_m <- data.table::melt.data.table(shap_contrib, id.vars = "id", variable.name = "feature", value.name = "shap_value")
-
-  p_data <- data.table::merge.data.table(data_m, shap_contrib_m, by = c("id", "feature"))
-
-  p_data
-}
-
-#' Scale feature values
-#'
-#' Internal function that scales feature values to mean 0 and standard deviation 1.
-#' Useful to compare multiple features on the same plot.
-#'
-#' @param x Numeric vector.
-#'
-#' @return Numeric vector with mean 0 and standard deviation 1.
-#' @noRd
-#' @keywords internal
-normalize <- function(x) {
-  loc <- mean(x, na.rm = TRUE)
-  scale <- stats::sd(x, na.rm = TRUE)
-
-  (x - loc) / scale
-}
-
 # Plot multiple ggplot graph aligned by rows and columns.
 # ... the plots
 # cols number of columns
 # internal utility function
-multiplot <- function(..., cols) {
+multiplot <- function(..., cols = 1) {
   plots <- list(...)
-  num_plots <- length(plots)
-
+  num_plots = length(plots)
+  
   layout <- matrix(seq(1, cols * ceiling(num_plots / cols)),
                    ncol = cols, nrow = ceiling(num_plots / cols))
-
+  
   if (num_plots == 1) {
     print(plots[[1]])
   } else {
@@ -197,7 +118,7 @@ multiplot <- function(..., cols) {
     for (i in 1:num_plots) {
       # Get the i,j matrix positions of the regions that contain this subplot
       matchidx <- as.data.table(which(layout == i, arr.ind = TRUE))
-
+      
       print(
         plots[[i]], vp = grid::viewport(
           layout.pos.row = matchidx$row,
@@ -210,5 +131,5 @@ multiplot <- function(..., cols) {
 
 globalVariables(c(
   "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight", "feature"
+  "element_blank", "element_text", "V1", "Weight"
 ))

R-package/R/xgb.importance.R

@@ -1,168 +1,136 @@
-#' Feature importance
-#'
-#' Creates a `data.table` of feature importances.
-#'
-#' @param feature_names Character vector used to overwrite the feature names
-#'        of the model. The default is `NULL` (use original feature names).
-#' @param model Object of class `xgb.Booster`.
-#' @param trees An integer vector of tree indices that should be included
-#'        into the importance calculation (only for the "gbtree" booster).
-#'        The default (`NULL`) parses all trees.
-#'        It could be useful, e.g., in multiclass classification to get feature importances
-#'        for each class separately. *Important*: the tree index in XGBoost models
-#'        is zero-based (e.g., use `trees = 0:4` for the first five trees).
-#' @param data Deprecated.
-#' @param label Deprecated.
-#' @param target Deprecated.
-#'
-#' @details
+#' Importance of features in a model.
+#' 
+#' Creates a \code{data.table} of feature importances in a model.
+#' 
+#' @param feature_names character vector of feature names. If the model already
+#'       contains feature names, those would be used when \code{feature_names=NULL} (default value).
+#'       Non-null \code{feature_names} could be provided to override those in the model.
+#' @param model object of class \code{xgb.Booster}.
+#' @param trees (only for the gbtree booster) an integer vector of tree indices that should be included
+#'          into the importance calculation. If set to \code{NULL}, all trees of the model are parsed.
+#'          It could be useful, e.g., in multiclass classification to get feature importances 
+#'          for each class separately. IMPORTANT: the tree index in xgboost models
+#'          is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
+#' @param data deprecated.
+#' @param label deprecated.
+#' @param target deprecated.
 #'
+#' @details 
+#' 
 #' This function works for both linear and tree models.
-#'
-#' For linear models, the importance is the absolute magnitude of linear coefficients.
-#' To obtain a meaningful ranking by importance for linear models, the features need to
-#' be on the same scale (which is also recommended when using L1 or L2 regularization).
-#'
-#' @return A `data.table` with the following columns:
-#'
-#' For a tree model:
-#' - `Features`: Names of the features used in the model.
-#' - `Gain`: Fractional contribution of each feature to the model based on
-#'    the total gain of this feature's splits. Higher percentage means higher importance.
-#' - `Cover`: Metric of the number of observation related to this feature.
-#' - `Frequency`: Percentage of times a feature has been used in trees.
-#'
-#' For a linear model:
-#' - `Features`: Names of the features used in the model.
-#' - `Weight`: Linear coefficient of this feature.
-#' - `Class`: Class label (only for multiclass models).
-#'
-#' If `feature_names` is not provided and `model` doesn't have `feature_names`,
-#' the index of the features will be used instead. Because the index is extracted from the model dump
+#' 
+#' For linear models, the importance is the absolute magnitude of linear coefficients. 
+#' For that reason, in order to obtain a meaningful ranking by importance for a linear model, 
+#' the features need to be on the same scale (which you also would want to do when using either 
+#' L1 or L2 regularization).
+#' 
+#' @return
+#' 
+#' For a tree model, a \code{data.table} with the following columns:
+#' \itemize{
+#'   \item \code{Features} names of the features used in the model;
+#'   \item \code{Gain} represents fractional contribution of each feature to the model based on
+#'        the total gain of this feature's splits. Higher percentage means a more important 
+#'        predictive feature.
+#'   \item \code{Cover} metric of the number of observation related to this feature;
+#'   \item \code{Frequency} percentage representing the relative number of times
+#'        a feature have been used in trees.
+#' }
+#' 
+#' A linear model's importance \code{data.table} has the following columns:
+#' \itemize{
+#'   \item \code{Features} names of the features used in the model;
+#'   \item \code{Weight} the linear coefficient of this feature;
+#'   \item \code{Class} (only for multiclass models) class label.
+#' }
+#' 
+#' If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names}, 
+#' index of the features will be used instead. Because the index is extracted from the model dump
 #' (based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
-#'
+#' 
 #' @examples
-#'
-#' # binomial classification using "gbtree":
-#' data(agaricus.train, package = "xgboost")
-#'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 2,
-#'   eta = 1,
-#'   nthread = 2,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
-#'
+#' 
+#' # binomial classification using gbtree:
+#' data(agaricus.train, package='xgboost')
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' xgb.importance(model = bst)
-#'
-#' # binomial classification using "gblinear":
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   booster = "gblinear",
-#'   eta = 0.3,
-#'   nthread = 1,
-#'   nrounds = 20,objective = "binary:logistic"
-#' )
-#'
+#' 
+#' # binomial classification using gblinear:
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear", 
+#'                eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
 #' xgb.importance(model = bst)
-#'
-#' # multiclass classification using "gbtree":
+#' 
+#' # multiclass classification using gbtree:
 #' nclass <- 3
 #' nrounds <- 10
-#' mbst <- xgboost(
-#'   data = as.matrix(iris[, -5]),
-#'   label = as.numeric(iris$Species) - 1,
-#'   max_depth = 3,
-#'   eta = 0.2,
-#'   nthread = 2,
-#'   nrounds = nrounds,
-#'   objective = "multi:softprob",
-#'   num_class = nclass
-#' )
-#'
+#' mbst <- xgboost(data = as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1,
+#'                max_depth = 3, eta = 0.2, nthread = 2, nrounds = nrounds,
+#'                objective = "multi:softprob", num_class = nclass)
 #' # all classes clumped together:
 #' xgb.importance(model = mbst)
-#'
 #' # inspect importances separately for each class:
-#' xgb.importance(
-#'   model = mbst, trees = seq(from = 0, by = nclass, length.out = nrounds)
-#' )
-#' xgb.importance(
-#'   model = mbst, trees = seq(from = 1, by = nclass, length.out = nrounds)
-#' )
-#' xgb.importance(
-#'   model = mbst, trees = seq(from = 2, by = nclass, length.out = nrounds)
-#' )
-#'
-#' # multiclass classification using "gblinear":
-#' mbst <- xgboost(
-#'   data = scale(as.matrix(iris[, -5])),
-#'   label = as.numeric(iris$Species) - 1,
-#'   booster = "gblinear",
-#'   eta = 0.2,
-#'   nthread = 1,
-#'   nrounds = 15,
-#'   objective = "multi:softprob",
-#'   num_class = nclass
-#' )
-#'
+#' xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
+#' xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
+#' xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
+#' 
+#' # multiclass classification using gblinear:
+#' mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
+#'                booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
+#'                objective = "multi:softprob", num_class = nclass)
 #' xgb.importance(model = mbst)
 #'
 #' @export
-xgb.importance <- function(model = NULL, feature_names = getinfo(model, "feature_name"), trees = NULL,
-                           data = NULL, label = NULL, target = NULL) {
-
+xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
+                           data = NULL, label = NULL, target = NULL){
+  
   if (!(is.null(data) && is.null(label) && is.null(target)))
     warning("xgb.importance: parameters 'data', 'label' and 'target' are deprecated")
-
+  
+  if (!inherits(model, "xgb.Booster"))
+    stop("model: must be an object of class xgb.Booster")
+  
+  if (is.null(feature_names) && !is.null(model$feature_names))
+    feature_names <- model$feature_names
+  
   if (!(is.null(feature_names) || is.character(feature_names)))
     stop("feature_names: Has to be a character vector")
 
-  handle <- xgb.get.handle(model)
-  if (xgb.booster_type(model) == "gblinear") {
-    args <- list(importance_type = "weight", feature_names = feature_names)
-    results <- .Call(
-      XGBoosterFeatureScore_R, handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
-    )
-    names(results) <- c("features", "shape", "weight")
-    if (length(results$shape) == 2) {
-        n_classes <- results$shape[2]
+  model_text_dump <- xgb.dump(model = model, with_stats = TRUE)
+  
+  # linear model
+  if(model_text_dump[2] == "bias:"){
+    weights <- which(model_text_dump == "weight:") %>%
+               {model_text_dump[(. + 1):length(model_text_dump)]} %>%
+               as.numeric
+    
+    num_class <- NVL(model$params$num_class, 1)
+    if(is.null(feature_names)) 
+      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 {
-        n_classes <- 0
+      data.table(Feature = rep(feature_names, each = num_class),
+                 Weight = weights,
+                 Class = seq_len(num_class) - 1)[order(Class, -abs(Weight))]
     }
-    importance <- if (n_classes == 0) {
-      data.table(Feature = results$features, Weight = results$weight)[order(-abs(Weight))]
-    } else {
-      data.table(
-        Feature = rep(results$features, each = n_classes), Weight = results$weight, Class = seq_len(n_classes) - 1
-      )[order(Class, -abs(Weight))]
-    }
-  } 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, 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)]
+  } else { 
+  # tree model
+    result <- xgb.model.dt.tree(feature_names = feature_names,
+                                text = model_text_dump,
+                                trees = trees)[
+      Feature != "Leaf", .(Gain = sum(Quality), 
+                           Cover = sum(Cover), 
+                           Frequency = .N), by = Feature][
+      ,`:=`(Gain = Gain / sum(Gain), 
+            Cover = Cover / sum(Cover),
+            Frequency = Frequency / sum(Frequency))][
+      order(Gain, decreasing = TRUE)]
   }
-  importance
+  result
 }
 
 # Avoid error messages during CRAN check.

R-package/R/xgb.load.R

@@ -5,8 +5,8 @@
 #' @param modelfile the name of the binary input file.
 #'
 #' @details
-#' The input file is expected to contain a model saved in an xgboost model format
-#' using either \code{\link{xgb.save}} or \code{\link{xgb.cb.save.model}} in R, or using some
+#' The input file is expected to contain a model saved in an xgboost-internal binary format
+#' using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
 #' appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 #' saved from there in xgboost format, could be loaded from R.
 #'
@@ -17,50 +17,31 @@
 #' An object of \code{xgb.Booster} class.
 #'
 #' @seealso
-#' \code{\link{xgb.save}}
+#' \code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}.
 #'
 #' @examples
-#' \dontshow{RhpcBLASctl::omp_set_num_threads(1)}
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#'
-#' ## Keep the number of threads to 1 for examples
-#' nthread <- 1
-#' data.table::setDTthreads(nthread)
-#'
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgb.train(
-#'   data = xgb.DMatrix(train$data, label = train$label),
-#'   max_depth = 2,
-#'   eta = 1,
-#'   nthread = nthread,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
-#'
-#' fname <- file.path(tempdir(), "xgb.ubj")
-#' xgb.save(bst, fname)
-#' bst <- xgb.load(fname)
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
+#' xgb.save(bst, 'xgb.model')
+#' bst <- xgb.load('xgb.model')
+#' if (file.exists('xgb.model')) file.remove('xgb.model')
+#' pred <- predict(bst, test$data)
 #' @export
 xgb.load <- function(modelfile) {
   if (is.null(modelfile))
     stop("xgb.load: modelfile cannot be NULL")
 
-  bst <- xgb.Booster(
-    params = list(),
-    cachelist = list(),
-    modelfile = modelfile
-  )
-  bst <- bst$bst
+  handle <- xgb.Booster.handle(modelfile = modelfile)
   # re-use modelfile if it is raw so we do not need to serialize
   if (typeof(modelfile) == "raw") {
-    warning(
-      paste(
-        "The support for loading raw booster with `xgb.load` will be ",
-        "discontinued in upcoming release. Use `xgb.load.raw` instead. "
-      )
-    )
+    bst <- xgb.handleToBooster(handle, modelfile)
+  } else {
+    bst <- xgb.handleToBooster(handle, NULL)
   }
+  bst <- xgb.Booster.complete(bst, saveraw = TRUE)
   return(bst)
 }

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

@@ -3,10 +3,12 @@
 #' User can generate raw memory buffer by calling xgb.save.raw
 #'
 #' @param buffer the buffer returned by xgb.save.raw
+#'
 #' @export
 xgb.load.raw <- function(buffer) {
   cachelist <- list()
-  bst <- .Call(XGBoosterCreate_R, cachelist)
-  .Call(XGBoosterLoadModelFromRaw_R, xgb.get.handle(bst), buffer)
-  return(bst)
+  handle <- .Call(XGBoosterCreate_R, cachelist)
+  .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
+  class(handle) <- "xgb.Booster.handle"
+  return (handle)
 }

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

@@ -1,202 +1,159 @@
-#' Parse model text dump
+#' Parse a boosted tree model text dump
+#' 
+#' Parse a boosted tree model text dump into a \code{data.table} structure.
+#' 
+#' @param feature_names character vector of feature names. If the model already
+#'          contains feature names, those would be used when \code{feature_names=NULL} (default value).
+#'          Non-null \code{feature_names} could be provided to override those in the model.
+#' @param model object of class \code{xgb.Booster}
+#' @param text \code{character} vector previously generated by the \code{xgb.dump} 
+#'          function  (where parameter \code{with_stats = TRUE} should have been set).
+#'          \code{text} takes precedence over \code{model}.
+#' @param trees an integer vector of tree indices that should be parsed.
+#'          If set to \code{NULL}, all trees of the model are parsed.
+#'          It could be useful, e.g., in multiclass classification to get only
+#'          the trees of one certain class. IMPORTANT: the tree index in xgboost models
+#'          is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
+#' @param use_int_id a logical flag indicating whether nodes in columns "Yes", "No", "Missing" should be
+#'          represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).
+#' @param ... currently not used.
 #'
-#' Parse a boosted tree model text dump into a `data.table` structure.
+#' @return 
+#' A \code{data.table} with detailed information about model trees' nodes.
 #'
-#' @param model Object of class `xgb.Booster`. If it contains feature names (they can be set through
-#'        \link{setinfo}), they will be used in the output from this function.
-#' @param text Character vector previously generated by the function [xgb.dump()]
-#'        (called with parameter `with_stats = TRUE`). `text` takes precedence over `model`.
-#' @param trees An integer vector of tree indices that should be used.
-#'        The default (`NULL`) uses all trees.
-#'        Useful, e.g., in multiclass classification to get only
-#'        the trees of one class. *Important*: the tree index in XGBoost models
-#'        is zero-based (e.g., use `trees = 0:4` for the first five trees).
-#' @param use_int_id A logical flag indicating whether nodes in columns "Yes", "No", and
-#'        "Missing" should be represented as integers (when `TRUE`) or as "Tree-Node"
-#'        character strings (when `FALSE`, default).
-#' @param ... Currently not used.
-#'
-#' @return
-#' A `data.table` with detailed information about tree nodes. It has the following columns:
-#' - `Tree`: integer ID of a tree in a model (zero-based index).
-#' - `Node`: integer ID of a node in a tree (zero-based index).
-#' - `ID`: character identifier of a node in a model (only when `use_int_id = FALSE`).
-#' - `Feature`: for a branch node, a feature ID or name (when available);
-#'              for a leaf node, it simply labels it as `"Leaf"`.
-#' - `Split`: location of the split for a branch node (split condition is always "less than").
-#' - `Yes`: ID of the next node when the split condition is met.
-#' - `No`: ID of the next node when the split condition is not met.
-#' - `Missing`: ID of the next node when the branch value is missing.
-#' - `Gain`: either the split gain (change in loss) or the leaf value.
-#' - `Cover`: metric related to the number of observations either seen by a split
-#'            or collected by a leaf during training.
-#'
-#' When `use_int_id = FALSE`, columns "Yes", "No", and "Missing" point to model-wide node identifiers
-#' in the "ID" column. When `use_int_id = TRUE`, those columns point to node identifiers from
+#' The columns of the \code{data.table} are:
+#' 
+#' \itemize{
+#'  \item \code{Tree}: integer ID of a tree in a model (zero-based index)
+#'  \item \code{Node}: integer ID of a node in a tree (zero-based index)
+#'  \item \code{ID}: character identifier of a node in a model (only when \code{use_int_id=FALSE})
+#'  \item \code{Feature}: for a branch node, it's a feature id or name (when available);
+#'              for a leaf note, it simply labels it as \code{'Leaf'}
+#'  \item \code{Split}: location of the split for a branch node (split condition is always "less than")
+#'  \item \code{Yes}: ID of the next node when the split condition is met
+#'  \item \code{No}: ID of the next node when the split condition is not met
+#'  \item \code{Missing}: ID of the next node when branch value is missing
+#'  \item \code{Quality}: either the split gain (change in loss) or the leaf value
+#'  \item \code{Cover}: metric related to the number of observation either seen by a split
+#'                      or collected by a leaf during training.
+#' } 
+#' 
+#' When \code{use_int_id=FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
+#' in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from 
 #' the corresponding trees in the "Node" column.
-#'
+#' 
 #' @examples
 #' # Basic use:
-#'
-#' data(agaricus.train, package = "xgboost")
-#' ## Keep the number of threads to 1 for examples
-#' nthread <- 1
-#' data.table::setDTthreads(nthread)
-#'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 2,
-#'   eta = 1,
-#'   nthread = nthread,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
-#'
-#' # This bst model already has feature_names stored with it, so those would be used when
+#' 
+#' data(agaricus.train, package='xgboost')
+#' 
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
+#' 
+#' (dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
+#' 
+#' # This bst model already has feature_names stored with it, so those would be used when 
 #' # feature_names is not set:
-#' dt <- xgb.model.dt.tree(bst)
-#'
+#' (dt <- xgb.model.dt.tree(model = bst))
+#' 
 #' # How to match feature names of splits that are following a current 'Yes' branch:
-#' merge(
-#'   dt,
-#'   dt[, .(ID, Y.Feature = Feature)], by.x = "Yes", by.y = "ID", all.x = TRUE
-#' )[
-#'   order(Tree, Node)
-#' ]
-#'
+#' 
+#' merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
+#'  
 #' @export
-xgb.model.dt.tree <- function(model = NULL, text = NULL,
-                              trees = NULL, use_int_id = FALSE, ...) {
+xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
+                              trees = NULL, use_int_id = FALSE, ...){
   check.deprecation(...)
-
+  
   if (!inherits(model, "xgb.Booster") && !is.character(text)) {
     stop("Either 'model' must be an object of class xgb.Booster\n",
          "  or 'text' must be a character vector with the result of xgb.dump\n",
          "  (or NULL if 'model' was provided).")
   }
-
+  
+  if (is.null(feature_names) && !is.null(model) && !is.null(model$feature_names))
+    feature_names <- model$feature_names
+  
+  if (!(is.null(feature_names) || is.character(feature_names))) {
+    stop("feature_names: must be a character vector")
+  }
+  
   if (!(is.null(trees) || is.numeric(trees))) {
     stop("trees: must be a vector of integers.")
   }
-
-  feature_names <- NULL
-  if (inherits(model, "xgb.Booster")) {
-    feature_names <- xgb.feature_names(model)
-  }
-
-  from_text <- TRUE
-  if (is.null(text)) {
+  
+  if (is.null(text)){
     text <- xgb.dump(model = model, with_stats = TRUE)
-    from_text <- FALSE
   }
-
-  if (length(text) < 2 || !any(grepl('leaf=(\\d+)', text))) {
+  
+  if (length(text) < 2 ||
+      sum(stri_detect_regex(text, 'yes=(\\d+),no=(\\d+)')) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
-
-  position <- which(grepl("booster", text, fixed = TRUE))
-
+  
+  position <- which(!is.na(stri_match_first_regex(text, "booster")))
+  
   add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
-
+  
   anynumber_regex <- "[-+]?[0-9]*\\.?[0-9]+([eE][-+]?[0-9]+)?"
-
+  
   td <- data.table(t = text)
   td[position, Tree := 1L]
   td[, Tree := cumsum(ifelse(is.na(Tree), 0L, Tree)) - 1L]
-
+  
   if (is.null(trees)) {
     trees <- 0:max(td$Tree)
   } else {
     trees <- trees[trees >= 0 & trees <= max(td$Tree)]
   }
   td <- td[Tree %in% trees & !grepl('^booster', t)]
-
-  td[, Node := as.integer(sub("^([0-9]+):.*", "\\1", t))]
+  
+  td[, Node := stri_match_first_regex(t, "(\\d+):")[,2] %>% as.integer ]
   if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := grepl("leaf", t, fixed = TRUE)]
+  td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
 
   # parse branch lines
-  branch_rx_nonames <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
-                              "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  branch_rx_w_names <- paste0("\\d+:\\[(.+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
-                              "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  text_has_feature_names <- FALSE
-  if (NROW(feature_names)) {
-    branch_rx <- branch_rx_w_names
-    text_has_feature_names <- TRUE
-  } else {
-    # Note: when passing a text dump, it might or might not have feature names,
-    # but that aspect is unknown from just the text attributes
-    branch_rx <- branch_rx_nonames
-    if (from_text) {
-      if (sum(grepl(branch_rx_w_names, text)) > sum(grepl(branch_rx_nonames, text))) {
-        branch_rx <- branch_rx_w_names
-        text_has_feature_names <- TRUE
-      }
-    }
-  }
-  branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Gain", "Cover")
-  td[
-    isLeaf == FALSE,
-    (branch_cols) := {
-      matches <- regmatches(t, regexec(branch_rx, t))
+  branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
+                      "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
+  branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
+  td[isLeaf == FALSE, 
+     (branch_cols) := {
       # 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 <- stri_match_first_regex(t, branch_rx)[, c(2,3,5,6,7,8,10), drop = FALSE]
       xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-      if (length(xtr) == 0) {
-        as.data.table(
-          list(Feature = "NA", Split = "NA", Yes = "NA", No = "NA", Missing = "NA", Gain = "NA", Cover = "NA")
-        )
-      } else {
-        as.data.table(xtr)
-      }
-    }
-  ]
-
+      lapply(seq_len(ncol(xtr)), function(i) xtr[,i])
+    }]
   # assign feature_names when available
-  is_stump <- function() {
-    return(length(td$Feature) == 1 && is.na(td$Feature))
+  if (!is.null(feature_names)) {
+    if (length(feature_names) <= max(as.numeric(td$Feature), na.rm = TRUE))
+      stop("feature_names has less elements than there are features used in the model")
+    td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1] ]
   }
-  if (!text_has_feature_names) {
-    if (!is.null(feature_names) && !is_stump()) {
-      if (length(feature_names) <= max(as.numeric(td$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]]
-    }
-  }
-
+  
   # parse leaf lines
   leaf_rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  leaf_cols <- c("Feature", "Gain", "Cover")
-  td[
-    isLeaf == TRUE,
-    (leaf_cols) := {
-      matches <- regmatches(t, regexec(leaf_rx, t))
-      xtr <- do.call(rbind, matches)[, c(2, 4)]
-      if (length(xtr) == 2) {
-        c("Leaf", as.data.table(xtr[1]), as.data.table(xtr[2]))
-      } else {
-        c("Leaf", as.data.table(xtr))
-      }
-    }
-  ]
-
+  leaf_cols <- c("Feature", "Quality", "Cover")
+  td[isLeaf == TRUE,
+     (leaf_cols) := {
+      xtr <- stri_match_first_regex(t, leaf_rx)[, c(2,4)]
+      c("Leaf", lapply(seq_len(ncol(xtr)), function(i) xtr[,i]))
+    }]
+  
   # convert some columns to numeric
-  numeric_cols <- c("Split", "Gain", "Cover")
+  numeric_cols <- c("Split", "Quality", "Cover")
   td[, (numeric_cols) := lapply(.SD, as.numeric), .SDcols = numeric_cols]
   if (use_int_id) {
     int_cols <- c("Yes", "No", "Missing")
     td[, (int_cols) := lapply(.SD, as.integer), .SDcols = int_cols]
   }
-
+  
   td[, t := NULL]
   td[, isLeaf := NULL]
-
+  
   td[order(Tree, Node)]
 }
 
 # Avoid error messages during CRAN check.
 # The reason is that these variables are never declared
 # They are mainly column names inferred by Data.table...
-globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf", ".SD", ".SDcols"))
+globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf",".SD", ".SDcols"))

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

@@ -1,80 +1,68 @@
-#' Plot model tree depth
-#'
-#' Visualizes distributions related to the depth of tree leaves.
-#' - `xgb.plot.deepness()` uses base R graphics, while
-#' - `xgb.ggplot.deepness()` uses "ggplot2".
-#'
-#' @param model Either an `xgb.Booster` model, or the "data.table" returned by [xgb.model.dt.tree()].
-#' @param which Which distribution to plot (see details).
-#' @param plot Should the plot be shown? Default is `TRUE`.
-#' @param ... Other parameters passed to [graphics::barplot()] or [graphics::plot()].
+#' Plot model trees deepness
 #'
+#' Visualizes distributions related to depth of tree leafs.
+#' \code{xgb.plot.deepness} uses base R graphics, while \code{xgb.ggplot.deepness} uses the ggplot backend.
+#' 
+#' @param model either an \code{xgb.Booster} model generated by the \code{xgb.train} function
+#'        or a data.table result of the \code{xgb.model.dt.tree} function.
+#' @param plot (base R barplot) whether a barplot should be produced. 
+#'        If FALSE, only a data.table is returned.
+#' @param which which distribution to plot (see details).
+#' @param ... other parameters passed to \code{barplot} or \code{plot}.
+#' 
 #' @details
-#'
-#' When `which = "2x1"`, two distributions with respect to the leaf depth
+#' 
+#' When \code{which="2x1"}, two distributions with respect to the leaf depth
 #' are plotted on top of each other:
-#' 1. The distribution of the number of leaves in a tree model at a certain depth.
-#' 2. The distribution of the average weighted number of observations ("cover")
-#'   ending up in leaves at a certain depth.
-#'
-#' Those could be helpful in determining sensible ranges of the `max_depth`
-#' and `min_child_weight` parameters.
-#'
-#' When `which = "max.depth"` or `which = "med.depth"`, plots of either maximum or
-#' median depth per tree with respect to the tree number are created.
-#'
-#' Finally, `which = "med.weight"` allows to see how
+#' \itemize{
+#'  \item the distribution of the number of leafs in a tree model at a certain depth;
+#'  \item the distribution of average weighted number of observations ("cover") 
+#'        ending up in leafs at certain depth.
+#' }
+#' Those could be helpful in determining sensible ranges of the \code{max_depth} 
+#' and \code{min_child_weight} parameters.
+#' 
+#' When \code{which="max.depth"} or \code{which="med.depth"}, plots of either maximum or median depth
+#' per tree with respect to tree number are created. And \code{which="med.weight"} allows to see how
 #' a tree's median absolute leaf weight changes through the iterations.
 #'
-#' These functions have been inspired by the blog post
-#' <https://github.com/aysent/random-forest-leaf-visualization>.
-#'
+#' This function was inspired by the blog post
+#' \url{https://github.com/aysent/random-forest-leaf-visualization}.
+#' 
 #' @return
-#' The return value of the two functions is as follows:
-#' - `xgb.plot.deepness()`: A "data.table" (invisibly).
-#'   Each row corresponds to a terminal leaf in the model. It contains its information
-#'   about depth, cover, and weight (used in calculating predictions).
-#'   If `plot = TRUE`, also a plot is shown.
-#' - `xgb.ggplot.deepness()`: When `which = "2x1"`, a list of two "ggplot" objects,
-#'   and a single "ggplot" object otherwise.
-#'
-#' @seealso [xgb.train()] and [xgb.model.dt.tree()].
+#' 
+#' Other than producing plots (when \code{plot=TRUE}), the \code{xgb.plot.deepness} function
+#' silently returns a processed data.table where each row corresponds to a terminal leaf in a tree model,
+#' and contains information about leaf's depth, cover, and weight (which is used in calculating predictions).
+#' 
+#' The \code{xgb.ggplot.deepness} silently returns either a list of two ggplot graphs when \code{which="2x1"}
+#' or a single ggplot graph for the other \code{which} options.
 #'
+#' @seealso 
+#' 
+#' \code{\link{xgb.train}}, \code{\link{xgb.model.dt.tree}}.
+#' 
 #' @examples
+#' 
+#' data(agaricus.train, package='xgboost')
 #'
-#' data(agaricus.train, package = "xgboost")
-#' ## Keep the number of threads to 2 for examples
-#' nthread <- 2
-#' data.table::setDTthreads(nthread)
-#'
-#' ## Change max_depth to a higher number to get a more significant result
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 6,
-#'   nthread = nthread,
-#'   nrounds = 50,
-#'   objective = "binary:logistic",
-#'   subsample = 0.5,
-#'   min_child_weight = 2
-#' )
+#' # Change max_depth to a higher number to get a more significant result
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 6,
+#'                eta = 0.1, nthread = 2, nrounds = 50, objective = "binary:logistic",
+#'                subsample = 0.5, min_child_weight = 2)
 #'
 #' xgb.plot.deepness(bst)
 #' xgb.ggplot.deepness(bst)
-#'
-#' xgb.plot.deepness(
-#'   bst, which = "max.depth", pch = 16, col = rgb(0, 0, 1, 0.3), cex = 2
-#' )
-#'
-#' xgb.plot.deepness(
-#'   bst, which = "med.weight", pch = 16, col = rgb(0, 0, 1, 0.3), cex = 2
-#' )
+#' 
+#' xgb.plot.deepness(bst, which='max.depth', pch=16, col=rgb(0,0,1,0.3), cex=2)
+#' 
+#' xgb.plot.deepness(bst, which='med.weight', pch=16, col=rgb(0,0,1,0.3), cex=2)
 #'
 #' @rdname xgb.plot.deepness
 #' @export
 xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.depth", "med.weight"),
                               plot = TRUE, ...) {
-
+  
   if (!(inherits(model, "xgb.Booster") || is.data.table(model)))
     stop("model: Has to be either an xgb.Booster model generaged by the xgb.train function\n",
          "or a data.table result of the xgb.importance function")
@@ -83,32 +71,32 @@ xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.d
     stop("igraph package is required for plotting the graph deepness.", call. = FALSE)
 
   which <- match.arg(which)
-
+  
   dt_tree <- model
   if (inherits(model, "xgb.Booster"))
     dt_tree <- xgb.model.dt.tree(model = model)
-
+  
   if (!all(c("Feature", "Tree", "ID", "Yes", "No", "Cover") %in% colnames(dt_tree)))
     stop("Model tree columns are not as expected!\n",
          "  Note that this function works only for tree models.")
-
-  dt_depths <- merge(get.leaf.depth(dt_tree), dt_tree[, .(ID, Cover, Weight = Gain)], by = "ID")
+  
+  dt_depths <- merge(get.leaf.depth(dt_tree), dt_tree[, .(ID, Cover, Weight = Quality)], by = "ID")
   setkeyv(dt_depths, c("Tree", "ID"))
   # count by depth levels, and also calculate average cover at a depth
   dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
   setkey(dt_summaries, "Depth")
-
+  
   if (plot) {
     if (which == "2x1") {
       op <- par(no.readonly = TRUE)
-      par(mfrow = c(2, 1),
-          oma = c(3, 1, 3, 1) + 0.1,
-          mar = c(1, 4, 1, 0) + 0.1)
+      par(mfrow = c(2,1),
+          oma = c(3,1,3,1) + 0.1,
+          mar = c(1,4,1,0) + 0.1)
 
       dt_summaries[, barplot(N, border = NA, ylab = 'Number of leafs', ...)]
 
       dt_summaries[, barplot(Cover, border = NA, ylab = "Weighted cover", names.arg = Depth, ...)]
-
+    
       title("Model complexity", xlab = "Leaf depth", outer = TRUE, line = 1)
       par(op)
     } else if (which == "max.depth") {
@@ -135,20 +123,20 @@ get.leaf.depth <- function(dt_tree) {
       dt_tree[Feature != "Leaf", .(ID, To = No, Tree)]
     ))
   # whether "To" is a leaf:
-  dt_edges <-
+  dt_edges <- 
     merge(dt_edges,
           dt_tree[Feature == "Leaf", .(ID, Leaf = TRUE)],
           all.x = TRUE, by.x = "To", by.y = "ID")
   dt_edges[is.na(Leaf), Leaf := FALSE]
 
   dt_edges[, {
-    graph <- igraph::graph_from_data_frame(.SD[, .(ID, To)])
+    graph <- igraph::graph_from_data_frame(.SD[,.(ID, To)])
     # min(ID) in a tree is a root node
     paths_tmp <- igraph::shortest_paths(graph, from = min(ID), to = To[Leaf == TRUE])
     # list of paths to each leaf in a tree
     paths <- lapply(paths_tmp$vpath, names)
     # combine into a resulting path lengths table for a tree
-    data.table(Depth = lengths(paths), ID = To[Leaf == TRUE])
+    data.table(Depth = sapply(paths, length), ID = To[Leaf == TRUE])
   }, by = Tree]
 }
 
@@ -157,6 +145,6 @@ get.leaf.depth <- function(dt_tree) {
 # They are mainly column names inferred by Data.table...
 globalVariables(
   c(
-    ".N", "N", "Depth", "Gain", "Cover", "Tree", "ID", "Yes", "No", "Feature", "Leaf", "Weight"
+    ".N", "N", "Depth", "Quality", "Cover", "Tree", "ID", "Yes", "No", "Feature", "Leaf", "Weight"
   )
 )

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

@@ -1,75 +1,59 @@
-#' Plot feature importance
+#' Plot feature importance as a bar graph
 #'
 #' Represents previously calculated feature importance as a bar graph.
-#' - `xgb.plot.importance()` uses base R graphics, while
-#' - `xgb.ggplot.importance()` uses "ggplot".
+#' \code{xgb.plot.importance} uses base R graphics, while \code{xgb.ggplot.importance} uses the ggplot backend.
 #'
-#' @param importance_matrix A `data.table` as returned by [xgb.importance()].
-#' @param top_n Maximal number of top features to include into the plot.
-#' @param measure The name of importance measure to plot.
-#'        When `NULL`, 'Gain' would be used for trees and 'Weight' would be used for gblinear.
-#' @param rel_to_first Whether importance values should be represented as relative to
-#'        the highest ranked feature, see Details.
-#' @param left_margin Adjust the left margin size to fit feature names.
-#'        When `NULL`, the existing `par("mar")` is used.
-#' @param cex Passed as `cex.names` parameter to [graphics::barplot()].
-#' @param plot Should the barplot be shown? Default is `TRUE`.
-#' @param n_clusters A numeric vector containing the min and the max range
+#' @param importance_matrix a \code{data.table} returned by \code{\link{xgb.importance}}.
+#' @param top_n maximal number of top features to include into the plot.
+#' @param measure the name of importance measure to plot.
+#'        When \code{NULL}, 'Gain' would be used for trees and 'Weight' would be used for gblinear.
+#' @param rel_to_first whether importance values should be represented as relative to the highest ranked feature.
+#'        See Details.
+#' @param left_margin (base R barplot) allows to adjust the left margin size to fit feature names.
+#'        When it is NULL, the existing \code{par('mar')} is used.
+#' @param cex (base R barplot) passed as \code{cex.names} parameter to \code{barplot}.
+#' @param plot (base R barplot) whether a barplot should be produced.
+#'        If FALSE, only a data.table is returned.
+#' @param n_clusters (ggplot only) a \code{numeric} vector containing the min and the max range
 #'        of the possible number of clusters of bars.
-#' @param ... Other parameters passed to [graphics::barplot()]
-#'        (except `horiz`, `border`, `cex.names`, `names.arg`, and `las`).
-#'        Only used in `xgb.plot.importance()`.
+#' @param ... other parameters passed to \code{barplot} (except horiz, border, cex.names, names.arg, and las).
 #'
 #' @details
 #' The graph represents each feature as a horizontal bar of length proportional to the importance of a feature.
-#' Features are sorted by decreasing importance.
-#' It works for both "gblinear" and "gbtree" models.
+#' Features are shown ranked in a decreasing importance order.
+#' It works for importances from both \code{gblinear} and \code{gbtree} models.
 #'
-#' When `rel_to_first = FALSE`, the values would be plotted as in `importance_matrix`.
-#' For a "gbtree" model, that would mean being normalized to the total of 1
+#' When \code{rel_to_first = FALSE}, the values would be plotted as they were in \code{importance_matrix}.
+#' For gbtree model, that would mean being normalized to the total of 1
 #' ("what is feature's importance contribution relative to the whole model?").
-#' For linear models, `rel_to_first = FALSE` would show actual values of the coefficients.
-#' Setting `rel_to_first = TRUE` allows to see the picture from the perspective of
+#' For linear models, \code{rel_to_first = FALSE} would show actual values of the coefficients.
+#' Setting \code{rel_to_first = TRUE} allows to see the picture from the perspective of
 #' "what is feature's importance contribution relative to the most important feature?"
 #'
-#' The "ggplot" backend performs 1-D clustering of the importance values,
-#' with bar colors corresponding to different clusters having similar importance values.
+#' The ggplot-backend method also performs 1-D clustering of the importance values,
+#' with bar colors corresponding to different clusters that have somewhat similar importance values.
 #'
 #' @return
-#' The return value depends on the function:
-#' - `xgb.plot.importance()`: Invisibly, a "data.table" with `n_top` features sorted
-#'   by importance. If `plot = TRUE`, the values are also plotted as barplot.
-#' - `xgb.ggplot.importance()`: A customizable "ggplot" object.
-#'   E.g., to change the title, set `+ ggtitle("A GRAPH NAME")`.
+#' The \code{xgb.plot.importance} function creates a \code{barplot} (when \code{plot=TRUE})
+#' and silently returns a processed data.table with \code{n_top} features sorted by importance.
 #'
-#' @seealso [graphics::barplot()]
+#' The \code{xgb.ggplot.importance} function returns a ggplot graph which could be customized afterwards.
+#' E.g., to change the title of the graph, add \code{+ ggtitle("A GRAPH NAME")} to the result.
+#'
+#' @seealso
+#' \code{\link[graphics]{barplot}}.
 #'
 #' @examples
 #' data(agaricus.train)
 #'
-#' ## Keep the number of threads to 2 for examples
-#' nthread <- 2
-#' data.table::setDTthreads(nthread)
-#'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 3,
-#'   eta = 1,
-#'   nthread = nthread,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
+#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #'
 #' importance_matrix <- xgb.importance(colnames(agaricus.train$data), model = bst)
-#' xgb.plot.importance(
-#'   importance_matrix, rel_to_first = TRUE, xlab = "Relative importance"
-#' )
 #'
-#' gg <- xgb.ggplot.importance(
-#'   importance_matrix, measure = "Frequency", rel_to_first = TRUE
-#' )
-#' gg
+#' xgb.plot.importance(importance_matrix, rel_to_first = TRUE, xlab = "Relative importance")
+#'
+#' (gg <- xgb.ggplot.importance(importance_matrix, measure = "Frequency", rel_to_first = TRUE))
 #' gg + ggplot2::ylab("Frequency")
 #'
 #' @rdname xgb.plot.importance
@@ -98,13 +82,7 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
   }
 
   # also aggregate, just in case when the values were not yet summed up by feature
-  importance_matrix <- importance_matrix[
-    , lapply(.SD, sum)
-    , .SDcols = setdiff(names(importance_matrix), "Feature")
-    , by = Feature
-  ][
-    , Importance := get(measure)
-  ]
+  importance_matrix <- importance_matrix[, Importance := sum(get(measure)), by = Feature]
 
   # make sure it's ordered
   importance_matrix <- importance_matrix[order(-abs(Importance))]
@@ -114,29 +92,28 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
     importance_matrix <- head(importance_matrix, top_n)
   }
   if (rel_to_first) {
-    importance_matrix[, Importance := Importance / max(abs(Importance))]
+    importance_matrix[, Importance := Importance/max(abs(Importance))]
   }
   if (is.null(cex)) {
-    cex <- 2.5 / log2(1 + nrow(importance_matrix))
+    cex <- 2.5/log2(1 + nrow(importance_matrix))
   }
 
   if (plot) {
-    original_mar <- par()$mar
-
-    # reset margins so this function doesn't have side effects
-    on.exit({
-        par(mar = original_mar)
-    })
-
-    mar <- original_mar
+    op <- par(no.readonly = TRUE)
+    mar <- op$mar
     if (!is.null(left_margin))
       mar[2] <- left_margin
     par(mar = mar)
 
     # reverse the order of rows to have the highest ranked at the top
-    importance_matrix[rev(seq_len(nrow(importance_matrix))),
+    importance_matrix[nrow(importance_matrix):1,
                       barplot(Importance, horiz = TRUE, border = NA, cex.names = cex,
                               names.arg = Feature, las = 1, ...)]
+    grid(NULL, NA)
+    # redraw over the grid
+    importance_matrix[nrow(importance_matrix):1,
+                      barplot(Importance, horiz = TRUE, border = NA, add = TRUE)]
+    par(op)
   }
 
   invisible(importance_matrix)

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

@@ -1,11 +1,15 @@
-#' Project all trees on one tree
+#' Project all trees on one tree and plot it
 #'
 #' Visualization of the ensemble of trees as a single collective unit.
 #'
-#' @inheritParams xgb.plot.tree
-#' @param features_keep Number of features to keep in each position of the multi trees,
-#'        by default 5.
-#'
+#' @param model produced by the \code{xgb.train} function.
+#' @param feature_names names of each feature as a \code{character} vector.
+#' @param features_keep number of features to keep in each position of the multi trees.
+#' @param plot_width width in pixels of the graph to produce
+#' @param plot_height height in pixels of the graph to produce
+#' @param render a logical flag for whether the graph should be rendered (see Value).
+#' @param ... currently not used
+#' 
 #' @details
 #'
 #' This function tries to capture the complexity of a gradient boosted tree model
@@ -20,139 +24,120 @@
 #' Moreover, the trees tend to reuse the same features.
 #'
 #' The function projects each tree onto one, and keeps for each position the
-#' `features_keep` first features (based on the Gain per feature measure).
+#' \code{features_keep} first features (based on the Gain per feature measure).
 #'
 #' This function is inspired by this blog post:
-#' <https://wellecks.wordpress.com/2015/02/21/peering-into-the-black-box-visualizing-lambdamart/>
+#' \url{https://wellecks.wordpress.com/2015/02/21/peering-into-the-black-box-visualizing-lambdamart/}
 #'
-#' @inherit xgb.plot.tree return
+#' @return
+#'
+#' When \code{render = TRUE}:
+#' returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
+#' Similar to ggplot objects, it needs to be printed to see it when not running from command line.
+#'
+#' When \code{render = FALSE}:
+#' silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
+#' This could be useful if one wants to modify some of the graph attributes
+#' before rendering the graph with \code{\link[DiagrammeR]{render_graph}}.
 #'
 #' @examples
 #'
-#' data(agaricus.train, package = "xgboost")
+#' data(agaricus.train, package='xgboost')
 #'
-#' ## Keep the number of threads to 2 for examples
-#' nthread <- 2
-#' data.table::setDTthreads(nthread)
-#'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 15,
-#'   eta = 1,
-#'   nthread = nthread,
-#'   nrounds = 30,
-#'   objective = "binary:logistic",
-#'   min_child_weight = 50,
-#'   verbose = 0
-#' )
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 15,
+#'                eta = 1, nthread = 2, nrounds = 30, objective = "binary:logistic",
+#'                min_child_weight = 50, verbose = 0)
 #'
 #' p <- xgb.plot.multi.trees(model = bst, features_keep = 3)
 #' print(p)
 #'
 #' \dontrun{
 #' # Below is an example of how to save this plot to a file.
-#' # Note that for export_graph() to work, the {DiagrammeRsvg} and {rsvg} packages
-#' # must also be installed.
-#'
+#' # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
 #' library(DiagrammeR)
-#'
-#' gr <- xgb.plot.multi.trees(model = bst, features_keep = 3, render = FALSE)
-#' export_graph(gr, "tree.pdf", width = 1500, height = 600)
+#' gr <- xgb.plot.multi.trees(model=bst, features_keep = 3, render=FALSE)
+#' export_graph(gr, 'tree.pdf', width=1500, height=600)
 #' }
 #'
 #' @export
-xgb.plot.multi.trees <- function(model, 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")
-  }
+xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5, plot_width = NULL, plot_height = NULL,
+                                 render = TRUE, ...){
   check.deprecation(...)
-  tree.matrix <- xgb.model.dt.tree(model = model)
+  tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
 
   # first number of the path represents the tree, then the following numbers are related to the path to follow
   # root init
-  root.nodes <- tree.matrix[Node == 0, ID]
+  root.nodes <- tree.matrix[stri_detect_regex(ID, "\\d+-0"), ID]
   tree.matrix[ID %in% root.nodes, abs.node.position := root.nodes]
 
   precedent.nodes <- root.nodes
 
-  while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
+  while(tree.matrix[,sum(is.na(abs.node.position))] > 0) {
     yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
     no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
-    yes.nodes.abs.pos <- paste0(yes.row.nodes[, abs.node.position], "_0")
-    no.nodes.abs.pos <- paste0(no.row.nodes[, abs.node.position], "_1")
-
+    yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
+    no.nodes.abs.pos <- no.row.nodes[, abs.node.position] %>% paste0("_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]
     precedent.nodes <- c(yes.nodes.abs.pos, no.nodes.abs.pos)
   }
-
+  
   tree.matrix[!is.na(Yes), Yes := paste0(abs.node.position, "_0")]
   tree.matrix[!is.na(No), No := paste0(abs.node.position, "_1")]
-
-  for (nm in c("abs.node.position", "Yes", "No"))
-    data.table::set(tree.matrix, j = nm, value = sub("^\\d+-", "", tree.matrix[[nm]]))
-
+  
+  remove.tree <- . %>% stri_replace_first_regex(pattern = "^\\d+-", replacement = "")
+  
+  tree.matrix[,`:=`(abs.node.position = remove.tree(abs.node.position),
+                    Yes = remove.tree(Yes),
+                    No = remove.tree(No))]
+  
   nodes.dt <- tree.matrix[
-        , .(Gain = sum(Gain))
+        , .(Quality = sum(Quality))
         , by = .(abs.node.position, Feature)
-      ][, .(Text = paste0(
-              paste0(
-                Feature[seq_len(min(length(Feature), features_keep))],
-                " (",
-                format(Gain[seq_len(min(length(Gain), features_keep))], digits = 5),
-                ")"
-              ),
-              collapse = "\n"
-            )
-          )
-        , by = abs.node.position
-      ]
-
-  edges.dt <- data.table::rbindlist(
-    l = list(
-      tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)],
-      tree.matrix[Feature != "Leaf", .(abs.node.position, No)]
-    )
-  )
-  data.table::setnames(edges.dt, c("From", "To"))
-  edges.dt <- edges.dt[, .N, .(From, To)]
-  edges.dt[, N := NULL]
-
+      ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
+                          " (",
+                          format(Quality[1:min(length(Quality), features_keep)], digits=5),
+                          ")") %>%
+                   paste0(collapse = "\n"))
+        , by = abs.node.position]
+  
+  edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
+    list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>%
+    rbindlist() %>%
+    setnames(c("From", "To")) %>%
+    .[, .N, .(From, To)] %>%
+    .[, N:=NULL]
+  
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
-    label = nodes.dt[, Text]
+    label = nodes.dt[,Text]
   )
-
+  
   edges <- DiagrammeR::create_edge_df(
-    from = match(edges.dt[, From], nodes.dt[, abs.node.position]),
-    to = match(edges.dt[, To], nodes.dt[, abs.node.position]),
+    from = match(edges.dt[,From], nodes.dt[,abs.node.position]),
+    to = match(edges.dt[,To], nodes.dt[,abs.node.position]),
     rel = "leading_to")
-
+  
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "node",
       attr  = c("color", "fillcolor", "style", "shape", "fontname"),
       value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       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

@@ -1,165 +1,104 @@
-#' SHAP dependence plots
+#' SHAP contribution dependency plots
 #'
-#' Visualizes SHAP values against feature values to gain an impression of feature effects.
+#' Visualizing the SHAP feature contribution to prediction dependencies on feature value.
 #'
-#' @param data The data to explain as a `matrix` or `dgCMatrix`.
-#' @param shap_contrib Matrix of SHAP contributions of `data`.
-#'        The default (`NULL`) computes it from `model` and `data`.
-#' @param features Vector of column indices or feature names to plot.
-#'        When `NULL` (default), the `top_n` most important features are selected
-#'        by [xgb.importance()].
-#' @param top_n How many of the most important features (<= 100) should be selected?
-#'        By default 1 for SHAP dependence and 10 for SHAP summary).
-#'        Only used when `features = NULL`.
-#' @param model An `xgb.Booster` model. Only required when `shap_contrib = NULL` or
-#'        `features = NULL`.
-#' @param trees Passed to [xgb.importance()] when `features = NULL`.
-#' @param target_class Only relevant for multiclass models. The default (`NULL`)
-#'        averages the SHAP values over all classes. Pass a (0-based) class index
-#'        to show only SHAP values of that class.
-#' @param approxcontrib Passed to `predict()` when `shap_contrib = NULL`.
-#' @param subsample Fraction of data points randomly picked for plotting.
-#'        The default (`NULL`) will use up to 100k data points.
-#' @param n_col Number of columns in a grid of plots.
-#' @param col Color of the scatterplot markers.
-#' @param pch Scatterplot marker.
-#' @param discrete_n_uniq Maximal number of unique feature values to consider the
-#'        feature as discrete.
-#' @param discrete_jitter Jitter amount added to the values of discrete features.
-#' @param ylab The y-axis label in 1D plots.
-#' @param plot_NA Should contributions of cases with missing values be plotted?
-#'        Default is `TRUE`.
-#' @param col_NA Color of marker for missing value contributions.
-#' @param pch_NA Marker type for `NA` values.
-#' @param pos_NA Relative position of the x-location where `NA` values are shown:
-#'        `min(x) + (max(x) - min(x)) * pos_NA`.
-#' @param plot_loess Should loess-smoothed curves be plotted? (Default is `TRUE`).
-#'        The smoothing is only done for features with more than 5 distinct values.
-#' @param col_loess Color of loess curves.
-#' @param span_loess The `span` parameter of [stats::loess()].
-#' @param which Whether to do univariate or bivariate plotting. Currently, only "1d" is implemented.
-#' @param plot Should the plot be drawn? (Default is `TRUE`).
-#'        If `FALSE`, only a list of matrices is returned.
-#' @param ... Other parameters passed to [graphics::plot()].
+#' @param data data as a \code{matrix} or \code{dgCMatrix}.
+#' @param shap_contrib a matrix of SHAP contributions that was computed earlier for the above
+#'          \code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.
+#' @param features a vector of either column indices or of feature names to plot. When it is NULL,
+#'          feature importance is calculated, and \code{top_n} high ranked features are taken.
+#' @param top_n when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.
+#' @param model an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
+#'          or \code{features} is missing.
+#' @param trees passed to \code{\link{xgb.importance}} when \code{features = NULL}.
+#' @param target_class is only relevant for multiclass models. When it is set to a 0-based class index,
+#'          only SHAP contributions for that specific class are used.
+#'          If it is not set, SHAP importances are averaged over all classes.
+#' @param approxcontrib passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.
+#' @param subsample a random fraction of data points to use for plotting. When it is NULL,
+#'          it is set so that up to 100K data points are used.
+#' @param n_col a number of columns in a grid of plots.
+#' @param col color of the scatterplot markers.
+#' @param pch scatterplot marker.
+#' @param discrete_n_uniq a maximal number of unique values in a feature to consider it as discrete.
+#' @param discrete_jitter an \code{amount} parameter of jitter added to discrete features' positions.
+#' @param ylab a y-axis label in 1D plots.
+#' @param plot_NA whether the contributions of cases with missing values should also be plotted.
+#' @param col_NA a color of marker for missing value contributions.
+#' @param pch_NA a marker type for NA values.
+#' @param pos_NA a relative position of the x-location where NA values are shown:
+#'          \code{min(x) + (max(x) - min(x)) * pos_NA}.
+#' @param plot_loess whether to plot loess-smoothed curves. The smoothing is only done for features with
+#'          more than 5 distinct values.
+#' @param col_loess a color to use for the loess curves.
+#' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
+#' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
+#' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
+#' @param ... other parameters passed to \code{plot}.
 #'
 #' @details
 #'
 #' These scatterplots represent how SHAP feature contributions depend of feature values.
-#' The similarity to partial dependence plots is that they also give an idea for how feature values
-#' affect predictions. However, in partial dependence plots, we see marginal dependencies
-#' of model prediction on feature value, while SHAP dependence plots display the estimated
-#' contributions of a feature to the prediction for each individual case.
+#' The similarity to partial dependency plots is that they also give an idea for how feature values
+#' affect predictions. However, in partial dependency plots, we usually see marginal dependencies
+#' of model prediction on feature value, while SHAP contribution dependency plots display the estimated
+#' contributions of a feature to model prediction for each individual case.
 #'
-#' When `plot_loess = TRUE`, feature values are rounded to three significant digits and
-#' weighted LOESS is computed and plotted, where the weights are the numbers of data points
+#' When \code{plot_loess = TRUE} is set, feature values are rounded to 3 significant digits and
+#' weighted LOESS is computed and plotted, where weights are the numbers of data points
 #' at each rounded value.
 #'
-#' Note: SHAP contributions are on the scale of the model margin.
-#' E.g., for a logistic binomial objective, the margin is on log-odds scale.
+#' Note: SHAP contributions are shown on the scale of model margin. E.g., for a logistic binomial objective,
+#' the margin is prediction before a sigmoidal transform into probability-like values.
 #' Also, since SHAP stands for "SHapley Additive exPlanation" (model prediction = sum of SHAP
 #' contributions for all features + bias), depending on the objective used, transforming SHAP
 #' contributions for a feature from the marginal to the prediction space is not necessarily
 #' a meaningful thing to do.
 #'
 #' @return
-#' In addition to producing plots (when `plot = TRUE`), it silently returns a list of two matrices:
-#' - `data`: Feature value matrix.
-#' - `shap_contrib`: Corresponding SHAP value matrix.
+#'
+#' In addition to producing plots (when \code{plot=TRUE}), it silently returns a list of two matrices:
+#' \itemize{
+#'  \item \code{data} the values of selected features;
+#'  \item \code{shap_contrib} the contributions of selected features.
+#' }
 #'
 #' @references
-#' 1. Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions",
-#'    NIPS Proceedings 2017, <https://arxiv.org/abs/1705.07874>
-#' 2. Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles",
-#'    <https://arxiv.org/abs/1706.06060>
+#'
+#' Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
+#'
+#' Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
 #'
 #' @examples
 #'
-#' data(agaricus.train, package = "xgboost")
-#' data(agaricus.test, package = "xgboost")
+#' data(agaricus.train, package='xgboost')
+#' data(agaricus.test, package='xgboost')
 #'
-#' ## Keep the number of threads to 1 for examples
-#' nthread <- 1
-#' data.table::setDTthreads(nthread)
-#' nrounds <- 20
-#'
-#' bst <- xgboost(
-#'   agaricus.train$data,
-#'   agaricus.train$label,
-#'   nrounds = nrounds,
-#'   eta = 0.1,
-#'   max_depth = 3,
-#'   subsample = 0.5,
-#'   objective = "binary:logistic",
-#'   nthread = nthread,
-#'   verbose = 0
-#' )
+#' bst <- xgboost(agaricus.train$data, agaricus.train$label, nrounds = 50,
+#'                eta = 0.1, max_depth = 3, subsample = .5,
+#'                method = "hist", objective = "binary:logistic", nthread = 2, verbose = 0)
 #'
 #' xgb.plot.shap(agaricus.test$data, model = bst, features = "odor=none")
-#'
 #' contr <- predict(bst, agaricus.test$data, predcontrib = TRUE)
 #' xgb.plot.shap(agaricus.test$data, contr, model = bst, top_n = 12, n_col = 3)
 #'
-#' # Summary plot
-#' xgb.ggplot.shap.summary(agaricus.test$data, contr, model = bst, top_n = 12)
-#'
-#' # Multiclass example - plots for each class separately:
+#' # multiclass example - plots for each class separately:
 #' nclass <- 3
+#' nrounds <- 20
 #' x <- as.matrix(iris[, -5])
 #' set.seed(123)
 #' is.na(x[sample(nrow(x) * 4, 30)]) <- TRUE # introduce some missing values
-#'
-#' mbst <- xgboost(
-#'   data = x,
-#'   label = as.numeric(iris$Species) - 1,
-#'   nrounds = nrounds,
-#'   max_depth = 2,
-#'   eta = 0.3,
-#'   subsample = 0.5,
-#'   nthread = nthread,
-#'   objective = "multi:softprob",
-#'   num_class = nclass,
-#'   verbose = 0
-#' )
-#' trees0 <- seq(from = 0, by = nclass, length.out = nrounds)
+#' mbst <- xgboost(data = x, label = as.numeric(iris$Species) - 1, nrounds = nrounds,
+#'                 max_depth = 2, eta = 0.3, subsample = .5, nthread = 2,
+#'                 objective = "multi:softprob", num_class = nclass, verbose = 0)
+#' trees0 <- seq(from=0, by=nclass, length.out=nrounds)
 #' col <- rgb(0, 0, 1, 0.5)
-#' xgb.plot.shap(
-#'   x,
-#'   model = mbst,
-#'   trees = trees0,
-#'   target_class = 0,
-#'   top_n = 4,
-#'   n_col = 2,
-#'   col = col,
-#'   pch = 16,
-#'   pch_NA = 17
-#' )
-#'
-#' xgb.plot.shap(
-#'   x,
-#'   model = mbst,
-#'   trees = trees0 + 1,
-#'   target_class = 1,
-#'   top_n = 4,
-#'   n_col = 2,
-#'   col = col,
-#'   pch = 16,
-#'   pch_NA = 17
-#' )
-#'
-#' xgb.plot.shap(
-#'   x,
-#'   model = mbst,
-#'   trees = trees0 + 2,
-#'   target_class = 2,
-#'   top_n = 4,
-#'   n_col = 2,
-#'   col = col,
-#'   pch = 16,
-#'   pch_NA = 17
-#' )
-#'
-#' # Summary plot
-#' xgb.ggplot.shap.summary(x, model = mbst, target_class = 0, top_n = 4)
+#' xgb.plot.shap(x, model = mbst, trees = trees0, target_class = 0, top_n = 4,
+#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
+#' xgb.plot.shap(x, model = mbst, trees = trees0 + 1, target_class = 1, top_n = 4,
+#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
+#' xgb.plot.shap(x, model = mbst, trees = trees0 + 2, target_class = 2, top_n = 4,
+#'               n_col = 2, col = col, pch = 16, pch_NA = 17)
 #'
 #' @rdname xgb.plot.shap
 #' @export
@@ -170,39 +109,75 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
                           plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6), pch_NA = '.', pos_NA = 1.07,
                           plot_loess = TRUE, col_loess = 2, span_loess = 0.5,
                           which = c("1d", "2d"), plot = TRUE, ...) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 100000
-  )
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-  features <- colnames(data)
+
+  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
+    stop("data: must be either matrix or dgCMatrix")
+
+  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
+
+  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
+
+  if (!is.null(shap_contrib) &&
+      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
+    stop("shap_contrib is not compatible with the provided data")
+
+  nsample <- if (is.null(subsample)) min(100000, nrow(data)) else as.integer(subsample * nrow(data))
+  idx <- sample(1:nrow(data), nsample)
+  data <- data[idx,]
+
+  if (is.null(shap_contrib)) {
+    shap_contrib <- predict(model, data, predcontrib = TRUE, approxcontrib = approxcontrib)
+  } else {
+    shap_contrib <- shap_contrib[idx,]
+  }
 
   which <- match.arg(which)
   if (which == "2d")
     stop("2D plots are not implemented yet")
 
+  if (is.null(features)) {
+    imp <- xgb.importance(model = model, trees = trees)
+    top_n <- as.integer(top_n[1])
+    if (top_n < 1 && top_n > 100)
+      stop("top_n: must be an integer within [1, 100]")
+    features <- imp$Feature[1:min(top_n, NROW(imp))]
+  }
+
+  if (is.character(features)) {
+    if (is.null(colnames(data)))
+      stop("Either provide `data` with column names or provide `features` as column indices")
+    features <- match(features, colnames(data))
+  }
+
   if (n_col > length(features)) n_col <- length(features)
+
+  if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
+    shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]]
+                    else Reduce("+", lapply(shap_contrib, abs))
+  }
+
+  shap_contrib <- shap_contrib[, features, drop = FALSE]
+  data <- data[, features, drop = FALSE]
+  cols <- colnames(data)
+  if (is.null(cols)) cols <- colnames(shap_contrib)
+  if (is.null(cols)) cols <- paste0('X', 1:ncol(data))
+  colnames(data) <- cols
+  colnames(shap_contrib) <- cols
+
   if (plot && which == "1d") {
     op <- par(mfrow = c(ceiling(length(features) / n_col), n_col),
-              oma = c(0, 0, 0, 0) + 0.2,
-              mar = c(3.5, 3.5, 0, 0) + 0.1,
+              oma = c(0,0,0,0) + 0.2,
+              mar = c(3.5,3.5,0,0) + 0.1,
               mgp = c(1.7, 0.6, 0))
-    for (f in features) {
+    for (f in cols) {
       ord <- order(data[, f])
       x <- data[, f][ord]
       y <- shap_contrib[, f][ord]
       x_lim <- range(x, na.rm = TRUE)
       y_lim <- range(y, na.rm = TRUE)
-      do_na <- plot_NA && anyNA(x)
+      do_na <- plot_NA && any(is.na(x))
       if (do_na) {
         x_range <- diff(x_lim)
         loc_na <- min(x, na.rm = TRUE) + x_range * pos_NA
@@ -216,8 +191,8 @@ 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-aggregate y
-        zz <- data.table(x = signif(x, 3), y)[, .(.N, y = mean(y)), x]
+        # compress x to 3 digits, and mean-aggredate 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)
         } else {
@@ -241,119 +216,3 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
   }
   invisible(list(data = data, shap_contrib = shap_contrib))
 }
-
-#' SHAP summary plot
-#'
-#' Visualizes SHAP contributions of different features.
-#'
-#' A point plot (each point representing one observation from `data`) is
-#' produced for each feature, with the points plotted on the SHAP value axis.
-#' Each point (observation) is coloured based on its feature value.
-#'
-#' The plot allows 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. Inspired by the summary plot of
-#' <https://github.com/shap/shap>.
-#'
-#' @inheritParams xgb.plot.shap
-#'
-#' @return A `ggplot2` object.
-#' @export
-#'
-#' @examples
-#' # See examples in xgb.plot.shap()
-#'
-#' @seealso [xgb.plot.shap()], [xgb.ggplot.shap.summary()],
-#'   and the Python library <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.
-  xgb.ggplot.shap.summary(data, shap_contrib, features, top_n, model, trees, target_class, approxcontrib, subsample)
-}
-
-#' Prepare data for SHAP plots
-#'
-#' Internal function used in [xgb.plot.shap()], [xgb.plot.shap.summary()], etc.
-#'
-#' @inheritParams xgb.plot.shap
-#' @param max_observations Maximum number of observations to consider.
-#' @keywords internal
-#' @noRd
-#'
-#' @return
-#' A list containing:
-#' - `data`: The matrix of feature values.
-#' - `shap_contrib`: The matrix with corresponding SHAP values.
-xgb.shap.data <- function(data, shap_contrib = NULL, features = NULL, top_n = 1, model = NULL,
-                          trees = NULL, target_class = NULL, approxcontrib = FALSE,
-                          subsample = NULL, max_observations = 100000) {
-  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
-    stop("data: must be either matrix or dgCMatrix")
-
-  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
-
-  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
-
-  if (!is.null(shap_contrib) &&
-      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
-    stop("shap_contrib is not compatible with the provided data")
-
-  if (is.character(features) && is.null(colnames(data)))
-    stop("either provide `data` with column names or provide `features` as column indices")
-
-  model_feature_names <- NULL
-  if (is.null(features) && !is.null(model)) {
-    model_feature_names <- xgb.feature_names(model)
-  }
-  if (is.null(model_feature_names) && xgb.num_feature(model) != ncol(data))
-    stop("if model has no feature_names, columns in `data` must match features in model")
-
-  if (!is.null(subsample)) {
-    idx <- sample(x = seq_len(nrow(data)), size = as.integer(subsample * nrow(data)), replace = FALSE)
-  } else {
-    idx <- seq_len(min(nrow(data), max_observations))
-  }
-  data <- data[idx, ]
-  if (is.null(colnames(data))) {
-    colnames(data) <- paste0("X", seq_len(ncol(data)))
-  }
-
-  if (!is.null(shap_contrib)) {
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-    shap_contrib <- shap_contrib[idx, ]
-    if (is.null(colnames(shap_contrib))) {
-      colnames(shap_contrib) <- paste0("X", seq_len(ncol(data)))
-    }
-  } else {
-    shap_contrib <- predict(model, newdata = data, predcontrib = TRUE, approxcontrib = approxcontrib)
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-  }
-
-  if (is.null(features)) {
-    if (!is.null(model_feature_names)) {
-      imp <- xgb.importance(model = model, trees = trees)
-    } else {
-      imp <- xgb.importance(model = model, trees = trees, feature_names = colnames(data))
-    }
-    top_n <- top_n[1]
-    if (top_n < 1 || top_n > 100) stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[seq_len(min(top_n, NROW(imp)))]
-  }
-  if (is.character(features)) {
-    features <- match(features, colnames(data))
-  }
-
-  shap_contrib <- shap_contrib[, features, drop = FALSE]
-  data <- data[, features, drop = FALSE]
-
-  list(
-    data = data,
-    shap_contrib = shap_contrib
-  )
-}

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

@@ -1,109 +1,74 @@
-#' Plot boosted trees
-#'
-#' Read a tree model text dump and plot the model.
-#'
-#' @param model Object of class `xgb.Booster`. If it contains feature names (they can be set through
-#'        \link{setinfo}), they will be used in the output from this function.
-#' @param trees An integer vector of tree indices that should be used.
-#'        The default (`NULL`) uses all trees.
-#'        Useful, e.g., in multiclass classification to get only
-#'        the trees of one class. *Important*: the tree index in XGBoost models
-#'        is zero-based (e.g., use `trees = 0:2` for the first three trees).
-#' @param plot_width,plot_height Width and height of the graph in pixels.
-#'        The values are passed to [DiagrammeR::render_graph()].
-#' @param render Should the graph be rendered or not? The default is `TRUE`.
+#' Plot a boosted tree model
+#' 
+#' Read a tree model text dump and plot the model. 
+#' 
+#' @param feature_names names of each feature as a \code{character} vector.
+#' @param model produced by the \code{xgb.train} function.
+#' @param trees an integer vector of tree indices that should be visualized.
+#'          If set to \code{NULL}, all trees of the model are included.
+#'          IMPORTANT: the tree index in xgboost model is zero-based
+#'          (e.g., use \code{trees = 0:2} for the first 3 trees in a model).
+#' @param plot_width  the width of the diagram in pixels.
+#' @param plot_height	the height of the diagram in pixels.
+#' @param render a logical flag for whether the graph should be rendered (see Value).
 #' @param show_node_id a logical flag for whether to show node id's in the graph.
-#' @param style Style to use for the plot. Options are:\itemize{
-#' \item `"xgboost"`: will use the plot style defined in the core XGBoost library,
-#' which is shared between different interfaces through the 'dot' format. This
-#' style was not available before version 2.1.0 in R. It always plots the trees
-#' vertically (from top to bottom).
-#' \item `"R"`: will use the style defined from XGBoost's R interface, which predates
-#' the introducition of the standardized style from the core library. It might plot
-#' the trees horizontally (from left to right).
-#' }
-#'
-#' Note that `style="xgboost"` is only supported when all of the following conditions are met:\itemize{
-#' \item Only a single tree is being plotted.
-#' \item Node IDs are not added to the graph.
-#' \item The graph is being returned as `htmlwidget` (`render=TRUE`).
-#' }
 #' @param ... currently not used.
 #'
-#' @details
-#'
-#' When using `style="xgboost"`, the content of each node is visualized as follows:
-#' - For non-terminal nodes, it will display the split condition (number or name if
-#'   available, and the condition that would decide to which node to go next).
-#' - Those nodes will be connected to their children by arrows that indicate whether the
-#'   branch corresponds to the condition being met or not being met.
-#' - Terminal (leaf) nodes contain the margin to add when ending there.
-#'
-#' When using `style="R"`, the content of each node is visualized like this:
-#' - *Feature name*.
-#' - *Cover:* The sum of second order gradients of training data.
-#'   For the squared loss, this simply corresponds to the number of instances in the node.
-#'   The deeper in the tree, the lower the value.
-#' - *Gain* (for split nodes): Information gain metric of a split
+#' @details 
+#' 
+#' The content of each node is organised that way:
+#' 
+#' \itemize{
+#'  \item Feature name.
+#'  \item \code{Cover}: The sum of second order gradient of training data classified to the leaf.
+#'        If it is square loss, this simply corresponds to the number of instances seen by a split
+#'        or collected by a leaf during training.
+#'        The deeper in the tree a node is, the lower this metric will be.
+#'  \item \code{Gain} (for split nodes): the information gain metric of a split
 #'        (corresponds to the importance of the node in the model).
-#' - *Value* (for leaves): Margin value that the leaf may contribute to the prediction.
-#'
-#' The tree root nodes also indicate the tree index (0-based).
-#'
+#'  \item \code{Value} (for leafs): the margin value that the leaf may contribute to prediction.
+#' } 
+#' The tree root nodes also indicate the Tree index (0-based).
+#' 
 #' The "Yes" branches are marked by the "< split_value" label.
-#' The branches also used for missing values are marked as bold
+#' The branches that also used for missing values are marked as bold
 #' (as in "carrying extra capacity").
-#'
-#' This function uses [GraphViz](https://www.graphviz.org/) as DiagrammeR backend.
-#'
+#' 
+#' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
+#'  
 #' @return
-#' The value depends on the `render` parameter:
-#' - If `render = TRUE` (default): Rendered graph object which is an htmlwidget of
-#'   class `grViz`. Similar to "ggplot" objects, it needs to be printed when not
-#'   running from the command line.
-#' - If `render = FALSE`: Graph object which is of DiagrammeR's class `dgr_graph`.
-#'   This could be useful if one wants to modify some of the graph attributes
-#'   before rendering the graph with [DiagrammeR::render_graph()].
+#' 
+#' When \code{render = TRUE}:
+#' returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
+#' Similar to ggplot objects, it needs to be printed to see it when not running from command line.
+#' 
+#' When \code{render = FALSE}:
+#' silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
+#' This could be useful if one wants to modify some of the graph attributes
+#' before rendering the graph with \code{\link[DiagrammeR]{render_graph}}.
 #'
 #' @examples
-#' data(agaricus.train, package = "xgboost")
-#'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
-#'   max_depth = 3,
-#'   eta = 1,
-#'   nthread = 2,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
-#'
-#' # plot the first tree, using the style from xgboost's core library
-#' # (this plot should look identical to the ones generated from other
-#' # interfaces like the python package for xgboost)
-#' xgb.plot.tree(model = bst, trees = 1, style = "xgboost")
-#'
+#' data(agaricus.train, package='xgboost')
+#' 
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
+#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' # plot all the trees
-#' xgb.plot.tree(model = bst, trees = NULL)
-#'
+#' xgb.plot.tree(model = bst)
 #' # plot only the first tree and display the node ID:
 #' xgb.plot.tree(model = bst, trees = 0, show_node_id = TRUE)
-#'
+#' 
 #' \dontrun{
-#' # Below is an example of how to save this plot to a file.
-#' # Note that for export_graph() to work, the {DiagrammeRsvg}
-#' # and {rsvg} packages must also be installed.
-#'
+#' # Below is an example of how to save this plot to a file. 
+#' # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
 #' library(DiagrammeR)
-#'
-#' gr <- xgb.plot.tree(model = bst, trees = 0:1, render = FALSE)
-#' export_graph(gr, "tree.pdf", width = 1500, height = 1900)
-#' export_graph(gr, "tree.png", width = 1500, height = 1900)
+#' gr <- xgb.plot.tree(model=bst, trees=0:1, render=FALSE)
+#' export_graph(gr, 'tree.pdf', width=1500, height=1900)
+#' export_graph(gr, 'tree.png', width=1500, height=1900)
 #' }
-#'
+#' 
 #' @export
-xgb.plot.tree <- function(model = NULL, trees = NULL, plot_width = NULL, plot_height = NULL,
-                          render = TRUE, show_node_id = FALSE, style = c("R", "xgboost"), ...) {
+xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot_width = NULL, plot_height = NULL,
+                          render = TRUE, show_node_id = FALSE, ...){
   check.deprecation(...)
   if (!inherits(model, "xgb.Booster")) {
     stop("model: Has to be an object of class xgb.Booster")
@@ -112,29 +77,18 @@ xgb.plot.tree <- function(model = NULL, trees = NULL, plot_width = NULL, plot_he
   if (!requireNamespace("DiagrammeR", quietly = TRUE)) {
     stop("DiagrammeR package is required for xgb.plot.tree", call. = FALSE)
   }
+  
+  dt <- xgb.model.dt.tree(feature_names = feature_names, model = model, trees = trees)
 
-  style <- as.character(head(style, 1L))
-  stopifnot(style %in% c("R", "xgboost"))
-  if (style == "xgboost") {
-    if (NROW(trees) != 1L || !render || show_node_id) {
-      stop("style='xgboost' is only supported for single, rendered tree, without node IDs.")
-    }
-
-    txt <- xgb.dump(model, dump_format = "dot")
-    return(DiagrammeR::grViz(txt[[trees + 1]], width = plot_width, height = plot_height))
-  }
-
-  dt <- xgb.model.dt.tree(model = model, trees = trees)
-
-  dt[, label := paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Gain)]
+  dt[, label:= paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
   if (show_node_id)
     dt[, label := paste0(ID, ": ", label)]
   dt[Node == 0, label := paste0("Tree ", Tree, "\n", label)]
-  dt[, shape := "rectangle"][Feature == "Leaf", shape := "oval"]
-  dt[, filledcolor := "Beige"][Feature == "Leaf", filledcolor := "Khaki"]
+  dt[, shape:= "rectangle"][Feature == "Leaf", shape:= "oval"]
+  dt[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"]
   # in order to draw the first tree on top:
   dt <- dt[order(-Tree)]
-
+  
   nodes <- DiagrammeR::create_node_df(
     n         = nrow(dt),
     ID        = dt$ID,
@@ -143,54 +97,42 @@ xgb.plot.tree <- function(model = NULL, trees = NULL, plot_width = NULL, plot_he
     shape     = dt$shape,
     data      = dt$Feature,
     fontcolor = "black")
-
-  if (nrow(dt[Feature != "Leaf"]) != 0) {
-    edges <- DiagrammeR::create_edge_df(
-      from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
-      to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-      label = c(
-        dt[Feature != "Leaf", paste("<", Split)],
-        rep("", nrow(dt[Feature != "Leaf"]))
-      ),
-      style = c(
-        dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
-        dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
-      ),
-      rel   = "leading_to")
-  } else {
-    edges <- NULL
-  }
+  
+  edges <- DiagrammeR::create_edge_df(
+    from  = match(dt[Feature != "Leaf", c(ID)] %>% rep(2), dt$ID),
+    to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
+    label = dt[Feature != "Leaf", paste("<", Split)] %>%
+            c(rep("", nrow(dt[Feature != "Leaf"]))),
+    style = dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")] %>%
+            c(dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]),
+    rel   = "leading_to")
 
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "node",
       attr  = c("color", "style", "fontname"),
       value = c("DimGray", "filled", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       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))
-
+  
   DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
 }
 
 # Avoid error messages during CRAN check.
 # The reason is that these variables are never declared
 # They are mainly column names inferred by Data.table...
-globalVariables(c("Feature", "ID", "Cover", "Gain", "Split", "Yes", "No", "Missing", ".", "shape", "filledcolor", "label"))
+globalVariables(c("Feature", "ID", "Cover", "Quality", "Split", "Yes", "No", "Missing", ".", "shape", "filledcolor", "label"))

R-package/R/xgb.save.R

@@ -1,61 +1,34 @@
 #' Save xgboost model to binary file
-#'
-#' Save xgboost model to a file in binary or JSON format.
-#'
-#' @param model Model object of \code{xgb.Booster} class.
-#' @param fname Name of the file to write.
-#'
-#' Note that the extension of this file name determined the serialization format to use:\itemize{
-#' \item Extension ".ubj" will use the universal binary JSON format (recommended).
-#' This format uses binary types for e.g. floating point numbers, thereby preventing any loss
-#' of precision when converting to a human-readable JSON text or similar.
-#' \item Extension ".json" will use plain JSON, which is a human-readable format.
-#' \item Extension ".deprecated" will use a \bold{deprecated} binary format. This format will
-#' not be able to save attributes introduced after v1 of XGBoost, such as the "best_iteration"
-#' attribute that boosters might keep, nor feature names or user-specifiec attributes.
-#' \item If the format is not specified by passing one of the file extensions above, will
-#' default to UBJ.
-#' }
-#'
-#' @details
-#' This methods allows to save a model in an xgboost-internal binary or text format which is universal
+#' 
+#' Save xgboost model to a file in binary format.
+#' 
+#' @param model model object of \code{xgb.Booster} class.
+#' @param fname name of the file to write.
+#' 
+#' @details 
+#' This methods allows to save a model in an xgboost-internal binary format which is universal 
 #' among the various xgboost interfaces. In R, the saved model file could be read-in later
-#' using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter
+#' using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter 
 #' of \code{\link{xgb.train}}.
-#'
-#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}}
-#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and
-#' corresponding R-methods would need to be used to load it. Moreover, persisting the model with
-#' \code{\link[base]{readRDS}} or \code{\link[base]{save}}) might cause compatibility problems in
-#' future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-#' how to persist models in a future-proof way, i.e. to make the model accessible in future
-#' releases of XGBoost.
-#'
-#' @seealso
-#' \code{\link{xgb.load}}
-#'
+#' 
+#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
+#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
+#' corresponding R-methods would need to be used to load it.
+#' 
+#' @seealso 
+#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}. 
+#' 
 #' @examples
-#' \dontshow{RhpcBLASctl::omp_set_num_threads(1)}
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#'
-#' ## Keep the number of threads to 1 for examples
-#' nthread <- 1
-#' data.table::setDTthreads(nthread)
-#'
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgb.train(
-#'   data = xgb.DMatrix(train$data, label = train$label),
-#'   max_depth = 2,
-#'   eta = 1,
-#'   nthread = nthread,
-#'   nrounds = 2,
-#'   objective = "binary:logistic"
-#' )
-#' fname <- file.path(tempdir(), "xgb.ubj")
-#' xgb.save(bst, fname)
-#' bst <- xgb.load(fname)
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
+#' xgb.save(bst, 'xgb.model')
+#' bst <- xgb.load('xgb.model')
+#' if (file.exists('xgb.model')) file.remove('xgb.model')
+#' pred <- predict(bst, test$data)
 #' @export
 xgb.save <- function(model, fname) {
   if (typeof(fname) != "character")
@@ -64,7 +37,7 @@ xgb.save <- function(model, fname) {
     stop("model must be xgb.Booster.",
          if (inherits(model, "xgb.DMatrix")) " Use xgb.DMatrix.save to save an xgb.DMatrix object." else "")
   }
-  fname <- path.expand(fname)
-  .Call(XGBoosterSaveModel_R, xgb.get.handle(model), enc2utf8(fname[1]))
+  model <- xgb.Booster.complete(model, saveraw = FALSE)
+  .Call(XGBoosterSaveModel_R, model$handle, fname[1])
   return(TRUE)
 }

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

@@ -4,33 +4,20 @@
 #' 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.
-#' }
 #'
 #' @examples
-#' \dontshow{RhpcBLASctl::omp_set_num_threads(1)}
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#'
-#' ## Keep the number of threads to 2 for examples
-#' nthread <- 2
-#' data.table::setDTthreads(nthread)
-#'
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgb.train(data = xgb.DMatrix(train$data, label = train$label), max_depth = 2,
-#'                  eta = 1, nthread = nthread, nrounds = 2,objective = "binary:logistic")
-#'
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+#'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' raw <- xgb.save.raw(bst)
 #' bst <- xgb.load.raw(raw)
+#' pred <- predict(bst, test$data)
 #'
 #' @export
-xgb.save.raw <- function(model, raw_format = "ubj") {
+xgb.save.raw <- function(model) {
   handle <- xgb.get.handle(model)
-  args <- list(format = raw_format)
-  .Call(XGBoosterSaveModelToRaw_R, handle, jsonlite::toJSON(args, auto_unbox = TRUE))
+  .Call(XGBoosterModelToRaw_R, handle)
 }

R-package/R/xgb.serialize.R

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

R-package/R/xgb.train.R

@@ -3,9 +3,9 @@
 #' \code{xgb.train} is an advanced interface for training an xgboost model.
 #' The \code{xgboost} function is a simpler wrapper for \code{xgb.train}.
 #'
-#' @param params the list of parameters. The complete list of parameters is
-#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
-#'   is a shorter summary:
+#' @param params the list of parameters.
+#'        The complete list of parameters is available at \url{http://xgboost.readthedocs.io/en/latest/parameter.html}.
+#'        Below is a shorter summary:
 #'
 #' 1. General Parameters
 #'
@@ -15,43 +15,21 @@
 #'
 #' 2. Booster Parameters
 #'
-#' 2.1. Parameters for Tree Booster
+#' 2.1. Parameter for Tree Booster
 #'
 #' \itemize{
-#'   \item{ \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1}
-#'          when it is added to the current approximation.
-#'          Used to prevent overfitting by making the boosting process more conservative.
-#'          Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model
-#'          more robust to overfitting but slower to compute. Default: 0.3}
-#'   \item{ \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree.
-#'          the larger, the more conservative the algorithm will be.}
+#'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
+#'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
 #'   \item \code{max_depth} maximum depth of a tree. Default: 6
-#'   \item{\code{min_child_weight} minimum sum of instance weight (hessian) needed in a child.
-#'         If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight,
-#'         then the building process will give up further partitioning.
-#'         In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node.
-#'         The larger, the more conservative the algorithm will be. Default: 1}
-#'   \item{ \code{subsample} subsample ratio of the training instance.
-#'         Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees
-#'         and this will prevent overfitting. It makes computation shorter (because less data to analyse).
-#'         It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1}
+#'   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
+#'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
 #'   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
-#'   \item \code{lambda} L2 regularization term on weights. Default: 1
-#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-#'   \item{ \code{num_parallel_tree} Experimental parameter. number of trees to grow per round.
-#'          Useful to test Random Forest through XGBoost
-#'          (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly.
-#'          Default: 1}
-#'   \item{ \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length
-#'          equals to the number of features in the training data.
-#'          \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.}
-#'   \item{ \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions.
-#'        Each item of the list represents one permitted interaction where specified features are allowed to interact with each other.
-#'        Feature index values should start from \code{0} (\code{0} references the first column).
-#'        Leave argument unspecified for no interaction constraints.}
+#'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
+#'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
+#'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 #' }
 #'
-#' 2.2. Parameters for Linear Booster
+#' 2.2. Parameter for Linear Booster
 #'
 #' \itemize{
 #'   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -62,65 +40,31 @@
 #' 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:logistic} logistic regression.
-#'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
-#'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item{ \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution.
-#'            \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).}
-#'     \item{ \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored).
-#'            Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional
-#'            hazard function \code{h(t) = h0(t) * HR)}.}
-#'     \item{ \code{survival:aft}: Accelerated failure time model for censored survival time data. See
-#'            \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time}
-#'            for details.}
-#'     \item \code{aft_loss_distribution}: 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{num_class} set the number of classes. To use only with multiclass objectives.
+#'     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
+#'     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
 #'     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
-#'     \item{ \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where
-#'            \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.}
-#'     \item{ \code{rank:map}: Use LambdaMART to perform list-wise ranking where
-#'            \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)}
-#'            is maximized.}
-#'     \item{ \code{reg:gamma}: gamma regression with log-link.
-#'            Output is a mean of gamma distribution.
-#'            It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be
-#'            \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.}
-#'     \item{ \code{reg:tweedie}: Tweedie regression with log-link.
-#'            It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be
-#'            \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.}
 #'   }
-#'  }
 #'   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
-#'   \item{ \code{eval_metric} evaluation metrics for validation data.
-#'          Users can pass a self-defined function to it.
-#'          Default: metric will be assigned according to objective
-#'          (rmse for regression, and error for classification, mean average precision for ranking).
-#'          List is provided in detail section.}
+#'   \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.
 #'        \code{xgboost}, in addition, also accepts \code{matrix}, \code{dgCMatrix}, or name of a local data file.
 #' @param nrounds max number of boosting iterations.
-#' @param evals Named list of `xgb.DMatrix` datasets to use for evaluating model performance.
+#' @param watchlist named list of xgb.DMatrix datasets to use for evaluating model performance.
 #'        Metrics specified in either \code{eval_metric} or \code{feval} will be computed for each
 #'        of these datasets during each boosting iteration, and stored in the end as a field named
 #'        \code{evaluation_log} in the resulting object. When either \code{verbose>=1} or
-#'        \code{\link{xgb.cb.print.evaluation}} callback is engaged, the performance results are continuously
+#'        \code{\link{cb.print.evaluation}} callback is engaged, the performance results are continuously
 #'        printed out during the training.
-#'        E.g., specifying \code{evals=list(validation1=mat1, validation2=mat2)} allows to track
+#'        E.g., specifying \code{watchlist=list(validation1=mat1, validation2=mat2)} allows to track
 #'        the performance of each round's model on mat1 and mat2.
 #' @param obj customized objective function. Returns gradient and second order
 #'        gradient with given prediction and dtrain.
@@ -130,33 +74,28 @@
 #' @param verbose If 0, xgboost will stay silent. If 1, it will print information about performance.
 #'        If 2, some additional information will be printed out.
 #'        Note that setting \code{verbose > 0} automatically engages the
-#'        \code{xgb.cb.print.evaluation(period=1)} callback function.
+#'        \code{cb.print.evaluation(period=1)} callback function.
 #' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
 #'        Default is 1 which means all messages are printed. This parameter is passed to the
-#'        \code{\link{xgb.cb.print.evaluation}} callback.
+#'        \code{\link{cb.print.evaluation}} callback.
 #' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
 #'        If set to an integer \code{k}, training with a validation set will stop if the performance
 #'        doesn't improve for \code{k} rounds.
-#'        Setting this parameter engages the \code{\link{xgb.cb.early.stop}} callback.
+#'        Setting this parameter engages the \code{\link{cb.early.stop}} callback.
 #' @param maximize If \code{feval} and \code{early_stopping_rounds} are set,
 #'        then this parameter must be set as well.
 #'        When it is \code{TRUE}, it means the larger the evaluation score the better.
-#'        This parameter is passed to the \code{\link{xgb.cb.early.stop}} callback.
+#'        This parameter is passed to the \code{\link{cb.early.stop}} callback.
 #' @param save_period when it is non-NULL, model is saved to disk after every \code{save_period} rounds,
-#'        0 means save at the end. The saving is handled by the \code{\link{xgb.cb.save.model}} callback.
+#'        0 means save at the end. The saving is handled by the \code{\link{cb.save.model}} callback.
 #' @param save_name the name or path for periodically saved model file.
 #' @param xgb_model a previously built model to continue the training from.
 #'        Could be either an object of class \code{xgb.Booster}, or its raw data, or the name of a
 #'        file with a previously saved model.
 #' @param callbacks a list of callback functions to perform various task during boosting.
-#'        See \code{\link{xgb.Callback}}. Some of the callbacks are automatically created depending on the
+#'        See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
 #'        parameters' values. User can provide either existing or their own callback methods in order
 #'        to customize the training process.
-#'
-#'        Note that some callbacks might try to leave attributes in the resulting model object,
-#'        such as an evaluation log (a `data.table` object) - be aware that these objects are kept
-#'        as R attributes, and thus do not get saved when using XGBoost's own serializaters like
-#'        \link{xgb.save} (but are kept when using R serializers like \link{saveRDS}).
 #' @param ... other parameters to pass to \code{params}.
 #' @param label vector of response values. Should not be provided when data is
 #'        a local data file name or an \code{xgb.DMatrix}.
@@ -165,73 +104,71 @@
 #'        This parameter is only used when input is a dense matrix.
 #' @param weight a vector indicating the weight for each row of the input.
 #'
-#' @return
-#' An object of class \code{xgb.Booster}.
-#'
 #' @details
 #' These are the training functions for \code{xgboost}.
 #'
-#' The \code{xgb.train} interface supports advanced features such as \code{evals},
+#' The \code{xgb.train} interface supports advanced features such as \code{watchlist},
 #' customized objective and evaluation metric functions, therefore it is more flexible
 #' than the \code{xgboost} interface.
 #'
 #' Parallelization is automatically enabled if \code{OpenMP} is present.
-#' Number of threads can also be manually specified via the \code{nthread}
-#' parameter.
+#' Number of threads can also be manually specified via \code{nthread} parameter.
 #'
-#' While in other interfaces, the default random seed defaults to zero, in R, if a parameter `seed`
-#' is not manually supplied, it will generate a random seed through R's own random number generator,
-#' whose seed in turn is controllable through `set.seed`. If `seed` is passed, it will override the
-#' RNG from R.
-#'
-#' 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}
-#'      \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
+#'      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
+#'      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
+#'      \item \code{mlogloss} multiclass logloss. \url{http://wiki.fast.ai/index.php/Log_Loss}
 #'      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
 #'            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
 #'            Different threshold (e.g., 0.) could be specified as "error@0."
 #'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'      \item \code{mae} Mean absolute error
-#'      \item \code{mape} Mean absolute percentage error
-#'      \item{ \code{auc} Area under the curve.
-#'             \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.}
+#'      \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
 #'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
+#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
 #'   }
 #'
 #' The following callbacks are automatically created when certain parameters are set:
 #' \itemize{
-#'   \item \code{xgb.cb.print.evaluation} is turned on when \code{verbose > 0};
+#'   \item \code{cb.print.evaluation} is turned on when \code{verbose > 0};
 #'         and the \code{print_every_n} parameter is passed to it.
-#'   \item \code{xgb.cb.evaluation.log} is on when \code{evals} is present.
-#'   \item \code{xgb.cb.early.stop}: when \code{early_stopping_rounds} is set.
-#'   \item \code{xgb.cb.save.model}: when \code{save_period > 0} is set.
+#'   \item \code{cb.evaluation.log} is on when \code{watchlist} is present.
+#'   \item \code{cb.early.stop}: when \code{early_stopping_rounds} is set.
+#'   \item \code{cb.save.model}: when \code{save_period > 0} is set.
 #' }
 #'
-#' Note that objects of type `xgb.Booster` as returned by this function behave a bit differently
-#' from typical R objects (it's an 'altrep' list class), and it makes a separation between
-#' internal booster attributes (restricted to jsonifyable data), accessed through \link{xgb.attr}
-#' and shared between interfaces through serialization functions like \link{xgb.save}; and
-#' R-specific attributes (typically the result from a callback), accessed through \link{attributes}
-#' and \link{attr}, which are otherwise
-#' only used in the R interface, only kept when using R's serializers like \link{saveRDS}, and
-#' not anyhow used by functions like \link{predict.xgb.Booster}.
-#'
-#' Be aware that one such R attribute that is automatically added is `params` - this attribute
-#' is assigned from the `params` argument to this function, and is only meant to serve as a
-#' reference for what went into the booster, but is not used in other methods that take a booster
-#' object - so for example, changing the booster's configuration requires calling `xgb.config<-`
-#' or 'xgb.parameters<-', while simply modifying `attributes(model)$params$<...>` will have no
-#' effect elsewhere.
+#' @return
+#' An object of class \code{xgb.Booster} with the following elements:
+#' \itemize{
+#'   \item \code{handle} a handle (pointer) to the xgboost model in memory.
+#'   \item \code{raw} a cached memory dump of the xgboost model saved as R's \code{raw} type.
+#'   \item \code{niter} number of boosting iterations.
+#'   \item \code{evaluation_log} evaluation history stored as a \code{data.table} with the
+#'         first column corresponding to iteration number and the rest corresponding to evaluation
+#'         metrics' values. It is created by the \code{\link{cb.evaluation.log}} callback.
+#'   \item \code{call} a function call.
+#'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not
+#'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
+#'   \item \code{callbacks} callback functions that were either automatically assigned or
+#'         explicitly passed.
+#'   \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
+#'         (only when column names were defined in training data).
+#'   \item \code{nfeatures} number of features in training data.
+#' }
 #'
 #' @seealso
-#' \code{\link{xgb.Callback}},
+#' \code{\link{callbacks}},
 #' \code{\link{predict.xgb.Booster}},
 #' \code{\link{xgb.cv}}
 #'
@@ -244,25 +181,17 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #'
-#' ## Keep the number of threads to 1 for examples
-#' nthread <- 1
-#' data.table::setDTthreads(nthread)
-#'
-#' dtrain <- with(
-#'   agaricus.train, xgb.DMatrix(data, label = label, nthread = nthread)
-#' )
-#' dtest <- with(
-#'   agaricus.test, xgb.DMatrix(data, label = label, nthread = nthread)
-#' )
-#' evals <- list(train = dtrain, eval = dtest)
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+#' dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
+#' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:
-#' param <- list(max_depth = 2, eta = 1, nthread = nthread,
+#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
 #'               objective = "binary:logistic", eval_metric = "auc")
-#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0)
+#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 #'
-#' ## An xgb.train example where custom objective and evaluation metric are
-#' ## used:
+#'
+#' ## An xgb.train example where custom objective and evaluation metric are used:
 #' logregobj <- function(preds, dtrain) {
 #'    labels <- getinfo(dtrain, "label")
 #'    preds <- 1/(1 + exp(-preds))
@@ -278,40 +207,40 @@
 #'
 #' # These functions could be used by passing them either:
 #' #  as 'objective' and 'eval_metric' parameters in the params list:
-#' param <- list(max_depth = 2, eta = 1, nthread = nthread,
+#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
 #'               objective = logregobj, eval_metric = evalerror)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0)
+#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
 #'
 #' #  or through the ... arguments:
-#' param <- list(max_depth = 2, eta = 1, nthread = nthread)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0,
+#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2)
+#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
 #'                  objective = logregobj, eval_metric = evalerror)
 #'
 #' #  or as dedicated 'obj' and 'feval' parameters of xgb.train:
-#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals,
+#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
 #'                  obj = logregobj, feval = evalerror)
 #'
 #'
 #' ## An xgb.train example of using variable learning rates at each iteration:
-#' param <- list(max_depth = 2, eta = 1, nthread = nthread,
+#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
 #'               objective = "binary:logistic", eval_metric = "auc")
 #' my_etas <- list(eta = c(0.5, 0.1))
-#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0,
-#'                  callbacks = list(xgb.cb.reset.parameters(my_etas)))
+#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
+#'                  callbacks = list(cb.reset.parameters(my_etas)))
 #'
 #' ## Early stopping:
-#' bst <- xgb.train(param, dtrain, nrounds = 25, evals = evals,
+#' bst <- xgb.train(param, dtrain, nrounds = 25, watchlist,
 #'                  early_stopping_rounds = 3)
 #'
 #' ## An 'xgboost' interface example:
 #' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label,
-#'                max_depth = 2, eta = 1, nthread = nthread, nrounds = 2,
+#'                max_depth = 2, eta = 1, nthread = 2, nrounds = 2,
 #'                objective = "binary:logistic")
 #' pred <- predict(bst, agaricus.test$data)
 #'
 #' @rdname xgb.train
 #' @export
-xgb.train <- function(params = list(), data, nrounds, evals = list(),
+xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
                       obj = NULL, feval = NULL, verbose = 1, print_every_n = 1L,
                       early_stopping_rounds = NULL, maximize = NULL,
                       save_period = NULL, save_name = "xgboost.model",
@@ -324,162 +253,125 @@ xgb.train <- function(params = list(), data, nrounds, evals = list(),
   check.custom.obj()
   check.custom.eval()
 
-  # data & evals checks
+  # data & watchlist checks
   dtrain <- data
   if (!inherits(dtrain, "xgb.DMatrix"))
     stop("second argument dtrain must be xgb.DMatrix")
-  if (length(evals) > 0) {
-    if (typeof(evals) != "list" ||
-        !all(vapply(evals, inherits, logical(1), what = 'xgb.DMatrix')))
-      stop("'evals' must be a list of xgb.DMatrix elements")
-    evnames <- names(evals)
+  if (length(watchlist) > 0) {
+    if (typeof(watchlist) != "list" ||
+        !all(vapply(watchlist, inherits, logical(1), what = 'xgb.DMatrix')))
+      stop("watchlist must be a list of xgb.DMatrix elements")
+    evnames <- names(watchlist)
     if (is.null(evnames) || any(evnames == ""))
-      stop("each element of 'evals' 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))
+      stop("each element of the watchlist must have a name tag")
   }
 
-  params <- c(params)
-  params['validate_parameters'] <- TRUE
-  if (!("seed" %in% names(params))) {
-    params[["seed"]] <- sample(.Machine$integer.max, size = 1)
-  }
-
-  # callbacks
-  tmp <- .process.callbacks(callbacks, is_cv = FALSE)
-  callbacks <- tmp$callbacks
-  cb_names <- tmp$cb_names
-  rm(tmp)
-
-  # Early stopping callback (should always come first)
-  if (!is.null(early_stopping_rounds) && !("early_stop" %in% cb_names)) {
-    callbacks <- add.callback(
-      callbacks,
-      xgb.cb.early.stop(
-        early_stopping_rounds,
-        maximize = maximize,
-        verbose = verbose
-      ),
-      as_first_elt = TRUE
-    )
-  }
   # evaluation printing callback
-  print_every_n <- max(as.integer(print_every_n), 1L)
-  if (verbose && !("print_evaluation" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.print.evaluation(print_every_n))
+  params <- c(params)
+  print_every_n <- max( as.integer(print_every_n), 1L)
+  if (!has.callbacks(callbacks, 'cb.print.evaluation') &&
+      verbose) {
+    callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n))
   }
-  # evaluation log callback:  it is automatically enabled when 'evals' is provided
-  if (length(evals) && !("evaluation_log" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.evaluation.log())
+  # evaluation log callback:  it is automatically enabled when watchlist is provided
+  evaluation_log <- list()
+  if (!has.callbacks(callbacks, 'cb.evaluation.log') &&
+      length(watchlist) > 0) {
+    callbacks <- add.cb(callbacks, cb.evaluation.log())
   }
   # Model saving callback
-  if (!is.null(save_period) && !("save_model" %in% cb_names)) {
-    callbacks <- add.callback(callbacks, xgb.cb.save.model(save_period, save_name))
+  if (!is.null(save_period) &&
+      !has.callbacks(callbacks, 'cb.save.model')) {
+    callbacks <- add.cb(callbacks, cb.save.model(save_period, save_name))
+  }
+  # Early stopping callback
+  stop_condition <- FALSE
+  if (!is.null(early_stopping_rounds) &&
+      !has.callbacks(callbacks, 'cb.early.stop')) {
+    callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
+                                                 maximize = maximize, verbose = verbose))
+  }
+
+  # Sort the callbacks into categories
+  cb <- categorize.callbacks(callbacks)
+  params['validate_parameters'] <- TRUE
+  if (!is.null(params[['seed']])) {
+    warning("xgb.train: `seed` is ignored in R package.  Use `set.seed()` instead.")
   }
 
   # The tree updating process would need slightly different handling
   is_update <- NVL(params[['process_type']], '.') == 'update'
 
   # Construct a booster (either a new one or load from xgb_model)
-  bst <- xgb.Booster(
-    params = params,
-    cachelist = append(evals, dtrain),
-    modelfile = xgb_model
-  )
-  niter_init <- bst$niter
-  bst <- bst$bst
-  .Call(
-    XGBoosterCopyInfoFromDMatrix_R,
-    xgb.get.handle(bst),
-    dtrain
-  )
+  handle <- xgb.Booster.handle(params, append(watchlist, dtrain), xgb_model)
+  bst <- xgb.handleToBooster(handle)
 
-  if (is_update && nrounds > niter_init)
+  # extract parameters that can affect the relationship b/w #trees and #iterations
+  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
+  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
+
+  # When the 'xgb_model' was set, find out how many boosting iterations it has
+  niter_init <- 0
+  if (!is.null(xgb_model)) {
+    niter_init <- as.numeric(xgb.attr(bst, 'niter')) + 1
+    if (length(niter_init) == 0) {
+      niter_init <- xgb.ntree(bst) %/% (num_parallel_tree * num_class)
+    }
+  }
+  if(is_update && nrounds > niter_init)
     stop("nrounds cannot be larger than ", niter_init, " (nrounds of xgb_model)")
 
+  # TODO: distributed code
+  rank <- 0
+
   niter_skip <- ifelse(is_update, 0, niter_init)
   begin_iteration <- niter_skip + 1
   end_iteration <- niter_skip + nrounds
 
-  .execute.cb.before.training(
-    callbacks,
-    bst,
-    dtrain,
-    evals,
-    begin_iteration,
-    end_iteration
-  )
-
   # the main loop for boosting iterations
   for (iteration in begin_iteration:end_iteration) {
 
-    .execute.cb.before.iter(
-      callbacks,
-      bst,
-      dtrain,
-      evals,
-      iteration
-    )
+    for (f in cb$pre_iter) f()
 
-    xgb.iter.update(
-      bst = bst,
-      dtrain = dtrain,
-      iter = iteration - 1,
-      obj = obj
-    )
+    xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
 
-    bst_evaluation <- NULL
-    if (length(evals) > 0) {
-      bst_evaluation <- xgb.iter.eval(
-        bst = bst,
-        evals = evals,
-        iter = iteration - 1,
-        feval = feval
-      )
+    bst_evaluation <- numeric(0)
+    if (length(watchlist) > 0)
+      bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
+
+    xgb.attr(bst$handle, 'niter') <- iteration - 1
+
+    for (f in cb$post_iter) f()
+
+    if (stop_condition) break
+  }
+  for (f in cb$finalize) f(finalize = TRUE)
+
+  bst <- xgb.Booster.complete(bst, saveraw = TRUE)
+
+  # store the total number of boosting iterations
+  bst$niter = end_iteration
+
+  # store the evaluation results
+  if (length(evaluation_log) > 0 &&
+      nrow(evaluation_log) > 0) {
+    # include the previous compatible history when available
+    if (inherits(xgb_model, 'xgb.Booster') &&
+        !is_update &&
+        !is.null(xgb_model$evaluation_log) &&
+        isTRUE(all.equal(colnames(evaluation_log),
+                         colnames(xgb_model$evaluation_log)))) {
+      evaluation_log <- rbindlist(list(xgb_model$evaluation_log, evaluation_log))
     }
-
-    should_stop <- .execute.cb.after.iter(
-      callbacks,
-      bst,
-      dtrain,
-      evals,
-      iteration,
-      bst_evaluation
-    )
-
-    if (should_stop) break
+    bst$evaluation_log <- evaluation_log
   }
 
-  cb_outputs <- .execute.cb.after.training(
-    callbacks,
-    bst,
-    dtrain,
-    evals,
-    iteration,
-    bst_evaluation
-  )
-
-  extra_attrs <- list(
-    call = match.call(),
-    params = params
-  )
-
-  curr_attrs <- attributes(bst)
-  if (NROW(curr_attrs)) {
-    curr_attrs <- curr_attrs[
-      setdiff(
-        names(curr_attrs),
-        c(names(extra_attrs), names(cb_outputs))
-      )
-    ]
-  }
-  curr_attrs <- c(extra_attrs, curr_attrs)
-  if (NROW(cb_outputs)) {
-    curr_attrs <- c(curr_attrs, cb_outputs)
-  }
-  attributes(bst) <- curr_attrs
+  bst$call <- match.call()
+  bst$params <- params
+  bst$callbacks <- callbacks
+  if (!is.null(colnames(dtrain)))
+    bst$feature_names <- colnames(dtrain)
+  bst$nfeatures <- ncol(dtrain)
 
   return(bst)
 }

R-package/R/xgb.unserialize.R

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

R-package/R/xgboost.R

@@ -9,22 +9,16 @@ 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 = data,
-    label = label,
-    missing = missing,
-    weight = weight,
-    nthread = merged$nthread
-  )
 
-  evals <- list(train = dtrain)
+  dtrain <- xgb.get.DMatrix(data, label, missing, weight)
 
-  bst <- xgb.train(params, dtrain, nrounds, evals, verbose = verbose, print_every_n = print_every_n,
+  watchlist <- list(train = dtrain)
+
+  bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, print_every_n = print_every_n,
                    early_stopping_rounds = early_stopping_rounds, maximize = maximize,
                    save_period = save_period, save_name = save_name,
                    xgb_model = xgb_model, callbacks = callbacks, ...)
-  return(bst)
+  return (bst)
 }
 
 #' Training part from Mushroom Data Set
@@ -40,10 +34,10 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
 #' }
 #'
 #' @references
-#' <https://archive.ics.uci.edu/ml/datasets/Mushroom>
+#' https://archive.ics.uci.edu/ml/datasets/Mushroom
 #'
 #' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
-#' <http://archive.ics.uci.edu/ml>. Irvine, CA: University of California,
+#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 #' School of Information and Computer Science.
 #'
 #' @docType data
@@ -67,10 +61,10 @@ NULL
 #' }
 #'
 #' @references
-#' <https://archive.ics.uci.edu/ml/datasets/Mushroom>
+#' https://archive.ics.uci.edu/ml/datasets/Mushroom
 #'
 #' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
-#' <http://archive.ics.uci.edu/ml>. Irvine, CA: University of California,
+#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 #' School of Information and Computer Science.
 #'
 #' @docType data
@@ -82,8 +76,12 @@ NULL
 NULL
 
 # Various imports
-#' @importClassesFrom Matrix dgCMatrix dgRMatrix CsparseMatrix
+#' @importClassesFrom Matrix dgCMatrix dgeMatrix
+#' @importFrom Matrix colSums
 #' @importFrom Matrix sparse.model.matrix
+#' @importFrom Matrix sparseVector
+#' @importFrom Matrix sparseMatrix
+#' @importFrom Matrix t
 #' @importFrom data.table data.table
 #' @importFrom data.table is.data.table
 #' @importFrom data.table as.data.table
@@ -92,15 +90,15 @@ NULL
 #' @importFrom data.table setkey
 #' @importFrom data.table setkeyv
 #' @importFrom data.table setnames
-#' @importFrom jsonlite fromJSON
-#' @importFrom jsonlite toJSON
-#' @importFrom methods new
+#' @importFrom magrittr %>%
+#' @importFrom stringi stri_detect_regex
+#' @importFrom stringi stri_match_first_regex
+#' @importFrom stringi stri_replace_first_regex
+#' @importFrom stringi stri_replace_all_regex
+#' @importFrom stringi stri_split_regex
 #' @importFrom utils object.size str tail
-#' @importFrom stats coef
 #' @importFrom stats predict
 #' @importFrom stats median
-#' @importFrom stats sd
-#' @importFrom stats variable.names
 #' @importFrom utils head
 #' @importFrom graphics barplot
 #' @importFrom graphics lines

R-package/README.md

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

R-package/cleanup

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

R-package/configure.ac

@@ -1,26 +1,11 @@
 ### configure.ac					-*- Autoconf -*-
 
-AC_PREREQ(2.69)
+AC_PREREQ(2.62)
 
-AC_INIT([xgboost],[2.1.0],[],[xgboost],[])
+AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
-: ${R_HOME=`R RHOME`}
-if test -z "${R_HOME}"; then
-  echo "could not determine R_HOME"
-  exit 1
-fi
-
-CXX17=`"${R_HOME}/bin/R" CMD config CXX17`
-CXX17STD=`"${R_HOME}/bin/R" CMD config CXX17STD`
-CXX="${CXX17} ${CXX17STD}"
-CXXFLAGS=`"${R_HOME}/bin/R" CMD config CXXFLAGS`
-
-CC=`"${R_HOME}/bin/R" CMD config CC`
-CFLAGS=`"${R_HOME}/bin/R" CMD config CFLAGS`
-CPPFLAGS=`"${R_HOME}/bin/R" CMD config CPPFLAGS`
-
-LDFLAGS=`"${R_HOME}/bin/R" CMD config LDFLAGS`
-AC_LANG(C++)
+# Use this line to set CC variable to a C compiler
+AC_PROG_CC
 
 ### Check whether backtrace() is part of libc or the external lib libexecinfo
 AC_MSG_CHECKING([Backtrace lib])
@@ -43,25 +28,18 @@ fi
 
 if test `uname -s` = "Darwin"
 then
-  if command -v brew &> /dev/null
-  then
-    HOMEBREW_LIBOMP_PREFIX=`brew --prefix libomp`
-  else
-    # Homebrew not found
-    HOMEBREW_LIBOMP_PREFIX=''
-  fi
-  OPENMP_CXXFLAGS="-Xpreprocessor -fopenmp -I${HOMEBREW_LIBOMP_PREFIX}/include"
-  OPENMP_LIB="-lomp -L${HOMEBREW_LIBOMP_PREFIX}/lib"
+  OPENMP_CXXFLAGS='-Xclang -fopenmp'
+  OPENMP_LIB='-lomp'
   ac_pkg_openmp=no
   AC_MSG_CHECKING([whether OpenMP will work in a package])
   AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
-  ${CXX} -o conftest conftest.cpp ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''
     OPENMP_LIB=''
     echo '*****************************************************************************************'
-    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
+    echo 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
     echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
     echo '             brew install libomp'
     echo '*****************************************************************************************'
@@ -74,3 +52,4 @@ AC_SUBST(ENDIAN_FLAG)
 AC_SUBST(BACKTRACE_LIB)
 AC_CONFIG_FILES([src/Makevars])
 AC_OUTPUT
+

R-package/demo/00Index

@@ -1,5 +1,6 @@
 basic_walkthrough               Basic feature walkthrough
-custom_objective                Customize loss function, and evaluation metric
+caret_wrapper                   Use xgboost to train in caret library
+custom_objective                Cutomize 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
@@ -7,8 +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
-tweedie_regression              Tweedie regression
+poisson_regression              Poisson Regression on count data
+tweedie_regression              Tweddie Regression
 gpu_accelerated                 GPU-accelerated tree building algorithms
 interaction_constraints         Interaction constraints among features
 

R-package/demo/README.md

@@ -1,7 +1,8 @@
 XGBoost R Feature Walkthrough
 ====
 * [Basic walkthrough of wrappers](basic_walkthrough.R)
-* [Customize loss function, and evaluation metric](custom_objective.R)
+* [Train a xgboost model from caret library](caret_wrapper.R)
+* [Cutomize 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)
@@ -16,4 +17,4 @@ Benchmarks
 Notes
 ====
 * Contribution of examples, benchmarks is more than welcomed!
-* If you like to share how you use xgboost to solve your problem, send a pull request :)
+* If you like to share how you use xgboost to solve your problem, send a pull request:)

R-package/demo/basic_walkthrough.R

@@ -3,8 +3,8 @@ require(methods)
 
 # we load in the agaricus dataset
 # In this example, we are aiming to predict whether a mushroom is edible
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
 # the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
@@ -26,7 +26,7 @@ bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2,
 # you can also put in xgb.DMatrix object, which stores label, data and other meta datas needed for advanced features
 print("Training xgboost with xgb.DMatrix")
 dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2,
+bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2, 
                objective = "binary:logistic")
 
 # Verbose = 0,1,2
@@ -40,13 +40,13 @@ 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")
 
 #--------------------basic prediction using xgboost--------------
 # you can do prediction using the following line
-# you can put in Matrix, sparseMatrix, or xgb.DMatrix
+# you can put in Matrix, sparseMatrix, or xgb.DMatrix 
 pred <- predict(bst, test$data)
 err <- mean(as.numeric(pred > 0.5) != test$label)
 print(paste("test-error=", err))
@@ -55,36 +55,34 @@ print(paste("test-error=", err))
 # save model to binary local file
 xgb.save(bst, "xgboost.model")
 # load binary model to R
-# Function doesn't take 'nthreads', but can be set like this:
-RhpcBLASctl::omp_set_num_threads(1)
 bst2 <- xgb.load("xgboost.model")
 pred2 <- predict(bst2, test$data)
 # pred2 should be identical to pred
-print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
+print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
 
 # save model to R's raw vector
-raw <- xgb.save.raw(bst)
+raw = xgb.save.raw(bst)
 # load binary model to R
-bst3 <- xgb.load.raw(raw)
+bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))
+print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix
-dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-dtest <- xgb.DMatrix(data = test$data, label = test$label)
-#---------------Using an evaluation set----------------
-# 'evals' is a list of xgb.DMatrix, each of them is tagged with name
-evals <- list(train = dtrain, test = dtest)
-# to train with an evaluation set, use xgb.train, which contains more advanced features
-# 'evals' argument allows us to monitor the evaluation result on all data in the list
-print("Train xgboost using xgb.train with evaluation data")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
+dtrain <- xgb.DMatrix(data = train$data, label=train$label)
+dtest <- xgb.DMatrix(data = test$data, label=test$label)
+#---------------Using watchlist----------------
+# watchlist is a list of xgb.DMatrix, each of them is tagged with name
+watchlist <- list(train=dtrain, test=dtest)
+# to train with watchlist, use xgb.train, which contains more advanced features
+# watchlist allows us to monitor the evaluation result on all data in the list 
+print("Train xgboost using xgb.train with watchlist")
+bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  nthread = 2, objective = "binary:logistic")
 # we can change evaluation metrics, or use multiple evaluation metrics
-print("train xgboost using xgb.train with evaluation data, watch logloss and error")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
+print("train xgboost using xgb.train with watchlist, watch logloss and error")
+bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  eval_metric = "error", eval_metric = "logloss",
                  nthread = 2, objective = "binary:logistic")
 
@@ -92,17 +90,17 @@ bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, evals = eva
 xgb.DMatrix.save(dtrain, "dtrain.buffer")
 # to load it in, simply call xgb.DMatrix
 dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
+bst <- xgb.train(data=dtrain2, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
                  nthread = 2, objective = "binary:logistic")
 # information can be extracted from xgb.DMatrix using getinfo
-label <- getinfo(dtest, "label")
+label = getinfo(dtest, "label")
 pred <- predict(bst, dtest)
-err <- as.numeric(sum(as.integer(pred > 0.5) != label)) / length(label)
+err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
 print(paste("test-error=", err))
 
 # You can dump the tree you learned using xgb.dump into a text file
-dump_path <- file.path(tempdir(), 'dump.raw.txt')
-xgb.dump(bst, dump_path, with_stats = TRUE)
+dump_path = file.path(tempdir(), 'dump.raw.txt')
+xgb.dump(bst, dump_path, with_stats = T)
 
 # Finally, you can check which features are the most important.
 print("Most important features (look at column Gain):")

R-package/demo/boost_from_prediction.R

@@ -1,26 +1,26 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
-evals <- list(eval = dtest, train = dtrain)
+watchlist <- list(eval = dtest, train = dtrain)
 ###
 # advanced: start from a initial base prediction
 #
 print('start running example to start from a initial prediction')
 # train xgboost for 1 round
-param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
-bst <- xgb.train(param, dtrain, 1, evals)
+param <- list(max_depth=2, eta=1, nthread = 2, silent=1, objective='binary:logistic')
+bst <- xgb.train(param, dtrain, 1, watchlist)
 # Note: we need the margin value instead of transformed prediction in set_base_margin
 # do predict with output_margin=TRUE, will always give you margin values before logistic transformation
-ptrain <- predict(bst, dtrain, outputmargin = TRUE)
-ptest  <- predict(bst, dtest, outputmargin = TRUE)
+ptrain <- predict(bst, dtrain, outputmargin=TRUE)
+ptest  <- predict(bst, dtest, outputmargin=TRUE)
 # set the base_margin property of dtrain and dtest
 # base margin is the base prediction we will boost from
 setinfo(dtrain, "base_margin", ptrain)
 setinfo(dtest, "base_margin", ptest)
 
 print('this is result of boost from initial prediction')
-bst <- xgb.train(params = param, data = dtrain, nrounds = 1, evals = evals)
+bst <- xgb.train(params = param, data = dtrain, nrounds = 1, watchlist = watchlist)

R-package/demo/caret_wrapper.R

@@ -0,0 +1,35 @@
+# install development version of caret library that contains xgboost models
+devtools::install_github("topepo/caret/pkg/caret") 
+require(caret)
+require(xgboost)
+require(data.table)
+require(vcd)
+require(e1071)
+
+# Load Arthritis dataset in memory.
+data(Arthritis)
+# Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
+df <- data.table(Arthritis, keep.rownames = F)
+
+# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
+# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
+df[,AgeDiscret:= as.factor(round(Age/10,0))]
+
+# 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).
+df[,ID:=NULL]
+
+#-------------Basic Training using XGBoost in caret Library-----------------
+# Set up control parameters for caret::train
+# Here we use 10-fold cross-validation, repeating twice, and using random search for tuning hyper-parameters.
+fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 2, search = "random")
+# train a xgbTree model using caret::train
+model <- train(factor(Improved)~., data = df, method = "xgbTree", trControl = fitControl)
+
+# 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
+print(model)

R-package/demo/create_sparse_matrix.R

@@ -2,94 +2,75 @@ 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.
-# 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.
+# 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.
 #
-# In R, categorical variable is called Factor.
+# 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).
-df <- data.table(Arthritis, keep.rownames = FALSE)
+# 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 = F)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
 print(df)
 
-# 2 columns have factor type, one has ordinal type
-# (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
+# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values wich can be ordered, here: None > Some > Marked).
 cat("Structure of the dataset\n")
 str(df)
 
-# Let's add some new categorical features to see if it helps.
-# Of course these feature are highly correlated to the Age feature.
-# Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features,
-# even in case of highly correlated features.
+# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 
-# For the first feature we create groups of age by rounding the real age.
-# Note that we transform it to factor (categorical data) so the algorithm treat them as independent values.
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
+# 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!).
-df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
+# 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).
-df[, ID := NULL]
+df[,ID:=NULL]
 
 # List the different values for the column Treatment: Placebo, Treated.
 cat("Values of the categorical feature Treatment\n")
-print(levels(df[, Treatment]))
+print(levels(df[,Treatment]))
 
 # Next step, we will transform the categorical data to dummy variables.
 # This method is also called one hot encoding.
 # 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.
-sparse_matrix <- sparse.model.matrix(Improved ~ . - 1, data = df)
+sparse_matrix = sparse.model.matrix(Improved~.-1, data = df)
 
 cat("Encoding of the sparse Matrix\n")
 print(sparse_matrix)
 
 # Create the output vector (not sparse)
-# 1. Set, for all rows, field in Y column to 0;
-# 2. set Y to 1 when Improved == Marked;
+# 1. Set, for all rows, field in Y column to 0; 
+# 2. set Y to 1 when Improved == Marked; 
 # 3. Return Y column
-output_vector <- df[, Y := 0][Improved == "Marked", Y := 1][, Y]
+output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
 
 # Following is the same process as other demo
 cat("Learning...\n")
-bst <- xgb.train(data = xgb.DMatrix(sparse_matrix, label = output_vector), max_depth = 9,
-                 eta = 1, nthread = 2, nrounds = 10, objective = "binary:logistic")
+bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 9,
+               eta = 1, nthread = 2, nrounds = 10, objective = "binary:logistic")
 
 importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst)
 print(importance)
-# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age.
-# The second most important feature is having received a placebo or not.
-# The sex is third.
-# Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
+# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age. The second most important feature is having received a placebo or not. The sex is third. Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).
 
 # Does these result make sense?
 # Let's check some Chi2 between each of these features and the outcome.
@@ -101,17 +82,8 @@ print(chisq.test(df$AgeDiscret, df$Y))
 # Our first simplification of Age gives a Pearson correlation of 8.
 
 print(chisq.test(df$AgeCat, df$Y))
-# The perfectly random split I did between young and old at 30 years old have a low correlation of 2.
-# It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that),
-# but for the illness we are studying, the age to be vulnerable is not the same.
-# Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
+# The perfectly random split I did between young and old at 30 years old have a low correlation of 2. It's a result we may expect as may be in my mind > 30 years is being old (I am 32 and starting feeling old, this may explain that), but  for the illness we are studying, the age to be vulnerable is not the same. Don't let your "gut" lower the quality of your model. In "data science", there is science :-)
 
-# As you can see, in general destroying information by simplifying it won't improve your model.
-# Chi2 just demonstrates that.
-# But in more complex cases, creating a new feature based on existing one which makes link with the outcome
-# more obvious may help the algorithm and improve the model.
-# The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
+# As you can see, in general destroying information by simplifying it won't improve your model. Chi2 just demonstrates that. But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model. The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
 # However it's almost always worse when you add some arbitrary rules.
-# Moreover, you can notice that even if we have added some not useful new features highly correlated with
-# other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age.
-# Linear model may not be that strong in these scenario.
+# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.

R-package/demo/cross_validation.R

@@ -1,46 +1,46 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 nrounds <- 2
-param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
+param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
 
 cat('running cross validation\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold = 5, metrics = 'error')
+xgb.cv(param, dtrain, nrounds, nfold=5, metrics={'error'})
 
 cat('running cross validation, disable standard deviation display\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nrounds, nfold = 5,
-       metrics = 'error', showsd = FALSE)
+xgb.cv(param, dtrain, nrounds, nfold=5,
+       metrics='error', showsd = FALSE)
 
 ###
-# you can also do cross validation with customized loss function
+# you can also do cross validation with cutomized loss function
 # See custom_objective.R
 ##
-print('running cross validation, with customized loss function')
+print ('running cross validation, with cutomsized loss function')
 
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1,
+param <- list(max_depth=2, eta=1, silent=1,
               objective = logregobj, eval_metric = evalerror)
 # train with customized objective
 xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)

R-package/demo/custom_objective.R

@@ -1,21 +1,21 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-evals <- list(eval = dtest, train = dtrain)
+watchlist <- list(eval = dtest, train = dtrain)
 num_round <- 2
 
 # user define objective function, given prediction, return gradient and second order gradient
-# this is log likelihood loss
+# this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -23,43 +23,43 @@ 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 builtin evaluation metric not function properly
+# this may make buildin evalution metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
+# the buildin 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")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
-              objective = logregobj, eval_metric = evalerror)
-print('start training with user customized objective')
+param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
+              objective=logregobj, eval_metric=evalerror)
+print ('start training with user customized objective')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, evals)
+bst <- xgb.train(param, dtrain, num_round, watchlist)
 
 #
-# there can be cases where you want additional information
+# there can be cases where you want additional information 
 # being considered besides the property of DMatrix you can get by getinfo
 # you can set additional information as attributes if DMatrix
 
-# set label attribute of dtrain to be label, we use label as an example, it can be anything
+# set label attribute of dtrain to be label, we use label as an example, it can be anything 
 attr(dtrain, 'label') <- getinfo(dtrain, 'label')
 # this is new customized objective, where you can access things you set
 # same thing applies to customized evaluation function
 logregobjattr <- function(preds, dtrain) {
   # now you can access the attribute in customized function
   labels <- attr(dtrain, 'label')
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
-param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
-              objective = logregobjattr, eval_metric = evalerror)
-print('start training with user customized objective, with additional attributes in DMatrix')
+param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
+              objective=logregobjattr, eval_metric=evalerror)
+print ('start training with user customized objective, with additional attributes in DMatrix')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, evals)
+bst <- xgb.train(param, dtrain, num_round, watchlist)

R-package/demo/early_stopping.R

@@ -1,38 +1,38 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-param <- list(max_depth = 2, eta = 1, nthread = 2, verbosity = 0)
-evals <- list(eval = dtest)
+param <- list(max_depth=2, eta=1, nthread=2, verbosity=0)
+watchlist <- list(eval = dtest)
 num_round <- 20
 # user define objective function, given prediction, return gradient and second order gradient
-# this is log likelihood loss
+# this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1 / (1 + exp(-preds))
+  preds <- 1/(1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
 # 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 builtin evaluation metric not function properly
+# this may make buildin evalution metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
+# the buildin 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")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
   return(list(metric = "error", value = err))
 }
-print('start training with early Stopping setting')
+print ('start training with early Stopping setting')
 
-bst <- xgb.train(param, dtrain, num_round, evals,
+bst <- xgb.train(param, dtrain, num_round, watchlist,
                  objective = logregobj, eval_metric = evalerror, maximize = FALSE,
                  early_stopping_round = 3)
 bst <- xgb.cv(param, dtrain, num_round, nfold = 5,

R-package/demo/generalized_linear_model.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
@@ -11,23 +11,24 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
 
 # change booster to gblinear, so that we are fitting a linear model
-# alpha is the L1 regularizer
+# alpha is the L1 regularizer 
 # lambda is the L2 regularizer
 # you can also set lambda_bias which is L2 regularizer on the bias term
 param <- list(objective = "binary:logistic", booster = "gblinear",
               nthread = 2, alpha = 0.0001, lambda = 1)
 
 # normally, you do not need to set eta (step_size)
-# XGBoost uses a parallel coordinate descent algorithm (shotgun),
+# XGBoost uses a parallel coordinate descent algorithm (shotgun), 
 # there could be affection on convergence with parallelization on certain cases
 # setting eta to be smaller value, e.g 0.5 can make the optimization more stable
 
 ##
 # the rest of settings are the same
 ##
-evals <- list(eval = dtest, train = dtrain)
+watchlist <- list(eval = dtest, train = dtrain)
 num_round <- 2
-bst <- xgb.train(param, dtrain, num_round, evals)
+bst <- xgb.train(param, dtrain, num_round, watchlist)
 ypred <- predict(bst, dtest)
 labels <- getinfo(dtest, 'label')
-cat('error of preds=', mean(as.numeric(ypred > 0.5) != labels), '\n')
+cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
+

R-package/demo/gpu_accelerated.R

@@ -1,9 +1,9 @@
 # An example of using GPU-accelerated tree building algorithms
-#
-# NOTE: it can only run if you have a CUDA-enable GPU and the package was
+# 
+# NOTE: it can only run if you have a CUDA-enable GPU and the package was 
 #       specially compiled with GPU support.
 #
-# For the current functionality, see
+# For the current functionality, see 
 # https://xgboost.readthedocs.io/en/latest/gpu/index.html
 #
 
@@ -21,9 +21,9 @@ m <- X[, sel] %*% betas - 1 + rnorm(N)
 y <- rbinom(N, 1, plogis(m))
 
 tr <- sample.int(N, N * 0.75)
-dtrain <- xgb.DMatrix(X[tr, ], label = y[tr])
-dtest <- xgb.DMatrix(X[-tr, ], label = y[-tr])
-evals <- list(train = dtrain, test = dtest)
+dtrain <- xgb.DMatrix(X[tr,], label = y[tr])
+dtest <- xgb.DMatrix(X[-tr,], label = y[-tr])
+wl <- list(train = dtrain, test = dtest)
 
 # An example of running 'gpu_hist' algorithm
 # which is
@@ -35,11 +35,11 @@ evals <- list(train = dtrain, test = dtest)
 param <- list(objective = 'reg:logistic', eval_metric = 'auc', subsample = 0.5, nthread = 4,
               max_bin = 64, tree_method = 'gpu_hist')
 pt <- proc.time()
-bst_gpu <- xgb.train(param, dtrain, evals = evals, nrounds = 50)
+bst_gpu <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
 proc.time() - pt
 
 # Compare to the 'hist' algorithm:
 param$tree_method <- 'hist'
 pt <- proc.time()
-bst_hist <- xgb.train(param, dtrain, evals = evals, nrounds = 50)
+bst_hist <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
 proc.time() - pt

R-package/demo/interaction_constraints.R

@@ -4,39 +4,34 @@ library(data.table)
 set.seed(1024)
 
 # Function to obtain a list of interactions fitted in trees, requires input of maximum depth
-treeInteractions <- function(input_tree, input_max_depth) {
-  ID_merge <- i.id <- i.feature <- NULL  # Suppress warning "no visible binding for global variable"
-
-  trees <- data.table::copy(input_tree)  # copy tree input to prevent overwriting
+treeInteractions <- function(input_tree, input_max_depth){
+  trees <- copy(input_tree)  # copy tree input to prevent overwriting
   if (input_max_depth < 2) return(list())  # no interactions if max depth < 2
   if (nrow(input_tree) == 1) return(list())
 
   # Attach parent nodes
-  for (i in 2:input_max_depth) {
-    if (i == 2) trees[, ID_merge := ID] else trees[, ID_merge := get(paste0('parent_', i - 2))]
-    parents_left <- trees[!is.na(Split), list(i.id = ID, i.feature = Feature, ID_merge = Yes)]
-    parents_right <- trees[!is.na(Split), list(i.id = ID, i.feature = Feature, ID_merge = No)]
+  for (i in 2:input_max_depth){
+    if (i == 2) trees[, ID_merge:=ID] else trees[, ID_merge:=get(paste0('parent_',i-2))]
+    parents_left <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=Yes)]
+    parents_right <- trees[!is.na(Split), list(i.id=ID, i.feature=Feature, ID_merge=No)]
 
-    data.table::setorderv(trees, 'ID_merge')
-    data.table::setorderv(parents_left, 'ID_merge')
-    data.table::setorderv(parents_right, 'ID_merge')
+    setorderv(trees, 'ID_merge')
+    setorderv(parents_left, 'ID_merge')
+    setorderv(parents_right, 'ID_merge')
 
-    trees <- merge(trees, parents_left, by = 'ID_merge', all.x = TRUE)
-    trees[!is.na(i.id), c(paste0('parent_', i - 1), paste0('parent_feat_', i - 1))
-          := list(i.id, i.feature)]
-    trees[, c('i.id', 'i.feature') := NULL]
+    trees <- merge(trees, parents_left, by='ID_merge', all.x=T)
+    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
+    trees[, c('i.id','i.feature'):=NULL]
 
-    trees <- merge(trees, parents_right, by = 'ID_merge', all.x = TRUE)
-    trees[!is.na(i.id), c(paste0('parent_', i - 1), paste0('parent_feat_', i - 1))
-          := list(i.id, i.feature)]
-    trees[, c('i.id', 'i.feature') := NULL]
+    trees <- merge(trees, parents_right, by='ID_merge', all.x=T)
+    trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
+    trees[, c('i.id','i.feature'):=NULL]
   }
 
   # Extract nodes with interactions
-  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),  # 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)))
+  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1), 
+                             c('Feature',paste0('parent_feat_',1:(input_max_depth-1))), with=F]
+  interaction_trees_split <- split(interaction_trees, 1:nrow(interaction_trees))
   interaction_list <- lapply(interaction_trees_split, as.character)
 
   # Remove NAs (no parent interaction)
@@ -44,7 +39,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
   # Remove non-interactions (same variable)
   interaction_list <- lapply(interaction_list, unique)  # remove same variables
-  interaction_length <- lengths(interaction_list)
+  interaction_length <- sapply(interaction_list, length)
   interaction_list <- interaction_list[interaction_length > 1]
   interaction_list <- unique(lapply(interaction_list, sort))
   return(interaction_list)
@@ -52,62 +47,59 @@ treeInteractions <- function(input_tree, input_max_depth) {
 
 # Generate sample data
 x <- list()
-for (i in 1:10) {
-  x[[i]] <- i * rnorm(1000, 10)
+for (i in 1:10){
+  x[[i]] = i*rnorm(1000, 10)
 }
 x <- as.data.table(x)
 
-y <- -1 * x[, rowSums(.SD)] + x[['V1']] * x[['V2']] + x[['V3']] * x[['V4']] * x[['V5']]
-     + rnorm(1000, 0.001) + 3 * sin(x[['V7']])
+y = -1*x[, rowSums(.SD)] + x[['V1']]*x[['V2']] + x[['V3']]*x[['V4']]*x[['V5']] + rnorm(1000, 0.001) + 3*sin(x[['V7']])
 
-train <- as.matrix(x)
+train = as.matrix(x)
 
 # Interaction constraint list (column names form)
-interaction_list <- list(c('V1', 'V2'), c('V3', 'V4', 'V5'))
+interaction_list <- list(c('V1','V2'),c('V3','V4','V5'))
 
 # Convert interaction constraint list into feature index form
 cols2ids <- function(object, col_names) {
   LUT <- seq_along(col_names) - 1
   names(LUT) <- col_names
-  rapply(object, function(x) LUT[x], classes = "character", how = "replace")
+  rapply(object, function(x) LUT[x], classes="character", how="replace")
 }
-interaction_list_fid <- cols2ids(interaction_list, colnames(train))
+interaction_list_fid = cols2ids(interaction_list, colnames(train))
 
 # Fit model with interaction constraints
-bst <- xgb.train(data = xgb.DMatrix(train, label = y), max_depth = 4,
-                 eta = 0.1, nthread = 2, nrounds = 1000,
-                 interaction_constraints = interaction_list_fid)
+bst = xgboost(data = train, label = y, max_depth = 4,
+              eta = 0.1, nthread = 2, nrounds = 1000,
+              interaction_constraints = interaction_list_fid)
 
 bst_tree <- xgb.model.dt.tree(colnames(train), bst)
-bst_interactions <- treeInteractions(bst_tree, 4)
-  # interactions constrained to combinations of V1*V2 and V3*V4*V5
+bst_interactions <- treeInteractions(bst_tree, 4)  # interactions constrained to combinations of V1*V2 and V3*V4*V5
 
 # Fit model without interaction constraints
-bst2 <- xgb.train(data = xgb.DMatrix(train, label = y), max_depth = 4,
-                  eta = 0.1, nthread = 2, nrounds = 1000)
+bst2 = xgboost(data = train, label = y, max_depth = 4,
+               eta = 0.1, nthread = 2, nrounds = 1000)
 
 bst2_tree <- xgb.model.dt.tree(colnames(train), bst2)
 bst2_interactions <- treeInteractions(bst2_tree, 4)  # much more interactions
 
 # Fit model with both interaction and monotonicity constraints
-bst3 <- xgb.train(data = xgb.DMatrix(train, label = y), max_depth = 4,
-                  eta = 0.1, nthread = 2, nrounds = 1000,
-                  interaction_constraints = interaction_list_fid,
-                  monotone_constraints = c(-1, 0, 0, 0, 0, 0, 0, 0, 0, 0))
+bst3 = xgboost(data = train, label = y, max_depth = 4,
+               eta = 0.1, nthread = 2, nrounds = 1000,
+               interaction_constraints = interaction_list_fid,
+               monotone_constraints = c(-1,0,0,0,0,0,0,0,0,0))
 
 bst3_tree <- xgb.model.dt.tree(colnames(train), bst3)
-bst3_interactions <- treeInteractions(bst3_tree, 4)
-  # interactions still constrained to combinations of V1*V2 and V3*V4*V5
+bst3_interactions <- treeInteractions(bst3_tree, 4)  # interactions still constrained to combinations of V1*V2 and V3*V4*V5
 
 # Show monotonic constraints still apply by checking scores after incrementing V1
 x1 <- sort(unique(x[['V1']]))
-for (i in seq_along(x1)){
-  testdata <- copy(x[, - ('V1')])
+for (i in 1:length(x1)){
+  testdata <- copy(x[, -c('V1')])
   testdata[['V1']] <- x1[i]
-  testdata <- testdata[, paste0('V', 1:10), with = FALSE]
+  testdata <- testdata[, paste0('V',1:10), with=F]
   pred <- predict(bst3, as.matrix(testdata))
-
+  
   # Should not print out anything due to monotonic constraints
   if (i > 1) if (any(pred > prev_pred)) print(i)
-  prev_pred <- pred
+  prev_pred <- pred 
 }

R-package/demo/poisson_regression.R

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

R-package/demo/predict_first_ntree.R

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

R-package/demo/predict_leaf_indices.R

@@ -5,34 +5,34 @@ require(Matrix)
 set.seed(1982)
 
 # load in the agaricus dataset
-data(agaricus.train, package = 'xgboost')
-data(agaricus.test, package = 'xgboost')
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 
-param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic')
-nrounds <- 4
+param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
+nrounds = 4
 
 # training the model for two rounds
-bst <- xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
+bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy without new features
-accuracy.before <- (sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label)
-                    / length(agaricus.test$label))
+accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
 
 # by default, we predict using all the trees
-pred_with_leaf <- predict(bst, dtest, predleaf = TRUE)
+
+pred_with_leaf = predict(bst, dtest, predleaf = TRUE)
 head(pred_with_leaf)
 
-create.new.tree.features <- function(model, original.features) {
+create.new.tree.features <- function(model, original.features){
   pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
   cols <- list()
-  for (i in 1:xgb.get.num.boosted.rounds(model)) {
+  for(i in 1:model$niter){
     # max is not the real max but it s not important for the purpose of adding features
-    leaf.id <- sort(unique(pred_with_leaf[, i]))
-    cols[[i]] <- factor(x = pred_with_leaf[, i], level = leaf.id)
+    leaf.id <- sort(unique(pred_with_leaf[,i]))
+    cols[[i]] <- factor(x = pred_with_leaf[,i], level = leaf.id)
   }
-  cbind(original.features, sparse.model.matrix(~ . - 1, as.data.frame(cols)))
+  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
 }
 
 # Convert previous features to one hot encoding
@@ -43,12 +43,11 @@ colnames(new.features.test) <- colnames(new.features.train)
 # learning with new features
 new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
 new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
+watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy with new features
-accuracy.after <- (sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label)
-                   / length(agaricus.test$label))
+accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
 
 # Here the accuracy was already good and is now perfect.
-cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
-          accuracy.after, "!\n"))
+cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now", accuracy.after, "!\n"))

R-package/demo/runall.R

@@ -1,13 +1,14 @@
-# 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')
-demo(predict_first_ntree, package = 'xgboost')
-demo(generalized_linear_model, package = 'xgboost')
-demo(cross_validation, package = 'xgboost')
-demo(create_sparse_matrix, package = 'xgboost')
-demo(predict_leaf_indices, package = 'xgboost')
-demo(early_stopping, package = 'xgboost')
-demo(poisson_regression, package = 'xgboost')
-demo(tweedie_regression, package = 'xgboost')
-#demo(gpu_accelerated, package = 'xgboost')  # can only run when built with GPU support
+# running all scripts in demo folder
+demo(basic_walkthrough)
+demo(custom_objective)
+demo(boost_from_prediction)
+demo(predict_first_ntree)
+demo(generalized_linear_model)
+demo(cross_validation)
+demo(create_sparse_matrix)
+demo(predict_leaf_indices)
+demo(early_stopping)
+demo(poisson_regression)
+demo(caret_wrapper)
+demo(tweedie_regression)
+#demo(gpu_accelerated) # can only run when built with GPU support

R-package/demo/tweedie_regression.R

@@ -8,12 +8,12 @@ data(AutoClaim)
 dt <- data.table(AutoClaim)
 
 # exclude these columns from the model matrix
-exclude <- c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
+exclude <-  c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_YY')
 
 # retains the missing values
 # NOTE: this dataset is comes ready out of the box
 options(na.action = 'na.pass')
-x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = FALSE])
+x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = F])
 options(na.action = 'na.omit')
 
 # response
@@ -21,29 +21,29 @@ y <- dt[, CLM_AMT5]
 
 d_train <- xgb.DMatrix(data = x, label = y, missing = NA)
 
-# the tweedie_variance_power parameter determines the shape of
+# the tweedie_variance_power parameter determines the shape of 
 # distribution
 # - closer to 1 is more poisson like and the mass
-#   is more concentrated near zero
-# - closer to 2 is more gamma like and the mass spreads to the
+#   is more concentrated near zero 
+# - closer to 2 is more gamma like and the mass spreads to the 
 #   the right with less concentration near zero
 
 params <- list(
   objective = 'reg:tweedie',
-  eval_metric = 'rmse',
+  eval_metric = 'rmse', 
   tweedie_variance_power = 1.4,
   max_depth = 6,
   eta = 1)
 
 bst <- xgb.train(
-  data = d_train,
-  params = params,
+  data = d_train, 
+  params = params, 
   maximize = FALSE,
-  evals = list(train = d_train),
+  watchlist = list(train = d_train), 
   nrounds = 20)
 
 var_imp <- xgb.importance(attr(x, 'Dimnames')[[2]], model = bst)
 
 preds <- predict(bst, d_train)
 
-rmse <- sqrt(sum(mean((y - preds) ^ 2)))
+rmse <- sqrt(sum(mean((y - preds)^2)))

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

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

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

@@ -1,95 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/utils.R
-\name{a-compatibility-note-for-saveRDS-save}
-\alias{a-compatibility-note-for-saveRDS-save}
-\title{Model Serialization and Compatibility}
-\description{
-When it comes to serializing XGBoost models, it's possible to use R serializers such as
-\link{save} or \link{saveRDS} to serialize an XGBoost R model, but XGBoost also provides
-its own serializers with better compatibility guarantees, which allow loading
-said models in other language bindings of XGBoost.
-
-Note that an \code{xgb.Booster} object, outside of its core components, might also keep:\itemize{
-\item Additional model configuration (accessible through \link{xgb.config}),
-which includes model fitting parameters like \code{max_depth} and runtime parameters like \code{nthread}.
-These are not necessarily useful for prediction/importance/plotting.
-\item Additional R-specific attributes  - e.g. results of callbacks, such as evaluation logs,
-which are kept as a \code{data.table} object, accessible through \code{attributes(model)$evaluation_log}
-if present.
-}
-
-The first one (configurations) does not have the same compatibility guarantees as
-the model itself, including attributes that are set and accessed through \link{xgb.attributes} - that is, such configuration
-might be lost after loading the booster in a different XGBoost version, regardless of the
-serializer that was used. These are saved when using \link{saveRDS}, but will be discarded
-if loaded into an incompatible XGBoost version. They are not saved when using XGBoost's
-serializers from its public interface including \link{xgb.save} and \link{xgb.save.raw}.
-
-The second ones (R attributes) are not part of the standard XGBoost model structure, and thus are
-not saved when using XGBoost's own serializers. These attributes are only used for informational
-purposes, such as keeping track of evaluation metrics as the model was fit, or saving the R
-call that produced the model, but are otherwise not used for prediction / importance / plotting / etc.
-These R attributes are only preserved when using R's serializers.
-
-Note that XGBoost models in R starting from version \verb{2.1.0} and onwards, and XGBoost models
-before version \verb{2.1.0}; have a very different R object structure and are incompatible with
-each other. Hence, models that were saved with R serializers live \code{saveRDS} or \code{save} before
-version \verb{2.1.0} will not work with latter \code{xgboost} versions and vice versa. Be aware that
-the structure of R model objects could in theory change again in the future, so XGBoost's serializers
-should be preferred for long-term storage.
-
-Furthermore, note that using the package \code{qs} for serialization will require version 0.26 or
-higher of said package, and will have the same compatibility restrictions as R serializers.
-}
-\details{
-Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-the JSON format by specifying the JSON extension. To read the model back, use
-\code{\link{xgb.load}}.
-
-Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-as part of another R object.
-
-Use \link{saveRDS} if you require the R-specific attributes that a booster might have, such
-as evaluation logs, but note that future compatibility of such objects is outside XGBoost's
-control as it relies on R's serialization format (see e.g. the details section in
-\link{serialize} and \link{save} from base R).
-
-For more details and explanation about model persistence and archival, consult the page
-\url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-bst <- xgb.train(data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
-                 max_depth = 2, eta = 1, nthread = 2, nrounds = 2,
-                 objective = "binary:logistic")
-
-# Save as a stand-alone file; load it with xgb.load()
-fname <- file.path(tempdir(), "xgb_model.ubj")
-xgb.save(bst, fname)
-bst2 <- xgb.load(fname)
-
-# Save as a stand-alone file (JSON); load it with xgb.load()
-fname <- file.path(tempdir(), "xgb_model.json")
-xgb.save(bst, fname)
-bst2 <- xgb.load(fname)
-
-# Save as a raw byte vector; load it with xgb.load.raw()
-xgb_bytes <- xgb.save.raw(bst)
-bst2 <- xgb.load.raw(xgb_bytes)
-
-# Persist XGBoost model as part of another R object
-obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-# Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-# xgb.Booster directly. What's being persisted is the future-proof byte representation
-# as given by xgb.save.raw().
-fname <- file.path(tempdir(), "my_object.Rds")
-saveRDS(obj, fname)
-# Read back the R object
-obj2 <- readRDS(fname)
-# Re-construct xgb.Booster object from the bytes
-bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-
-}

R-package/man/agaricus.test.Rd

@@ -19,15 +19,15 @@ UCI Machine Learning Repository.
 This data set includes the following fields:
 
 \itemize{
-\item \code{label} the label for each record
-\item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
+ \item \code{label} the label for each record
+ \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
 }
 }
 \references{
-\url{https://archive.ics.uci.edu/ml/datasets/Mushroom}
+https://archive.ics.uci.edu/ml/datasets/Mushroom
 
 Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
-\url{http://archive.ics.uci.edu/ml}. Irvine, CA: University of California,
+[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 School of Information and Computer Science.
 }
 \keyword{datasets}

R-package/man/agaricus.train.Rd

@@ -19,15 +19,15 @@ UCI Machine Learning Repository.
 This data set includes the following fields:
 
 \itemize{
-\item \code{label} the label for each record
-\item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
+ \item \code{label} the label for each record
+ \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
 }
 }
 \references{
-\url{https://archive.ics.uci.edu/ml/datasets/Mushroom}
+https://archive.ics.uci.edu/ml/datasets/Mushroom
 
 Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
-\url{http://archive.ics.uci.edu/ml}. Irvine, CA: University of California,
+[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 School of Information and Computer Science.
 }
 \keyword{datasets}

R-package/man/callbacks.Rd

@@ -0,0 +1,37 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{callbacks}
+\alias{callbacks}
+\title{Callback closures for booster training.}
+\description{
+These are used to perform various service tasks either during boosting iterations or at the end.
+This approach helps to modularize many of such tasks without bloating the main training methods,
+and it offers .
+}
+\details{
+By default, a callback function is run after each boosting iteration.
+An R-attribute \code{is_pre_iteration} could be set for a callback to define a pre-iteration function.
+
+When a callback function has \code{finalize} parameter, its finalizer part will also be run after
+the boosting is completed.
+
+WARNING: side-effects!!! Be aware that these callback functions access and modify things in
+the environment from which they are called from, which is a fairly uncommon thing to do in R.
+
+To write a custom callback closure, make sure you first understand the main concepts about R environments.
+Check either R documentation on \code{\link[base]{environment}} or the
+\href{http://adv-r.had.co.nz/Environments.html}{Environments chapter} from the "Advanced R"
+book by Hadley Wickham. Further, the best option is to read the code of some of the existing callbacks -
+choose ones that do something similar to what you want to achieve. Also, you would need to get familiar
+with the objects available inside of the \code{xgb.train} and \code{xgb.cv} internal environments.
+}
+\seealso{
+\code{\link{cb.print.evaluation}},
+\code{\link{cb.evaluation.log}},
+\code{\link{cb.reset.parameters}},
+\code{\link{cb.early.stop}},
+\code{\link{cb.save.model}},
+\code{\link{cb.cv.predict}},
+\code{\link{xgb.train}},
+\code{\link{xgb.cv}}
+}

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

@@ -1,27 +1,16 @@
 % Generated by roxygen2: do not edit by hand
 % Please edit documentation in R/callbacks.R
-\name{xgb.cb.cv.predict}
-\alias{xgb.cb.cv.predict}
-\title{Callback for returning cross-validation based predictions.}
+\name{cb.cv.predict}
+\alias{cb.cv.predict}
+\title{Callback closure for returning cross-validation based predictions.}
 \usage{
-xgb.cb.cv.predict(save_models = FALSE, outputmargin = FALSE)
+cb.cv.predict(save_models = FALSE)
 }
 \arguments{
-\item{save_models}{A flag for whether to save the folds' models.}
-
-\item{outputmargin}{Whether to save margin predictions (same effect as passing this
-parameter to \link{predict.xgb.Booster}).}
+\item{save_models}{a flag for whether to save the folds' models.}
 }
 \value{
-An \code{xgb.Callback} object, which can be passed to \link{xgb.cv},
-but \bold{not} to \link{xgb.train}.
-}
-\description{
-This callback function saves predictions for all of the test folds,
-and also allows to save the folds' models.
-}
-\details{
-Predictions are saved inside of the \code{pred} element, which is either a vector or a matrix,
+Predictions are returned inside of the \code{pred} element, which is either a vector or a matrix,
 depending on the number of prediction outputs per data row. The order of predictions corresponds
 to the order of rows in the original dataset. Note that when a custom \code{folds} list is
 provided in \code{xgb.cv}, the predictions would only be returned properly when this list is a
@@ -30,3 +19,25 @@ meaningful when user-provided folds have overlapping indices as in, e.g., random
 When some of the indices in the training dataset are not included into user-provided \code{folds},
 their prediction value would be \code{NA}.
 }
+\description{
+Callback closure for returning cross-validation based predictions.
+}
+\details{
+This callback function saves predictions for all of the test folds,
+and also allows to save the folds' models.
+
+It is a "finalizer" callback and it uses early stopping information whenever it is available,
+thus it must be run after the early stopping callback if the early stopping is used.
+
+Callback function expects the following values to be set in its calling frame:
+\code{bst_folds},
+\code{basket},
+\code{data},
+\code{end_iteration},
+\code{params},
+\code{num_parallel_tree},
+\code{num_class}.
+}
+\seealso{
+\code{\link{callbacks}}
+}

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

@@ -0,0 +1,66 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{cb.early.stop}
+\alias{cb.early.stop}
+\title{Callback closure to activate the early stopping.}
+\usage{
+cb.early.stop(
+  stopping_rounds,
+  maximize = FALSE,
+  metric_name = NULL,
+  verbose = TRUE
+)
+}
+\arguments{
+\item{stopping_rounds}{The number of rounds with no improvement in
+the evaluation metric in order to stop the training.}
+
+\item{maximize}{whether to maximize the evaluation metric}
+
+\item{metric_name}{the name of an evaluation column to use as a criteria for early
+stopping. If not set, the last column would be used.
+Let's say the test data in \code{watchlist} was labelled as \code{dtest},
+and one wants to use the AUC in test data for early stopping regardless of where
+it is in the \code{watchlist}, then one of the following would need to be set:
+\code{metric_name='dtest-auc'} or \code{metric_name='dtest_auc'}.
+All dash '-' characters in metric names are considered equivalent to '_'.}
+
+\item{verbose}{whether to print the early stopping information.}
+}
+\description{
+Callback closure to activate the early stopping.
+}
+\details{
+This callback function determines the condition for early stopping
+by setting the \code{stop_condition = TRUE} flag in its calling frame.
+
+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)
+\item \code{best_msg} message string is also stored.
+}
+
+At least one data element is required in the evaluation watchlist for early stopping to work.
+
+Callback function expects the following values to be set in its calling frame:
+\code{stop_condition},
+\code{bst_evaluation},
+\code{rank},
+\code{bst} (or \code{bst_folds} and \code{basket}),
+\code{iteration},
+\code{begin_iteration},
+\code{end_iteration},
+\code{num_parallel_tree}.
+}
+\seealso{
+\code{\link{callbacks}},
+\code{\link{xgb.attr}}
+}

R-package/man/cb.evaluation.log.Rd

@@ -0,0 +1,31 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{cb.evaluation.log}
+\alias{cb.evaluation.log}
+\title{Callback closure for logging the evaluation history}
+\usage{
+cb.evaluation.log()
+}
+\description{
+Callback closure for logging the evaluation history
+}
+\details{
+This callback function appends the current iteration evaluation results \code{bst_evaluation}
+available in the calling parent frame to the \code{evaluation_log} list in a calling frame.
+
+The finalizer callback (called with \code{finalize = TURE} in the end) converts
+the \code{evaluation_log} list into a final data.table.
+
+The iteration evaluation result \code{bst_evaluation} must be a named numeric vector.
+
+Note: in the column names of the final data.table, the dash '-' character is replaced with
+the underscore '_' in order to make the column names more like regular R identifiers.
+
+Callback function expects the following values to be set in its calling frame:
+\code{evaluation_log},
+\code{bst_evaluation},
+\code{iteration}.
+}
+\seealso{
+\code{\link{callbacks}}
+}

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

@@ -1,69 +1,53 @@
 % Generated by roxygen2: do not edit by hand
 % Please edit documentation in R/callbacks.R
-\name{xgb.cb.gblinear.history}
-\alias{xgb.cb.gblinear.history}
-\title{Callback for collecting coefficients history of a gblinear booster}
+\name{cb.gblinear.history}
+\alias{cb.gblinear.history}
+\title{Callback closure for collecting the model coefficients history of a gblinear booster
+during its training.}
 \usage{
-xgb.cb.gblinear.history(sparse = FALSE)
+cb.gblinear.history(sparse = FALSE)
 }
 \arguments{
-\item{sparse}{when set to \code{FALSE}/\code{TRUE}, a dense/sparse matrix is used to store the result.
+\item{sparse}{when set to FALSE/TURE, 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{
-An \code{xgb.Callback} object, which can be passed to \link{xgb.train} or \link{xgb.cv}.
+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.
+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.
 }
 \description{
-Callback for collecting coefficients history of a gblinear booster
+Callback closure for collecting the model coefficients history of a gblinear booster
+during its training.
 }
 \details{
 To keep things fast and simple, gblinear booster does not internally store the history of linear
 model coefficients at each boosting iteration. This callback provides a workaround for storing
 the coefficients' path, by extracting them after each training iteration.
 
-This callback will construct a matrix where rows are boosting iterations and columns are
-feature coefficients (same order as when calling \link{coef.xgb.Booster}, with the intercept
-corresponding to the first column).
-
-When there is more than one coefficient per feature (e.g. multi-class classification),
-the result will be reshaped into a vector where coefficients are arranged first by features and
-then by class (e.g. first 1 through N coefficients will be for the first class, then
-coefficients N+1 through 2N for the second class, and so on).
-
-If the result has only one coefficient per feature in the data, then the resulting matrix
-will have column names matching with the feature names, otherwise (when there's more than
-one coefficient per feature) the names will be composed as 'column name' + ':' + 'class index'
-(so e.g. column 'c1' for class '0' will be named 'c1:0').
-
-With \code{xgb.train}, the output is either a dense or a sparse matrix.
-With with \code{xgb.cv}, it is a list (one element per each fold) of such
-matrices.
-
-Function \link{xgb.gblinear.history} function provides an easy way to retrieve the
-outputs from this callback.
+Callback function expects the following values to be set in its calling frame:
+\code{bst} (or \code{bst_folds}).
 }
 \examples{
 #### Binary classification:
-
-## Keep the number of threads to 1 for examples
-nthread <- 1
-data.table::setDTthreads(nthread)
-
+#
 # 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$Species == "versicolor"), nthread = nthread)
+dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
 param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
-              lambda = 0.0003, alpha = 0.0003, nthread = nthread)
+              lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For 'shotgun', which is a default linear updater, using high eta values may result in
 # unstable behaviour in some datasets. With this simple dataset, however, the high learning
 # rate does not break the convergence, but allows us to illustrate the typical pattern of
 # "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
-                 callbacks = list(xgb.cb.gblinear.history()))
+                 callbacks = list(cb.gblinear.history()))
 # Extract the coefficients' path and plot them vs boosting iteration number:
 coef_path <- xgb.gblinear.history(bst)
 matplot(coef_path, type = 'l')
@@ -72,40 +56,40 @@ matplot(coef_path, type = 'l')
 # Will try the classical componentwise boosting which selects a single best feature per round:
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
-                 callbacks = list(xgb.cb.gblinear.history()))
-matplot(xgb.gblinear.history(bst), type = 'l')
+                 callbacks = list(cb.gblinear.history()))
+xgb.gblinear.history(bst) \%>\% matplot(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.
 
 # For xgb.cv:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-              callbacks = list(xgb.cb.gblinear.history()))
+             callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
-matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
+xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
 
 
 #### Multiclass classification:
 #
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = nthread)
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
 param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-              lambda = 0.0003, alpha = 0.0003, nthread = nthread)
+              lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For the default linear updater 'shotgun' it sometimes is helpful
 # to use smaller eta to reduce instability
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 50, eta = 0.5,
-                 callbacks = list(xgb.cb.gblinear.history()))
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
+                 callbacks = list(cb.gblinear.history()))
 # Will plot the coefficient paths separately for each class:
-matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
-matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
-matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
+xgb.gblinear.history(bst, class_index = 0) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 1) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 2) \%>\% matplot(type = 'l')
 
 # CV:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-              callbacks = list(xgb.cb.gblinear.history(FALSE)))
-# 1st fold of 1st class
-matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
+              callbacks = list(cb.gblinear.history(FALSE)))
+# 1st forld of 1st class
+xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
 
 }
 \seealso{
-\link{xgb.gblinear.history}, \link{coef.xgb.Booster}.
+\code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
 }

R-package/man/cb.print.evaluation.Rd

@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{cb.print.evaluation}
+\alias{cb.print.evaluation}
+\title{Callback closure for printing the result of evaluation}
+\usage{
+cb.print.evaluation(period = 1, showsd = TRUE)
+}
+\arguments{
+\item{period}{results would be printed every number of periods}
+
+\item{showsd}{whether standard deviations should be printed (when available)}
+}
+\description{
+Callback closure for printing the result of evaluation
+}
+\details{
+The callback function prints the result of evaluation at every \code{period} iterations.
+The initial and the last iteration's evaluations are always printed.
+
+Callback function expects the following values to be set in its calling frame:
+\code{bst_evaluation} (also \code{bst_evaluation_err} when available),
+\code{iteration},
+\code{begin_iteration},
+\code{end_iteration}.
+}
+\seealso{
+\code{\link{callbacks}}
+}

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

@@ -1,10 +1,10 @@
 % Generated by roxygen2: do not edit by hand
 % Please edit documentation in R/callbacks.R
-\name{xgb.cb.reset.parameters}
-\alias{xgb.cb.reset.parameters}
-\title{Callback for resetting the booster's parameters at each iteration.}
+\name{cb.reset.parameters}
+\alias{cb.reset.parameters}
+\title{Callback closure for resetting the booster's parameters at each iteration.}
 \usage{
-xgb.cb.reset.parameters(new_params)
+cb.reset.parameters(new_params)
 }
 \arguments{
 \item{new_params}{a list where each element corresponds to a parameter that needs to be reset.
@@ -14,16 +14,23 @@ or a function of two parameters \code{learning_rates(iteration, nrounds)}
 which returns a new parameter value by using the current iteration number
 and the total number of boosting rounds.}
 }
-\value{
-An \code{xgb.Callback} object, which can be passed to \link{xgb.train} or \link{xgb.cv}.
-}
 \description{
-Callback for resetting the booster's parameters at each iteration.
+Callback closure for resetting the booster's parameters at each iteration.
 }
 \details{
+This is a "pre-iteration" callback function used to reset booster's parameters
+at the beginning of each iteration.
+
 Note that when training is resumed from some previous model, and a function is used to
 reset a parameter value, the \code{nrounds} argument in this function would be the
 the number of boosting rounds in the current training.
 
-Does not leave any attribute in the booster.
+Callback function expects the following values to be set in its calling frame:
+\code{bst} or \code{bst_folds},
+\code{iteration},
+\code{begin_iteration},
+\code{end_iteration}.
+}
+\seealso{
+\code{\link{callbacks}}
 }

R-package/man/cb.save.model.Rd

@@ -0,0 +1,33 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{cb.save.model}
+\alias{cb.save.model}
+\title{Callback closure for saving a model file.}
+\usage{
+cb.save.model(save_period = 0, save_name = "xgboost.model")
+}
+\arguments{
+\item{save_period}{save the model to disk after every
+\code{save_period} iterations; 0 means save the model at the end.}
+
+\item{save_name}{the name or path for the saved model file.
+It can contain a \code{\link[base]{sprintf}} formatting specifier
+to include the integer iteration number in the file name.
+E.g., with \code{save_name} = 'xgboost_%04d.model',
+the file saved at iteration 50 would be named "xgboost_0050.model".}
+}
+\description{
+Callback closure for saving a model file.
+}
+\details{
+This callback function allows to save an xgb-model file, either periodically after each \code{save_period}'s or at the end.
+
+Callback function expects the following values to be set in its calling frame:
+\code{bst},
+\code{iteration},
+\code{begin_iteration},
+\code{end_iteration}.
+}
+\seealso{
+\code{\link{callbacks}}
+}

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

@@ -1,50 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{coef.xgb.Booster}
-\alias{coef.xgb.Booster}
-\title{Extract coefficients from linear booster}
-\usage{
-\method{coef}{xgb.Booster}(object, ...)
-}
-\arguments{
-\item{object}{A fitted booster of 'gblinear' type.}
-
-\item{...}{Not used.}
-}
-\value{
-The extracted coefficients:\itemize{
-\item If there's only one coefficient per column in the data, will be returned as a
-vector, potentially containing the feature names if available, with the intercept
-as first column.
-\item If there's more than one coefficient per column in the data (e.g. when using
-\code{objective="multi:softmax"}), will be returned as a matrix with dimensions equal
-to \verb{[num_features, num_cols]}, with the intercepts as first row. Note that the column
-(classes in multi-class classification) dimension will not be named.
-}
-
-The intercept returned here will include the 'base_score' parameter (unlike the 'bias'
-or the last coefficient in the model dump, which doesn't have 'base_score' added to it),
-hence one should get the same values from calling \code{predict(..., outputmargin = TRUE)} and
-from performing a matrix multiplication with \code{model.matrix(~., ...)}.
-
-Be aware that the coefficients are obtained by first converting them to strings and
-back, so there will always be some very small lose of precision compared to the actual
-coefficients as used by \link{predict.xgb.Booster}.
-}
-\description{
-Extracts the coefficients from a 'gblinear' booster object,
-as produced by \code{xgb.train} when using parameter \code{booster="gblinear"}.
-
-Note: this function will error out if passing a booster model
-which is not of "gblinear" type.
-}
-\examples{
-library(xgboost)
-data(mtcars)
-y <- mtcars[, 1]
-x <- as.matrix(mtcars[, -1])
-dm <- xgb.DMatrix(data = x, label = y, nthread = 1)
-params <- list(booster = "gblinear", nthread = 1)
-model <- xgb.train(data = dm, params = params, nrounds = 2)
-coef(model)
-}

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

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

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

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

R-package/man/getinfo.Rd

@@ -1,93 +1,45 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R, R/xgb.DMatrix.R
-\name{getinfo.xgb.Booster}
-\alias{getinfo.xgb.Booster}
-\alias{setinfo.xgb.Booster}
+% Please edit documentation in R/xgb.DMatrix.R
+\name{getinfo}
 \alias{getinfo}
 \alias{getinfo.xgb.DMatrix}
-\alias{setinfo}
-\alias{setinfo.xgb.DMatrix}
-\title{Get or set information of xgb.DMatrix and xgb.Booster objects}
+\title{Get information of an xgb.DMatrix object}
 \usage{
-\method{getinfo}{xgb.Booster}(object, name)
+getinfo(object, ...)
 
-\method{setinfo}{xgb.Booster}(object, name, info)
-
-getinfo(object, name)
-
-\method{getinfo}{xgb.DMatrix}(object, name)
-
-setinfo(object, name, info)
-
-\method{setinfo}{xgb.DMatrix}(object, name, info)
+\method{getinfo}{xgb.DMatrix}(object, name, ...)
 }
 \arguments{
-\item{object}{Object of class \code{xgb.DMatrix} of \code{xgb.Booster}.}
+\item{object}{Object of class \code{xgb.DMatrix}}
+
+\item{...}{other parameters}
 
 \item{name}{the name of the information field to get (see details)}
-
-\item{info}{the specific field of information to set}
-}
-\value{
-For \code{getinfo}, will return the requested field. For \code{setinfo}, will always return value \code{TRUE}
-if it succeeds.
 }
 \description{
-Get or set information of xgb.DMatrix and xgb.Booster objects
+Get information of an xgb.DMatrix object
 }
 \details{
-The \code{name} field can be one of the following for \code{xgb.DMatrix}:
+The \code{name} field can be one of the following:
 
 \itemize{
-\item \code{label}
-\item \code{weight}
-\item \code{base_margin}
-\item \code{label_lower_bound}
-\item \code{label_upper_bound}
-\item \code{group}
-\item \code{feature_type}
-\item \code{feature_name}
-\item \code{nrow}
-}
-See the documentation for \link{xgb.DMatrix} for more information about these fields.
+    \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{nrow}: number of rows of the \code{xgb.DMatrix}.
 
-For \code{xgb.Booster}, can be one of the following:
-\itemize{
-\item \code{feature_type}
-\item \code{feature_name}
 }
 
-Note that, while 'qid' cannot be retrieved, it's possible to get the equivalent 'group'
-for a DMatrix that had 'qid' assigned.
-
-\bold{Important}: when calling \code{setinfo}, the objects are modified in-place. See
-\link{xgb.copy.Booster} for an idea of this in-place assignment works.
-
-See the documentation for \link{xgb.DMatrix} for possible fields that can be set
-(which correspond to arguments in that function).
-
-Note that the following fields are allowed in the construction of an \code{xgb.DMatrix}
-but \bold{aren't} allowed here:\itemize{
-\item data
-\item missing
-\item silent
-\item nthread
-}
+\code{group} can be setup by \code{setinfo} but can't be retrieved by \code{getinfo}.
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+train <- agaricus.train
+dtrain <- xgb.DMatrix(train$data, label=train$label)
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)
 
 labels2 <- getinfo(dtrain, 'label')
 stopifnot(all(labels2 == 1-labels))
-data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
-
-labels <- getinfo(dtrain, 'label')
-setinfo(dtrain, 'label', 1-labels)
-labels2 <- getinfo(dtrain, 'label')
-stopifnot(all.equal(labels2, 1-labels))
 }

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

@@ -2,157 +2,97 @@
 % Please edit documentation in R/xgb.Booster.R
 \name{predict.xgb.Booster}
 \alias{predict.xgb.Booster}
-\title{Predict method for XGBoost model}
+\alias{predict.xgb.Booster.handle}
+\title{Predict method for eXtreme Gradient Boosting model}
 \usage{
 \method{predict}{xgb.Booster}(
   object,
   newdata,
   missing = NA,
   outputmargin = FALSE,
+  ntreelimit = NULL,
   predleaf = FALSE,
   predcontrib = FALSE,
   approxcontrib = FALSE,
   predinteraction = FALSE,
   reshape = FALSE,
   training = FALSE,
-  iterationrange = NULL,
-  strict_shape = FALSE,
-  validate_features = FALSE,
-  base_margin = NULL,
   ...
 )
+
+\method{predict}{xgb.Booster.handle}(object, ...)
 }
 \arguments{
-\item{object}{Object of class \code{xgb.Booster}.}
+\item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
 
-\item{newdata}{Takes \code{data.frame}, \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-local data file, or \code{xgb.DMatrix}.
+\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.}
 
-\if{html}{\out{<div class="sourceCode">}}\preformatted{   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).}
 
-   Note that, for repeated predictions on the same data, one might want to create a DMatrix to
-   pass here instead of passing R types like matrices or data frames, as predictions will be
-   faster on DMatrix.
-
-   If `newdata` is a `data.frame`, be aware that:\\itemize\{
-   \\item Columns will be converted to numeric if they aren't already, which could potentially make
-         the operation slower than in an equivalent `matrix` object.
-   \\item The order of the columns must match with that of the data from which the model was fitted
-         (i.e. columns will not be referenced by their names, just by their order in the data).
-   \\item If the model was fitted to data with categorical columns, these columns must be of
-         `factor` type here, and must use the same encoding (i.e. have the same levels).
-   \\item If `newdata` contains any `factor` columns, they will be converted to base-0
-         encoding (same as during DMatrix creation) - hence, one should not pass a `factor`
-         under a column which during training had a different type.
-   \}
-}\if{html}{\out{</div>}}}
-
-\item{missing}{Float value that represents missing values in data (e.g., 0 or some other extreme value).
-
-\if{html}{\out{<div class="sourceCode">}}\preformatted{   This parameter is not used when `newdata` is an `xgb.DMatrix` - in such cases, should pass
-   this as an argument to the DMatrix constructor instead.
-}\if{html}{\out{</div>}}}
-
-\item{outputmargin}{Whether the prediction should be returned in the form of original untransformed
+\item{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 return log-odds instead of probabilities.}
+logistic regression would result in predictions for log-odds instead of probabilities.}
 
-\item{predleaf}{Whether to predict per-tree leaf indices.}
+\item{ntreelimit}{limit the number of model's trees or boosting iterations used in prediction (see Details).
+It will use all the trees by default (\code{NULL} value).}
 
-\item{predcontrib}{Whether to return feature contributions to individual predictions (see Details).}
+\item{predleaf}{whether predict leaf index.}
 
-\item{approxcontrib}{Whether to use a fast approximation for feature contributions (see Details).}
+\item{predcontrib}{whether to return feature contributions to individual predictions (see Details).}
 
-\item{predinteraction}{Whether to return contributions of feature interactions to individual predictions (see Details).}
+\item{approxcontrib}{whether to use a fast approximation for feature contributions (see Details).}
 
-\item{reshape}{Whether to reshape the vector of predictions to matrix form when there are several
-prediction outputs per case. No effect if \code{predleaf}, \code{predcontrib},
-or \code{predinteraction} is \code{TRUE}.}
+\item{predinteraction}{whether to return contributions of feature interactions to individual predictions (see Details).}
 
-\item{training}{Whether the prediction result is used for training. For dart booster,
+\item{reshape}{whether to reshape the vector of predictions to a matrix form when there are several
+prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
+or predinteraction flags is TRUE.}
+
+\item{training}{whether is the prediction result used for training.  For dart booster,
 training predicting will perform dropout.}
 
-\item{iterationrange}{Sequence of rounds/iterations from the model to use for prediction, specified by passing
-a two-dimensional vector with the start and end numbers in the sequence (same format as R's \code{seq} - i.e.
-base-1 indexing, and inclusive of both ends).
-
-\if{html}{\out{<div class="sourceCode">}}\preformatted{   For example, passing `c(1,20)` will predict using the first twenty iterations, while passing `c(1,1)` will
-   predict using only the first one.
-
-   If passing `NULL`, will either stop at the best iteration if the model used early stopping, or use all
-   of the iterations (rounds) otherwise.
-
-   If passing "all", will use all of the rounds regardless of whether the model had early stopping or not.
-}\if{html}{\out{</div>}}}
-
-\item{strict_shape}{Default is \code{FALSE}. When set to \code{TRUE}, the output
-type and shape of predictions are invariant to the model type.}
-
-\item{validate_features}{When \code{TRUE}, validate that the Booster's and newdata's feature_names
-match (only applicable when both \code{object} and \code{newdata} have feature names).
-
-\if{html}{\out{<div class="sourceCode">}}\preformatted{   If the column names differ and `newdata` is not an `xgb.DMatrix`, will try to reorder
-   the columns in `newdata` to match with the booster's.
-
-   If the booster has feature types and `newdata` is either an `xgb.DMatrix` or `data.frame`,
-   will additionally verify that categorical columns are of the correct type in `newdata`,
-   throwing an error if they do not match.
-
-   If passing `FALSE`, it is assumed that the feature names and types are the same,
-   and come in the same order as in the training data.
-
-   Note that this check might add some sizable latency to the predictions, so it's
-   recommended to disable it for performance-sensitive applications.
-}\if{html}{\out{</div>}}}
-
-\item{base_margin}{Base margin used for boosting from existing model.
-
-\if{html}{\out{<div class="sourceCode">}}\preformatted{   Note that, if `newdata` is an `xgb.DMatrix` object, this argument will
-   be ignored as it needs to be added to the DMatrix instead (e.g. by passing it as
-   an argument in its constructor, or by calling \link{setinfo.xgb.DMatrix}).
-}\if{html}{\out{</div>}}}
-
-\item{...}{Not used.}
+\item{...}{Parameters passed to \code{predict.xgb.Booster}}
 }
 \value{
-The return type depends on \code{strict_shape}. If \code{FALSE} (default):
-\itemize{
-\item For regression or binary classification: A vector of length \code{nrows(newdata)}.
-\item For multiclass classification: A vector of length \code{num_class * nrows(newdata)} or
-a \verb{(nrows(newdata), num_class)} matrix, depending on the \code{reshape} value.
-\item When \code{predleaf = TRUE}: A matrix with one column per tree.
-\item When \code{predcontrib = TRUE}: When not multiclass, a matrix with
-\code{ num_features + 1} columns. The last "+ 1" column corresponds to the baseline value.
-In the multiclass case, a list of \code{num_class} such matrices.
-The contribution values are on the scale of untransformed margin
-(e.g., for binary classification, the values are log-odds deviations from the baseline).
-\item When \code{predinteraction = TRUE}: When not multiclass, the output is a 3d array of
-dimension \code{c(nrow, num_features + 1, num_features + 1)}. The off-diagonal (in the last two dimensions)
-elements represent different feature interaction contributions. The array is symmetric WRT the last
-two dimensions. The "+ 1" columns corresponds to the baselines. Summing this array along the last dimension should
-produce practically the same result as \code{predcontrib = TRUE}.
-In the multiclass case, a list of \code{num_class} such arrays.
-}
+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.
 
-When \code{strict_shape = TRUE}, the output is always an array:
-\itemize{
-\item For normal predictions, the output has dimension \verb{(num_class, nrow(newdata))}.
-\item For \code{predcontrib = TRUE}, the dimension is \verb{(ncol(newdata) + 1, num_class, nrow(newdata))}.
-\item For \code{predinteraction = TRUE}, the dimension is \verb{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}.
-\item For \code{predleaf = TRUE}, the dimension is \verb{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}.
-}
+When \code{predleaf = TRUE}, the output is a matrix object with the
+number of columns corresponding to the number of trees.
+
+When \code{predcontrib = TRUE} and it is not a multiclass setting, the output is a matrix object with
+\code{num_features + 1} columns. The last "+ 1" column in a matrix corresponds to bias.
+For a multiclass case, a list of \code{num_class} elements is returned, where each element is
+such a matrix. The contribution values are on the scale of untransformed margin
+(e.g., for binary classification would mean that the contributions are log-odds deviations from bias).
+
+When \code{predinteraction = TRUE} and it is not a multiclass setting, the output is a 3d array with
+dimensions \code{c(nrow, num_features + 1, num_features + 1)}. The off-diagonal (in the last two dimensions)
+elements represent different features interaction contributions. The array is symmetric WRT the last
+two dimensions. The "+ 1" columns corresponds to bias. Summing this array along the last dimension should
+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.
 }
 \description{
-Predict values on data based on xgboost model.
+Predicted values based on either xgboost model or model handle object.
 }
 \details{
-Note that \code{iterationrange} would currently do nothing for predictions from "gblinear",
-since "gblinear" doesn't keep its boosting history.
+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,
+since gblinear doesn't keep its boosting history.
 
 One possible practical applications of the \code{predleaf} option is to use the model
 as a generator of new features which capture non-linearity and interactions,
-e.g., as implemented in \code{\link[=xgb.create.features]{xgb.create.features()}}.
+e.g., as implemented in \code{\link{xgb.create.features}}.
 
 Setting \code{predcontrib = TRUE} allows to calculate contributions of each feature to
 individual predictions. For "gblinear" booster, feature contributions are simply linear terms
@@ -166,37 +106,21 @@ 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, assign a new number to \code{nthread} using \code{\link[=xgb.parameters<-]{xgb.parameters<-()}}.
-Note that converting a matrix to \code{\link[=xgb.DMatrix]{xgb.DMatrix()}} uses multiple threads too.
 }
 \examples{
 ## binary classification:
 
-data(agaricus.train, package = "xgboost")
-data(agaricus.test, package = "xgboost")
-
-## Keep the number of threads to 2 for examples
-nthread <- 2
-data.table::setDTthreads(nthread)
-
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
 
-bst <- xgb.train(
-  data = xgb.DMatrix(train$data, label = train$label),
-  max_depth = 2,
-  eta = 0.5,
-  nthread = nthread,
-  nrounds = 5,
-  objective = "binary:logistic"
-)
-
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+               eta = 0.5, nthread = 2, nrounds = 5, objective = "binary:logistic")
 # use all trees by default
 pred <- predict(bst, test$data)
 # use only the 1st tree
-pred1 <- predict(bst, test$data, iterationrange = c(1, 1))
+pred1 <- predict(bst, test$data, ntreelimit = 1)
 
 # Predicting tree leafs:
 # the result is an nsamples X ntrees matrix
@@ -224,61 +148,55 @@ par(mar = old_mar)
 
 lb <- as.numeric(iris$Species) - 1
 num_class <- 3
-
 set.seed(11)
-
-bst <- xgb.train(
-  data = xgb.DMatrix(as.matrix(iris[, -5]), label = lb),
-  max_depth = 4,
-  eta = 0.5,
-  nthread = 2,
-  nrounds = 10,
-  subsample = 0.5,
-  objective = "multi:softprob",
-  num_class = num_class
-)
-
+bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
+               max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
+               objective = "multi:softprob", num_class = num_class)
 # predict for softmax returns num_class probability numbers per case:
 pred <- predict(bst, as.matrix(iris[, -5]))
 str(pred)
 # reshape it to a num_class-columns matrix
-pred <- matrix(pred, ncol = num_class, byrow = TRUE)
+pred <- matrix(pred, ncol=num_class, byrow=TRUE)
 # convert the probabilities to softmax labels
 pred_labels <- max.col(pred) - 1
 # the following should result in the same error as seen in the last iteration
-sum(pred_labels != lb) / length(lb)
+sum(pred_labels != lb)/length(lb)
 
-# compare with predictions from softmax:
+# compare that to the predictions from softmax:
 set.seed(11)
-
-bst <- xgb.train(
-  data = xgb.DMatrix(as.matrix(iris[, -5]), label = lb),
-  max_depth = 4,
-  eta = 0.5,
-  nthread = 2,
-  nrounds = 10,
-  subsample = 0.5,
-  objective = "multi:softmax",
-  num_class = num_class
-)
-
+bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
+               max_depth = 4, eta = 0.5, nthread = 2, nrounds = 10, subsample = 0.5,
+               objective = "multi:softmax", num_class = num_class)
 pred <- predict(bst, as.matrix(iris[, -5]))
 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]), iterationrange = c(1, 5))
-sum(pred5 != lb) / length(lb)
+pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
+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{
-\enumerate{
-\item Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions",
-NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
-\item Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles",
-\url{https://arxiv.org/abs/1706.06060}
-}
+Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}
+
+Scott M. Lundberg, Su-In Lee, "Consistent feature attribution for tree ensembles", \url{https://arxiv.org/abs/1706.06060}
 }
 \seealso{
-\code{\link[=xgb.train]{xgb.train()}}
+\code{\link{xgb.train}}.
 }

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

@@ -4,35 +4,26 @@
 \alias{print.xgb.Booster}
 \title{Print xgb.Booster}
 \usage{
-\method{print}{xgb.Booster}(x, ...)
+\method{print}{xgb.Booster}(x, verbose = FALSE, ...)
 }
 \arguments{
-\item{x}{An \code{xgb.Booster} object.}
+\item{x}{an xgb.Booster object}
 
-\item{...}{Not used.}
-}
-\value{
-The same \code{x} object, returned invisibly
+\item{verbose}{whether to print detailed data (e.g., attribute values)}
+
+\item{...}{not currently used}
 }
 \description{
-Print information about \code{xgb.Booster}.
+Print information about xgb.Booster.
 }
 \examples{
-data(agaricus.train, package = "xgboost")
+data(agaricus.train, package='xgboost')
 train <- agaricus.train
-
-bst <- xgboost(
-  data = train$data,
-  label = train$label,
-  max_depth = 2,
-  eta = 1,
-  nthread = 2,
-  nrounds = 2,
-  objective = "binary:logistic"
-)
-
-attr(bst, "myattr") <- "memo"
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+attr(bst, 'myattr') <- 'memo'
 
 print(bst)
+print(bst, verbose=TRUE)
 
 }

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

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

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

@@ -23,8 +23,8 @@ including the best iteration (when available).
 \examples{
 data(agaricus.train, package='xgboost')
 train <- agaricus.train
-cv <- xgb.cv(data = xgb.DMatrix(train$data, label = train$label), nfold = 5, max_depth = 2,
-             eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+cv <- xgb.cv(data = train$data, label = train$label, nfold = 5, max_depth = 2,
+               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 print(cv)
 print(cv, verbose=TRUE)
 

R-package/man/setinfo.Rd

@@ -0,0 +1,43 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.DMatrix.R
+\name{setinfo}
+\alias{setinfo}
+\alias{setinfo.xgb.DMatrix}
+\title{Set information of an xgb.DMatrix object}
+\usage{
+setinfo(object, ...)
+
+\method{setinfo}{xgb.DMatrix}(object, name, info, ...)
+}
+\arguments{
+\item{object}{Object of class "xgb.DMatrix"}
+
+\item{...}{other parameters}
+
+\item{name}{the name of the field to get}
+
+\item{info}{the specific field of information to set}
+}
+\description{
+Set information of an xgb.DMatrix object
+}
+\details{
+The \code{name} field can be one of the following:
+
+\itemize{
+    \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{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
+}
+}
+\examples{
+data(agaricus.train, package='xgboost')
+train <- agaricus.train
+dtrain <- xgb.DMatrix(train$data, label=train$label)
+
+labels <- getinfo(dtrain, 'label')
+setinfo(dtrain, 'label', 1-labels)
+labels2 <- getinfo(dtrain, 'label')
+stopifnot(all.equal(labels2, 1-labels))
+}

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

@@ -1,23 +1,24 @@
 % Generated by roxygen2: do not edit by hand
 % Please edit documentation in R/xgb.DMatrix.R
-\name{xgb.slice.DMatrix}
-\alias{xgb.slice.DMatrix}
+\name{slice}
+\alias{slice}
+\alias{slice.xgb.DMatrix}
 \alias{[.xgb.DMatrix}
 \title{Get a new DMatrix containing the specified rows of
 original xgb.DMatrix object}
 \usage{
-xgb.slice.DMatrix(object, idxset, allow_groups = FALSE)
+slice(object, ...)
+
+\method{slice}{xgb.DMatrix}(object, idxset, ...)
 
 \method{[}{xgb.DMatrix}(object, idxset, colset = NULL)
 }
 \arguments{
-\item{object}{Object of class "xgb.DMatrix".}
+\item{object}{Object of class "xgb.DMatrix"}
 
-\item{idxset}{An integer vector of indices of rows needed (base-1 indexing).}
+\item{...}{other parameters (currently not used)}
 
-\item{allow_groups}{Whether to allow slicing an \code{xgb.DMatrix} with \code{group} (or
-equivalently \code{qid}) field. Note that in such case, the result will not have
-the groups anymore - they need to be set manually through \code{setinfo}.}
+\item{idxset}{a integer vector of indices of rows needed}
 
 \item{colset}{currently not used (columns subsetting is not available)}
 }
@@ -27,9 +28,10 @@ original xgb.DMatrix object
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+train <- agaricus.train
+dtrain <- xgb.DMatrix(train$data, label=train$label)
 
-dsub <- xgb.slice.DMatrix(dtrain, 1:42)
+dsub <- slice(dtrain, 1:42)
 labels1 <- getinfo(dsub, 'label')
 dsub <- dtrain[1:42, ]
 labels2 <- getinfo(dsub, 'label')

R-package/man/variable.names.xgb.Booster.Rd

@@ -1,22 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{variable.names.xgb.Booster}
-\alias{variable.names.xgb.Booster}
-\title{Get Features Names from Booster}
-\usage{
-\method{variable.names}{xgb.Booster}(object, ...)
-}
-\arguments{
-\item{object}{An \code{xgb.Booster} object.}
-
-\item{...}{Not used.}
-}
-\description{
-Returns the feature / variable / column names from a fitted
-booster object, which are set automatically during the call to \link{xgb.train}
-from the DMatrix names, or which can be set manually through \link{setinfo}.
-
-If the object doesn't have feature names, will return \code{NULL}.
-
-It is equivalent to calling \code{getinfo(object, "feature_name")}.
-}

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

@@ -0,0 +1,50 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.Booster.R
+\name{xgb.Booster.complete}
+\alias{xgb.Booster.complete}
+\title{Restore missing parts of an incomplete xgb.Booster object.}
+\usage{
+xgb.Booster.complete(object, saveraw = TRUE)
+}
+\arguments{
+\item{object}{object of class \code{xgb.Booster}}
+
+\item{saveraw}{a flag indicating whether to append \code{raw} Booster memory dump data
+when it doesn't already exist.}
+}
+\value{
+An object of \code{xgb.Booster} class.
+}
+\description{
+It attempts to complete an \code{xgb.Booster} object by restoring either its missing
+raw model memory dump (when it has no \code{raw} data but its \code{xgb.Booster.handle} is valid)
+or its missing internal handle (when its \code{xgb.Booster.handle} is not valid
+but it has a raw Booster memory dump).
+}
+\details{
+While this method is primarily for internal use, it might be useful in some practical situations.
+
+E.g., when an \code{xgb.Booster} model is saved as an R object and then is loaded as an R object,
+its handle (pointer) to an internal xgboost model would be invalid. The majority of xgboost methods
+should still work for such a model object since those methods would be using
+\code{xgb.Booster.complete} internally. However, one might find it to be more efficient to call the
+\code{xgb.Booster.complete} function explicitly once after loading a model as an R-object.
+That would prevent further repeated implicit reconstruction of an internal booster model.
+}
+\examples{
+
+data(agaricus.train, package='xgboost')
+bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
+               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+saveRDS(bst, "xgb.model.rds")
+
+bst1 <- readRDS("xgb.model.rds")
+if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
+# the handle is invalid:
+print(bst1$handle)
+
+bst1 <- xgb.Booster.complete(bst1)
+# now the handle points to a valid internal booster model:
+print(bst1$handle)
+
+}