add dump nice to regression demo

.clang-format

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

.clang-tidy

@@ -1,21 +0,0 @@
-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  }
-  - { key: readability-identifier-naming.TypeAliasCase,             value: CamelCase  }
-  - { key: readability-identifier-naming.TypedefCase,               value: CamelCase  }
-  - { key: readability-identifier-naming.TypeTemplateParameterCase, value: CamelCase  }
-  - { key: readability-identifier-naming.MemberCase,                value: lower_case }
-  - { key: readability-identifier-naming.PrivateMemberSuffix,       value: '_'        }
-  - { key: readability-identifier-naming.ProtectedMemberSuffix,     value: '_'        }
-  - { key: readability-identifier-naming.EnumCase,                  value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstant,              value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstantPrefix,        value: k          }
-  - { key: readability-identifier-naming.GlobalConstantCase,        value: CamelCase  }
-  - { key: readability-identifier-naming.GlobalConstantPrefix,      value: k          }
-  - { key: readability-identifier-naming.StaticConstantCase,        value: CamelCase  }
-  - { key: readability-identifier-naming.StaticConstantPrefix,      value: k          }
-  - { key: readability-identifier-naming.ConstexprVariableCase,     value: CamelCase  }
-  - { key: readability-identifier-naming.ConstexprVariablePrefix,   value: k          }
-  - { key: readability-identifier-naming.FunctionCase,              value: CamelCase  }
-  - { key: readability-identifier-naming.NamespaceCase,             value: lower_case }

.editorconfig

@@ -1,11 +0,0 @@
-root = true
-
-[*]
-charset=utf-8
-indent_style = space
-indent_size = 2
-insert_final_newline = true
-
-[*.py]
-indent_style = space
-indent_size = 4

.github/FUNDING.yml

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

.github/ISSUE_TEMPLATE.md

@@ -1,7 +0,0 @@
-Thanks for participating in the XGBoost community! We use https://discuss.xgboost.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion, roadmaps, and bug tracking.  You are always welcomed to post on the forum first :)
-
-Issues that are inactive for a period of time may get closed. We adopt this policy so that we won't lose track of actionable issues that may fall at the bottom of the pile. Feel free to reopen a new one if you feel there is an additional problem that needs attention when an old one gets closed.
-
-For bug reports, to help the developer act on the issues, please include a description of your environment, preferably a minimum script to reproduce the problem.
-
-For feature proposals, list clear, small actionable items so we can track the progress of the change.

.github/lock.yml

@@ -1,32 +0,0 @@
-# Configuration for lock-threads - https://github.com/dessant/lock-threads
-
-# Number of days of inactivity before a closed issue or pull request is locked
-daysUntilLock: 90
-
-# Issues and pull requests with these labels will not be locked. Set to `[]` to disable
-exemptLabels:
-  - feature-request
-
-# Label to add before locking, such as `outdated`. Set to `false` to disable
-lockLabel: false
-
-# Comment to post before locking. Set to `false` to disable
-lockComment: false
-
-# Assign `resolved` as the reason for locking. Set to `false` to disable
-setLockReason: true
-
-# Limit to only `issues` or `pulls`
-# only: issues
-
-# Optionally, specify configuration settings just for `issues` or `pulls`
-# issues:
-#   exemptLabels:
-#     - help-wanted
-#   lockLabel: outdated
-
-# pulls:
-#   daysUntilLock: 30
-
-# Repository to extend settings from
-# _extends: repo

.github/workflows/jvm_tests.yml

@@ -1,77 +0,0 @@
-name: XGBoost-JVM-Tests
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-jobs:
-  test-with-jvm:
-    name: Test JVM on OS ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [windows-latest, ubuntu-latest, macos-11]
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-        architecture: 'x64'
-
-    - uses: actions/setup-java@v1
-      with:
-        java-version: 1.8
-
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-
-    - name: Cache Maven packages
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2
-        key: ${{ runner.os }}-m2-${{ hashFiles('./jvm-packages/pom.xml') }}
-        restore-keys: ${{ runner.os }}-m2
-
-    - name: Test XGBoost4J
-      run: |
-        cd jvm-packages
-        mvn test -B -pl :xgboost4j_2.12
-
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-
-    - name: Publish artifact xgboost4j.dll to S3
-      run: |
-        cd lib/
-        Rename-Item -Path xgboost4j.dll -NewName xgboost4j_${{ github.sha }}.dll
-        dir
-        python -m awscli s3 cp xgboost4j_${{ github.sha }}.dll s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'windows-latest'
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-
-    - name: Test XGBoost4J-Spark
-      run: |
-        rm -rfv build/
-        cd jvm-packages
-        mvn -B test
-      if: matrix.os == 'ubuntu-latest'  # Distributed training doesn't work on Windows
-      env:
-        RABIT_MOCK: ON

.github/workflows/main.yml

@@ -1,213 +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)
-
-# 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@v2
-      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 -DPLUGIN_DENSE_PARSER=ON -GNinja
-        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@v2
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -GNinja -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON -DUSE_OPENMP=OFF
-        ninja -v
-    - name: Run gtest binary
-      run: |
-        cd build
-        ctest --extra-verbose
-
-  c-api-demo:
-    name: Test installing XGBoost lib + building the C API demo
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost static library
-      shell: bash -l {0}
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-        ninja -v install
-        cd -
-    - name: Build and run C API demo with static
-      shell: bash -l {0}
-      run: |
-        pushd .
-        cd demo/c-api/
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v
-        ctest
-        cd ..
-        rm -rf ./build
-        popd
-    - name: Build and install XGBoost shared library
-      shell: bash -l {0}
-      run: |
-        cd build
-        cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
-        ninja -v install
-        cd -
-    - name: Build and run C API demo with shared
-      shell: bash -l {0}
-      run: |
-        pushd .
-        cd demo/c-api/
-        mkdir build
-        cd build
-        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja -v
-        ctest
-        popd
-        ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
-        ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
-
-  lint:
-    runs-on: ubuntu-latest
-    name: Code linting for C++
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools cpplint pylint
-    - name: Run lint
-      run: |
-        LINT_LANG=cpp make lint
-
-  doxygen:
-    runs-on: ubuntu-latest
-    name: Generate C/C++ API doc using Doxygen
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends doxygen graphviz ninja-build
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-    - name: Run Doxygen
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_C_DOC=ON -GNinja
-        ninja -v doc_doxygen
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Publish
-      run: |
-        cd build/
-        tar cvjf ${{ steps.extract_branch.outputs.branch }}.tar.bz2 doc_doxygen/
-        python -m awscli s3 cp ./${{ steps.extract_branch.outputs.branch }}.tar.bz2 s3://xgboost-docs/doxygen/ --acl public-read
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-  sphinx:
-    runs-on: ubuntu-latest
-    name: Build docs using Sphinx
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends graphviz
-        python -m pip install wheel setuptools
-        python -m pip install -r doc/requirements.txt
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Run Sphinx
-      run: |
-        make -C doc html
-      env:
-        SPHINX_GIT_BRANCH: ${{ steps.extract_branch.outputs.branch }}

.github/workflows/python_tests.yml

@@ -1,180 +0,0 @@
-name: XGBoost-Python-Tests
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-jobs:
-  python-mypy-lint:
-    runs-on: ubuntu-latest
-    name: Type and format checks for the Python package
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: python_lint
-        environment-file: tests/ci_build/conda_env/python_lint.yml
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Run mypy
-      shell: bash -l {0}
-      run: |
-        python tests/ci_build/lint_python.py --format=0 --type-check=1 --pylint=0
-    - name: Run formatter
-      shell: bash -l {0}
-      run: |
-        python tests/ci_build/lint_python.py --format=1 --type-check=0 --pylint=0
-    - name: Run pylint
-      shell: bash -l {0}
-      run: |
-        python tests/ci_build/lint_python.py --format=0 --type-check=0 --pylint=1
-
-  python-sdist-test:
-    runs-on: ${{ matrix.os }}
-    name: Test installing XGBoost Python source package on ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-11, windows-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install osx system dependencies
-      if: matrix.os == 'macos-11'
-      run: |
-        brew install ninja libomp
-    - name: Install Ubuntu system dependencies
-      if: matrix.os == 'ubuntu-latest'
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py sdist
-        pip install -v ./dist/xgboost-*.tar.gz
-        cd ..
-        python -c 'import xgboost'
-
-  python-tests-on-win:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    strategy:
-      matrix:
-        config:
-          - {os: windows-latest, python-version: '3.8'}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.config.python-version }}
-        activate-environment: win64_env
-        environment-file: tests/ci_build/conda_env/win64_cpu_test.yml
-
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on Windows
-      shell: bash -l {0}
-      run: |
-        mkdir build_msvc
-        cd build_msvc
-        cmake .. -G"Visual Studio 17 2022" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
-        cmake --build . --config Release --parallel $(nproc)
-
-    - name: Install Python package
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py bdist_wheel --universal
-        pip install ./dist/*.whl
-
-    - name: Test Python package
-      shell: bash -l {0}
-      run: |
-        pytest -s -v ./tests/python
-
-  python-tests-on-macos:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 90
-    strategy:
-      matrix:
-        config:
-          - {os: macos-11, python-version "3.8" }
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.config.python-version }}
-        activate-environment: macos_test
-        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
-
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on macos
-      shell: bash -l {0}
-      run: |
-        brew install ninja
-
-        mkdir build
-        cd build
-        # Set prefix, to use OpenMP library from Conda env
-        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
-        # to learn why we don't use libomp from Homebrew.
-        cmake .. -GNinja -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja
-
-    - name: Install Python package
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py install
-
-    - name: Test Python package
-      shell: bash -l {0}
-      run: |
-        pytest -s -v ./tests/python

.github/workflows/python_wheels.yml

@@ -1,41 +0,0 @@
-name: XGBoost-Python-Wheels
-
-on: [push, pull_request]
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-jobs:
-  python-wheels:
-    name: Build wheel for ${{ matrix.platform_id }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        include:
-        - os: macos-latest
-          platform_id: macosx_x86_64
-        - os: macos-latest
-          platform_id: macosx_arm64
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Setup Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-    - name: Build wheels
-      run: bash tests/ci_build/build_python_wheels.sh ${{ matrix.platform_id }} ${{ github.sha }}
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Upload Python wheel
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      run: |
-        python -m pip install awscli
-        python -m awscli s3 cp wheelhouse/*.whl s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}

.github/workflows/r_nold.yml

@@ -1,47 +0,0 @@
-# Run R tests with noLD R. Only triggered by a pull request review
-# See discussion at https://github.com/dmlc/xgboost/pull/6378
-
-name: XGBoost-R-noLD
-
-on:
-  pull_request_review_comment:
-    types: [created]
-
-env:
-  R_PACKAGES: c('XML', 'igraph', 'data.table', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-jobs:
-  test-R-noLD:
-    if: github.event.comment.body == '/gha run r-nold-test' && contains('OWNER,MEMBER,COLLABORATOR', github.event.comment.author_association)
-    timeout-minutes: 120
-    runs-on: ubuntu-latest
-    container: rhub/debian-gcc-devel-nold
-    steps:
-    - name: Install git and system packages
-      shell: bash
-      run: |
-        apt-get update && apt-get install -y git libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev libxml2-dev
-
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - name: Install dependencies
-      shell: bash
-      run: |
-        cat > install_libs.R <<EOT
-          install.packages(${{ env.R_PACKAGES }},
-                           repos = 'http://cloud.r-project.org',
-                           dependencies = c('Depends', 'Imports', 'LinkingTo'))
-        EOT
-        /tmp/R-devel/bin/Rscript install_libs.R
-
-    - name: Run R tests
-      shell: bash
-      run: |
-        cd R-package && \
-        /tmp/R-devel/bin/R CMD INSTALL . && \
-        /tmp/R-devel/bin/R -q -e "library(testthat); setwd('tests'); source('testthat.R')"

.github/workflows/r_tests.yml

@@ -1,158 +0,0 @@
-name: XGBoost-R-Tests
-
-on: [push, pull_request]
-
-env:
-  R_PACKAGES: c('XML', 'data.table', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
-  GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
-
-permissions:
-  contents: read # to fetch code (actions/checkout)
-
-jobs:
-  lintr:
-    runs-on: ${{ matrix.config.os }}
-    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@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@v2
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-    - name: Install igraph on Windows
-      shell: Rscript {0}
-      if: matrix.config.os == 'windows-latest'
-      run: |
-        install.packages('igraph', type='binary')
-
-    - name: Run lintr
-      run: |
-        cd R-package
-        R CMD INSTALL .
-        # Disable lintr errors for now: https://github.com/dmlc/xgboost/issues/8012
-        Rscript tests/helper_scripts/run_lint.R || true
-
-  test-with-R:
-    runs-on: ${{ matrix.config.os }}
-    name: Test R on OS ${{ matrix.config.os }}, R ${{ matrix.config.r }}, Compiler ${{ matrix.config.compiler }}, Build ${{ matrix.config.build }}
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'cmake'}
-          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
-    env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@v2
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      if: matrix.config.os != 'windows-latest'
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Install binary dependencies
-      shell: Rscript {0}
-      if: matrix.config.os == 'windows-latest'
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         type = 'binary',
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: "3.8"
-        architecture: 'x64'
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool='${{ matrix.config.build }}'
-
-  test-R-CRAN:
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {r: 'release'}
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: r-lib/actions/setup-r@v2
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - uses: r-lib/actions/setup-tinytex@v2
-
-    - name: Install system packages
-      run: |
-        sudo apt-get update && sudo apt-get install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev pandoc pandoc-citeproc libglpk-dev
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-5-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-        install.packages('igraph', repos = 'http://cloud.r-project.org', dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Check R Package
-      run: |
-        # Print stacktrace upon success of failure
-        make Rcheck || tests/ci_build/print_r_stacktrace.sh fail
-        tests/ci_build/print_r_stacktrace.sh success

.github/workflows/scorecards.yml

@@ -1,54 +0,0 @@
-name: Scorecards supply-chain security
-on:
-  # Only the default branch is supported.
-  branch_protection_rule:
-  schedule:
-    - cron: '17 2 * * 6'
-  push:
-    branches: [ "master" ]
-
-# Declare default permissions as read only.
-permissions: read-all
-
-jobs:
-  analysis:
-    name: Scorecards analysis
-    runs-on: ubuntu-latest
-    permissions:
-      # Needed to upload the results to code-scanning dashboard.
-      security-events: write
-      # Used to receive a badge.
-      id-token: write
-
-    steps:
-      - name: "Checkout code"
-        uses: actions/checkout@a12a3943b4bdde767164f792f33f40b04645d846 # tag=v3.0.0
-        with:
-          persist-credentials: false
-
-      - name: "Run analysis"
-        uses: ossf/scorecard-action@865b4092859256271290c77adbd10a43f4779972 # tag=v2.0.3
-        with:
-          results_file: results.sarif
-          results_format: sarif
-
-          # Publish the results for public repositories to enable scorecard badges. For more details, see
-          # https://github.com/ossf/scorecard-action#publishing-results. 
-          # For private repositories, `publish_results` will automatically be set to `false`, regardless 
-          # of the value entered here.
-          publish_results: true
-
-      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
-      # format to the repository Actions tab.
-      - name: "Upload artifact"
-        uses: actions/upload-artifact@6673cd052c4cd6fcf4b4e6e60ea986c889389535 # tag=v3.0.0
-        with:
-          name: SARIF file
-          path: results.sarif
-          retention-days: 5
-
-      # Upload the results to GitHub's code scanning dashboard.
-      - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@5f532563584d71fdef14ee64d17bafb34f751ce5 # tag=v1.0.26
-        with:
-          sarif_file: results.sarif

.gitignore

@@ -2,140 +2,18 @@
 *.slo
 *.lo
 *.o
-*.page
+
 # Compiled Dynamic libraries
 *.so
 *.dylib
-*.page
+
 # Compiled Static libraries
 *.lai
 *.la
 *.a
 *~
-*.Rcheck
-*.rds
-*.tar.gz
+*txt*
 *conf
 *buffer
-*.model
-*pyc
-*.train
-*.test
-*.tar
-*group
-*rar
-*vali
-*sdf
-Release
-*exe*
-*exp
-ipch
-*.filters
-*.user
-*log
-Debug
-*suo
-.Rhistory
-*.dll
-*i386
-*x64
-*dump
-*save
-*csv
-.Rproj.user
-*.cpage.col
-*.cpage
-*.Rproj
-./xgboost.mpi
-./xgboost.mock
-#.Rbuildignore
-R-package.Rproj
-*.cache*
-.mypy_cache/
-doxygen
-
-# java
-java/xgboost4j/target
-java/xgboost4j/tmp
-java/xgboost4j-demo/target
-java/xgboost4j-demo/data/
-java/xgboost4j-demo/tmp/
-java/xgboost4j-demo/model/
-nb-configuration*
-# Eclipse
-.project
-.cproject
-.classpath
-.pydevproject
-.settings/
-build
-/xgboost
-*.data
-build_plugin
-recommonmark/
-tags
-TAGS
-*.class
-target
-*.swp
-
-# cpp tests and gcov generated files
-*.gcov
-*.gcda
-*.gcno
-build_tests
-/tests/cpp/xgboost_test
-
-.DS_Store
-lib/
-
-# spark
-metastore_db
-
-/include/xgboost/build_config.h
-
-# files from R-package source install
-**/config.status
-R-package/src/Makevars
-*.lib
-
-# Visual Studio
-.vs/
-CMakeSettings.json
-*.ilk
-*.pdb
-
-# IntelliJ/CLion
-.idea
-*.iml
-/cmake-build-debug/
-
-# GDB
-.gdb_history
-
-# Python joblib.Memory used in pytest.
-cachedir/
-
-# Files from local Dask work
-dask-worker-space/
-
-# Jupyter notebook checkpoints
-.ipynb_checkpoints/
-
-# credentials and key material
-config
-credentials
-credentials.csv
-*.env
-*.pem
-*.pub
-*.rdp
-*_rsa
-
-# Visual Studio code + extensions
-.vscode
-.metals
-.bloop
-
-# hypothesis python tests
-.hypothesis
+*model
+xgboost

.gitmodules

@@ -1,10 +0,0 @@
-[submodule "dmlc-core"]
-	path = dmlc-core
-	url = https://github.com/dmlc/dmlc-core
-	branch = main
-[submodule "cub"]
-	path = cub
-	url = https://github.com/NVlabs/cub
-[submodule "gputreeshap"]
-	path = gputreeshap
-	url = https://github.com/rapidsai/gputreeshap.git

.readthedocs.yaml

@@ -1,35 +0,0 @@
-# .readthedocs.yaml
-# Read the Docs configuration file
-# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
-
-# Required
-version: 2
-
-submodules:
-  include: all
-
-# Set the version of Python and other tools you might need
-build:
-  os: ubuntu-22.04
-  tools:
-    python: "3.8"
-  apt_packages:
-    - graphviz
-    - cmake
-    - g++
-    - doxygen
-    - ninja-build
-
-# Build documentation in the docs/ directory with Sphinx
-sphinx:
-   configuration: doc/conf.py
-
-# If using Sphinx, optionally build your docs in additional formats such as PDF
-formats:
-   - pdf
-
-# Optionally declare the Python requirements required to build your docs
-python:
-  install:
-   - requirements: doc/requirements.txt
-  system_packages: true

.travis.yml

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

CITATION

@@ -1,18 +0,0 @@
-@inproceedings{Chen:2016:XST:2939672.2939785,
- author = {Chen, Tianqi and Guestrin, Carlos},
- title = {{XGBoost}: A Scalable Tree Boosting System},
- booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
- series = {KDD '16},
- year = {2016},
- isbn = {978-1-4503-4232-2},
- location = {San Francisco, California, USA},
- pages = {785--794},
- numpages = {10},
- url = {http://doi.acm.org/10.1145/2939672.2939785},
- doi = {10.1145/2939672.2939785},
- acmid = {2939785},
- publisher = {ACM},
- address = {New York, NY, USA},
- keywords = {large-scale machine learning},
-}
-

CMakeLists.txt

@@ -1,394 +0,0 @@
-cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.7.0)
-include(cmake/Utils.cmake)
-list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
-cmake_policy(SET CMP0022 NEW)
-cmake_policy(SET CMP0079 NEW)
-cmake_policy(SET CMP0076 NEW)
-set(CMAKE_POLICY_DEFAULT_CMP0063 NEW)
-cmake_policy(SET CMP0063 NEW)
-
-if ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
-  cmake_policy(SET CMP0077 NEW)
-endif ((${CMAKE_VERSION} VERSION_GREATER 3.13) OR (${CMAKE_VERSION} VERSION_EQUAL 3.13))
-
-message(STATUS "CMake version ${CMAKE_VERSION}")
-
-if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 5.0)
-  message(FATAL_ERROR "GCC version must be at least 5.0!")
-endif()
-
-include(${xgboost_SOURCE_DIR}/cmake/FindPrefetchIntrinsics.cmake)
-find_prefetch_intrinsics()
-include(${xgboost_SOURCE_DIR}/cmake/Version.cmake)
-write_version()
-set_default_configuration_release()
-
-#-- Options
-## User options
-option(BUILD_C_DOC "Build documentation for C APIs using Doxygen." OFF)
-option(USE_OPENMP "Build with OpenMP support." ON)
-option(BUILD_STATIC_LIB "Build static library" OFF)
-option(FORCE_SHARED_CRT "Build with dynamic CRT on Windows (/MD)" OFF)
-option(RABIT_BUILD_MPI "Build MPI" OFF)
-## Bindings
-option(JVM_BINDINGS "Build JVM bindings" OFF)
-option(R_LIB "Build shared library for R package" OFF)
-## Dev
-option(USE_DEBUG_OUTPUT "Dump internal training results like gradients and predictions to stdout.
-Should only be used for debugging." OFF)
-option(FORCE_COLORED_OUTPUT "Force colored output from compilers, useful when ninja is used instead of make." OFF)
-option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC/Clang" OFF)
-option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
-option(GOOGLE_TEST "Build google tests" OFF)
-option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
-option(USE_DEVICE_DEBUG "Generate CUDA device debug info." OFF)
-option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
-set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
-option(RABIT_MOCK "Build rabit with mock" OFF)
-option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
-## CUDA
-option(USE_CUDA  "Build with GPU acceleration" OFF)
-option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
-option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
-option(BUILD_WITH_CUDA_CUB "Build with cub in CUDA installation" OFF)
-set(GPU_COMPUTE_VER "" CACHE STRING
-  "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
-## 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.")
-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_DENSE_PARSER "Build dense parser plugin" OFF)
-option(PLUGIN_RMM "Build with RAPIDS Memory Manager (RMM)" OFF)
-option(PLUGIN_FEDERATED "Build with Federated Learning" OFF)
-## TODO: 1. Add check if DPC++ compiler is used for building
-option(PLUGIN_UPDATER_ONEAPI "DPC++ updater" OFF)
-option(ADD_PKGCONFIG "Add xgboost.pc into system." ON)
-
-#-- Checks for building XGBoost
-if (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
-  message(SEND_ERROR "Do not enable `USE_DEBUG_OUTPUT' with release build.")
-endif (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
-if (USE_NCCL AND NOT (USE_CUDA))
-  message(SEND_ERROR "`USE_NCCL` must be enabled with `USE_CUDA` flag.")
-endif (USE_NCCL AND NOT (USE_CUDA))
-if (USE_DEVICE_DEBUG AND NOT (USE_CUDA))
-  message(SEND_ERROR "`USE_DEVICE_DEBUG` must be enabled with `USE_CUDA` flag.")
-endif (USE_DEVICE_DEBUG AND NOT (USE_CUDA))
-if (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-  message(SEND_ERROR "Build XGBoost with -DUSE_NCCL=ON to enable BUILD_WITH_SHARED_NCCL.")
-endif (BUILD_WITH_SHARED_NCCL AND (NOT USE_NCCL))
-if (JVM_BINDINGS AND R_LIB)
-  message(SEND_ERROR "`R_LIB' is not compatible with `JVM_BINDINGS' as they both have customized configurations.")
-endif (JVM_BINDINGS AND R_LIB)
-if (R_LIB AND GOOGLE_TEST)
-  message(WARNING "Some C++ unittests will fail with `R_LIB` enabled,
- as R package redirects some functions to R runtime implementation.")
-endif (R_LIB AND GOOGLE_TEST)
-if (USE_AVX)
-  message(SEND_ERROR  "The option 'USE_AVX' is deprecated as experimental AVX features have been removed from XGBoost.")
-endif (USE_AVX)
-if (PLUGIN_LZ4)
-  message(SEND_ERROR  "The option 'PLUGIN_LZ4' is removed from XGBoost.")
-endif (PLUGIN_LZ4)
-if (PLUGIN_RMM AND NOT (USE_CUDA))
-  message(SEND_ERROR "`PLUGIN_RMM` must be enabled with `USE_CUDA` flag.")
-endif (PLUGIN_RMM AND NOT (USE_CUDA))
-if (PLUGIN_RMM AND NOT ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") OR (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with GCC or Clang compiler.")
-endif (PLUGIN_RMM AND NOT ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") OR (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")))
-if (PLUGIN_RMM AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-  message(SEND_ERROR "`PLUGIN_RMM` must be used with Linux.")
-endif (PLUGIN_RMM AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-if (ENABLE_ALL_WARNINGS)
-  if ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-    message(SEND_ERROR "ENABLE_ALL_WARNINGS is only available for Clang and GCC.")
-  endif ((NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang") AND (NOT CMAKE_CXX_COMPILER_ID STREQUAL "GNU"))
-endif (ENABLE_ALL_WARNINGS)
-if (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
-  message(SEND_ERROR "Cannot build a static library libxgboost.a when R or JVM packages are enabled.")
-endif (BUILD_STATIC_LIB AND (R_LIB OR JVM_BINDINGS))
-if (PLUGIN_RMM AND (NOT BUILD_WITH_CUDA_CUB))
-  message(SEND_ERROR "Cannot build with RMM using cub submodule.")
-endif (PLUGIN_RMM AND (NOT BUILD_WITH_CUDA_CUB))
-if (PLUGIN_FEDERATED)
-  if (CMAKE_CROSSCOMPILING)
-    message(SEND_ERROR "Cannot cross compile with federated learning support")
-  endif ()
-  if (BUILD_STATIC_LIB)
-    message(SEND_ERROR "Cannot build static lib with federated learning support")
-  endif ()
-  if (R_LIB OR JVM_BINDINGS)
-    message(SEND_ERROR "Cannot enable federated learning support when R or JVM packages are enabled.")
-  endif ()
-  if (WIN32)
-    message(SEND_ERROR "Federated learning not supported for Windows platform")
-  endif ()
-endif ()
-
-#-- Sanitizer
-if (USE_SANITIZER)
-  include(cmake/Sanitizer.cmake)
-  enable_sanitizers("${ENABLED_SANITIZERS}")
-endif (USE_SANITIZER)
-
-if (USE_CUDA)
-  set(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
-  # `export CXX=' is ignored by CMake CUDA.
-  set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
-  message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
-
-  enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 11.0)
-    message(FATAL_ERROR "CUDA version must be at least 11.0!")
-  endif()
-  set(GEN_CODE "")
-  format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
-  add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
-
-  if ((${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 11.4) AND (NOT BUILD_WITH_CUDA_CUB))
-    set(BUILD_WITH_CUDA_CUB ON)
-  endif ()
-endif (USE_CUDA)
-
-if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
-    ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
-      (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-color=always")
-endif()
-
-find_package(Threads REQUIRED)
-
-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)
-    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 ${HOMEBREW_LIBOMP_PREFIX}/lib/libomp.dylib)
-      find_package(OpenMP REQUIRED)
-    endif ()
-  else ()
-    find_package(OpenMP REQUIRED)
-  endif ()
-endif (USE_OPENMP)
-#Add for IBM i
-if (${CMAKE_SYSTEM_NAME} MATCHES "OS400")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
-  set(CMAKE_CXX_ARCHIVE_CREATE "<CMAKE_AR> -X64 qc <TARGET> <OBJECTS>")
-endif()
-
-if (USE_NCCL)
-  find_package(Nccl REQUIRED)
-endif (USE_NCCL)
-
-# dmlc-core
-msvc_use_static_runtime()
-if (FORCE_SHARED_CRT)
-  set(DMLC_FORCE_SHARED_CRT ON)
-endif ()
-add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-
-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 (TARGET dmlc_unit_tests)
-endif (MSVC)
-
-# rabit
-add_subdirectory(rabit)
-if (RABIT_BUILD_MPI)
-  find_package(MPI REQUIRED)
-endif (RABIT_BUILD_MPI)
-
-# core xgboost
-add_subdirectory(${xgboost_SOURCE_DIR}/src)
-target_link_libraries(objxgboost PUBLIC dmlc)
-
-# Exports some R specific definitions and objects
-if (R_LIB)
-  add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
-endif (R_LIB)
-
-# This creates its own shared library `xgboost4j'.
-if (JVM_BINDINGS)
-  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
-endif (JVM_BINDINGS)
-
-# Plugin
-add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
-
-if (PLUGIN_RMM)
-  find_package(rmm REQUIRED)
-endif (PLUGIN_RMM)
-
-#-- library
-if (BUILD_STATIC_LIB)
-  add_library(xgboost STATIC)
-else (BUILD_STATIC_LIB)
-  add_library(xgboost SHARED)
-endif (BUILD_STATIC_LIB)
-target_link_libraries(xgboost PRIVATE objxgboost)
-target_include_directories(xgboost
-  INTERFACE
-  $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
-#-- End shared library
-
-#-- CLI for xgboost
-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
-  ${xgboost_SOURCE_DIR}/rabit/include
-)
-set_target_properties(runxgboost PROPERTIES OUTPUT_NAME xgboost)
-#-- End CLI for xgboost
-
-# Common setup for all targets
-foreach(target xgboost objxgboost dmlc runxgboost)
-  xgboost_target_properties(${target})
-  xgboost_target_link_libraries(${target})
-  xgboost_target_defs(${target})
-endforeach()
-
-if (JVM_BINDINGS)
-  xgboost_target_properties(xgboost4j)
-  xgboost_target_link_libraries(xgboost4j)
-  xgboost_target_defs(xgboost4j)
-endif (JVM_BINDINGS)
-
-set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
-set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
-# Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
-add_dependencies(xgboost runxgboost)
-
-#-- Installing XGBoost
-if (R_LIB)
-  include(cmake/RPackageInstallTargetSetup.cmake)
-  set_target_properties(xgboost PROPERTIES PREFIX "")
-  if (APPLE)
-    set_target_properties(xgboost PROPERTIES SUFFIX ".so")
-  endif (APPLE)
-  setup_rpackage_install_target(xgboost "${CMAKE_CURRENT_BINARY_DIR}/R-package-install")
-  set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
-endif (R_LIB)
-if (MINGW)
-  set_target_properties(xgboost PROPERTIES PREFIX "")
-endif (MINGW)
-
-if (BUILD_C_DOC)
-  include(cmake/Doc.cmake)
-  run_doxygen()
-endif (BUILD_C_DOC)
-
-include(CPack)
-
-include(GNUInstallDirs)
-# Install all headers.  Please note that currently the C++ headers does not form an "API".
-install(DIRECTORY ${xgboost_SOURCE_DIR}/include/xgboost
-  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)
-  set(INSTALL_TARGETS xgboost runxgboost objxgboost dmlc)
-else (BUILD_STATIC_LIB)
-  set(INSTALL_TARGETS xgboost runxgboost)
-endif (BUILD_STATIC_LIB)
-
-install(TARGETS ${INSTALL_TARGETS}
-  EXPORT XGBoostTargets
-  ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
-  INCLUDES DESTINATION ${LIBLEGACY_INCLUDE_DIRS})
-install(EXPORT XGBoostTargets
-  FILE XGBoostTargets.cmake
-  NAMESPACE xgboost::
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-
-include(CMakePackageConfigHelpers)
-configure_package_config_file(
-  ${CMAKE_CURRENT_LIST_DIR}/cmake/xgboost-config.cmake.in
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
-  INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-write_basic_package_version_file(
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  VERSION ${XGBOOST_VERSION}
-  COMPATIBILITY AnyNewerVersion)
-install(
-  FILES
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
-  ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
-  DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
-
-#-- Test
-if (GOOGLE_TEST)
-  enable_testing()
-  # Unittests.
-  add_executable(testxgboost)
-  target_link_libraries(testxgboost PRIVATE objxgboost)
-  xgboost_target_properties(testxgboost)
-  xgboost_target_link_libraries(testxgboost)
-  xgboost_target_defs(testxgboost)
-
-  add_subdirectory(${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)
-  add_test(
-    NAME TestXGBoostCLI
-    COMMAND runxgboost ${xgboost_BINARY_DIR}/tests/cli/machine.conf
-    WORKING_DIRECTORY ${xgboost_BINARY_DIR})
-  set_tests_properties(TestXGBoostCLI
-    PROPERTIES
-    PASS_REGULAR_EXPRESSION ".*test-rmse:0.087.*")
-endif (GOOGLE_TEST)
-
-# For MSVC: Call msvc_use_static_runtime() once again to completely
-# replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
-# for issues caused by mixing of /MD and /MT flags
-msvc_use_static_runtime()
-
-# Add xgboost.pc
-if (ADD_PKGCONFIG)
-  configure_file(${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 (ADD_PKGCONFIG)

CONTRIBUTORS.md

@@ -1,106 +0,0 @@
-Contributors of DMLC/XGBoost
-============================
-XGBoost has been developed and used by a group of active community. Everyone is more than welcomed to is a great way to make the project better and more accessible to more users.
-
-Project Management Committee(PMC) 
-----------
-The Project Management Committee(PMC) consists group of active committers that moderate the discussion, manage the project release, and proposes new committer/PMC members. 
-
-* [Tianqi Chen](https://github.com/tqchen), University of Washington
-  - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
-* [Michael Benesty](https://github.com/pommedeterresautee)
-  - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Akuity
-  - Yuan is a founding engineer at Akuity. He contributed mostly in R and Python packages.
-* [Nan Zhu](https://github.com/CodingCat), Uber
-  - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
-* [Jiaming Yuan](https://github.com/trivialfis)
-  - Jiaming contributed to the GPU algorithms. He has also introduced new abstractions to improve the quality of the C++ codebase.
-* [Hyunsu Cho](http://hyunsu-cho.io/), NVIDIA
-  - Hyunsu is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater.
-* [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
-  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
-* [Hongliang Liu](https://github.com/phunterlau)
-
-
-Committers
-----------
-Committers are people who have made substantial contribution to the project and granted write access to the project.
-
-* [Tong He](https://github.com/hetong007), Amazon AI
-  - Tong is an applied scientist in Amazon AI. He is the maintainer of XGBoost R package.
-* [Vadim Khotilovich](https://github.com/khotilov)
-  - Vadim contributes many improvements in R and core packages.
-* [Bing Xu](https://github.com/antinucleon)
-  - Bing is the original creator of XGBoost Python package and currently the maintainer of [XGBoost.jl](https://github.com/antinucleon/XGBoost.jl).
-* [Sergei Lebedev](https://github.com/superbobry), Criteo
-  - 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.
-Committers comes from contributors who:
-* Made substantial contribution to the project.
-* Willing to spent time on maintaining and lead the project.
-
-New committers will be proposed by current committer members, with support from more than two of current committers.
-
-List of Contributors
---------------------
-* [Full List of Contributors](https://github.com/dmlc/xgboost/graphs/contributors)
-  - To contributors: please add your name to the list when you submit a patch to the project:)
-* [Kailong Chen](https://github.com/kalenhaha)
-  - Kailong is an early contributor of XGBoost, he is creator of ranking objectives in XGBoost.
-* [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.
-* [Ajinkya Kale](https://github.com/ajkl)
-* [Boliang Chen](https://github.com/cblsjtu)
-* [Yangqing Men](https://github.com/yanqingmen)
-  - Yangqing is the creator of XGBoost java package.
-* [Engpeng Yao](https://github.com/yepyao)
-* [Giulio](https://github.com/giuliohome)
-  - Giulio is the creator of Windows project of XGBoost
-* [Jamie Hall](https://github.com/nerdcha)
-  - Jamie is the initial creator of XGBoost scikit-learn module.
-* [Yen-Ying Lee](https://github.com/white1033)
-* [Masaaki Horikoshi](https://github.com/sinhrks)
-  - Masaaki is the initial creator of XGBoost Python plotting module.
-* [daiyl0320](https://github.com/daiyl0320)
-  - daiyl0320 contributed patch to XGBoost distributed version more robust, and scales stably on TB scale datasets.
-* [Huayi Zhang](https://github.com/irachex)
-* [Johan Manders](https://github.com/johanmanders)
-* [yoori](https://github.com/yoori)
-* [Mathias Müller](https://github.com/far0n)
-* [Sam Thomson](https://github.com/sammthomson)
-* [ganesh-krishnan](https://github.com/ganesh-krishnan)
-* [Damien Carol](https://github.com/damiencarol)
-* [Alex Bain](https://github.com/convexquad)
-* [Baltazar Bieniek](https://github.com/bbieniek)
-* [Adam Pocock](https://github.com/Craigacp)
-* [Gideon Whitehead](https://github.com/gaw89)
-* [Yi-Lin Juang](https://github.com/frankyjuang)
-* [Andrew Hannigan](https://github.com/andrewhannigan)
-* [Andy Adinets](https://github.com/canonizer)
-* [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.
-* [Andrew Thia](https://github.com/BlueTea88)
-  - Andrew Thia implemented feature interaction constraints
-* [Wei Tian](https://github.com/weitian)
-* [Chen Qin](https://github.com/chenqin)
-* [Sam Wilkinson](https://samwilkinson.io)
-* [Matthew Jones](https://github.com/mt-jones)
-* [Jiaxiang Li](https://github.com/JiaxiangBU)
-* [Bryan Woods](https://github.com/bryan-woods)
-  - Bryan added support for cross-validation for the ranking objective
-* [Haoda Fu](https://github.com/fuhaoda)
-* [Evan Kepner](https://github.com/EvanKepner)
-  - Evan Kepner added support for os.PathLike file paths in Python

LICENSE

@@ -1,201 +1,13 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
+Copyright (c) 2014 Tianqi Chen
 
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+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
 
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "{}"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright (c) 2019 by 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
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

Makefile

@@ -1,146 +1,25 @@
-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 CC  = gcc
 export CXX = g++
-endif
-endif
-
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++14 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
-CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
-
-ifeq ($(TEST_COVER), 1)
-	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
-else
-	CFLAGS += -O3 -funroll-loops
-endif
-
-ifndef LINT_LANG
-	LINT_LANG= "all"
-endif
+export CFLAGS = -Wall -O3 -msse2  -Wno-unknown-pragmas -fopenmp
 
 # specify tensor path
-.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck
+BIN = xgboost
+OBJ = 
+.PHONY: clean all
 
-build/%.o: src/%.cc
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.d
-	$(CXX) -c $(CFLAGS) $< -o $@
+all: $(BIN) $(OBJ)
+export LDFLAGS= -pthread -lm 
 
-# 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 $@
+xgboost: regression/xgboost_reg_main.cpp regression/*.h booster/*.h booster/*/*.hpp booster/*.hpp
 
-rcpplint:
-	python3 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
+$(BIN) : 
+	$(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^)
 
-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)) $(COV_OBJ) > gcov.log || cat gcov.log; \
-	)
-endif
+$(OBJ) : 
+	$(CXX) -c $(CFLAGS) -o $@ $(firstword $(filter %.cpp %.c, $^) )
 
+install:
+	cp -f -r $(BIN)  $(INSTALL_PATH)
 
 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
-	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
-	cat R-package/src/Makevars.win|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.win
-	rm -f xgboost/src/Makevars.win-e   # OSX sed create this extra file; remove it
-	rm -f xgboost/cleanup
-	bash R-package/remove_warning_suppression_pragma.sh
-	bash xgboost/remove_warning_suppression_pragma.sh
-	rm xgboost/remove_warning_suppression_pragma.sh
-	rm xgboost/CMakeLists.txt
-	rm -rfv xgboost/tests/helper_scripts/
-
-R ?= R
-
-Rbuild: Rpack
-	$(R) CMD build xgboost
-	rm -rf xgboost
-
-Rcheck: Rbuild
-	$(R) CMD check --as-cran xgboost*.tar.gz
-
--include build/*.d
--include build/*/*.d
+	$(RM) $(OBJ) $(BIN) *~

R-package/.Rbuildignore

@@ -1,6 +0,0 @@
-\.o$
-\.so$
-\.dll$
-^.*\.Rproj$
-^\.Rproj\.user$
-README.md

R-package/CMakeLists.txt

@@ -1,44 +0,0 @@
-find_package(LibR REQUIRED)
-message(STATUS "LIBR_CORE_LIBRARY " ${LIBR_CORE_LIBRARY})
-
-file(GLOB_RECURSE R_SOURCES
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.cc
-  ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
-# Use object library to expose symbols
-add_library(xgboost-r OBJECT ${R_SOURCES})
-if (ENABLE_ALL_WARNINGS)
-  target_compile_options(xgboost-r PRIVATE -Wall -Wextra)
-endif (ENABLE_ALL_WARNINGS)
-target_compile_definitions(xgboost-r
-  PUBLIC
-  -DXGBOOST_STRICT_R_MODE=1
-  -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
-  -DDMLC_LOG_BEFORE_THROW=0
-  -DDMLC_DISABLE_STDIN=1
-  -DDMLC_LOG_CUSTOMIZE=1
-  -DRABIT_CUSTOMIZE_MSG_
-  -DRABIT_STRICT_CXX98_)
-target_include_directories(xgboost-r
-  PRIVATE
-  ${LIBR_INCLUDE_DIRS}
-  ${PROJECT_SOURCE_DIR}/include
-  ${PROJECT_SOURCE_DIR}/dmlc-core/include
-  ${PROJECT_SOURCE_DIR}/rabit/include)
-target_link_libraries(xgboost-r PUBLIC ${LIBR_CORE_LIBRARY})
-if (USE_OPENMP)
-  find_package(OpenMP REQUIRED)
-  target_link_libraries(xgboost-r PUBLIC OpenMP::OpenMP_CXX OpenMP::OpenMP_C)
-endif (USE_OPENMP)
-set_target_properties(
-  xgboost-r PROPERTIES
-  CXX_STANDARD 14
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-
-# Get compilation and link flags of xgboost-r and propagate to objxgboost
-target_link_libraries(objxgboost PUBLIC xgboost-r)
-# Add all objects of xgboost-r to objxgboost
-target_sources(objxgboost INTERFACE $<TARGET_OBJECTS:xgboost-r>)
-
-set(LIBR_HOME "${LIBR_HOME}" PARENT_SCOPE)
-set(LIBR_EXECUTABLE "${LIBR_EXECUTABLE}" PARENT_SCOPE)

R-package/DESCRIPTION

@@ -1,70 +0,0 @@
-Package: xgboost
-Type: Package
-Title: Extreme Gradient Boosting
-Version: 1.7.0.1
-Date: 2022-10-18
-Authors@R: c(
-  person("Tianqi", "Chen", role = c("aut"),
-         email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut"),
-         email = "hetong007@gmail.com"),
-  person("Michael", "Benesty", role = c("aut"),
-         email = "michael@benesty.fr"),
-  person("Vadim", "Khotilovich", role = c("aut"),
-         email = "khotilovich@gmail.com"),
-  person("Yuan", "Tang", role = c("aut"),
-         email = "terrytangyuan@gmail.com",
-         comment = c(ORCID = "0000-0001-5243-233X")),
-  person("Hyunsu", "Cho", role = c("aut"),
-         email = "chohyu01@cs.washington.edu"),
-  person("Kailong", "Chen", role = c("aut")),
-  person("Rory", "Mitchell", role = c("aut")),
-  person("Ignacio", "Cano", role = c("aut")),
-  person("Tianyi", "Zhou", role = c("aut")),
-  person("Mu", "Li", role = c("aut")),
-  person("Junyuan", "Xie", role = c("aut")),
-  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
-    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
-    their own objectives easily.
-License: Apache License (== 2.0) | file LICENSE
-URL: https://github.com/dmlc/xgboost
-BugReports: https://github.com/dmlc/xgboost/issues
-NeedsCompilation: yes
-VignetteBuilder: knitr
-Suggests:
-    knitr,
-    rmarkdown,
-    ggplot2 (>= 1.0.1),
-    DiagrammeR (>= 0.9.0),
-    Ckmeans.1d.dp (>= 3.3.1),
-    vcd (>= 1.3),
-    testthat,
-    lintr,
-    igraph (>= 1.0.1),
-    float,
-    crayon,
-    titanic
-Depends:
-    R (>= 3.3.0)
-Imports:
-    Matrix (>= 1.1-0),
-    methods,
-    data.table (>= 1.9.6),
-    jsonlite (>= 1.0),
-RoxygenNote: 7.1.1
-SystemRequirements: GNU make, C++14

R-package/LICENSE

@@ -1,13 +0,0 @@
-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
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.

R-package/NAMESPACE

@@ -1,91 +0,0 @@
-# Generated by roxygen2: do not edit by hand
-
-S3method("[",xgb.DMatrix)
-S3method("dimnames<-",xgb.DMatrix)
-S3method(dim,xgb.DMatrix)
-S3method(dimnames,xgb.DMatrix)
-S3method(getinfo,xgb.DMatrix)
-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.DMatrix)
-S3method(slice,xgb.DMatrix)
-export("xgb.attr<-")
-export("xgb.attributes<-")
-export("xgb.config<-")
-export("xgb.parameters<-")
-export(cb.cv.predict)
-export(cb.early.stop)
-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(slice)
-export(xgb.Booster.complete)
-export(xgb.DMatrix)
-export(xgb.DMatrix.save)
-export(xgb.attr)
-export(xgb.attributes)
-export(xgb.config)
-export(xgb.create.features)
-export(xgb.cv)
-export(xgb.dump)
-export(xgb.gblinear.history)
-export(xgb.get.config)
-export(xgb.ggplot.deepness)
-export(xgb.ggplot.importance)
-export(xgb.ggplot.shap.summary)
-export(xgb.importance)
-export(xgb.load)
-export(xgb.load.raw)
-export(xgb.model.dt.tree)
-export(xgb.plot.deepness)
-export(xgb.plot.importance)
-export(xgb.plot.multi.trees)
-export(xgb.plot.shap)
-export(xgb.plot.shap.summary)
-export(xgb.plot.tree)
-export(xgb.save)
-export(xgb.save.raw)
-export(xgb.serialize)
-export(xgb.set.config)
-export(xgb.train)
-export(xgb.unserialize)
-export(xgboost)
-import(methods)
-importClassesFrom(Matrix,dgCMatrix)
-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)
-importFrom(data.table,is.data.table)
-importFrom(data.table,rbindlist)
-importFrom(data.table,setkey)
-importFrom(data.table,setkeyv)
-importFrom(data.table,setnames)
-importFrom(grDevices,rgb)
-importFrom(graphics,barplot)
-importFrom(graphics,grid)
-importFrom(graphics,lines)
-importFrom(graphics,par)
-importFrom(graphics,points)
-importFrom(graphics,title)
-importFrom(jsonlite,fromJSON)
-importFrom(jsonlite,toJSON)
-importFrom(stats,median)
-importFrom(stats,predict)
-importFrom(utils,head)
-importFrom(utils,object.size)
-importFrom(utils,str)
-importFrom(utils,tail)
-useDynLib(xgboost, .registration = TRUE)

R-package/R/callbacks.R

@@ -1,835 +0,0 @@
-#' Callback closures for booster training.
-#'
-#' 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}}
-#'
-#' @name callbacks
-NULL
-
-#
-# Callbacks -------------------------------------------------------------------
-#
-
-#' Callback closure for printing the result of evaluation
-#'
-#' @param period  results would be printed every number of periods
-#' @param showsd  whether standard deviations should be printed (when available)
-#'
-#' @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}}
-#'
-#' @export
-cb.print.evaluation <- function(period = 1, showsd = TRUE) {
-
-  callback <- function(env = parent.frame()) {
-    if (length(env$bst_evaluation) == 0 ||
-        period == 0 ||
-        NVL(env$rank, 0) != 0)
-      return()
-
-    i <- env$iteration
-    if ((i - 1) %% period == 0 ||
-        i == env$begin_iteration ||
-        i == env$end_iteration) {
-      stdev <- if (showsd) env$bst_evaluation_err else NULL
-      msg <- format.eval.string(i, env$bst_evaluation, stdev)
-      cat(msg, '\n')
-    }
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.print.evaluation'
-  callback
-}
-
-
-#' Callback closure for logging the evaluation history
-#'
-#' @details
-#' This callback function appends the current iteration evaluation results \code{bst_evaluation}
-#' available in the calling parent frame to the \code{evaluation_log} list in a calling frame.
-#'
-#' The finalizer callback (called with \code{finalize = TURE} in the end) converts
-#' the \code{evaluation_log} list into a final data.table.
-#'
-#' The iteration evaluation result \code{bst_evaluation} must be a named numeric vector.
-#'
-#' Note: in the column names of the final data.table, the dash '-' character is replaced with
-#' the underscore '_' in order to make the column names more like regular R identifiers.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{evaluation_log},
-#' \code{bst_evaluation},
-#' \code{iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.evaluation.log <- function() {
-
-  mnames <- NULL
-
-  init <- function(env) {
-    if (!is.list(env$evaluation_log))
-      stop("'evaluation_log' has to be a list")
-    mnames <<- names(env$bst_evaluation)
-    if (is.null(mnames) || any(mnames == ""))
-      stop("bst_evaluation must have non-empty names")
-
-    mnames <<- gsub('-', '_', names(env$bst_evaluation))
-    if (!is.null(env$bst_evaluation_err))
-      mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
-  }
-
-  finalizer <- function(env) {
-    env$evaluation_log <- as.data.table(t(simplify2array(env$evaluation_log)))
-    setnames(env$evaluation_log, c('iter', mnames))
-
-    if (!is.null(env$bst_evaluation_err)) {
-      # rearrange col order from _mean,_mean,...,_std,_std,...
-      # to be _mean,_std,_mean,_std,...
-      len <- length(mnames)
-      means <- mnames[seq_len(len / 2)]
-      stds <- mnames[(len / 2 + 1):len]
-      cnames <- numeric(len)
-      cnames[c(TRUE, FALSE)] <- means
-      cnames[c(FALSE, TRUE)] <- stds
-      env$evaluation_log <- env$evaluation_log[, c('iter', cnames), with = FALSE]
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (is.null(mnames))
-      init(env)
-
-    if (finalize)
-      return(finalizer(env))
-
-    ev <- env$bst_evaluation
-    if (!is.null(env$bst_evaluation_err))
-      ev <- c(ev, env$bst_evaluation_err)
-    env$evaluation_log <- c(env$evaluation_log,
-                            list(c(iter = env$iteration, ev)))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.evaluation.log'
-  callback
-}
-
-#' Callback closure for resetting the booster's parameters at each iteration.
-#'
-#' @param new_params a list where each element corresponds to a parameter that needs to be reset.
-#'        Each element's value must be either a vector of values of length \code{nrounds}
-#'        to be set at each iteration,
-#'        or a function of two parameters \code{learning_rates(iteration, nrounds)}
-#'        which returns a new parameter value by using the current iteration number
-#'        and the total number of boosting rounds.
-#'
-#' @details
-#' This is a "pre-iteration" callback function used to reset booster's parameters
-#' at the beginning of each iteration.
-#'
-#' Note that when training is resumed from some previous model, and a function is used to
-#' reset a parameter value, the \code{nrounds} argument in this function would be the
-#' the number of boosting rounds in the current training.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst} or \code{bst_folds},
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.reset.parameters <- function(new_params) {
-
-  if (typeof(new_params) != "list")
-    stop("'new_params' must be a list")
-  pnames <- gsub("\\.", "_", names(new_params))
-  nrounds <- NULL
-
-  # run some checks in the beginning
-  init <- function(env) {
-    nrounds <<- env$end_iteration - env$begin_iteration + 1
-
-    if (is.null(env$bst) && is.null(env$bst_folds))
-      stop("Parent frame has neither 'bst' nor 'bst_folds'")
-
-    # Some parameters are not allowed to be changed,
-    # since changing them would simply wreck some chaos
-    not_allowed <- pnames %in%
-      c('num_class', 'num_output_group', 'size_leaf_vector', 'updater_seq')
-    if (any(not_allowed))
-      stop('Parameters ', paste(pnames[not_allowed]), " cannot be changed during boosting.")
-
-    for (n in pnames) {
-      p <- new_params[[n]]
-      if (is.function(p)) {
-        if (length(formals(p)) != 2)
-          stop("Parameter '", n, "' is a function but not of two arguments")
-      } else if (is.numeric(p) || is.character(p)) {
-        if (length(p) != nrounds)
-          stop("Length of '", n, "' has to be equal to 'nrounds'")
-      } else {
-        stop("Parameter '", n, "' is not a function or a vector")
-      }
-    }
-  }
-
-  callback <- function(env = parent.frame()) {
-    if (is.null(nrounds))
-      init(env)
-
-    i <- env$iteration
-    pars <- lapply(new_params, function(p) {
-      if (is.function(p))
-        return(p(i, nrounds))
-      p[i]
-    })
-
-    if (!is.null(env$bst)) {
-      xgb.parameters(env$bst$handle) <- pars
-    } else {
-      for (fd in env$bst_folds)
-        xgb.parameters(fd$bst) <- pars
-    }
-  }
-  attr(callback, 'is_pre_iteration') <- TRUE
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.reset.parameters'
-  callback
-}
-
-
-#' Callback closure to activate the early stopping.
-#'
-#' @param stopping_rounds The number of rounds with no improvement in
-#'        the evaluation metric in order to stop the training.
-#' @param maximize whether to maximize the evaluation metric
-#' @param 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 '_'.
-#' @param verbose whether to print the early stopping information.
-#'
-#' @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)
-#' }
-#' 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}}
-#'
-#' @export
-cb.early.stop <- function(stopping_rounds, maximize = FALSE,
-                          metric_name = NULL, verbose = TRUE) {
-  # state variables
-  best_iteration <- -1
-  best_ntreelimit <- -1
-  best_score <- Inf
-  best_msg <- NULL
-  metric_idx <- 1
-
-  init <- function(env) {
-    if (length(env$bst_evaluation) == 0)
-      stop("For early stopping, watchlist must have at least one element")
-
-    eval_names <- gsub('-', '_', names(env$bst_evaluation))
-    if (!is.null(metric_name)) {
-      metric_idx <<- which(gsub('-', '_', metric_name) == eval_names)
-      if (length(metric_idx) == 0)
-        stop("'metric_name' for early stopping is not one of the following:\n",
-             paste(eval_names, collapse = ' '), '\n')
-    }
-    if (is.null(metric_name) &&
-        length(env$bst_evaluation) > 1) {
-      metric_idx <<- length(eval_names)
-      if (verbose)
-        cat('Multiple eval metrics are present. Will use ',
-            eval_names[metric_idx], ' for early stopping.\n', sep = '')
-    }
-
-    metric_name <<- eval_names[metric_idx]
-
-    # maximize is usually NULL when not set in xgb.train and built-in metrics
-    if (is.null(maximize))
-      maximize <<- grepl('(_auc|_map|_ndcg)', metric_name)
-
-    if (verbose && NVL(env$rank, 0) == 0)
-      cat("Will train until ", metric_name, " hasn't improved in ",
-          stopping_rounds, " rounds.\n\n", sep = '')
-
-    best_iteration <<- 1
-    if (maximize) best_score <<- -Inf
-
-    env$stop_condition <- FALSE
-
-    if (!is.null(env$bst)) {
-      if (!inherits(env$bst, 'xgb.Booster'))
-        stop("'bst' in the parent frame must be an 'xgb.Booster'")
-      if (!is.null(best_score <- xgb.attr(env$bst$handle, 'best_score'))) {
-        best_score <<- as.numeric(best_score)
-        best_iteration <<- as.numeric(xgb.attr(env$bst$handle, 'best_iteration')) + 1
-        best_msg <<- as.numeric(xgb.attr(env$bst$handle, 'best_msg'))
-      } else {
-        xgb.attributes(env$bst$handle) <- list(best_iteration = best_iteration - 1,
-                                               best_score = best_score)
-      }
-    } else if (is.null(env$bst_folds) || is.null(env$basket)) {
-      stop("Parent frame has neither 'bst' nor ('bst_folds' and 'basket')")
-    }
-  }
-
-  finalizer <- function(env) {
-    if (!is.null(env$bst)) {
-      attr_best_score <- as.numeric(xgb.attr(env$bst$handle, 'best_score'))
-      if (best_score != attr_best_score) {
-        # If the difference is too big, throw an error
-        if (abs(best_score - attr_best_score) >= 1e-14) {
-          stop("Inconsistent 'best_score' values between the closure state: ", best_score,
-               " and the xgb.attr: ", attr_best_score)
-        }
-        # If the difference is due to floating-point truncation, update best_score
-        best_score <- attr_best_score
-      }
-      env$bst$best_iteration <- best_iteration
-      env$bst$best_ntreelimit <- best_ntreelimit
-      env$bst$best_score <- best_score
-    } else {
-      env$basket$best_iteration <- best_iteration
-      env$basket$best_ntreelimit <- best_ntreelimit
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (best_iteration < 0)
-      init(env)
-
-    if (finalize)
-      return(finalizer(env))
-
-    i <- env$iteration
-    score <- env$bst_evaluation[metric_idx]
-
-    if ((maximize && score > best_score) ||
-        (!maximize && score < best_score)) {
-
-      best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
-      best_score <<- score
-      best_iteration <<- i
-      best_ntreelimit <<- best_iteration * env$num_parallel_tree
-      # save the property to attributes, so they will occur in checkpoint
-      if (!is.null(env$bst)) {
-        xgb.attributes(env$bst) <- list(
-          best_iteration = best_iteration - 1, # convert to 0-based index
-          best_score = best_score,
-          best_msg = best_msg,
-          best_ntreelimit = best_ntreelimit)
-      }
-    } else if (i - best_iteration >= stopping_rounds) {
-      env$stop_condition <- TRUE
-      env$end_iteration <- i
-      if (verbose && NVL(env$rank, 0) == 0)
-        cat("Stopping. Best iteration:\n", best_msg, "\n\n", sep = '')
-    }
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.early.stop'
-  callback
-}
-
-
-#' Callback closure for saving a model file.
-#'
-#' @param save_period save the model to disk after every
-#'        \code{save_period} iterations; 0 means save the model at the end.
-#' @param save_name the name or path for the saved model file.
-#'        It can contain a \code{\link[base]{sprintf}} formatting specifier
-#'        to include the integer iteration number in the file name.
-#'        E.g., with \code{save_name} = 'xgboost_%04d.model',
-#'        the file saved at iteration 50 would be named "xgboost_0050.model".
-#'
-#' @details
-#' This callback function allows to save an xgb-model file, either periodically after each \code{save_period}'s or at the end.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst},
-#' \code{iteration},
-#' \code{begin_iteration},
-#' \code{end_iteration}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.save.model <- function(save_period = 0, save_name = "xgboost.model") {
-
-  if (save_period < 0)
-    stop("'save_period' cannot be negative")
-
-  callback <- function(env = parent.frame()) {
-    if (is.null(env$bst))
-      stop("'save_model' callback requires the 'bst' booster object in its calling frame")
-
-    if ((save_period > 0 && (env$iteration - env$begin_iteration) %% save_period == 0) ||
-        (save_period == 0 && env$iteration == env$end_iteration))
-      xgb.save(env$bst, sprintf(save_name, env$iteration))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.save.model'
-  callback
-}
-
-
-#' Callback closure for returning cross-validation based predictions.
-#'
-#' @param save_models a flag for whether to save the folds' models.
-#'
-#' @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}.
-#'
-#' @return
-#' 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
-#' non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be
-#' meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
-#' When some of the indices in the training dataset are not included into user-provided \code{folds},
-#' their prediction value would be \code{NA}.
-#'
-#' @seealso
-#' \code{\link{callbacks}}
-#'
-#' @export
-cb.cv.predict <- function(save_models = FALSE) {
-
-  finalizer <- function(env) {
-    if (is.null(env$basket) || is.null(env$bst_folds))
-      stop("'cb.cv.predict' callback requires 'basket' and 'bst_folds' lists in its calling frame")
-
-    N <- nrow(env$data)
-    pred <-
-      if (env$num_class > 1) {
-        matrix(NA_real_, N, env$num_class)
-      } else {
-        rep(NA_real_, N)
-      }
-
-    iterationrange <- c(1, NVL(env$basket$best_iteration, env$end_iteration) + 1)
-    if (NVL(env$params[['booster']], '') == 'gblinear') {
-      iterationrange <- c(1, 1)  # must be 0 for gblinear
-    }
-    for (fd in env$bst_folds) {
-      pr <- predict(fd$bst, fd$watchlist[[2]], iterationrange = iterationrange, reshape = TRUE)
-      if (is.matrix(pred)) {
-        pred[fd$index, ] <- pr
-      } else {
-        pred[fd$index] <- pr
-      }
-    }
-    env$basket$pred <- pred
-    if (save_models) {
-      env$basket$models <- lapply(env$bst_folds, function(fd) {
-        xgb.attr(fd$bst, 'niter') <- env$end_iteration - 1
-        xgb.Booster.complete(xgb.handleToBooster(fd$bst), saveraw = TRUE)
-      })
-    }
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (finalize)
-      return(finalizer(env))
-  }
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.cv.predict'
-  callback
-}
-
-
-#' Callback closure for collecting the model coefficients history of a gblinear booster
-#' during its training.
-#'
-#' @param sparse when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
-#'       Sparse format is useful when one expects only a subset of coefficients to be non-zero,
-#'       when using the "thrifty" feature selector with fairly small number of top features
-#'       selected per iteration.
-#'
-#' @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.
-#'
-#' Callback function expects the following values to be set in its calling frame:
-#' \code{bst} (or \code{bst_folds}).
-#'
-#' @return
-#' Results are stored in the \code{coefs} element of the closure.
-#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
-#' 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.
-#'
-#' @seealso
-#' \code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
-#'
-#' @examples
-#' #### Binary classification:
-#' #
-#' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
-#' # without considering the 2nd order interactions:
-#' x <- model.matrix(Species ~ .^2, iris)[,-1]
-#' colnames(x)
-#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
-#' param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
-#' # For 'shotgun', which is a default linear updater, using high eta values may result in
-#' # unstable behaviour in some datasets. With this simple dataset, however, the high learning
-#' # rate does not break the convergence, but allows us to illustrate the typical pattern of
-#' # "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
-#'                  callbacks = list(cb.gblinear.history()))
-#' # Extract the coefficients' path and plot them vs boosting iteration number:
-#' coef_path <- xgb.gblinear.history(bst)
-#' matplot(coef_path, type = 'l')
-#'
-#' # With the deterministic coordinate descent updater, it is safer to use higher learning rates.
-#' # Will try the classical componentwise boosting which selects a single best feature per round:
-#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
-#'                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
-#'                  callbacks = list(cb.gblinear.history()))
-#' matplot(xgb.gblinear.history(bst), type = 'l')
-#' #  Componentwise boosting is known to have similar effect to Lasso regularization.
-#' # Try experimenting with various values of top_k, eta, nrounds,
-#' # as well as different feature_selectors.
-#'
-#' # For xgb.cv:
-#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-#'              callbacks = list(cb.gblinear.history()))
-#' # coefficients in the CV fold #3
-#' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
-#'
-#'
-#' #### Multiclass classification:
-#' #
-#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
-#' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-#'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
-#' # For the default linear updater 'shotgun' it sometimes is helpful
-#' # to use smaller eta to reduce instability
-#' 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')
-#'
-#' # CV:
-#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-#'               callbacks = list(cb.gblinear.history(FALSE)))
-#' # 1st fold of 1st class
-#' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
-#'
-#' @export
-cb.gblinear.history <- function(sparse=FALSE) {
-  coefs <- NULL
-
-  init <- function(env) {
-    if (!is.null(env$bst)) { # xgb.train:
-    } else if (!is.null(env$bst_folds)) { # xgb.cv:
-    } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
-  }
-
-  # convert from list to (sparse) matrix
-  list2mat <- function(coef_list) {
-    if (sparse) {
-      coef_mat <- sparseMatrix(x = unlist(lapply(coef_list, slot, "x")),
-                               i = unlist(lapply(coef_list, slot, "i")),
-                               p = c(0, cumsum(sapply(coef_list, function(x) length(x@x)))),
-                               dims = c(length(coef_list[[1]]), length(coef_list)))
-      return(t(coef_mat))
-    } else {
-      return(do.call(rbind, coef_list))
-    }
-  }
-
-  finalizer <- function(env) {
-    if (length(coefs) == 0)
-      return()
-    if (!is.null(env$bst)) { # # xgb.train:
-      coefs <<- list2mat(coefs)
-    } else { # xgb.cv:
-      # second lapply transposes the list
-      coefs <<- lapply(
-        X = lapply(
-          X = seq_along(coefs[[1]]),
-          FUN = function(i) lapply(coefs, "[[", i)
-        ),
-        FUN = list2mat
-      )
-    }
-  }
-
-  extract.coef <- function(env) {
-    if (!is.null(env$bst)) { # # xgb.train:
-      cf <- as.numeric(grep('(booster|bias|weigh)', xgb.dump(env$bst), invert = TRUE, value = TRUE))
-      if (sparse) cf <- as(cf, "sparseVector")
-    } else { # xgb.cv:
-      cf <- vector("list", length(env$bst_folds))
-      for (i in seq_along(env$bst_folds)) {
-        dmp <- xgb.dump(xgb.handleToBooster(env$bst_folds[[i]]$bst))
-        cf[[i]] <- as.numeric(grep('(booster|bias|weigh)', dmp, invert = TRUE, value = TRUE))
-        if (sparse) cf[[i]] <- as(cf[[i]], "sparseVector")
-      }
-    }
-    cf
-  }
-
-  callback <- function(env = parent.frame(), finalize = FALSE) {
-    if (is.null(coefs)) init(env)
-    if (finalize) return(finalizer(env))
-    cf <- extract.coef(env)
-    coefs <<- c(coefs, list(cf))
-  }
-
-  attr(callback, 'call') <- match.call()
-  attr(callback, 'name') <- 'cb.gblinear.history'
-  callback
-}
-
-#' Extract gblinear coefficients history.
-#'
-#' A helper function to extract the matrix of linear coefficients' history
-#' from a gblinear model created while using the \code{cb.gblinear.history()}
-#' callback.
-#'
-#' @param model either an \code{xgb.Booster} or a result of \code{xgb.cv()}, trained
-#'        using the \code{cb.gblinear.history()} callback.
-#' @param class_index zero-based class index to extract the coefficients for only that
-#'        specific class in a multinomial multiclass model. When it is NULL, all the
-#'        coefficients are returned. Has no effect in non-multiclass models.
-#'
-#' @return
-#' For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns
-#' corresponding to iteration's coefficients (in the order as \code{xgb.dump()} would
-#' return) and the rows corresponding to boosting iterations.
-#'
-#' For an \code{xgb.cv} result, a list of such matrices is returned with the elements
-#' corresponding to CV folds.
-#'
-#' @export
-xgb.gblinear.history <- function(model, class_index = NULL) {
-
-  if (!(inherits(model, "xgb.Booster") ||
-        inherits(model, "xgb.cv.synchronous")))
-    stop("model must be an object of either xgb.Booster or xgb.cv.synchronous class")
-  is_cv <- inherits(model, "xgb.cv.synchronous")
-
-  if (is.null(model[["callbacks"]]) || is.null(model$callbacks[["cb.gblinear.history"]]))
-    stop("model must be trained while using the cb.gblinear.history() callback")
-
-  if (!is_cv) {
-    # extract num_class & num_feat from the internal model
-    dmp <- xgb.dump(model)
-    if (length(dmp) < 2 || dmp[2] != "bias:")
-      stop("It does not appear to be a gblinear model")
-    dmp <- dmp[-c(1, 2)]
-    n <- which(dmp == 'weight:')
-    if (length(n) != 1)
-      stop("It does not appear to be a gblinear model")
-    num_class <- n - 1
-    num_feat <- (length(dmp) - 4) / num_class
-  } else {
-    # in case of CV, the object is expected to have this info
-    if (model$params$booster != "gblinear")
-      stop("It does not appear to be a gblinear model")
-    num_class <- NVL(model$params$num_class, 1)
-    num_feat <- model$nfeatures
-    if (is.null(num_feat))
-      stop("This xgb.cv result does not have nfeatures info")
-  }
-
-  if (!is.null(class_index) &&
-      num_class > 1 &&
-      (class_index[1] < 0 || class_index[1] >= num_class))
-    stop("class_index has to be within [0,", num_class - 1, "]")
-
-  coef_path <- environment(model$callbacks$cb.gblinear.history)[["coefs"]]
-  if (!is.null(class_index) && num_class > 1) {
-    coef_path <- if (is.list(coef_path)) {
-      lapply(coef_path,
-             function(x) x[, seq(1 + class_index, by = num_class, length.out = num_feat)])
-    } else {
-      coef_path <- coef_path[, seq(1 + class_index, by = num_class, length.out = num_feat)]
-    }
-  }
-  coef_path
-}
-
-
-#
-# Internal utility functions for callbacks ------------------------------------
-#
-
-# Format the evaluation metric string
-format.eval.string <- function(iter, eval_res, eval_err = NULL) {
-  if (length(eval_res) == 0)
-    stop('no evaluation results')
-  enames <- names(eval_res)
-  if (is.null(enames))
-    stop('evaluation results must have names')
-  iter <- sprintf('[%d]\t', iter)
-  if (!is.null(eval_err)) {
-    if (length(eval_res) != length(eval_err))
-      stop('eval_res & eval_err lengths mismatch')
-    res <- paste0(sprintf("%s:%f+%f", enames, eval_res, eval_err), collapse = '\t')
-  } else {
-    res <- paste0(sprintf("%s:%f", enames, eval_res), collapse = '\t')
-  }
-  return(paste0(iter, res))
-}
-
-# Extract callback names from the list of callbacks
-callback.names <- function(cb_list) {
-  unlist(lapply(cb_list, function(x) attr(x, 'name')))
-}
-
-# Extract callback calls from the list of callbacks
-callback.calls <- function(cb_list) {
-  unlist(lapply(cb_list, function(x) attr(x, 'call')))
-}
-
-# Add a callback cb to the list and make sure that
-# cb.early.stop and cb.cv.predict are at the end of the list
-# with cb.cv.predict being the last (when present)
-add.cb <- function(cb_list, cb) {
-  cb_list <- c(cb_list, cb)
-  names(cb_list) <- callback.names(cb_list)
-  if ('cb.early.stop' %in% names(cb_list)) {
-    cb_list <- c(cb_list, cb_list['cb.early.stop'])
-    # this removes only the first one
-    cb_list['cb.early.stop'] <- NULL
-  }
-  if ('cb.cv.predict' %in% names(cb_list)) {
-    cb_list <- c(cb_list, cb_list['cb.cv.predict'])
-    cb_list['cb.cv.predict'] <- NULL
-  }
-  cb_list
-}
-
-# Sort callbacks list into categories
-categorize.callbacks <- function(cb_list) {
-  list(
-    pre_iter = Filter(function(x) {
-        pre <- attr(x, 'is_pre_iteration')
-        !is.null(pre) && pre
-      }, cb_list),
-    post_iter = Filter(function(x) {
-        pre <- attr(x, 'is_pre_iteration')
-        is.null(pre) || !pre
-      }, cb_list),
-    finalize = Filter(function(x) {
-        'finalize' %in% names(formals(x))
-      }, cb_list)
-  )
-}
-
-# Check whether all callback functions with names given by 'query_names' are present in the 'cb_list'.
-has.callbacks <- function(cb_list, query_names) {
-  if (length(cb_list) < length(query_names))
-    return(FALSE)
-  if (!is.list(cb_list) ||
-      any(sapply(cb_list, class) != 'function')) {
-    stop('`cb_list` must be a list of callback functions')
-  }
-  cb_names <- callback.names(cb_list)
-  if (!is.character(cb_names) ||
-      length(cb_names) != length(cb_list) ||
-      any(cb_names == "")) {
-    stop('All callbacks in the `cb_list` must have a non-empty `name` attribute')
-  }
-  if (!is.character(query_names) ||
-      length(query_names) == 0 ||
-      any(query_names == "")) {
-    stop('query_names must be a non-empty vector of non-empty character names')
-  }
-  return(all(query_names %in% cb_names))
-}

R-package/R/utils.R

@@ -1,428 +0,0 @@
-#
-# This file is for the low level reusable utility functions
-# that are not supposed to be visible to a user.
-#
-
-#
-# General helper utilities ----------------------------------------------------
-#
-
-# SQL-style NVL shortcut.
-NVL <- function(x, val) {
-  if (is.null(x))
-    return(val)
-  if (is.vector(x)) {
-    x[is.na(x)] <- val
-    return(x)
-  }
-  if (typeof(x) == 'closure')
-    return(x)
-  stop("typeof(x) == ", typeof(x), " is not supported by NVL")
-}
-
-# List of classification and ranking objectives
-.CLASSIFICATION_OBJECTIVES <- function() {
-  return(c('binary:logistic', 'binary:logitraw', 'binary:hinge', 'multi:softmax',
-           'multi:softprob', 'rank:pairwise', 'rank:ndcg', 'rank:map'))
-}
-
-
-#
-# Low-level functions for boosting --------------------------------------------
-#
-
-# Merges booster params with whatever is provided in ...
-# plus runs some checks
-check.booster.params <- function(params, ...) {
-  if (!identical(class(params), "list"))
-    stop("params must be a list")
-
-  # in R interface, allow for '.' instead of '_' in parameter names
-  names(params) <- gsub("\\.", "_", names(params))
-
-  # merge parameters from the params and the dots-expansion
-  dot_params <- list(...)
-  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.")
-  params <- c(params, dot_params)
-
-  # providing a parameter multiple times makes sense only for 'eval_metric'
-  name_freqs <- table(names(params))
-  multi_names <- setdiff(names(name_freqs[name_freqs > 1]), 'eval_metric')
-  if (length(multi_names) > 0) {
-    warning("The following parameters were provided multiple times:\n\t",
-            paste(multi_names, collapse = ', '), "\n  Only the last value for each of them will be used.\n")
-    # While xgboost internals would choose the last value for a multiple-times parameter,
-    # enforce it here in R as well (b/c multi-parameters might be used further in R code,
-    # and R takes the 1st value when multiple elements with the same name are present in a list).
-    for (n in multi_names) {
-      del_idx <- which(n == names(params))
-      del_idx <- del_idx[-length(del_idx)]
-      params[[del_idx]] <- NULL
-    }
-  }
-
-  # for multiclass, expect num_class to be set
-  if (typeof(params[['objective']]) == "character" &&
-      substr(NVL(params[['objective']], 'x'), 1, 6) == 'multi:' &&
-      as.numeric(NVL(params[['num_class']], 0)) < 2) {
-        stop("'num_class' > 1 parameter must be set for multiclass classification")
-  }
-
-  # monotone_constraints parser
-
-  if (!is.null(params[['monotone_constraints']]) &&
-      typeof(params[['monotone_constraints']]) != "character") {
-        vec2str <- paste(params[['monotone_constraints']], collapse = ',')
-        vec2str <- paste0('(', vec2str, ')')
-        params[['monotone_constraints']] <- vec2str
-  }
-
-  # interaction constraints parser (convert from list of column indices to string)
-  if (!is.null(params[['interaction_constraints']]) &&
-      typeof(params[['interaction_constraints']]) != "character"){
-    # check input class
-    if (!identical(class(params[['interaction_constraints']]), 'list')) stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric', 'integer'))) {
-      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 = ','), ']')
-  }
-  return(params)
-}
-
-
-# Performs some checks related to custom objective function.
-# WARNING: has side-effects and can modify 'params' and 'obj' in its calling frame
-check.custom.obj <- function(env = parent.frame()) {
-  if (!is.null(env$params[['objective']]) && !is.null(env$obj))
-    stop("Setting objectives in 'params' and 'obj' at the same time is not allowed")
-
-  if (!is.null(env$obj) && typeof(env$obj) != 'closure')
-    stop("'obj' must be a function")
-
-  # handle the case when custom objective function was provided through params
-  if (!is.null(env$params[['objective']]) &&
-      typeof(env$params$objective) == 'closure') {
-    env$obj <- env$params$objective
-    env$params$objective <- NULL
-  }
-}
-
-# Performs some checks related to custom evaluation function.
-# WARNING: has side-effects and can modify 'params' and 'feval' in its calling frame
-check.custom.eval <- function(env = parent.frame()) {
-  if (!is.null(env$params[['eval_metric']]) && !is.null(env$feval))
-    stop("Setting evaluation metrics in 'params' and 'feval' at the same time is not allowed")
-
-  if (!is.null(env$feval) && typeof(env$feval) != 'closure')
-    stop("'feval' must be a function")
-
-  # handle a situation when custom eval function was provided through params
-  if (!is.null(env$params[['eval_metric']]) &&
-      typeof(env$params$eval_metric) == 'closure') {
-    env$feval <- env$params$eval_metric
-    env$params$eval_metric <- NULL
-  }
-
-  # require maximize to be set when custom feval and early stopping are used together
-  if (!is.null(env$feval) &&
-      is.null(env$maximize) && (
-        !is.null(env$early_stopping_rounds) ||
-        has.callbacks(env$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(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")
-  }
-
-  if (is.null(obj)) {
-    .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
-  } else {
-    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE,
-                    ntreelimit = 0)
-    gpair <- obj(pred, dtrain)
-    .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
-  }
-  return(TRUE)
-}
-
-
-# Evaluate one iteration.
-# Returns a named vector of evaluation metrics
-# with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
-  if (!identical(class(booster_handle), "xgb.Booster.handle"))
-    stop("class of booster_handle must be xgb.Booster.handle")
-
-  if (length(watchlist) == 0)
-    return(NULL)
-
-  evnames <- names(watchlist)
-  if (is.null(feval)) {
-    msg <- .Call(XGBoosterEvalOneIter_R, booster_handle, as.integer(iter), watchlist, as.list(evnames))
-    mat <- matrix(strsplit(msg, '\\s+|:')[[1]][-1], nrow = 2)
-    res <- structure(as.numeric(mat[2, ]), names = mat[1, ])
-  } else {
-    res <- sapply(seq_along(watchlist), function(j) {
-      w <- watchlist[[j]]
-      ## predict using all trees
-      preds <- predict(booster_handle, w, outputmargin = TRUE, iterationrange = c(1, 1))
-      eval_res <- feval(preds, w)
-      out <- eval_res$value
-      names(out) <- paste0(evnames[j], "-", eval_res$metric)
-      out
-    })
-  }
-  return(res)
-}
-
-
-#
-# Helper functions for cross validation ---------------------------------------
-#
-
-# Possibly convert the labels into factors, depending on the objective.
-# The labels are converted into factors only when the given objective refers to the classification
-# or ranking tasks.
-convert.labels <- function(labels, objective_name) {
-  if (objective_name %in% .CLASSIFICATION_OBJECTIVES()) {
-    return(as.factor(labels))
-  } else {
-    return(labels)
-  }
-}
-
-# Generates random (stratified if needed) CV folds
-generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
-
-  # cannot do it for rank
-  objective <- params$objective
-  if (is.character(objective) && strtrim(objective, 5) == 'rank:') {
-    stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
-         "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
-  }
-  # shuffle
-  rnd_idx <- sample.int(nrows)
-  if (stratified &&
-      length(label) == length(rnd_idx)) {
-    y <- label[rnd_idx]
-    # WARNING: some heuristic logic is employed to identify classification setting!
-    #  - For classification, need to convert y labels to factor before making the folds,
-    #    and then do stratification by factor levels.
-    #  - For regression, leave y numeric and do stratification by quantiles.
-    if (is.character(objective)) {
-      y <- convert.labels(y, params$objective)
-    } else {
-      # If no 'objective' given in params, it means that user either wants to
-      # use the default 'reg:squarederror' objective or has provided a custom
-      # obj function.  Here, assume classification setting when y has 5 or less
-      # unique values:
-      if (length(unique(y)) <= 5) {
-        y <- factor(y)
-      }
-    }
-    folds <- xgb.createFolds(y, nfold)
-  } else {
-    # make simple non-stratified folds
-    kstep <- length(rnd_idx) %/% nfold
-    folds <- list()
-    for (i in seq_len(nfold - 1)) {
-      folds[[i]] <- rnd_idx[seq_len(kstep)]
-      rnd_idx <- rnd_idx[-seq_len(kstep)]
-    }
-    folds[[nfold]] <- rnd_idx
-  }
-  return(folds)
-}
-
-# Creates CV folds stratified by the values of y.
-# It was borrowed from caret::createFolds and simplified
-# by always returning an unnamed list of fold indices.
-xgb.createFolds <- function(y, k = 10)
-{
-  if (is.numeric(y)) {
-    ## Group the numeric data based on their magnitudes
-    ## and sample within those groups.
-
-    ## When the number of samples is low, we may have
-    ## issues further slicing the numeric data into
-    ## groups. The number of groups will depend on the
-    ## ratio of the number of folds to the sample size.
-    ## At most, we will use quantiles. If the sample
-    ## is too small, we just do regular unstratified
-    ## CV
-    cuts <- floor(length(y) / k)
-    if (cuts < 2) cuts <- 2
-    if (cuts > 5) cuts <- 5
-    y <- cut(y,
-             unique(stats::quantile(y, probs = seq(0, 1, length = cuts))),
-             include.lowest = TRUE)
-  }
-
-  if (k < length(y)) {
-    ## reset levels so that the possible levels and
-    ## the levels in the vector are the same
-    y <- factor(as.character(y))
-    numInClass <- table(y)
-    foldVector <- vector(mode = "integer", length(y))
-
-    ## For each class, balance the fold allocation as far
-    ## as possible, then resample the remainder.
-    ## The final assignment of folds is also randomized.
-    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.
-      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))
-      ## shuffle the integers for fold assignment and assign to this classes's data
-      ## seqVector[sample.int(length(seqVector))] is used to handle length(seqVector) == 1
-      foldVector[y == dimnames(numInClass)$y[i]] <- seqVector[sample.int(length(seqVector))]
-    }
-  } else {
-    foldVector <- seq(along = y)
-  }
-
-  out <- split(seq(along = y), foldVector)
-  names(out) <- NULL
-  out
-}
-
-
-#
-# Deprectaion notice utilities ------------------------------------------------
-#
-
-#' Deprecation notices.
-#'
-#' At this time, some of the parameter names were changed in order to make the code style more uniform.
-#' The deprecated parameters would be removed in the next release.
-#'
-#' To see all the current deprecated and new parameters, check the \code{xgboost:::depr_par_lut} table.
-#'
-#' A deprecation warning is shown when any of the deprecated parameters is used in a call.
-#' An additional warning is shown when there was a partial match to a deprecated parameter
-#' (as R is able to partially match parameter names).
-#'
-#' @name xgboost-deprecated
-NULL
-
-#' Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
-#' models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.
-#'
-#' It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
-#' \code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
-#' \code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
-#' the model is to be accessed in the future. If you train a model with the current version of
-#' XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
-#' accessible in later releases of XGBoost. To ensure that your model can be accessed in future
-#' releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
-#'
-#' @details
-#' Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
-#' the JSON format by specifying the JSON extension. To read the model back, use
-#' \code{\link{xgb.load}}.
-#'
-#' Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
-#' in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
-#' re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
-#' The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
-#' as part of another R object.
-#'
-#' Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
-#' model but also internal configurations and parameters, and its format is not stable across
-#' multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
-#'
-#' For more details and explanation about model persistence and archival, consult the page
-#' \url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' # Save as a stand-alone file; load it with xgb.load()
-#' xgb.save(bst, 'xgb.model')
-#' bst2 <- xgb.load('xgb.model')
-#'
-#' # Save as a stand-alone file (JSON); load it with xgb.load()
-#' xgb.save(bst, 'xgb.model.json')
-#' bst2 <- xgb.load('xgb.model.json')
-#' if (file.exists('xgb.model.json')) file.remove('xgb.model.json')
-#'
-#' # Save as a raw byte vector; load it with xgb.load.raw()
-#' xgb_bytes <- xgb.save.raw(bst)
-#' bst2 <- xgb.load.raw(xgb_bytes)
-#'
-#' # Persist XGBoost model as part of another R object
-#' obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
-#' # Persist the R object. Here, saveRDS() is okay, since it doesn't persist
-#' # xgb.Booster directly. What's being persisted is the future-proof byte representation
-#' # as given by xgb.save.raw().
-#' saveRDS(obj, 'my_object.rds')
-#' # Read back the R object
-#' obj2 <- readRDS('my_object.rds')
-#' # Re-construct xgb.Booster object from the bytes
-#' bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
-#' if (file.exists('my_object.rds')) file.remove('my_object.rds')
-#'
-#' @name a-compatibility-note-for-saveRDS-save
-NULL
-
-# Lookup table for the deprecated parameters bookkeeping
-depr_par_lut <- matrix(c(
-  'print.every.n', 'print_every_n',
-  'early.stop.round', 'early_stopping_rounds',
-  'training.data', 'data',
-  'with.stats', 'with_stats',
-  'numberOfClusters', 'n_clusters',
-  'features.keep', 'features_keep',
-  'plot.height', 'plot_height',
-  'plot.width', 'plot_width',
-  'n_first_tree', 'trees',
-  'dummy', 'DUMMY'
-), ncol = 2, byrow = TRUE)
-colnames(depr_par_lut) <- c('old', 'new')
-
-# Checks the dot-parameters for deprecated names
-# (including partial matching), gives a deprecation warning,
-# and sets new parameters to the old parameters' values within its parent frame.
-# WARNING: has side-effects
-check.deprecation <- function(..., env = parent.frame()) {
-  pars <- list(...)
-  # exact and partial matches
-  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)
-  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, "'")
-    }
-    .Deprecated(new_par, old = old_par, package = 'xgboost')
-    if (new_par != 'NULL') {
-      eval(parse(text = paste(new_par, '<-', pars[[pars_par]])), envir = env)
-    }
-  }
-}

R-package/R/xgb.Booster.R

@@ -1,786 +0,0 @@
-# Construct an internal xgboost Booster and return a handle to it.
-# internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(),
-                               modelfile = NULL, handle = NULL) {
-  if (typeof(cachelist) != "list" ||
-      !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
-    stop("cachelist must be a list of xgb.DMatrix objects")
-  }
-  ## Load existing model, dispatch for on disk model file and in memory buffer
-  if (!is.null(modelfile)) {
-    if (typeof(modelfile) == "character") {
-      ## A filename
-      handle <- .Call(XGBoosterCreate_R, cachelist)
-      modelfile <- path.expand(modelfile)
-      .Call(XGBoosterLoadModel_R, handle, modelfile[1])
-      class(handle) <- "xgb.Booster.handle"
-      if (length(params) > 0) {
-        xgb.parameters(handle) <- params
-      }
-      return(handle)
-    } else if (typeof(modelfile) == "raw") {
-      ## A memory buffer
-      bst <- xgb.unserialize(modelfile, handle)
-      xgb.parameters(bst) <- params
-      return (bst)
-    } else if (inherits(modelfile, "xgb.Booster")) {
-      ## A booster object
-      bst <- xgb.Booster.complete(modelfile, saveraw = TRUE)
-      bst <- xgb.unserialize(bst$raw)
-      xgb.parameters(bst) <- params
-      return (bst)
-    } else {
-      stop("modelfile must be either character filename, or raw booster dump, or xgb.Booster object")
-    }
-  }
-  ## Create new model
-  handle <- .Call(XGBoosterCreate_R, cachelist)
-  class(handle) <- "xgb.Booster.handle"
-  if (length(params) > 0) {
-    xgb.parameters(handle) <- params
-  }
-  return(handle)
-}
-
-# Convert xgb.Booster.handle to xgb.Booster
-# internal utility function
-xgb.handleToBooster <- function(handle, raw = NULL) {
-  bst <- list(handle = handle, raw = raw)
-  class(bst) <- "xgb.Booster"
-  return(bst)
-}
-
-# Check whether xgb.Booster.handle is null
-# internal utility function
-is.null.handle <- function(handle) {
-  if (is.null(handle)) return(TRUE)
-
-  if (!identical(class(handle), "xgb.Booster.handle"))
-    stop("argument type must be xgb.Booster.handle")
-
-  if (.Call(XGCheckNullPtr_R, handle))
-    return(TRUE)
-
-  return(FALSE)
-}
-
-# Return a verified to be valid handle out of either xgb.Booster.handle or
-# xgb.Booster internal utility function
-xgb.get.handle <- function(object) {
-  if (inherits(object, "xgb.Booster")) {
-    handle <- object$handle
-  } else if (inherits(object, "xgb.Booster.handle")) {
-    handle <- object
-  } else {
-    stop("argument must be of either xgb.Booster or xgb.Booster.handle class")
-  }
-  if (is.null.handle(handle)) {
-    stop("invalid xgb.Booster.handle")
-  }
-  handle
-}
-
-#' Restore missing parts of an incomplete xgb.Booster object.
-#'
-#' 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).
-#'
-#' @param object object of class \code{xgb.Booster}
-#' @param saveraw a flag indicating whether to append \code{raw} Booster memory dump data
-#'                when it doesn't already exist.
-#'
-#' @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.
-#'
-#' @return
-#' An object of \code{xgb.Booster} class.
-#'
-#' @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")
-#'
-#' # Warning: The resulting RDS file is only compatible with the current XGBoost version.
-#' # Refer to the section titled "a-compatibility-note-for-saveRDS-save".
-#' bst1 <- readRDS("xgb.model.rds")
-#' if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
-#' # the handle is invalid:
-#' print(bst1$handle)
-#'
-#' bst1 <- xgb.Booster.complete(bst1)
-#' # now the handle points to a valid internal booster model:
-#' print(bst1$handle)
-#'
-#' @export
-xgb.Booster.complete <- function(object, saveraw = TRUE) {
-  if (!inherits(object, "xgb.Booster"))
-    stop("argument type must be xgb.Booster")
-
-  if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(modelfile = object$raw, handle = object$handle)
-  } else {
-    if (is.null(object$raw) && saveraw) {
-      object$raw <- xgb.serialize(object$handle)
-    }
-  }
-
-  attrs <- xgb.attributes(object)
-  if (!is.null(attrs$best_ntreelimit)) {
-    object$best_ntreelimit <- as.integer(attrs$best_ntreelimit)
-  }
-  if (!is.null(attrs$best_iteration)) {
-    ## Convert from 0 based back to 1 based.
-    object$best_iteration <- as.integer(attrs$best_iteration) + 1
-  }
-  if (!is.null(attrs$best_score)) {
-    object$best_score <- as.numeric(attrs$best_score)
-  }
-  if (!is.null(attrs$best_msg)) {
-    object$best_msg <- attrs$best_msg
-  }
-  if (!is.null(attrs$niter)) {
-    object$niter <- as.integer(attrs$niter)
-  }
-
-  return(object)
-}
-
-#' Predict method for eXtreme Gradient Boosting model
-#'
-#' Predicted values based on either xgboost model or model handle object.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}
-#' @param newdata takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-#'        local data file or \code{xgb.DMatrix}.
-#'
-#'        For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-#'        a sparse vector, it will take it as a row vector.
-#' @param missing Missing is only used when input is dense matrix. Pick a float value that represents
-#'        missing values in data (e.g., sometimes 0 or some other extreme value is used).
-#' @param outputmargin whether the prediction should be returned in the for of original untransformed
-#'        sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
-#'        logistic regression would result in predictions for log-odds instead of probabilities.
-#' @param ntreelimit Deprecated, use \code{iterationrange} instead.
-#' @param predleaf whether predict leaf index.
-#' @param predcontrib whether to return feature contributions to individual predictions (see Details).
-#' @param approxcontrib whether to use a fast approximation for feature contributions (see Details).
-#' @param predinteraction whether to return contributions of feature interactions to individual predictions (see Details).
-#' @param reshape whether to reshape the vector of predictions to a matrix form when there are several
-#'        prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
-#'        or predinteraction flags is TRUE.
-#' @param training whether is the prediction result used for training.  For dart booster,
-#'        training predicting will perform dropout.
-#' @param iterationrange Specifies which layer of trees are used in prediction.  For
-#'        example, if a random forest is trained with 100 rounds.  Specifying
-#'        `iterationrange=(1, 21)`, then only the forests built during [1, 21) (half open set)
-#'        rounds are used in this prediction.  It's 1-based index just like R vector.  When set
-#'        to \code{c(1, 1)} XGBoost will use all trees.
-#' @param strict_shape  Default is \code{FALSE}. When it's set to \code{TRUE}, output
-#'        type and shape of prediction are invariant to model type.
-#'
-#' @param ... Parameters passed to \code{predict.xgb.Booster}
-#'
-#' @details
-#'
-#' Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
-#' since gblinear doesn't keep its boosting history.
-#'
-#' One possible practical applications of the \code{predleaf} option is to use the model
-#' as a generator of new features which capture non-linearity and interactions,
-#' 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
-#' (feature_beta * feature_value). For "gbtree" booster, feature contributions are SHAP
-#' values (Lundberg 2017) that sum to the difference between the expected output
-#' of the model and the current prediction (where the hessian weights are used to compute the expectations).
-#' Setting \code{approxcontrib = TRUE} approximates these values following the idea explained
-#' in \url{http://blog.datadive.net/interpreting-random-forests/}.
-#'
-#' With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
-#' are computed. Note that this operation might be rather expensive in terms of compute and memory.
-#' Since it quadratically depends on the number of features, it is recommended to perform selection
-#' of the most important features first. See below about the format of the returned results.
-#'
-#' @return
-#' The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
-#' for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
-#' 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{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.
-#'
-#' When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
-#' normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
-#'
-#' For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
-#' For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
-#' For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
-#'
-#' @seealso
-#' \code{\link{xgb.train}}.
-#'
-#' @references
-#'
-#' 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
-#' ## binary classification:
-#'
-#' 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 = 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, 2))
-#'
-#' # Predicting tree leafs:
-#' # the result is an nsamples X ntrees matrix
-#' pred_leaf <- predict(bst, test$data, predleaf = TRUE)
-#' str(pred_leaf)
-#'
-#' # Predicting feature contributions to predictions:
-#' # the result is an nsamples X (nfeatures + 1) matrix
-#' pred_contr <- predict(bst, test$data, predcontrib = TRUE)
-#' str(pred_contr)
-#' # verify that contributions' sums are equal to log-odds of predictions (up to float precision):
-#' summary(rowSums(pred_contr) - qlogis(pred))
-#' # for the 1st record, let's inspect its features that had non-zero contribution to prediction:
-#' contr1 <- pred_contr[1,]
-#' contr1 <- contr1[-length(contr1)]    # drop BIAS
-#' contr1 <- contr1[contr1 != 0]        # drop non-contributing features
-#' contr1 <- contr1[order(abs(contr1))] # order by contribution magnitude
-#' old_mar <- par("mar")
-#' par(mar = old_mar + c(0,7,0,0))
-#' barplot(contr1, horiz = TRUE, las = 2, xlab = "contribution to prediction in log-odds")
-#' par(mar = old_mar)
-#'
-#'
-#' ## multiclass classification in iris dataset:
-#'
-#' lb <- as.numeric(iris$Species) - 1
-#' num_class <- 3
-#' set.seed(11)
-#' 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)
-#' # 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)
-#'
-#' # compare that to the predictions from softmax:
-#' set.seed(11)
-#' 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, 6))
-#' sum(pred5 != lb)/length(lb)
-#'
-#' @rdname predict.xgb.Booster
-#' @export
-predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE, ntreelimit = NULL,
-                                predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, training = FALSE, iterationrange = NULL, strict_shape = FALSE, ...) {
-  object <- xgb.Booster.complete(object, saveraw = FALSE)
-  if (!inherits(newdata, "xgb.DMatrix"))
-    newdata <- xgb.DMatrix(newdata, missing = missing)
-  if (!is.null(object[["feature_names"]]) &&
-      !is.null(colnames(newdata)) &&
-      !identical(object[["feature_names"]], colnames(newdata)))
-    stop("Feature names stored in `object` and `newdata` are different!")
-
-  if (NVL(object$params[['booster']], '') == 'gblinear' || is.null(ntreelimit))
-    ntreelimit <- 0
-
-  if (ntreelimit != 0 && is.null(iterationrange)) {
-    ## only ntreelimit, initialize iteration range
-    iterationrange <- c(0, 0)
-  } else if (ntreelimit == 0 && !is.null(iterationrange)) {
-    ## only iteration range, handle 1-based indexing
-    iterationrange <- c(iterationrange[1] - 1, iterationrange[2] - 1)
-  } else if (ntreelimit != 0 && !is.null(iterationrange)) {
-    ## both are specified, let libgxgboost throw an error
-  } else {
-    ## no limit is supplied, use best
-    if (is.null(object$best_iteration)) {
-      iterationrange <- c(0, 0)
-    } else {
-      ## We don't need to + 1 as R is 1-based index.
-      iterationrange <- c(0, as.integer(object$best_iteration))
-    }
-  }
-  ## Handle the 0 length values.
-  box <- function(val) {
-    if (length(val) == 0) {
-      cval <- vector(, 1)
-      cval[0] <- val
-      return(cval)
-    }
-    return (val)
-  }
-
-  ## We set strict_shape to TRUE then drop the dimensions conditionally
-  args <- list(
-    training = box(training),
-    strict_shape = box(TRUE),
-    iteration_begin = box(as.integer(iterationrange[1])),
-    iteration_end = box(as.integer(iterationrange[2])),
-    ntree_limit = box(as.integer(ntreelimit)),
-    type = box(as.integer(0))
-  )
-
-  set_type <- function(type) {
-    if (args$type != 0) {
-      stop("One type of prediction at a time.")
-    }
-    return(box(as.integer(type)))
-  }
-  if (outputmargin) {
-    args$type <- set_type(1)
-  }
-  if (predcontrib) {
-    args$type <- set_type(if (approxcontrib) 3 else 2)
-  }
-  if (predinteraction) {
-    args$type <- set_type(if (approxcontrib) 5 else 4)
-  }
-  if (predleaf) {
-    args$type <- set_type(6)
-  }
-
-  predts <- .Call(
-    XGBoosterPredictFromDMatrix_R, object$handle, newdata, jsonlite::toJSON(args, auto_unbox = TRUE)
-  )
-  names(predts) <- c("shape", "results")
-  shape <- predts$shape
-  ret <- predts$results
-
-  n_ret <- length(ret)
-  n_row <- nrow(newdata)
-  if (n_row != shape[1]) {
-    stop("Incorrect predict shape.")
-  }
-
-  arr <- array(data = ret, dim = rev(shape))
-
-  cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
-  n_groups <- shape[2]
-
-  ## Needed regardless of whether strict shape is being used.
-  if (predcontrib) {
-    dimnames(arr) <- list(cnames, NULL, NULL)
-  } else if (predinteraction) {
-    dimnames(arr) <- list(cnames, cnames, NULL, NULL)
-  }
-  if (strict_shape) {
-    return(arr) # strict shape is calculated by libxgboost uniformly.
-  }
-
-  if (predleaf) {
-    ## Predict leaf
-    arr <- if (n_ret == n_row) {
-      matrix(arr, ncol = 1)
-    } else {
-      matrix(arr, nrow = n_row, byrow = TRUE)
-    }
-  } else if (predcontrib) {
-    ## Predict contribution
-    arr <- aperm(a = arr, perm = c(2, 3, 1)) # [group, row, col]
-    arr <- if (n_ret == n_row) {
-      matrix(arr, ncol =  1, dimnames = list(NULL, cnames))
-    } else if (n_groups != 1) {
-      ## turns array into list of matrices
-      lapply(seq_len(n_groups), function(g) arr[g, , ])
-    } else {
-      ## remove the first axis (group)
-      dn <- dimnames(arr)
-      matrix(arr[1, , ], nrow = dim(arr)[2], ncol = dim(arr)[3], dimnames = c(dn[2], dn[3]))
-    }
-  } else if (predinteraction) {
-    ## Predict interaction
-    arr <- aperm(a = arr, perm = c(3, 4, 1, 2)) # [group, row, col, col]
-    arr <- if (n_ret == n_row) {
-      matrix(arr, ncol = 1, dimnames = list(NULL, cnames))
-    } else if (n_groups != 1) {
-      ## turns array into list of matrices
-      lapply(seq_len(n_groups), function(g) arr[g, , , ])
-    } else {
-      ## remove the first axis (group)
-      arr <- arr[1, , , , drop = FALSE]
-      array(arr, dim = dim(arr)[2:4], dimnames(arr)[2:4])
-    }
-  } else {
-    ## Normal prediction
-    arr <- if (reshape && n_groups != 1) {
-      matrix(arr, ncol = n_groups, byrow = TRUE)
-    } else {
-      as.vector(ret)
-    }
-  }
-  return(arr)
-}
-
-#' @rdname predict.xgb.Booster
-#' @export
-predict.xgb.Booster.handle <- function(object, ...) {
-
-  bst <- xgb.handleToBooster(object)
-
-  ret <- predict(bst, ...)
-  return(ret)
-}
-
-
-#' Accessors for serializable attributes of a model.
-#'
-#' These methods allow to manipulate the key-value attribute strings of an xgboost model.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.
-#' @param name a non-empty character string specifying which attribute is to be accessed.
-#' @param value a value of an attribute for \code{xgb.attr<-}; for \code{xgb.attributes<-}
-#'        it's a list (or an object coercible to a list) with the names of attributes to set
-#'        and the elements corresponding to attribute values.
-#'        Non-character values are converted to character.
-#'        When attribute value is not a scalar, only the first index is used.
-#'        Use \code{NULL} to remove an attribute.
-#'
-#' @details
-#' The primary purpose of xgboost model attributes is to store some meta-data about the model.
-#' Note that they are a separate concept from the object attributes in R.
-#' Specifically, they refer to key-value strings that can be attached to an xgboost model,
-#' stored together with the model's binary representation, and accessed later
-#' (from R or any other interface).
-#' In contrast, any R-attribute assigned to an R-object of \code{xgb.Booster} class
-#' would not be saved by \code{xgb.save} because an xgboost model is an external memory object
-#' and its serialization is handled externally.
-#' Also, setting an attribute that has the same name as one of xgboost's parameters wouldn't
-#' change the value of that parameter for a model.
-#' Use \code{\link{xgb.parameters<-}} to set or change model parameters.
-#'
-#' The attribute setters would usually work more efficiently for \code{xgb.Booster.handle}
-#' than for \code{xgb.Booster}, since only just a handle (pointer) would need to be copied.
-#' That would only matter if attributes need to be set many times.
-#' Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
-#' the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-#' and it would be user's responsibility to call \code{xgb.serialize} to update it.
-#'
-#' The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
-#' but it doesn't delete the other existing attributes.
-#'
-#' @return
-#' \code{xgb.attr} returns either a string value of an attribute
-#' or \code{NULL} if an attribute wasn't stored in a model.
-#'
-#' \code{xgb.attributes} returns a list of all attribute stored in a model
-#' or \code{NULL} if a model has no stored attributes.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' xgb.attr(bst, "my_attribute") <- "my attribute value"
-#' print(xgb.attr(bst, "my_attribute"))
-#' xgb.attributes(bst) <- list(a = 123, b = "abc")
-#'
-#' xgb.save(bst, 'xgb.model')
-#' bst1 <- xgb.load('xgb.model')
-#' if (file.exists('xgb.model')) file.remove('xgb.model')
-#' print(xgb.attr(bst1, "my_attribute"))
-#' print(xgb.attributes(bst1))
-#'
-#' # deletion:
-#' xgb.attr(bst1, "my_attribute") <- NULL
-#' print(xgb.attributes(bst1))
-#' xgb.attributes(bst1) <- list(a = NULL, b = NULL)
-#' print(xgb.attributes(bst1))
-#'
-#' @rdname xgb.attr
-#' @export
-xgb.attr <- function(object, name) {
-  if (is.null(name) || nchar(as.character(name[1])) == 0) stop("invalid attribute name")
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterGetAttr_R, handle, as.character(name[1]))
-}
-
-#' @rdname xgb.attr
-#' @export
-`xgb.attr<-` <- function(object, name, value) {
-  if (is.null(name) || nchar(as.character(name[1])) == 0) stop("invalid attribute name")
-  handle <- xgb.get.handle(object)
-  if (!is.null(value)) {
-    # Coerce the elements to be scalar strings.
-    # Q: should we warn user about non-scalar elements?
-    if (is.numeric(value[1])) {
-      value <- format(value[1], digits = 17)
-    } else {
-      value <- as.character(value[1])
-    }
-  }
-  .Call(XGBoosterSetAttr_R, handle, as.character(name[1]), value)
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
-  }
-  object
-}
-
-#' @rdname xgb.attr
-#' @export
-xgb.attributes <- function(object) {
-  handle <- xgb.get.handle(object)
-  attr_names <- .Call(XGBoosterGetAttrNames_R, handle)
-  if (is.null(attr_names)) return(NULL)
-  res <- lapply(attr_names, function(x) {
-    .Call(XGBoosterGetAttr_R, handle, x)
-  })
-  names(res) <- attr_names
-  res
-}
-
-#' @rdname xgb.attr
-#' @export
-`xgb.attributes<-` <- function(object, value) {
-  a <- as.list(value)
-  if (is.null(names(a)) || any(nchar(names(a)) == 0)) {
-    stop("attribute names cannot be empty strings")
-  }
-  # Coerce the elements to be scalar strings.
-  # Q: should we warn a user about non-scalar elements?
-  a <- lapply(a, function(x) {
-    if (is.null(x)) return(NULL)
-    if (is.numeric(x[1])) {
-      format(x[1], digits = 17)
-    } else {
-      as.character(x[1])
-    }
-  })
-  handle <- xgb.get.handle(object)
-  for (i in seq_along(a)) {
-    .Call(XGBoosterSetAttr_R, handle, names(a[i]), a[[i]])
-  }
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
-  }
-  object
-}
-
-#' Accessors for model parameters as JSON string.
-#'
-#' @param object Object of class \code{xgb.Booster}
-#' @param value A JSON string.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' config <- xgb.config(bst)
-#'
-#' @rdname xgb.config
-#' @export
-xgb.config <- function(object) {
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterSaveJsonConfig_R, handle);
-}
-
-#' @rdname xgb.config
-#' @export
-`xgb.config<-` <- function(object, value) {
-  handle <- xgb.get.handle(object)
-  .Call(XGBoosterLoadJsonConfig_R, handle, value)
-  object$raw <- NULL  # force renew the raw buffer
-  object <- xgb.Booster.complete(object)
-  object
-}
-
-#' Accessors for model parameters.
-#'
-#' Only the setter for xgboost parameters is currently implemented.
-#'
-#' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}.
-#' @param value a list (or an object coercible to a list) with the names of parameters to set
-#'        and the elements corresponding to parameter values.
-#'
-#' @details
-#' Note that the setter would usually work more efficiently for \code{xgb.Booster.handle}
-#' than for \code{xgb.Booster}, since only just a handle would need to be copied.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#'
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#'
-#' xgb.parameters(bst) <- list(eta = 0.1)
-#'
-#' @rdname xgb.parameters
-#' @export
-`xgb.parameters<-` <- function(object, value) {
-  if (length(value) == 0) return(object)
-  p <- as.list(value)
-  if (is.null(names(p)) || any(nchar(names(p)) == 0)) {
-    stop("parameter names cannot be empty strings")
-  }
-  names(p) <- gsub("\\.", "_", names(p))
-  p <- lapply(p, function(x) as.character(x)[1])
-  handle <- xgb.get.handle(object)
-  for (i in seq_along(p)) {
-    .Call(XGBoosterSetParam_R, handle, names(p[i]), p[[i]])
-  }
-  if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.serialize(object$handle)
-  }
-  object
-}
-
-# Extract the number of trees in a model.
-# TODO: either add a getter to C-interface, or simply set an 'ntree' attribute after each iteration.
-# internal utility function
-xgb.ntree <- function(bst) {
-  length(grep('^booster', xgb.dump(bst)))
-}
-
-
-#' Print xgb.Booster
-#'
-#' Print information about xgb.Booster.
-#'
-#' @param x an xgb.Booster object
-#' @param verbose whether to print detailed data (e.g., attribute values)
-#' @param ... not currently used
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' attr(bst, 'myattr') <- 'memo'
-#'
-#' print(bst)
-#' print(bst, verbose=TRUE)
-#'
-#' @method print xgb.Booster
-#' @export
-print.xgb.Booster <- function(x, verbose = FALSE, ...) {
-  cat('##### xgb.Booster\n')
-
-  valid_handle <- !is.null.handle(x$handle)
-  if (!valid_handle)
-    cat("Handle is invalid! Suggest using xgb.Booster.complete\n")
-
-  cat('raw: ')
-  if (!is.null(x$raw)) {
-    cat(format(object.size(x$raw), units = "auto"), '\n')
-  } else {
-    cat('NULL\n')
-  }
-  if (!is.null(x$call)) {
-    cat('call:\n  ')
-    print(x$call)
-  }
-
-  if (!is.null(x$params)) {
-    cat('params (as set within xgb.train):\n')
-    cat('  ',
-         paste(names(x$params),
-               paste0('"', unlist(x$params), '"'),
-               sep = ' = ', collapse = ', '), '\n', sep = '')
-  }
-  # TODO: need an interface to access all the xgboosts parameters
-
-  attrs <- character(0)
-  if (valid_handle)
-    attrs <- xgb.attributes(x)
-  if (length(attrs) > 0) {
-    cat('xgb.attributes:\n')
-    if (verbose) {
-        cat(paste(paste0('  ', names(attrs)),
-                  paste0('"', unlist(attrs), '"'),
-                  sep = ' = ', collapse = '\n'), '\n', sep = '')
-    } else {
-      cat('  ', paste(names(attrs), collapse = ', '), '\n', sep = '')
-    }
-  }
-
-  if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
-    cat('callbacks:\n')
-    lapply(callback.calls(x$callbacks), function(x) {
-      cat('  ')
-      print(x)
-    })
-  }
-
-  if (!is.null(x$feature_names))
-    cat('# of features:', length(x$feature_names), '\n')
-
-  cat('niter: ', x$niter, '\n', sep = '')
-  # TODO: uncomment when faster xgb.ntree is implemented
-  #cat('ntree: ', xgb.ntree(x), '\n', sep='')
-
-  for (n in setdiff(names(x), c('handle', 'raw', 'call', 'params', 'callbacks',
-                                'evaluation_log', 'niter', 'feature_names'))) {
-    if (is.atomic(x[[n]])) {
-      cat(n, ':', x[[n]], '\n', sep = ' ')
-    } else {
-      cat(n, ':\n\t', sep = ' ')
-      print(x[[n]])
-    }
-  }
-
-  if (!is.null(x$evaluation_log)) {
-    cat('evaluation_log:\n')
-    print(x$evaluation_log, row.names = FALSE, topn = 2)
-  }
-
-  invisible(x)
-}

R-package/R/xgb.DMatrix.R

@@ -1,431 +0,0 @@
-#' Construct xgb.DMatrix object
-#'
-#' Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-#' Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
-#' \code{\link{xgb.DMatrix.save}}).
-#'
-#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-#'        a \code{dgRMatrix} object (only when making predictions from a fitted model),
-#'        a \code{dsparseVector} object (only when making predictions from a fitted model, will be
-#'        interpreted as a row vector), or a character string representing a filename.
-#' @param info a named list of additional information to store in the \code{xgb.DMatrix} object.
-#'        See \code{\link{setinfo}} for the specific allowed kinds of
-#' @param missing a float value to represents missing values in data (used only when input is a dense matrix).
-#'        It is useful when a 0 or some other extreme value represents missing values in data.
-#' @param silent whether to suppress printing an informational message after loading from a file.
-#' @param nthread Number of threads used for creating DMatrix.
-#' @param ... the \code{info} data could be passed directly as parameters, without creating an \code{info} list.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-#' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
-#' @export
-xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthread = NULL, ...) {
-  cnames <- NULL
-  if (typeof(data) == "character") {
-    if (length(data) > 1)
-      stop("'data' has class 'character' and length ", length(data),
-           ".\n  'data' accepts either a numeric matrix or a single filename.")
-    data <- path.expand(data)
-    handle <- .Call(XGDMatrixCreateFromFile_R, data, as.integer(silent))
-  } else if (is.matrix(data)) {
-    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing, as.integer(NVL(nthread, -1)))
-    cnames <- colnames(data)
-  } else if (inherits(data, "dgCMatrix")) {
-    handle <- .Call(
-      XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data), as.integer(NVL(nthread, -1))
-    )
-    cnames <- colnames(data)
-  } else if (inherits(data, "dgRMatrix")) {
-    handle <- .Call(
-      XGDMatrixCreateFromCSR_R, data@p, data@j, data@x, ncol(data), as.integer(NVL(nthread, -1))
-    )
-    cnames <- colnames(data)
-  } else if (inherits(data, "dsparseVector")) {
-    indptr <- c(0L, as.integer(length(data@i)))
-    ind <- as.integer(data@i) - 1L
-    handle <- .Call(
-      XGDMatrixCreateFromCSR_R, indptr, ind, data@x, length(data), as.integer(NVL(nthread, -1))
-    )
-  } else {
-    stop("xgb.DMatrix does not support construction from ", typeof(data))
-  }
-  dmat <- handle
-  attributes(dmat) <- list(class = "xgb.DMatrix")
-  if (!is.null(cnames)) {
-    setinfo(dmat, "feature_name", cnames)
-  }
-
-  info <- append(info, list(...))
-  for (i in seq_along(info)) {
-    p <- info[i]
-    setinfo(dmat, names(p), p[[1]])
-  }
-  return(dmat)
-}
-
-
-# get dmatrix from data, label
-# internal helper method
-xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nthread = NULL) {
-  if (inherits(data, "dgCMatrix") || is.matrix(data)) {
-    if (is.null(label)) {
-      stop("label must be provided when data is a matrix")
-    }
-    dtrain <- xgb.DMatrix(data, label = label, missing = missing, nthread = nthread)
-    if (!is.null(weight)){
-      setinfo(dtrain, "weight", weight)
-    }
-  } else {
-    if (!is.null(label)) {
-      warning("xgboost: label will be ignored.")
-    }
-    if (is.character(data)) {
-      data <- path.expand(data)
-      dtrain <- xgb.DMatrix(data[1])
-    } else if (inherits(data, "xgb.DMatrix")) {
-      dtrain <- data
-    } else if (inherits(data, "data.frame")) {
-      stop("xgboost doesn't support data.frame as input. Convert it to matrix first.")
-    } else {
-      stop("xgboost: invalid input data")
-    }
-  }
-  return (dtrain)
-}
-
-
-#' Dimensions of xgb.DMatrix
-#'
-#' Returns a vector of numbers of rows and of columns in an \code{xgb.DMatrix}.
-#' @param x Object of class \code{xgb.DMatrix}
-#'
-#' @details
-#' Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
-#' 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)
-#'
-#' stopifnot(nrow(dtrain) == nrow(train$data))
-#' stopifnot(ncol(dtrain) == ncol(train$data))
-#' stopifnot(all(dim(dtrain) == dim(train$data)))
-#'
-#' @export
-dim.xgb.DMatrix <- function(x) {
-  c(.Call(XGDMatrixNumRow_R, x), .Call(XGDMatrixNumCol_R, x))
-}
-
-
-#' Handling of column names of \code{xgb.DMatrix}
-#'
-#' Only column names are supported for \code{xgb.DMatrix}, thus setting of
-#' row names would have no effect and returned row names would be NULL.
-#'
-#' @param x object of class \code{xgb.DMatrix}
-#' @param value a list of two elements: the first one is ignored
-#'        and the second one is column names
-#'
-#' @details
-#' Generic \code{dimnames} methods are used by \code{colnames}.
-#' Since row names are irrelevant, it is recommended to use \code{colnames} directly.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
-#' dimnames(dtrain)
-#' colnames(dtrain)
-#' colnames(dtrain) <- make.names(1:ncol(train$data))
-#' print(dtrain, verbose=TRUE)
-#'
-#' @rdname dimnames.xgb.DMatrix
-#' @export
-dimnames.xgb.DMatrix <- function(x) {
-  fn <- getinfo(x, "feature_name")
-  ## row names is null.
-  list(NULL, fn)
-}
-
-#' @rdname dimnames.xgb.DMatrix
-#' @export
-`dimnames<-.xgb.DMatrix` <- function(x, value) {
-  if (!is.list(value) || length(value) != 2L)
-    stop("invalid 'dimnames' given: must be a list of two elements")
-  if (!is.null(value[[1L]]))
-    stop("xgb.DMatrix does not have rownames")
-  if (is.null(value[[2]])) {
-    setinfo(x, "feature_name", NULL)
-    return(x)
-  }
-  if (ncol(x) != length(value[[2]])) {
-    stop("can't assign ", length(value[[2]]), " colnames to a ", ncol(x), " column xgb.DMatrix")
-  }
-  setinfo(x, "feature_name", value[[2]])
-  x
-}
-
-
-#' Get information of an xgb.DMatrix object
-#'
-#' Get information of an xgb.DMatrix object
-#' @param object Object of class \code{xgb.DMatrix}
-#' @param name the name of the information field to get (see details)
-#' @param ... other parameters
-#'
-#' @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{nrow}: number of rows of the \code{xgb.DMatrix}.
-#'
-#' }
-#'
-#' \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))
-#'
-#' labels <- getinfo(dtrain, 'label')
-#' setinfo(dtrain, 'label', 1-labels)
-#'
-#' labels2 <- getinfo(dtrain, 'label')
-#' stopifnot(all(labels2 == 1-labels))
-#' @rdname getinfo
-#' @export
-getinfo <- function(object, ...) UseMethod("getinfo")
-
-#' @rdname getinfo
-#' @export
-getinfo.xgb.DMatrix <- function(object, name, ...) {
-  if (typeof(name) != "character" ||
-        length(name) != 1 ||
-        !name %in% c('label', 'weight', 'base_margin', 'nrow',
-                     'label_lower_bound', 'label_upper_bound', "feature_type", "feature_name")) {
-    stop(
-      "getinfo: name must be one of the following\n",
-      "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound', 'feature_type', 'feature_name'"
-    )
-  }
-  if (name == "feature_name" || name == "feature_type") {
-    ret <- .Call(XGDMatrixGetStrFeatureInfo_R, object, name)
-  } else if (name != "nrow"){
-    ret <- .Call(XGDMatrixGetInfo_R, object, name)
-  } else {
-    ret <- nrow(object)
-  }
-  if (length(ret) == 0) return(NULL)
-  return(ret)
-}
-
-
-#' Set information of an xgb.DMatrix object
-#'
-#' Set information of an xgb.DMatrix object
-#'
-#' @param object Object of class "xgb.DMatrix"
-#' @param name the name of the field to get
-#' @param info the specific field of information to set
-#' @param ... other parameters
-#'
-#' @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')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#'
-#' labels <- getinfo(dtrain, 'label')
-#' setinfo(dtrain, 'label', 1-labels)
-#' labels2 <- getinfo(dtrain, 'label')
-#' stopifnot(all.equal(labels2, 1-labels))
-#' @rdname setinfo
-#' @export
-setinfo <- function(object, ...) UseMethod("setinfo")
-
-#' @rdname setinfo
-#' @export
-setinfo.xgb.DMatrix <- function(object, name, info, ...) {
-  if (name == "label") {
-    if (length(info) != nrow(object))
-      stop("The length of labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "label_lower_bound") {
-    if (length(info) != nrow(object))
-      stop("The length of lower-bound labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "label_upper_bound") {
-    if (length(info) != nrow(object))
-      stop("The length of upper-bound labels must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "weight") {
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "base_margin") {
-    # if (length(info)!=nrow(object))
-    #   stop("The length of base margin must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-  if (name == "group") {
-    if (sum(info) != nrow(object))
-      stop("The sum of groups must equal to the number of rows in the input data")
-    .Call(XGDMatrixSetInfo_R, object, name, as.integer(info))
-    return(TRUE)
-  }
-  if (name == "feature_weights") {
-    if (length(info) != ncol(object)) {
-      stop("The number of feature weights must equal to the number of columns in the input data")
-    }
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
-
-  set_feat_info <- function(name) {
-    msg <- sprintf(
-      "The number of %s must equal to the number of columns in the input data. %s vs. %s",
-      name,
-      length(info),
-      ncol(object)
-    )
-    if (!is.null(info)) {
-      info <- as.list(info)
-      if (length(info) != ncol(object)) {
-        stop(msg)
-      }
-    }
-    .Call(XGDMatrixSetStrFeatureInfo_R, object, name, info)
-  }
-  if (name == "feature_name") {
-    set_feat_info("feature_name")
-    return(TRUE)
-  }
-  if (name == "feature_type") {
-    set_feat_info("feature_type")
-    return(TRUE)
-  }
-  stop("setinfo: unknown info name ", name)
-  return(FALSE)
-}
-
-
-#' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
-#'
-#' Get a new DMatrix containing the specified rows of
-#' original xgb.DMatrix object
-#'
-#' @param object Object of class "xgb.DMatrix"
-#' @param idxset a integer vector of indices of rows needed
-#' @param colset currently not used (columns subsetting is not available)
-#' @param ... other parameters (currently not used)
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#'
-#' dsub <- slice(dtrain, 1:42)
-#' labels1 <- getinfo(dsub, 'label')
-#' dsub <- dtrain[1:42, ]
-#' labels2 <- getinfo(dsub, 'label')
-#' all.equal(labels1, labels2)
-#'
-#' @rdname slice.xgb.DMatrix
-#' @export
-slice <- function(object, ...) UseMethod("slice")
-
-#' @rdname slice.xgb.DMatrix
-#' @export
-slice.xgb.DMatrix <- function(object, idxset, ...) {
-  if (!inherits(object, "xgb.DMatrix")) {
-    stop("object must be xgb.DMatrix")
-  }
-  ret <- .Call(XGDMatrixSliceDMatrix_R, object, idxset)
-
-  attr_list <- attributes(object)
-  nr <- nrow(object)
-  len <- sapply(attr_list, NROW)
-  ind <- which(len == nr)
-  if (length(ind) > 0) {
-    nms <- names(attr_list)[ind]
-    for (i in seq_along(ind)) {
-      obj_attr <- attr(object, nms[i])
-      if (NCOL(obj_attr) > 1) {
-        attr(ret, nms[i]) <- obj_attr[idxset, ]
-      } else {
-        attr(ret, nms[i]) <- obj_attr[idxset]
-      }
-    }
-  }
-  return(structure(ret, class = "xgb.DMatrix"))
-}
-
-#' @rdname slice.xgb.DMatrix
-#' @export
-`[.xgb.DMatrix` <- function(object, idxset, colset = NULL) {
-  slice(object, idxset)
-}
-
-
-#' Print xgb.DMatrix
-#'
-#' Print information about xgb.DMatrix.
-#' Currently it displays dimensions and presence of info-fields and colnames.
-#'
-#' @param x an xgb.DMatrix object
-#' @param verbose whether to print colnames (when present)
-#' @param ... not currently used
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#'
-#' dtrain
-#' print(dtrain, verbose=TRUE)
-#'
-#' @method print xgb.DMatrix
-#' @export
-print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
-  cat('xgb.DMatrix  dim:', nrow(x), 'x', ncol(x), ' info: ')
-  infos <- character(0)
-  if (length(getinfo(x, 'label')) > 0) infos <- 'label'
-  if (length(getinfo(x, 'weight')) > 0) infos <- c(infos, 'weight')
-  if (length(getinfo(x, 'base_margin')) > 0) infos <- c(infos, 'base_margin')
-  if (length(infos) == 0) infos <- 'NA'
-  cat(infos)
-  cnames <- colnames(x)
-  cat('  colnames:')
-  if (verbose & !is.null(cnames)) {
-    cat("\n'")
-    cat(cnames, sep = "','")
-    cat("'")
-  } else {
-    if (is.null(cnames)) cat(' no')
-    else cat(' yes')
-  }
-  cat("\n")
-  invisible(x)
-}

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

@@ -1,24 +0,0 @@
-#' 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
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
-#' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
-#' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
-#' @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

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

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

@@ -1,87 +0,0 @@
-#' 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
-#' 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,
-#' 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/}.
-#'
-#' 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,
-#' 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))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
-#'
-#' 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)
-#' 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, ...){
-  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
-}

R-package/R/xgb.cv.R

@@ -1,322 +0,0 @@
-#' Cross Validation
-#'
-#' 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:
-#' \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{eta} step size of each boosting step
-#'   \item \code{max_depth} maximum depth of the tree
-#'   \item \code{nthread} number of thread used in training, if not set, all threads are used
-#' }
-#'
-#'   See \code{\link{xgb.train}} for further details.
-#'   See also demo/ for walkthrough example in R.
-#' @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{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.
-#'   Possible options are:
-#' \itemize{
-#'   \item \code{error} binary classification error rate
-#'   \item \code{rmse} Rooted mean square error
-#'   \item \code{logloss} negative log-likelihood function
-#'   \item \code{mae} Mean absolute error
-#'   \item \code{mape} Mean absolute percentage error
-#'   \item \code{auc} Area under curve
-#'   \item \code{aucpr} Area under PR curve
-#'   \item \code{merror} Exact matching error, used to evaluate multi-class classification
-#' }
-#' @param obj customized objective function. Returns gradient and second order
-#'        gradient with given prediction and dtrain.
-#' @param feval customized evaluation function. Returns
-#'        \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.
-#' @param folds \code{list} provides a possibility to use a list of pre-defined CV folds
-#'        (each element must be a vector of test fold's indices). When folds are supplied,
-#'        the \code{nfold} and \code{stratified} parameters are ignored.
-#' @param train_folds \code{list} list specifying which indicies to use for training. If \code{NULL}
-#'        (the default) all indices not specified in \code{folds} will be used for training.
-#' @param verbose \code{boolean}, print the statistics during the process
-#' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
-#'        Default is 1 which means all messages are printed. This parameter is passed to the
-#'        \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{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{cb.early.stop}} callback.
-#' @param callbacks a list of callback functions to perform various task during boosting.
-#'        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}.
-#'
-#' @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.
-#'
-#' 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}
-#'
-#' @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{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{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} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
-#'   \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.
-#' }
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-#'                   max_depth = 3, eta = 1, objective = "binary:logistic")
-#' print(cv)
-#' print(cv, verbose=TRUE)
-#'
-#' @export
-xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NA,
-                   prediction = FALSE, showsd = TRUE, metrics=list(),
-                   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(...)
-
-  params <- check.booster.params(params, ...)
-  # TODO: should we deprecate the redundant 'metrics' parameter?
-  for (m in metrics)
-    params <- c(params, list("eval_metric" = m))
-
-  check.custom.obj()
-  check.custom.eval()
-
-  #if (is.null(params[['eval_metric']]) && is.null(feval))
-  #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
-
-  # Check the labels
-  if ((inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
-      (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
-    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)
-      stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
-    nfold <- length(folds)
-  } else {
-    if (nfold <= 1)
-      stop("'nfold' must be > 1")
-    folds <- generate.cv.folds(nfold, nrow(data), stratified, cv_label, params)
-  }
-
-  # Potential TODO: sequential CV
-  #if (strategy == 'sequential')
-  #  stop('Sequential CV strategy is not yet implemented')
-
-  # verbosity & evaluation printing callback:
-  params <- c(params, list(silent = 1))
-  print_every_n <- max(as.integer(print_every_n), 1L)
-  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
-  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 &&
-      !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 <- xgb.get.DMatrix(data, label, missing)
-  bst_folds <- lapply(seq_along(folds), function(k) {
-    dtest  <- slice(dall, folds[[k]])
-    # code originally contributed by @RolandASc on stackoverflow
-    if (is.null(train_folds))
-       dtrain <- slice(dall, unlist(folds[-k]))
-    else
-       dtrain <- slice(dall, train_folds[[k]])
-    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_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1) # nolint
-
-  # those are fixed for CV (no training continuation)
-  begin_iteration <- 1
-  end_iteration <- nrounds
-
-  # synchronous CV boosting: run CV folds' models within each iteration
-  for (iteration in begin_iteration:end_iteration) {
-
-    for (f in cb$pre_iter) f()
-
-    msg <- lapply(bst_folds, function(fd) {
-      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
-      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
-    })
-    msg <- simplify2array(msg)
-    bst_evaluation <- rowMeans(msg)
-    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2) # nolint
-
-    for (f in cb$post_iter) f()
-
-    if (stop_condition) break
-  }
-  for (f in cb$finalize) f(finalize = TRUE)
-
-  # the CV result
-  ret <- list(
-    call = match.call(),
-    params = params,
-    callbacks = callbacks,
-    evaluation_log = evaluation_log,
-    niter = end_iteration,
-    nfeatures = ncol(data),
-    folds = folds
-  )
-  ret <- c(ret, basket)
-
-  class(ret) <- 'xgb.cv.synchronous'
-  invisible(ret)
-}
-
-
-
-#' Print xgb.cv result
-#'
-#' Prints formatted results of \code{xgb.cv}.
-#'
-#' @param x an \code{xgb.cv.synchronous} object
-#' @param verbose whether to print detailed data
-#' @param ... passed to \code{data.table.print}
-#'
-#' @details
-#' When not verbose, it would only print the evaluation results,
-#' including the best iteration (when available).
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' cv <- xgb.cv(data = train$data, label = train$label, nfold = 5, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-#' print(cv)
-#' print(cv, verbose=TRUE)
-#'
-#' @rdname print.xgb.cv
-#' @method print xgb.cv.synchronous
-#' @export
-print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
-  cat('##### xgb.cv ', length(x$folds), '-folds\n', sep = '')
-
-  if (verbose) {
-    if (!is.null(x$call)) {
-      cat('call:\n  ')
-      print(x$call)
-    }
-    if (!is.null(x$params)) {
-      cat('params (as set within xgb.cv):\n')
-      cat('  ',
-          paste(names(x$params),
-                paste0('"', unlist(x$params), '"'),
-                sep = ' = ', collapse = ', '), '\n', sep = '')
-    }
-    if (!is.null(x$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', 'best_ntreelimit')) {
-      if (is.null(x[[n]]))
-        next
-      cat(n, ': ', x[[n]], '\n', sep = '')
-    }
-
-    if (!is.null(x$pred)) {
-      cat('pred:\n')
-      str(x$pred)
-    }
-  }
-
-  if (verbose)
-    cat('evaluation_log:\n')
-  print(x$evaluation_log, row.names = FALSE, ...)
-
-  if (!is.null(x$best_iteration)) {
-    cat('Best iteration:\n')
-    print(x$evaluation_log[x$best_iteration], row.names = FALSE, ...)
-  }
-  invisible(x)
-}

R-package/R/xgb.dump.R

@@ -1,71 +0,0 @@
-#' 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.
-#'        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.
-#'        See demo/ for walkthrough example in R, and
-#'        \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' or 'json' format could be specified.
-#' @param ... currently not used
-#'
-#' @return
-#' If fname is not provided or set to \code{NULL} the function will return the model
-#' as a \code{character} vector. Otherwise it will return \code{TRUE}.
-#'
-#' @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")
-#' # 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'))
-#'
-#' @export
-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"))
-    stop("model: argument must be of type xgb.Booster")
-  if (!(is.null(fname) || is.character(fname)))
-    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$handle, NVL(fmap, "")[1], as.integer(with_stats),
-                      as.character(dump_format))
-
-  if (is.null(fname))
-    model_dump <- gsub('\t', '', model_dump, fixed = TRUE)
-
-  if (dump_format == "text")
-    model_dump <- unlist(strsplit(model_dump, '\n', fixed = TRUE))
-
-  model_dump <- grep('^\\s*$', 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

@@ -1,213 +0,0 @@
-# ggplot backend for the xgboost plotting facilities
-
-
-#' @rdname xgb.plot.importance
-#' @export
-xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
-                                  rel_to_first = FALSE, n_clusters = c(1:10), ...) {
-
-  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)) {
-    stop("ggplot2 package is required", call. = FALSE)
-  }
-  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::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"),
-                   panel.grid.major.y = ggplot2::element_blank())
-  return(plot)
-}
-
-
-#' @rdname xgb.plot.deepness
-#' @export
-xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.depth", "med.weight")) {
-
-  if (!requireNamespace("ggplot2", quietly = TRUE))
-    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')
-
-  if (which == "2x1") {
-    p1 <-
-      ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = N), stat = "Identity") +
-      ggplot2::xlab("") +
-      ggplot2::ylab("Number of leafs") +
-      ggplot2::ggtitle("Model complexity") +
-      ggplot2::theme(
-        plot.title = ggplot2::element_text(lineheight = 0.9, face = "bold"),
-        panel.grid.major.y = ggplot2::element_blank(),
-        axis.ticks = ggplot2::element_blank(),
-        axis.text.x = ggplot2::element_blank()
-      )
-
-    p2 <-
-      ggplot2::ggplot(dt_summaries) +
-      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) +
-      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) +
-      ggplot2::xlab("tree #") +
-      ggplot2::ylab("Median tree leaf depth")
-    return(p)
-
-  } else if (which == "med.weight") {
-    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) +
-      ggplot2::xlab("tree #") +
-      ggplot2::ylab("Median absolute leaf weight")
-    return(p)
-  }
-}
-
-#' @rdname xgb.plot.shap.summary
-#' @export
-xgb.ggplot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
-                                    trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 10000  # 10,000 samples per feature.
-  )
-  p_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
-  # Reverse factor levels so that the first level is at the top of the plot
-  p_data[, "feature" := factor(feature, rev(levels(feature)))]
-  p <- ggplot2::ggplot(p_data, ggplot2::aes(x = feature, y = p_data$shap_value, colour = p_data$feature_value)) +
-    ggplot2::geom_jitter(alpha = 0.5, width = 0.1) +
-    ggplot2::scale_colour_viridis_c(limits = c(-3, 3), option = "plasma", direction = -1) +
-    ggplot2::geom_abline(slope = 0, intercept = 0, colour = "darkgrey") +
-    ggplot2::coord_flip()
-
-  p
-}
-
-#' Combine and melt feature values and SHAP contributions for sample
-#' observations.
-#'
-#' Conforms to data format required for ggplot functions.
-#'
-#' Internal utility function.
-#'
-#' @param data_list List containing 'data' and 'shap_contrib' returned by
-#'   \code{xgb.shap.data()}.
-#' @param normalize Whether to standardize feature values to have mean 0 and
-#'   standard deviation 1 (useful for comparing multiple features on the same
-#'   plot). Default \code{FALSE}.
-#'
-#' @return A data.table containing the observation ID, the feature name, the
-#'   feature value (normalized if specified), and the SHAP contribution value.
-prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-
-  data <- data.table::as.data.table(as.matrix(data))
-  if (normalize) {
-    data[, (names(data)) := lapply(.SD, normalize)]
-  }
-  data[, "id" := seq_len(nrow(data))]
-  data_m <- data.table::melt.data.table(data, id.vars = "id", variable.name = "feature", value.name = "feature_value")
-
-  shap_contrib <- data.table::as.data.table(as.matrix(shap_contrib))
-  shap_contrib[, "id" := seq_len(nrow(shap_contrib))]
-  shap_contrib_m <- data.table::melt.data.table(shap_contrib, id.vars = "id", variable.name = "feature", value.name = "shap_value")
-
-  p_data <- data.table::merge.data.table(data_m, shap_contrib_m, by = c("id", "feature"))
-
-  p_data
-}
-
-#' Scale feature value to have mean 0, standard deviation 1
-#'
-#' This is used to compare multiple features on the same plot.
-#' Internal utility function
-#'
-#' @param x Numeric vector
-#'
-#' @return Numeric vector with mean 0 and sd 1.
-normalize <- function(x) {
-  loc <- mean(x, na.rm = TRUE)
-  scale <- stats::sd(x, na.rm = TRUE)
-
-  (x - loc) / scale
-}
-
-# Plot multiple ggplot graph aligned by rows and columns.
-# ... the plots
-# cols number of columns
-# internal utility function
-multiplot <- function(..., cols = 1) {
-  plots <- list(...)
-  num_plots <- length(plots)
-
-  layout <- matrix(seq(1, cols * ceiling(num_plots / cols)),
-                   ncol = cols, nrow = ceiling(num_plots / cols))
-
-  if (num_plots == 1) {
-    print(plots[[1]])
-  } else {
-    grid::grid.newpage()
-    grid::pushViewport(grid::viewport(layout = grid::grid.layout(nrow(layout), ncol(layout))))
-    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$row,
-          layout.pos.col = matchidx$col
-        )
-      )
-    }
-  }
-}
-
-globalVariables(c(
-  "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight", "feature"
-))

R-package/R/xgb.importance.R

@@ -1,142 +0,0 @@
-#' 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.
-#' 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")
-#' 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")
-#' xgb.importance(model = bst)
-#'
-#' # multiclass classification using gbtree:
-#' nclass <- 3
-#' nrounds <- 10
-#' mbst <- xgboost(data = as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1,
-#'                max_depth = 3, eta = 0.2, nthread = 2, nrounds = nrounds,
-#'                objective = "multi:softprob", num_class = nclass)
-#' # all classes clumped together:
-#' xgb.importance(model = mbst)
-#' # inspect importances separately for each class:
-#' xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
-#' xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
-#' xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
-#'
-#' # multiclass classification using gblinear:
-#' mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
-#'                booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
-#'                objective = "multi:softprob", num_class = nclass)
-#' xgb.importance(model = mbst)
-#'
-#' @export
-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")
-
-  model <- xgb.Booster.complete(model)
-  config <- jsonlite::fromJSON(xgb.config(model))
-  if (config$learner$gradient_booster$name == "gblinear") {
-    args <- list(importance_type = "weight", feature_names = feature_names)
-    results <- .Call(
-      XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
-    )
-    names(results) <- c("features", "shape", "weight")
-    n_classes <-  if (length(results$shape) == 2) { results$shape[2] } else { 0 }
-    importance <- if (n_classes == 0) {
-      data.table(Feature = results$features, Weight = results$weight)[order(-abs(Weight))]
-    } else {
-      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, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
-      )
-      names(results) <- c("features", "shape", importance_type)
-      concatenated[
-        switch(importance_type, "weight" = "Frequency", "total_gain" = "Gain", "total_cover" = "Cover")
-      ] <- results[importance_type]
-      output_names <- results$features
-    }
-    importance <- data.table(
-        Feature = output_names,
-        Gain = concatenated$Gain / sum(concatenated$Gain),
-        Cover = concatenated$Cover / sum(concatenated$Cover),
-        Frequency = concatenated$Frequency / sum(concatenated$Frequency)
-    )[order(Gain, decreasing = TRUE)]
-  }
-  importance
-}
-
-# Avoid error messages during CRAN check.
-# The reason is that these variables are never declared
-# They are mainly column names inferred by Data.table...
-globalVariables(c(".", ".N", "Gain", "Cover", "Frequency", "Feature", "Class"))

R-package/R/xgb.load.R

@@ -1,54 +0,0 @@
-#' Load xgboost model from binary file
-#'
-#' Load xgboost model from the binary model file.
-#'
-#' @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{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.
-#'
-#' Note: a model saved as an R-object, has to be loaded using corresponding R-methods,
-#' not \code{xgb.load}.
-#'
-#' @return
-#' An object of \code{xgb.Booster} class.
-#'
-#' @seealso
-#' \code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}.
-#'
-#' @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")
-#' 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")
-
-  handle <- xgb.Booster.handle(modelfile = modelfile)
-  # re-use modelfile if it is raw so we do not need to serialize
-  if (typeof(modelfile) == "raw") {
-    warning(
-      paste(
-        "The support for loading raw booster with `xgb.load` will be ",
-        "discontinued in upcoming release. Use `xgb.load.raw` or",
-        " `xgb.unserialize` instead. "
-      )
-    )
-    bst <- xgb.handleToBooster(handle, modelfile)
-  } else {
-    bst <- xgb.handleToBooster(handle, NULL)
-  }
-  bst <- xgb.Booster.complete(bst, saveraw = TRUE)
-  return(bst)
-}

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

@@ -1,23 +0,0 @@
-#' Load serialised xgboost model from R's raw vector
-#'
-#' User can generate raw memory buffer by calling xgb.save.raw
-#'
-#' @param buffer the buffer returned by xgb.save.raw
-#' @param as_booster Return the loaded model as xgb.Booster instead of xgb.Booster.handle.
-#'
-#' @export
-xgb.load.raw <- function(buffer, as_booster = FALSE) {
-  cachelist <- list()
-  handle <- .Call(XGBoosterCreate_R, cachelist)
-  .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
-  class(handle) <- "xgb.Booster.handle"
-
-  if (as_booster) {
-    booster <- list(handle = handle, raw = NULL)
-    class(booster) <- "xgb.Booster"
-    booster <- xgb.Booster.complete(booster, saveraw = TRUE)
-    return(booster)
-  } else {
-    return (handle)
-  }
-}

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

@@ -1,179 +0,0 @@
-#' 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.
-#'
-#' @return
-#' A \code{data.table} with detailed information about model trees' nodes.
-#'
-#' 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')
-#'
-#' 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$data), bst))
-#'
-#' # This bst model already has feature_names stored with it, so those would be used when
-#' # feature_names is not set:
-#' (dt <- xgb.model.dt.tree(model = bst))
-#'
-#' # How to match feature names of splits that are following a current 'Yes' branch:
-#'
-#' merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
-#'
-#' @export
-xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
-                              trees = NULL, use_int_id = FALSE, ...){
-  check.deprecation(...)
-
-  if (!inherits(model, "xgb.Booster") && !is.character(text)) {
-    stop("Either 'model' must be an object of class xgb.Booster\n",
-         "  or 'text' must be a character vector with the result of xgb.dump\n",
-         "  (or NULL if 'model' was provided).")
-  }
-
-  if (is.null(feature_names) && !is.null(model) && !is.null(model$feature_names))
-    feature_names <- model$feature_names
-
-  if (!(is.null(feature_names) || is.character(feature_names))) {
-    stop("feature_names: must be a character vector")
-  }
-
-  if (!(is.null(trees) || is.numeric(trees))) {
-    stop("trees: must be a vector of integers.")
-  }
-
-  if (is.null(text)){
-    text <- xgb.dump(model = model, with_stats = TRUE)
-  }
-
-  if (length(text) < 2 ||
-      sum(grepl('leaf=(\\d+)', text)) < 1) {
-    stop("Non-tree model detected! This function can only be used with tree models.")
-  }
-
-  position <- which(grepl("booster", text, fixed = TRUE))
-
-  add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
-
-  anynumber_regex <- "[-+]?[0-9]*\\.?[0-9]+([eE][-+]?[0-9]+)?"
-
-  td <- data.table(t = text)
-  td[position, Tree := 1L]
-  td[, Tree := cumsum(ifelse(is.na(Tree), 0L, Tree)) - 1L]
-
-  if (is.null(trees)) {
-    trees <- 0:max(td$Tree)
-  } else {
-    trees <- trees[trees >= 0 & trees <= max(td$Tree)]
-  }
-  td <- td[Tree %in% trees & !grepl('^booster', t)]
-
-  td[, Node := as.integer(sub("^([0-9]+):.*", "\\1", t))]
-  if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := grepl("leaf", t, fixed = TRUE)]
-
-  # parse branch lines
-  branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
-                      "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
-  branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
-  td[
-    isLeaf == FALSE,
-    (branch_cols) := {
-      matches <- regmatches(t, regexec(branch_rx, t))
-      # skip some indices with spurious capture groups from anynumber_regex
-      xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
-      xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-      if (length(xtr) == 0) {
-        as.data.table(
-          list(Feature = "NA", Split = "NA", Yes = "NA", No = "NA", Missing = "NA", Quality = "NA", Cover = "NA")
-        )
-      } else {
-        as.data.table(xtr)
-      }
-    }
-  ]
-
-  # assign feature_names when available
-  is_stump <- function() {
-    return(length(td$Feature) == 1 && is.na(td$Feature))
-  }
-  if (!is.null(feature_names) && !is_stump()) {
-    if (length(feature_names) <= max(as.numeric(td$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", "Quality", "Cover")
-  td[
-    isLeaf == TRUE,
-    (leaf_cols) := {
-      matches <- regmatches(t, regexec(leaf_rx, t))
-      xtr <- do.call(rbind, matches)[, c(2, 4)]
-      if (length(xtr) == 2) {
-        c("Leaf", as.data.table(xtr[1]), as.data.table(xtr[2]))
-      } else {
-        c("Leaf", as.data.table(xtr))
-      }
-    }
-  ]
-
-  # convert some columns to numeric
-  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"))

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

@@ -1,150 +0,0 @@
-#' 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 \code{which="2x1"}, two distributions with respect to the leaf depth
-#' are plotted on top of each other:
-#' \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.
-#'
-#' This function was inspired by the blog post
-#' \url{https://github.com/aysent/random-forest-leaf-visualization}.
-#'
-#' @return
-#'
-#' 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')
-#'
-#' # 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)
-#'
-#' @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")
-
-  if (!requireNamespace("igraph", quietly = TRUE))
-    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 = 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)
-
-      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") {
-      dt_depths[, max(Depth), Tree][
-                , plot(jitter(V1, amount = 0.1) ~ Tree, ylab = 'Max tree leaf depth', xlab = "tree #", ...)]
-    } else if (which == "med.depth") {
-      dt_depths[, median(as.numeric(Depth)), Tree][
-                , plot(jitter(V1, amount = 0.1) ~ Tree, ylab = 'Median tree leaf depth', xlab = "tree #", ...)]
-    } else if (which == "med.weight") {
-      dt_depths[, median(abs(Weight)), Tree][
-                , plot(V1 ~ Tree, ylab = 'Median absolute leaf weight', xlab = "tree #", ...)]
-    }
-  }
-  invisible(dt_depths)
-}
-
-# Extract path depths from root to leaf
-# from data.table containing the nodes and edges of the trees.
-# internal utility function
-get.leaf.depth <- function(dt_tree) {
-  # extract tree graph's edges
-  dt_edges <- rbindlist(list(
-      dt_tree[Feature != "Leaf", .(ID, To = Yes, Tree)],
-      dt_tree[Feature != "Leaf", .(ID, To = No, Tree)]
-    ))
-  # whether "To" is a leaf:
-  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)])
-    # 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 = sapply(paths, length), ID = To[Leaf == TRUE])
-  }, by = Tree]
-}
-
-# 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(
-    ".N", "N", "Depth", "Quality", "Cover", "Tree", "ID", "Yes", "No", "Feature", "Leaf", "Weight"
-  )
-)

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

@@ -1,124 +0,0 @@
-#' Plot feature importance as a bar graph
-#'
-#' Represents previously calculated feature importance as a bar graph.
-#' \code{xgb.plot.importance} uses base R graphics, while \code{xgb.ggplot.importance} uses the ggplot backend.
-#'
-#' @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 \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 shown ranked in a decreasing importance order.
-#' It works for importances from both \code{gblinear} and \code{gbtree} models.
-#'
-#' 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, \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 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 \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.
-#'
-#' 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)
-#'
-#' 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$data), model = bst)
-#'
-#' xgb.plot.importance(importance_matrix, rel_to_first = TRUE, xlab = "Relative importance")
-#'
-#' (gg <- xgb.ggplot.importance(importance_matrix, measure = "Frequency", rel_to_first = TRUE))
-#' gg + ggplot2::ylab("Frequency")
-#'
-#' @rdname xgb.plot.importance
-#' @export
-xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
-                                rel_to_first = FALSE, left_margin = 10, cex = NULL, plot = TRUE, ...) {
-  check.deprecation(...)
-  if (!is.data.table(importance_matrix))  {
-    stop("importance_matrix: must be a data.table")
-  }
-
-  imp_names <- colnames(importance_matrix)
-  if (is.null(measure)) {
-    if (all(c("Feature", "Gain") %in% imp_names)) {
-      measure <- "Gain"
-    } else if (all(c("Feature", "Weight") %in% imp_names)) {
-      measure <- "Weight"
-    } else {
-      stop("Importance matrix column names are not as expected!")
-    }
-  } else {
-    if (!measure %in% imp_names)
-      stop("Invalid `measure`")
-    if (!"Feature" %in% imp_names)
-      stop("Importance matrix column names are not as expected!")
-  }
-
-  # also aggregate, just in case when the values were not yet summed up by feature
-  importance_matrix <- importance_matrix[, Importance := sum(get(measure)), by = Feature]
-
-  # make sure it's ordered
-  importance_matrix <- importance_matrix[order(-abs(Importance))]
-
-  if (!is.null(top_n)) {
-    top_n <- min(top_n, nrow(importance_matrix))
-    importance_matrix <- head(importance_matrix, top_n)
-  }
-  if (rel_to_first) {
-    importance_matrix[, Importance := Importance / max(abs(Importance))]
-  }
-  if (is.null(cex)) {
-    cex <- 2.5 / log2(1 + nrow(importance_matrix))
-  }
-
-  if (plot) {
-    original_mar <- par()$mar
-
-    # reset margins so this function doesn't have side effects
-    on.exit({par(mar = original_mar)})
-
-    mar <- original_mar
-    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))),
-                      barplot(Importance, horiz = TRUE, border = NA, cex.names = cex,
-                              names.arg = Feature, las = 1, ...)]
-  }
-
-  invisible(importance_matrix)
-}
-
-# 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", "Importance"))

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

@@ -1,161 +0,0 @@
-#' Project all trees on one tree and plot it
-#'
-#' Visualization of the ensemble of trees as a single collective unit.
-#'
-#' @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
-#' in a cohesive way by compressing an ensemble of trees into a single tree-graph representation.
-#' The goal is to improve the interpretability of a model generally seen as black box.
-#'
-#' Note: this function is applicable to tree booster-based models only.
-#'
-#' It takes advantage of the fact that the shape of a binary tree is only defined by
-#' its depth (therefore, in a boosting model, all trees have similar shape).
-#'
-#' Moreover, the trees tend to reuse the same features.
-#'
-#' The function projects each tree onto one, and keeps for each position the
-#' \code{features_keep} first features (based on the Gain per feature measure).
-#'
-#' This function is inspired by this blog post:
-#' \url{https://wellecks.wordpress.com/2015/02/21/peering-into-the-black-box-visualizing-lambdamart/}
-#'
-#' @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')
-#'
-#' 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.
-#' library(DiagrammeR)
-#' 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, feature_names = NULL, features_keep = 5, plot_width = NULL, plot_height = NULL,
-                                 render = TRUE, ...){
-  if (!requireNamespace("DiagrammeR", quietly = TRUE)) {
-    stop("DiagrammeR is required for xgb.plot.multi.trees")
-  }
-  check.deprecation(...)
-  tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
-
-  # 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]
-  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) {
-    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")
-
-    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]]))
-
-  nodes.dt <- tree.matrix[
-        , .(Quality = sum(Quality))
-        , by = .(abs.node.position, Feature)
-      ][, .(Text = paste0(
-              paste0(
-                Feature[1:min(length(Feature), features_keep)],
-                " (",
-                format(Quality[1:min(length(Quality), 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]
-
-  nodes <- DiagrammeR::create_node_df(
-    n = nrow(nodes.dt),
-    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]),
-    rel = "leading_to")
-
-  graph <- DiagrammeR::create_graph(
-      nodes_df = nodes,
-      edges_df = edges,
-      attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "graph",
-      attr  = c("layout", "rankdir"),
-      value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "node",
-      attr  = c("color", "fillcolor", "style", "shape", "fontname"),
-      value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "edge",
-      attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica")
-  )
-
-  if (!render) return(invisible(graph))
-
-  DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
-}
-
-globalVariables(c(".N", "N", "From", "To", "Text", "Feature", "no.nodes.abs.pos",
-                  "ID", "Yes", "No", "Tree", "yes.nodes.abs.pos", "abs.node.position"))

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

@@ -1,289 +0,0 @@
-#' SHAP contribution dependency plots
-#'
-#' Visualizing the SHAP feature contribution to prediction dependencies on feature value.
-#'
-#' @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 list 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 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 \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 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 \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
-#'
-#' 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')
-#'
-#' 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$data, contr, model = bst, top_n = 12, n_col = 3)
-#' xgb.ggplot.shap.summary(agaricus.test$data, contr, model = bst, top_n = 12)  # Summary plot
-#'
-#' # 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 = .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)
-#' xgb.ggplot.shap.summary(x, model = mbst, target_class = 0, top_n = 4)  # Summary plot
-#'
-#' @rdname xgb.plot.shap
-#' @export
-xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1, model = NULL,
-                          trees = NULL, target_class = NULL, approxcontrib = FALSE,
-                          subsample = NULL, n_col = 1, col = rgb(0, 0, 1, 0.2), pch = '.',
-                          discrete_n_uniq = 5, discrete_jitter = 0.01, ylab = "SHAP",
-                          plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6), pch_NA = '.', pos_NA = 1.07,
-                          plot_loess = TRUE, col_loess = 2, span_loess = 0.5,
-                          which = c("1d", "2d"), plot = TRUE, ...) {
-  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)
-
-  which <- match.arg(which)
-  if (which == "2d")
-    stop("2D plots are not implemented yet")
-
-  if (n_col > length(features)) n_col <- length(features)
-  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,
-              mgp = c(1.7, 0.6, 0))
-    for (f in features) {
-      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 && any(is.na(x))
-      if (do_na) {
-        x_range <- diff(x_lim)
-        loc_na <- min(x, na.rm = TRUE) + x_range * pos_NA
-        x_lim <- range(c(x_lim, loc_na))
-      }
-      x_uniq <- unique(x)
-      x2plot <- x
-      # add small jitter for discrete features with <= 5 distinct values
-      if (length(x_uniq) <= discrete_n_uniq)
-        x2plot <- jitter(x, amount = discrete_jitter * min(diff(x_uniq), na.rm = TRUE))
-      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]
-        if (nrow(zz) <= 5) {
-          lines(zz$x, zz$y, col = col_loess)
-        } else {
-          lo <- stats::loess(y ~ x, data = zz, weights = zz$N, span = span_loess)
-          zz$y_lo <- predict(lo, zz, type = "link")
-          lines(zz$x, zz$y_lo, col = col_loess)
-        }
-      }
-      if (do_na) {
-        i_na <- which(is.na(x))
-        x_na <- rep(loc_na, length(i_na))
-        x_na <- jitter(x_na, amount = x_range * 0.01)
-        points(x_na, y[i_na], pch = pch_NA, col = col_NA)
-      }
-    }
-    par(op)
-  }
-  if (plot && which == "2d") {
-    # TODO
-    warning("Bivariate plotting is currently not available.")
-  }
-  invisible(list(data = data, shap_contrib = shap_contrib))
-}
-
-#' SHAP contribution dependency summary plot
-#'
-#' Compare SHAP contributions of different features.
-#'
-#' A point plot (each point representing one sample from \code{data}) is
-#' produced for each feature, with the points plotted on the SHAP value axis.
-#' Each point (observation) is coloured based on its feature value. The plot
-#' hence allows us to see which features have a negative / positive contribution
-#' on the model prediction, and whether the contribution is different for larger
-#' or smaller values of the feature. We effectively try to replicate the
-#' \code{summary_plot} function from https://github.com/slundberg/shap.
-#'
-#' @inheritParams xgb.plot.shap
-#'
-#' @return A \code{ggplot2} object.
-#' @export
-#'
-#' @examples # See \code{\link{xgb.plot.shap}}.
-#' @seealso \code{\link{xgb.plot.shap}}, \code{\link{xgb.ggplot.shap.summary}},
-#'   \url{https://github.com/slundberg/shap}
-xgb.plot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
-                                  trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
-  # Only ggplot implementation is available.
-  xgb.ggplot.shap.summary(data, shap_contrib, features, top_n, model, trees, target_class, approxcontrib, subsample)
-}
-
-#' Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-#' Internal utility function.
-#'
-#' @inheritParams xgb.plot.shap
-#' @keywords internal
-#'
-#' @return A list containing: 'data', a matrix containing sample observations
-#'   and their feature values; 'shap_contrib', a matrix containing the SHAP contribution
-#'   values for these observations.
-xgb.shap.data <- function(data, shap_contrib = NULL, features = NULL, top_n = 1, model = NULL,
-                          trees = NULL, target_class = NULL, approxcontrib = FALSE,
-                          subsample = NULL, max_observations = 100000) {
-  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
-    stop("data: must be either matrix or dgCMatrix")
-
-  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
-
-  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
-    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
-
-  if (!is.null(shap_contrib) &&
-      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
-    stop("shap_contrib is not compatible with the provided data")
-
-  if (is.character(features) && is.null(colnames(data)))
-    stop("either provide `data` with column names or provide `features` as column indices")
-
-  if (is.null(model$feature_names) && model$nfeatures != ncol(data))
-    stop("if model has no feature_names, columns in `data` must match features in model")
-
-  if (!is.null(subsample)) {
-    idx <- sample(x = seq_len(nrow(data)), size = as.integer(subsample * nrow(data)), replace = FALSE)
-  } else {
-    idx <- seq_len(min(nrow(data), max_observations))
-  }
-  data <- data[idx, ]
-  if (is.null(colnames(data))) {
-    colnames(data) <- paste0("X", seq_len(ncol(data)))
-  }
-
-  if (!is.null(shap_contrib)) {
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-    shap_contrib <- shap_contrib[idx, ]
-    if (is.null(colnames(shap_contrib))) {
-      colnames(shap_contrib) <- paste0("X", seq_len(ncol(data)))
-    }
-  } else {
-    shap_contrib <- predict(model, newdata = data, predcontrib = TRUE, approxcontrib = approxcontrib)
-    if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-      shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]] else Reduce("+", lapply(shap_contrib, abs))
-    }
-  }
-
-  if (is.null(features)) {
-    if (!is.null(model$feature_names)) {
-      imp <- xgb.importance(model = model, trees = trees)
-    } else {
-      imp <- xgb.importance(model = model, trees = trees, feature_names = colnames(data))
-    }
-    top_n <- top_n[1]
-    if (top_n < 1 | top_n > 100) stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[1:min(top_n, NROW(imp))]
-  }
-  if (is.character(features)) {
-    features <- match(features, colnames(data))
-  }
-
-  shap_contrib <- shap_contrib[, features, drop = FALSE]
-  data <- data[, features, drop = FALSE]
-
-  list(
-    data = data,
-    shap_contrib = shap_contrib
-  )
-}

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

@@ -1,150 +0,0 @@
-#' 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 ... currently not used.
-#'
-#' @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).
-#'  \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 that also used for missing values are marked as bold
-#' (as in "carrying extra capacity").
-#'
-#' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
-#'
-#' @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')
-#'
-#' 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)
-#' # 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.
-#' 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)
-#' }
-#'
-#' @export
-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")
-  }
-
-  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)
-
-  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"]
-  # in order to draw the first tree on top:
-  dt <- dt[order(-Tree)]
-
-  nodes <- DiagrammeR::create_node_df(
-    n         = nrow(dt),
-    ID        = dt$ID,
-    label     = dt$label,
-    fillcolor = dt$filledcolor,
-    shape     = dt$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
-  }
-
-  graph <- DiagrammeR::create_graph(
-      nodes_df = nodes,
-      edges_df = edges,
-      attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "graph",
-      attr  = c("layout", "rankdir"),
-      value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "node",
-      attr  = c("color", "style", "fontname"),
-      value = c("DimGray", "filled", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
-      attr_type = "edge",
-      attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      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", "Quality", "Split", "Yes", "No", "Missing", ".", "shape", "filledcolor", "label"))

R-package/R/xgb.save.R

@@ -1,48 +0,0 @@
-#' Save xgboost model to binary file
-#'
-#' 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
-#' of \code{\link{xgb.train}}.
-#'
-#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}}
-#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and
-#' corresponding R-methods would need to be used to load it. Moreover, persisting the model with
-#' \code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
-#' future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
-#' how to persist models in a future-proof way, i.e. to make the model accessible in future
-#' releases of XGBoost.
-#'
-#' @seealso
-#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}.
-#'
-#' @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")
-#' xgb.save(bst, 'xgb.model')
-#' bst <- xgb.load('xgb.model')
-#' if (file.exists('xgb.model')) file.remove('xgb.model')
-#' pred <- predict(bst, test$data)
-#' @export
-xgb.save <- function(model, fname) {
-  if (typeof(fname) != "character")
-    stop("fname must be character")
-  if (!inherits(model, "xgb.Booster")) {
-    stop("model must be xgb.Booster.",
-         if (inherits(model, "xgb.DMatrix")) " Use xgb.DMatrix.save to save an xgb.DMatrix object." else "")
-  }
-  model <- xgb.Booster.complete(model, saveraw = FALSE)
-  fname <- path.expand(fname)
-  .Call(XGBoosterSaveModel_R, model$handle, fname[1])
-  return(TRUE)
-}

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

@@ -1,32 +0,0 @@
-#' Save xgboost model to R's raw vector,
-#' user can call xgb.load.raw to load the model back from raw vector
-#'
-#' Save xgboost model from xgboost or xgb.train
-#'
-#' @param model the model object.
-#' @param raw_format The format for encoding the booster.  Available options are
-#' \itemize{
-#'     \item \code{json}: Encode the booster into JSON text document.
-#'     \item \code{ubj}:  Encode the booster into Universal Binary JSON.
-#'     \item \code{deprecated}: Encode the booster into old customized binary format.
-#' }
-#'
-#' Right now the default is \code{deprecated} but will be changed to \code{ubj} in upcoming release.
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' 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.save.raw(bst)
-#' bst <- xgb.load.raw(raw)
-#' pred <- predict(bst, test$data)
-#'
-#' @export
-xgb.save.raw <- function(model, raw_format = "deprecated") {
-  handle <- xgb.get.handle(model)
-  args <- list(format = raw_format)
-  .Call(XGBoosterSaveModelToRaw_R, handle, jsonlite::toJSON(args, auto_unbox = TRUE))
-}

R-package/R/xgb.serialize.R

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

R-package/R/xgb.train.R

@@ -1,384 +0,0 @@
-#' eXtreme Gradient Boosting Training
-#'
-#' \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:
-#'
-#' 1. General Parameters
-#'
-#' \itemize{
-#'   \item \code{booster} which booster to use, can be \code{gbtree} or \code{gblinear}. Default: \code{gbtree}.
-#' }
-#'
-#' 2. Booster Parameters
-#'
-#' 2.1. Parameters for Tree Booster
-#'
-#' \itemize{
-#'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
-#'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
-#'   \item \code{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{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
-#'   \item \code{lambda} L2 regularization term on weights. Default: 1
-#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-#'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through XGBoost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
-#'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
-#'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
-#' }
-#'
-#' 2.2. Parameters for Linear Booster
-#'
-#' \itemize{
-#'   \item \code{lambda} L2 regularization term on weights. Default: 0
-#'   \item \code{lambda_bias} L2 regularization term on bias. Default: 0
-#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
-#' }
-#'
-#' 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:
-#'   \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{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.
-#' }
-#'
-#' @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 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{cb.print.evaluation}} callback is engaged, the performance results are continuously
-#'        printed out during the training.
-#'        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.
-#' @param feval customized evaluation function. Returns
-#'        \code{list(metric='metric-name', value='metric-value')} with given
-#'        prediction and dtrain.
-#' @param verbose If 0, xgboost will stay silent. If 1, it will print information about performance.
-#'        If 2, some additional information will be printed out.
-#'        Note that setting \code{verbose > 0} automatically engages the
-#'        \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{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{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{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{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{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}.
-#' @param label vector of response values. Should not be provided when data is
-#'        a local data file name or an \code{xgb.DMatrix}.
-#' @param missing 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.
-#'        This parameter is only used when input is a dense matrix.
-#' @param weight a vector indicating the weight for each row of the input.
-#'
-#' @details
-#' These are the training functions for \code{xgboost}.
-#'
-#' 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 \code{nthread} parameter.
-#'
-#' 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:
-#'   \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{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{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}
-#'   }
-#'
-#' The following callbacks are automatically created when certain parameters are set:
-#' \itemize{
-#'   \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{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.
-#' }
-#'
-#' @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_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{callbacks}},
-#' \code{\link{predict.xgb.Booster}},
-#' \code{\link{xgb.cv}}
-#'
-#' @references
-#'
-#' Tianqi Chen and Carlos Guestrin, "XGBoost: A Scalable Tree Boosting System",
-#' 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016, \url{https://arxiv.org/abs/1603.02754}
-#'
-#' @examples
-#' data(agaricus.train, package='xgboost')
-#' data(agaricus.test, package='xgboost')
-#'
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
-#' watchlist <- list(train = dtrain, eval = dtest)
-#'
-#' ## A simple xgb.train example:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
-#'               objective = "binary:logistic", eval_metric = "auc")
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
-#'
-#'
-#' ## 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))
-#'    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)
-#'   return(list(metric = "error", value = err))
-#' }
-#'
-#' # These functions could be used by passing them either:
-#' #  as 'objective' and 'eval_metric' parameters in the params list:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2,
-#'               objective = logregobj, eval_metric = evalerror)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
-#'
-#' #  or through the ... arguments:
-#' param <- list(max_depth = 2, eta = 1, verbose = 0, nthread = 2)
-#' 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, watchlist,
-#'                  obj = logregobj, feval = evalerror)
-#'
-#'
-#' ## An xgb.train example of using variable learning rates at each iteration:
-#' 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, watchlist,
-#'                  callbacks = list(cb.reset.parameters(my_etas)))
-#'
-#' ## Early stopping:
-#' 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 = 2, nrounds = 2,
-#'                objective = "binary:logistic")
-#' pred <- predict(bst, agaricus.test$data)
-#'
-#' @rdname xgb.train
-#' @export
-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",
-                      xgb_model = NULL, callbacks = list(), ...) {
-
-  check.deprecation(...)
-
-  params <- check.booster.params(params, ...)
-
-  check.custom.obj()
-  check.custom.eval()
-
-  # data & watchlist checks
-  dtrain <- data
-  if (!inherits(dtrain, "xgb.DMatrix"))
-    stop("second argument dtrain must be xgb.DMatrix")
-  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 the watchlist must have a name tag")
-  }
-
-  # evaluation printing callback
-  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 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) &&
-      !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)
-  handle <- xgb.Booster.handle(params, append(watchlist, dtrain), xgb_model)
-  bst <- xgb.handleToBooster(handle)
-
-  # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
-  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)")
-
-  niter_skip <- ifelse(is_update, 0, niter_init)
-  begin_iteration <- niter_skip + 1
-  end_iteration <- niter_skip + nrounds
-
-  # the main loop for boosting iterations
-  for (iteration in begin_iteration:end_iteration) {
-
-    for (f in cb$pre_iter) f()
-
-    xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
-
-    if (length(watchlist) > 0)
-      bst_evaluation <- xgb.iter.eval(bst$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$evaluation_log, evaluation_log))
-    }
-    bst$evaluation_log <- evaluation_log
-  }
-
-  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

@@ -1,41 +0,0 @@
-#' Load the instance back from \code{\link{xgb.serialize}}
-#'
-#' @param buffer the buffer containing booster instance saved by \code{\link{xgb.serialize}}
-#' @param handle An \code{xgb.Booster.handle} object which will be overwritten with
-#' the new deserialized object. Must be a null handle (e.g. when loading the model through
-#' `readRDS`). If not provided, a new handle will be created.
-#' @return An \code{xgb.Booster.handle} object.
-#'
-#' @export
-xgb.unserialize <- function(buffer, handle = NULL) {
-  cachelist <- list()
-  if (is.null(handle)) {
-    handle <- .Call(XGBoosterCreate_R, cachelist)
-  } else {
-    if (!is.null.handle(handle))
-      stop("'handle' is not null/empty. Cannot overwrite existing handle.")
-    .Call(XGBoosterCreateInEmptyObj_R, cachelist, handle)
-  }
-  tryCatch(
-    .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer),
-    error = function(e) {
-      error_msg <- conditionMessage(e)
-      m <- regexec("(src[\\\\/]learner.cc:[0-9]+): Check failed: (header == serialisation_header_)",
-                   error_msg, perl = TRUE)
-      groups <- regmatches(error_msg, m)[[1]]
-      if (length(groups) == 3) {
-        warning(paste("The model had been generated by XGBoost version 1.0.0 or earlier and was ",
-                      "loaded from a RDS file. We strongly ADVISE AGAINST using saveRDS() ",
-                      "function, to ensure that your model can be read in current and upcoming ",
-                      "XGBoost releases. Please use xgb.save() instead to preserve models for the ",
-                      "long term. For more details and explanation, see ",
-                      "https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html",
-                      sep = ""))
-        .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
-      } else {
-        stop(e)
-      }
-    })
-  class(handle) <- "xgb.Booster.handle"
-  return (handle)
-}

R-package/R/xgboost.R

@@ -1,109 +0,0 @@
-# Simple interface for training an xgboost model that wraps \code{xgb.train}.
-# Its documentation is combined with xgb.train.
-#
-#' @rdname xgb.train
-#' @export
-xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
-                    params = list(), nrounds,
-                    verbose = 1, print_every_n = 1L,
-                    early_stopping_rounds = NULL, maximize = NULL,
-                    save_period = NULL, save_name = "xgboost.model",
-                    xgb_model = NULL, callbacks = list(), ...) {
-  merged <- check.booster.params(params, ...)
-  dtrain <- xgb.get.DMatrix(data, label, missing, weight, nthread = merged$nthread)
-
-  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)
-}
-
-#' Training part from Mushroom Data Set
-#'
-#' This data set is originally from the Mushroom data set,
-#' 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.
-#' }
-#'
-#' @references
-#' 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,
-#' School of Information and Computer Science.
-#'
-#' @docType data
-#' @keywords datasets
-#' @name agaricus.train
-#' @usage data(agaricus.train)
-#' @format A list containing a label vector, and a dgCMatrix object with 6513
-#' rows and 127 variables
-NULL
-
-#' Test part from Mushroom Data Set
-#'
-#' This data set is originally from the Mushroom data set,
-#' 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.
-#' }
-#'
-#' @references
-#' 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,
-#' School of Information and Computer Science.
-#'
-#' @docType data
-#' @keywords datasets
-#' @name agaricus.test
-#' @usage data(agaricus.test)
-#' @format A list containing a label vector, and a dgCMatrix object with 1611
-#' rows and 126 variables
-NULL
-
-# Various imports
-#' @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
-#' @importFrom data.table :=
-#' @importFrom data.table rbindlist
-#' @importFrom data.table setkey
-#' @importFrom data.table setkeyv
-#' @importFrom data.table setnames
-#' @importFrom jsonlite fromJSON
-#' @importFrom jsonlite toJSON
-#' @importFrom utils object.size str tail
-#' @importFrom stats predict
-#' @importFrom stats median
-#' @importFrom utils head
-#' @importFrom graphics barplot
-#' @importFrom graphics lines
-#' @importFrom graphics points
-#' @importFrom graphics grid
-#' @importFrom graphics par
-#' @importFrom graphics title
-#' @importFrom grDevices rgb
-#'
-#' @import methods
-#' @useDynLib xgboost, .registration = TRUE
-NULL

R-package/README.md

@@ -1,33 +0,0 @@
-XGBoost R Package for Scalable GBM
-==================================
-
-[![CRAN Status Badge](http://www.r-pkg.org/badges/version/xgboost)](https://cran.r-project.org/web/packages/xgboost)
-[![CRAN Downloads](http://cranlogs.r-pkg.org/badges/xgboost)](https://cran.rstudio.com/web/packages/xgboost/index.html)
-[![Documentation Status](https://readthedocs.org/projects/xgboost/badge/?version=latest)](http://xgboost.readthedocs.org/en/latest/R-package/index.html)
-
-Resources
----------
-* [XGBoost R Package Online Documentation](http://xgboost.readthedocs.org/en/latest/R-package/index.html)
-  - Check this out for detailed documents, examples and tutorials.
-
-Installation
-------------
-
-We are [on CRAN](https://cran.r-project.org/web/packages/xgboost/index.html) now. For stable/pre-compiled(for Windows and OS X) version, please install from CRAN:
-
-```r
-install.packages('xgboost')
-```
-
-For more detailed installation instructions, please see [here](http://xgboost.readthedocs.org/en/latest/build.html#r-package-installation).
-
-Examples
---------
-
-* Please visit [walk through example](demo).
-* See also the [example scripts](../demo/kaggle-higgs) for Kaggle Higgs Challenge, including [speedtest script](../demo/kaggle-higgs/speedtest.R) on this dataset and the one related to [Otto challenge](../demo/kaggle-otto), including a [RMarkdown documentation](../demo/kaggle-otto/understandingXGBoostModel.Rmd).
-
-Development
------------
-
-* See the [R Package section](https://xgboost.readthedocs.io/en/latest/contrib/coding_guide.html#r-coding-guideline) of the contributors guide.

R-package/cleanup

@@ -1,3 +0,0 @@
-#!/bin/sh
-
-rm -f src/Makevars

R-package/configure.ac

@@ -1,61 +0,0 @@
-### configure.ac					-*- Autoconf -*-
-
-AC_PREREQ(2.69)
-
-AC_INIT([xgboost],[1.7.0],[],[xgboost],[])
-
-# Use this line to set CC variable to a C compiler
-AC_PROG_CC
-
-### Check whether backtrace() is part of libc or the external lib libexecinfo
-AC_MSG_CHECKING([Backtrace lib])
-AC_MSG_RESULT([])
-AC_CHECK_LIB([execinfo], [backtrace], [BACKTRACE_LIB=-lexecinfo], [BACKTRACE_LIB=''])
-
-### Endian detection
-AC_MSG_CHECKING([endian])
-AC_MSG_RESULT([])
-AC_RUN_IFELSE([AC_LANG_PROGRAM([[#include <stdint.h>]], [[const uint16_t endianness = 256; return !!(*(const uint8_t *)&endianness);]])],
-  [ENDIAN_FLAG="-DDMLC_CMAKE_LITTLE_ENDIAN=1"],
-  [ENDIAN_FLAG="-DDMLC_CMAKE_LITTLE_ENDIAN=0"])
-
-OPENMP_CXXFLAGS=""
-
-if test `uname -s` = "Linux"
-then
-  OPENMP_CXXFLAGS="\$(SHLIB_OPENMP_CXXFLAGS)"
-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"
-  ac_pkg_openmp=no
-  AC_MSG_CHECKING([whether OpenMP will work in a package])
-  AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
-  ${CC} -o conftest conftest.c ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
-  AC_MSG_RESULT([${ac_pkg_openmp}])
-  if test "${ac_pkg_openmp}" = no; then
-    OPENMP_CXXFLAGS=''
-    OPENMP_LIB=''
-    echo '*****************************************************************************************'
-    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
-    echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
-    echo '             brew install libomp'
-    echo '*****************************************************************************************'
-  fi
-fi
-
-AC_SUBST(OPENMP_CXXFLAGS)
-AC_SUBST(OPENMP_LIB)
-AC_SUBST(ENDIAN_FLAG)
-AC_SUBST(BACKTRACE_LIB)
-AC_CONFIG_FILES([src/Makevars])
-AC_OUTPUT

R-package/demo/00Index

@@ -1,15 +0,0 @@
-basic_walkthrough               Basic feature walkthrough
-caret_wrapper                   Use xgboost to train in caret library
-custom_objective                Customize loss function, and evaluation metric
-boost_from_prediction           Boosting from existing prediction
-predict_first_ntree             Predicting using first n trees
-generalized_linear_model        Generalized Linear Model
-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
-gpu_accelerated                 GPU-accelerated tree building algorithms
-interaction_constraints         Interaction constraints among features
-

R-package/demo/README.md

@@ -1,20 +0,0 @@
-XGBoost R Feature Walkthrough
-====
-* [Basic walkthrough of wrappers](basic_walkthrough.R)
-* [Train a xgboost model from caret library](caret_wrapper.R)
-* [Customize loss function, and evaluation metric](custom_objective.R)
-* [Boosting from existing prediction](boost_from_prediction.R)
-* [Predicting using first n trees](predict_first_ntree.R)
-* [Generalized Linear Model](generalized_linear_model.R)
-* [Cross validation](cross_validation.R)
-* [Create a sparse matrix from a dense one](create_sparse_matrix.R)
-* [Use GPU-accelerated tree building algorithms](gpu_accelerated.R)
-
-Benchmarks
-====
-* [Starter script for Kaggle Higgs Boson](../../demo/kaggle-higgs)
- 
-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 :)

R-package/demo/basic_walkthrough.R

@@ -1,112 +0,0 @@
-require(xgboost)
-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')
-train <- agaricus.train
-test <- agaricus.test
-# the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
-class(train$label)
-class(train$data)
-
-#-------------Basic Training using XGBoost-----------------
-# this is the basic usage of xgboost you can put matrix in data field
-# note: we are putting in sparse matrix here, xgboost naturally handles sparse input
-# use sparse matrix when your feature is sparse(e.g. when you are using one-hot encoding vector)
-print("Training xgboost with sparseMatrix")
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic")
-# alternatively, you can put in dense matrix, i.e. basic R-matrix
-print("Training xgboost with Matrix")
-bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic")
-
-# 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,
-               objective = "binary:logistic")
-
-# Verbose = 0,1,2
-print("Train xgboost with verbose 0, no message")
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic", verbose = 0)
-print("Train xgboost with verbose 1, print evaluation metric")
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
-               nthread = 2, objective = "binary:logistic", verbose = 1)
-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
-# 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
-pred <- predict(bst, test$data)
-err <- mean(as.numeric(pred > 0.5) != test$label)
-print(paste("test-error=", err))
-
-#-------------------save and load models-------------------------
-# save model to binary local file
-xgb.save(bst, "xgboost.model")
-# load binary model to R
-bst2 <- xgb.load("xgboost.model")
-pred2 <- predict(bst2, test$data)
-# pred2 should be identical to pred
-print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
-
-# save model to R's raw vector
-raw <- xgb.save.raw(bst)
-# load binary model to R
-bst3 <- xgb.load.raw(raw)
-pred3 <- predict(bst3, test$data)
-# pred3 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))
-
-#----------------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 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 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")
-
-# xgb.DMatrix can also be saved using xgb.DMatrix.save
-xgb.DMatrix.save(dtrain, "dtrain.buffer")
-# to load it in, simply call xgb.DMatrix
-dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
-                 nthread = 2, objective = "binary:logistic")
-# information can be extracted from xgb.DMatrix using getinfo
-label <- getinfo(dtest, "label")
-pred <- predict(bst, dtest)
-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)
-
-# Finally, you can check which features are the most important.
-print("Most important features (look at column Gain):")
-imp_matrix <- xgb.importance(feature_names = colnames(train$data), model = bst)
-print(imp_matrix)
-
-# Feature importance bar plot by gain
-print("Feature importance Plot : ")
-print(xgb.plot.importance(importance_matrix = imp_matrix))

R-package/demo/boost_from_prediction.R

@@ -1,26 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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)
-
-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, 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)
-# 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, watchlist = watchlist)

R-package/demo/caret_wrapper.R

@@ -1,35 +0,0 @@
-# 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 = FALSE)
-
-# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-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

@@ -1,89 +0,0 @@
-require(xgboost)
-require(Matrix)
-require(data.table)
-if (!require(vcd)) {
-  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.
-#
-# 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.
-# 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)
-
-# 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).
-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.
-
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independent values.
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
-
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-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]
-
-# List the different values for the column Treatment: Placebo, Treated.
-cat("Values of the categorical feature Treatment\n")
-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.
-#
-# 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)
-
-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;
-# 3. Return Y column
-output_vector <- df[, Y := 0][Improved == "Marked", Y := 1][, Y]
-
-# Following is the same process as other demo
-cat("Learning...\n")
-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).
-
-# Does these result make sense?
-# Let's check some Chi2 between each of these features and the outcome.
-
-print(chisq.test(df$Age, df$Y))
-# Pearson correlation between Age and illness disappearing is 35
-
-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 :-)
-
-# 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.

R-package/demo/cross_validation.R

@@ -1,51 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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')
-
-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'})
-
-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)
-
-###
-# you can also do cross validation with customized loss function
-# See custom_objective.R
-##
-print ('running cross validation, with customized loss function')
-
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  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)
-  return(list(metric = "error", value = err))
-}
-
-param <- list(max_depth = 2, eta = 1,
-              objective = logregobj, eval_metric = evalerror)
-# train with customized objective
-xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)
-
-# do cross validation with prediction values for each fold
-res <- xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5, prediction = TRUE)
-res$evaluation_log
-length(res$pred)

R-package/demo/custom_objective.R

@@ -1,65 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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
-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
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  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
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
-# Take this in mind when you use the customization, and maybe you need write customized evaluation function
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  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')
-# 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, watchlist)
-
-#
-# 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
-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))
-  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')
-# 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, watchlist)

R-package/demo/early_stopping.R

@@ -1,40 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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)
-watchlist <- list(eval = dtest)
-num_round <- 20
-# user define objective function, given prediction, return gradient and second order gradient
-# this is log likelihood loss
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  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
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
-# Take this in mind when you use the customization, and maybe you need write customized evaluation function
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
-  return(list(metric = "error", value = err))
-}
-print ('start training with early Stopping setting')
-
-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,
-              objective = logregobj, eval_metric = evalerror,
-              maximize = FALSE, early_stopping_rounds = 3)

R-package/demo/generalized_linear_model.R

@@ -1,33 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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)
-##
-#  this script demonstrate how to fit generalized linear model in xgboost
-#  basically, we are using linear model, instead of tree for our boosters
-#  you can fit a linear regression, or logistic regression model
-##
-
-# change booster to gblinear, so that we are fitting a linear model
-# 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),
-# 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
-##
-watchlist <- list(eval = dtest, train = dtrain)
-num_round <- 2
-bst <- xgb.train(param, dtrain, num_round, watchlist)
-ypred <- predict(bst, dtest)
-labels <- getinfo(dtest, 'label')
-cat('error of preds=', mean(as.numeric(ypred > 0.5) != labels), '\n')

R-package/demo/gpu_accelerated.R

@@ -1,45 +0,0 @@
-# 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
-#       specially compiled with GPU support.
-#
-# For the current functionality, see
-# https://xgboost.readthedocs.io/en/latest/gpu/index.html
-#
-
-library('xgboost')
-
-# Simulate N x p random matrix with some binomial response dependent on pp columns
-set.seed(111)
-N <- 1000000
-p <- 50
-pp <- 25
-X <- matrix(runif(N * p), ncol = p)
-betas <- 2 * runif(pp) - 1
-sel <- sort(sample(p, pp))
-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])
-wl <- list(train = dtrain, test = dtest)
-
-# An example of running 'gpu_hist' algorithm
-# which is
-# - similar to the 'hist'
-# - the fastest option for moderately large datasets
-# - current limitations: max_depth < 16, does not implement guided loss
-# You can use tree_method = 'gpu_hist' for another GPU accelerated algorithm,
-# which is slower, more memory-hungry, but does not use binning.
-param <- list(objective = 'reg:logistic', eval_metric = 'auc', subsample = 0.5, nthread = 4,
-              max_bin = 64, tree_method = 'gpu_hist')
-pt <- proc.time()
-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, watchlist = wl, nrounds = 50)
-proc.time() - pt

R-package/demo/interaction_constraints.R

@@ -1,113 +0,0 @@
-library(xgboost)
-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
-  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)]
-
-    data.table::setorderv(trees, 'ID_merge')
-    data.table::setorderv(parents_left, 'ID_merge')
-    data.table::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_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]
-  }
-
-  # Extract nodes with interactions
-  interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),
-                             c('Feature', paste0('parent_feat_', 1:(input_max_depth - 1))),
-                             with = FALSE]
-  interaction_trees_split <- split(interaction_trees, seq_len(nrow(interaction_trees)))
-  interaction_list <- lapply(interaction_trees_split, as.character)
-
-  # Remove NAs (no parent interaction)
-  interaction_list <- lapply(interaction_list, function(x) x[!is.na(x)])
-
-  # Remove non-interactions (same variable)
-  interaction_list <- lapply(interaction_list, unique)  # remove same variables
-  interaction_length <- sapply(interaction_list, length)
-  interaction_list <- interaction_list[interaction_length > 1]
-  interaction_list <- unique(lapply(interaction_list, sort))
-  return(interaction_list)
-}
-
-# Generate sample data
-x <- list()
-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']])
-
-train <- as.matrix(x)
-
-# Interaction constraint list (column names form)
-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")
-}
-interaction_list_fid <- cols2ids(interaction_list, colnames(train))
-
-# Fit model with interaction constraints
-bst <- xgboost(data = train, label = y, max_depth = 4,
-               eta = 0.1, nthread = 2, nrounds = 1000,
-               interaction_constraints = interaction_list_fid)
-
-bst_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
-
-# Fit model without interaction constraints
-bst2 <- xgboost(data = train, label = y, max_depth = 4,
-                eta = 0.1, nthread = 2, nrounds = 1000)
-
-bst2_tree <- xgb.model.dt.tree(colnames(train), bst2)
-bst2_interactions <- treeInteractions(bst2_tree, 4)  # much more interactions
-
-# Fit model with both interaction and monotonicity constraints
-bst3 <- xgboost(data = train, label = y, max_depth = 4,
-                eta = 0.1, nthread = 2, nrounds = 1000,
-                interaction_constraints = interaction_list_fid,
-                monotone_constraints = c(-1, 0, 0, 0, 0, 0, 0, 0, 0, 0))
-
-bst3_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
-
-# 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')])
-  testdata[['V1']] <- x1[i]
-  testdata <- testdata[, paste0('V', 1:10), with = FALSE]
-  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
-}

R-package/demo/poisson_regression.R

@@ -1,6 +0,0 @@
-data(mtcars)
-head(mtcars)
-bst <- xgboost(data = as.matrix(mtcars[, -11]), label = mtcars[, 11],
-               objective = 'count:poisson', nrounds = 5)
-pred <- predict(bst, as.matrix(mtcars[, -11]))
-sqrt(mean((pred - mtcars[, 11]) ^ 2))

R-package/demo/predict_first_ntree.R

@@ -1,23 +0,0 @@
-require(xgboost)
-# load in the agaricus dataset
-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')
-watchlist <- list(eval = dtest, train = dtrain)
-nrounds <- 2
-
-# training the model for two rounds
-bst <- xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
-cat('start testing prediction from first n trees\n')
-labels <- getinfo(dtest, 'label')
-
-### predict using first 1 tree
-ypred1 <- predict(bst, dtest, ntreelimit = 1)
-# by default, we predict using all the trees
-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')

R-package/demo/predict_leaf_indices.R

@@ -1,55 +0,0 @@
-require(xgboost)
-require(data.table)
-require(Matrix)
-
-set.seed(1982)
-
-# load in the agaricus dataset
-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
-
-# training the model for two rounds
-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$label))
-
-# by default, we predict using all the trees
-pred_with_leaf <- predict(bst, dtest, predleaf = TRUE)
-head(pred_with_leaf)
-
-create.new.tree.features <- function(model, original.features){
-  pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
-  cols <- list()
-  for (i in 1:model$niter) {
-    # 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)
-  }
-  cbind(original.features, sparse.model.matrix(~ . - 1, as.data.frame(cols)))
-}
-
-# Convert previous features to one hot encoding
-new.features.train <- create.new.tree.features(bst, agaricus.train$data)
-new.features.test <- create.new.tree.features(bst, agaricus.test$data)
-colnames(new.features.test) <- colnames(new.features.train)
-
-# learning with new features
-new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
-new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$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"))

R-package/demo/runall.R

@@ -1,14 +0,0 @@
-# running all scripts in demo folder
-demo(basic_walkthrough, package = 'xgboost')
-demo(custom_objective, package = 'xgboost')
-demo(boost_from_prediction, package = 'xgboost')
-demo(predict_first_ntree, package = 'xgboost')
-demo(generalized_linear_model, package = 'xgboost')
-demo(cross_validation, package = 'xgboost')
-demo(create_sparse_matrix, package = 'xgboost')
-demo(predict_leaf_indices, package = 'xgboost')
-demo(early_stopping, package = 'xgboost')
-demo(poisson_regression, package = 'xgboost')
-demo(caret_wrapper, package = 'xgboost')
-demo(tweedie_regression, package = 'xgboost')
-#demo(gpu_accelerated, package = 'xgboost')  # can only run when built with GPU support

R-package/demo/tweedie_regression.R

@@ -1,49 +0,0 @@
-library(xgboost)
-library(data.table)
-library(cplm)
-
-data(AutoClaim)
-
-# auto insurance dataset analyzed by Yip and Yau (2005)
-dt <- data.table(AutoClaim)
-
-# exclude these columns from the model matrix
-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])
-options(na.action = 'na.omit')
-
-# response
-y <- dt[, CLM_AMT5]
-
-d_train <- xgb.DMatrix(data = x, label = y, missing = NA)
-
-# 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
-#   the right with less concentration near zero
-
-params <- list(
-  objective = 'reg:tweedie',
-  eval_metric = 'rmse',
-  tweedie_variance_power = 1.4,
-  max_depth = 6,
-  eta = 1)
-
-bst <- xgb.train(
-  data = d_train,
-  params = params,
-  maximize = FALSE,
-  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)))

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

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

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

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

R-package/man/agaricus.test.Rd

@@ -1,33 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgboost.R
-\docType{data}
-\name{agaricus.test}
-\alias{agaricus.test}
-\title{Test part from Mushroom Data Set}
-\format{
-A list containing a label vector, and a dgCMatrix object with 1611
-rows and 126 variables
-}
-\usage{
-data(agaricus.test)
-}
-\description{
-This data set is originally from the Mushroom data set,
-UCI Machine Learning Repository.
-}
-\details{
-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.
-}
-}
-\references{
-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,
-School of Information and Computer Science.
-}
-\keyword{datasets}

R-package/man/agaricus.train.Rd

@@ -1,33 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgboost.R
-\docType{data}
-\name{agaricus.train}
-\alias{agaricus.train}
-\title{Training part from Mushroom Data Set}
-\format{
-A list containing a label vector, and a dgCMatrix object with 6513
-rows and 127 variables
-}
-\usage{
-data(agaricus.train)
-}
-\description{
-This data set is originally from the Mushroom data set,
-UCI Machine Learning Repository.
-}
-\details{
-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.
-}
-}
-\references{
-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,
-School of Information and Computer Science.
-}
-\keyword{datasets}

R-package/man/callbacks.Rd

@@ -1,37 +0,0 @@
-% 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

@@ -1,43 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.cv.predict}
-\alias{cb.cv.predict}
-\title{Callback closure for returning cross-validation based predictions.}
-\usage{
-cb.cv.predict(save_models = FALSE)
-}
-\arguments{
-\item{save_models}{a flag for whether to save the folds' models.}
-}
-\value{
-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
-non-overlapping list of k sets of indices, as in a standard k-fold CV. The predictions would not be
-meaningful when user-provided folds have overlapping indices as in, e.g., random sampling splits.
-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

@@ -1,63 +0,0 @@
-% 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)
-}
-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

@@ -1,31 +0,0 @@
-% 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

@@ -1,94 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\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{
-cb.gblinear.history(sparse = FALSE)
-}
-\arguments{
-\item{sparse}{when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
-Sparse format is useful when one expects only a subset of coefficients to be non-zero,
-when using the "thrifty" feature selector with fairly small number of top features
-selected per iteration.}
-}
-\value{
-Results are stored in the \code{coefs} element of the closure.
-The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
-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 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.
-
-Callback function expects the following values to be set in its calling frame:
-\code{bst} (or \code{bst_folds}).
-}
-\examples{
-#### Binary classification:
-#
-# In the iris dataset, it is hard to linearly separate Versicolor class from the rest
-# without considering the 2nd order interactions:
-x <- model.matrix(Species ~ .^2, iris)[,-1]
-colnames(x)
-dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
-param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
-              lambda = 0.0003, alpha = 0.0003, nthread = 2)
-# For 'shotgun', which is a default linear updater, using high eta values may result in
-# unstable behaviour in some datasets. With this simple dataset, however, the high learning
-# rate does not break the convergence, but allows us to illustrate the typical pattern of
-# "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
-                 callbacks = list(cb.gblinear.history()))
-# Extract the coefficients' path and plot them vs boosting iteration number:
-coef_path <- xgb.gblinear.history(bst)
-matplot(coef_path, type = 'l')
-
-# With the deterministic coordinate descent updater, it is safer to use higher learning rates.
-# Will try the classical componentwise boosting which selects a single best feature per round:
-bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
-                 updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
-                 callbacks = list(cb.gblinear.history()))
-matplot(xgb.gblinear.history(bst), type = 'l')
-#  Componentwise boosting is known to have similar effect to Lasso regularization.
-# Try experimenting with various values of top_k, eta, nrounds,
-# as well as different feature_selectors.
-
-# For xgb.cv:
-bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-             callbacks = list(cb.gblinear.history()))
-# coefficients in the CV fold #3
-matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
-
-
-#### Multiclass classification:
-#
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
-param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
-              lambda = 0.0003, alpha = 0.0003, nthread = 2)
-# For the default linear updater 'shotgun' it sometimes is helpful
-# to use smaller eta to reduce instability
-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')
-
-# CV:
-bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-              callbacks = list(cb.gblinear.history(FALSE)))
-# 1st fold of 1st class
-matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
-
-}
-\seealso{
-\code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
-}

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

@@ -1,29 +0,0 @@
-% 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

@@ -1,36 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/callbacks.R
-\name{cb.reset.parameters}
-\alias{cb.reset.parameters}
-\title{Callback closure for resetting the booster's parameters at each iteration.}
-\usage{
-cb.reset.parameters(new_params)
-}
-\arguments{
-\item{new_params}{a list where each element corresponds to a parameter that needs to be reset.
-Each element's value must be either a vector of values of length \code{nrounds}
-to be set at each iteration,
-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.}
-}
-\description{
-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.
-
-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

@@ -1,33 +0,0 @@
-% 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/dim.xgb.DMatrix.Rd

@@ -1,28 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{dim.xgb.DMatrix}
-\alias{dim.xgb.DMatrix}
-\title{Dimensions of xgb.DMatrix}
-\usage{
-\method{dim}{xgb.DMatrix}(x)
-}
-\arguments{
-\item{x}{Object of class \code{xgb.DMatrix}}
-}
-\description{
-Returns a vector of numbers of rows and of columns in an \code{xgb.DMatrix}.
-}
-\details{
-Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
-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)
-
-stopifnot(nrow(dtrain) == nrow(train$data))
-stopifnot(ncol(dtrain) == ncol(train$data))
-stopifnot(all(dim(dtrain) == dim(train$data)))
-
-}

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

@@ -1,35 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{dimnames.xgb.DMatrix}
-\alias{dimnames.xgb.DMatrix}
-\alias{dimnames<-.xgb.DMatrix}
-\title{Handling of column names of \code{xgb.DMatrix}}
-\usage{
-\method{dimnames}{xgb.DMatrix}(x)
-
-\method{dimnames}{xgb.DMatrix}(x) <- value
-}
-\arguments{
-\item{x}{object of class \code{xgb.DMatrix}}
-
-\item{value}{a list of two elements: the first one is ignored
-and the second one is column names}
-}
-\description{
-Only column names are supported for \code{xgb.DMatrix}, thus setting of
-row names would have no effect and returned row names would be NULL.
-}
-\details{
-Generic \code{dimnames} methods are used by \code{colnames}.
-Since row names are irrelevant, it is recommended to use \code{colnames} directly.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
-dimnames(dtrain)
-colnames(dtrain)
-colnames(dtrain) <- make.names(1:ncol(train$data))
-print(dtrain, verbose=TRUE)
-
-}

R-package/man/getinfo.Rd

@@ -1,44 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{getinfo}
-\alias{getinfo}
-\alias{getinfo.xgb.DMatrix}
-\title{Get information of an xgb.DMatrix object}
-\usage{
-getinfo(object, ...)
-
-\method{getinfo}{xgb.DMatrix}(object, name, ...)
-}
-\arguments{
-\item{object}{Object of class \code{xgb.DMatrix}}
-
-\item{...}{other parameters}
-
-\item{name}{the name of the information field to get (see details)}
-}
-\description{
-Get 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{nrow}: number of rows of the \code{xgb.DMatrix}.
-
-}
-
-\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))
-
-labels <- getinfo(dtrain, 'label')
-setinfo(dtrain, 'label', 1-labels)
-
-labels2 <- getinfo(dtrain, 'label')
-stopifnot(all(labels2 == 1-labels))
-}

R-package/man/normalize.Rd

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

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

@@ -1,202 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{predict.xgb.Booster}
-\alias{predict.xgb.Booster}
-\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,
-  ...
-)
-
-\method{predict}{xgb.Booster.handle}(object, ...)
-}
-\arguments{
-\item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
-
-\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-       local data file or \code{xgb.DMatrix}.
-
-       For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-       a sparse vector, it will take it as a row vector.}
-
-\item{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).}
-
-\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 result in predictions for log-odds instead of probabilities.}
-
-\item{ntreelimit}{Deprecated, use \code{iterationrange} instead.}
-
-\item{predleaf}{whether predict leaf index.}
-
-\item{predcontrib}{whether to return feature contributions to individual predictions (see Details).}
-
-\item{approxcontrib}{whether to use a fast approximation for feature contributions (see Details).}
-
-\item{predinteraction}{whether to return contributions of feature interactions to individual predictions (see Details).}
-
-\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}{Specifies which layer of trees are used in prediction.  For
-example, if a random forest is trained with 100 rounds.  Specifying
-`iterationrange=(1, 21)`, then only the forests built during [1, 21) (half open set)
-rounds are used in this prediction.  It's 1-based index just like R vector.  When set
-to \code{c(1, 1)} XGBoost will use all trees.}
-
-\item{strict_shape}{Default is \code{FALSE}. When it's set to \code{TRUE}, output
-type and shape of prediction are invariant to model type.}
-
-\item{...}{Parameters passed to \code{predict.xgb.Booster}}
-}
-\value{
-The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
-for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
-For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
-a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
-the \code{reshape} value.
-
-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.
-
-When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
-normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
-
-For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
-For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
-For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
-}
-\description{
-Predicted values based on either xgboost model or model handle object.
-}
-\details{
-Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
-since gblinear doesn't keep its boosting history.
-
-One possible practical applications of the \code{predleaf} option is to use the model
-as a generator of new features which capture non-linearity and interactions,
-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
-(feature_beta * feature_value). For "gbtree" booster, feature contributions are SHAP
-values (Lundberg 2017) that sum to the difference between the expected output
-of the model and the current prediction (where the hessian weights are used to compute the expectations).
-Setting \code{approxcontrib = TRUE} approximates these values following the idea explained
-in \url{http://blog.datadive.net/interpreting-random-forests/}.
-
-With \code{predinteraction = TRUE}, SHAP values of contributions of interaction of each pair of features
-are computed. Note that this operation might be rather expensive in terms of compute and memory.
-Since it quadratically depends on the number of features, it is recommended to perform selection
-of the most important features first. See below about the format of the returned results.
-}
-\examples{
-## binary classification:
-
-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 = 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, 2))
-
-# Predicting tree leafs:
-# the result is an nsamples X ntrees matrix
-pred_leaf <- predict(bst, test$data, predleaf = TRUE)
-str(pred_leaf)
-
-# Predicting feature contributions to predictions:
-# the result is an nsamples X (nfeatures + 1) matrix
-pred_contr <- predict(bst, test$data, predcontrib = TRUE)
-str(pred_contr)
-# verify that contributions' sums are equal to log-odds of predictions (up to float precision):
-summary(rowSums(pred_contr) - qlogis(pred))
-# for the 1st record, let's inspect its features that had non-zero contribution to prediction:
-contr1 <- pred_contr[1,]
-contr1 <- contr1[-length(contr1)]    # drop BIAS
-contr1 <- contr1[contr1 != 0]        # drop non-contributing features
-contr1 <- contr1[order(abs(contr1))] # order by contribution magnitude
-old_mar <- par("mar")
-par(mar = old_mar + c(0,7,0,0))
-barplot(contr1, horiz = TRUE, las = 2, xlab = "contribution to prediction in log-odds")
-par(mar = old_mar)
-
-
-## multiclass classification in iris dataset:
-
-lb <- as.numeric(iris$Species) - 1
-num_class <- 3
-set.seed(11)
-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)
-# 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)
-
-# compare that to the predictions from softmax:
-set.seed(11)
-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, 6))
-sum(pred5 != lb)/length(lb)
-
-}
-\references{
-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}}.
-}

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

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

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

@@ -1,29 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.Booster.R
-\name{print.xgb.Booster}
-\alias{print.xgb.Booster}
-\title{Print xgb.Booster}
-\usage{
-\method{print}{xgb.Booster}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an xgb.Booster object}
-
-\item{verbose}{whether to print detailed data (e.g., attribute values)}
-
-\item{...}{not currently used}
-}
-\description{
-Print information about xgb.Booster.
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
-attr(bst, 'myattr') <- 'memo'
-
-print(bst)
-print(bst, verbose=TRUE)
-
-}

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

@@ -1,27 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\name{print.xgb.DMatrix}
-\alias{print.xgb.DMatrix}
-\title{Print xgb.DMatrix}
-\usage{
-\method{print}{xgb.DMatrix}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an xgb.DMatrix object}
-
-\item{verbose}{whether to print colnames (when present)}
-
-\item{...}{not currently used}
-}
-\description{
-Print information about xgb.DMatrix.
-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))
-
-dtrain
-print(dtrain, verbose=TRUE)
-
-}

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

@@ -1,31 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.cv.R
-\name{print.xgb.cv.synchronous}
-\alias{print.xgb.cv.synchronous}
-\title{Print xgb.cv result}
-\usage{
-\method{print}{xgb.cv.synchronous}(x, verbose = FALSE, ...)
-}
-\arguments{
-\item{x}{an \code{xgb.cv.synchronous} object}
-
-\item{verbose}{whether to print detailed data}
-
-\item{...}{passed to \code{data.table.print}}
-}
-\description{
-Prints formatted results of \code{xgb.cv}.
-}
-\details{
-When not verbose, it would only print the evaluation results,
-including the best iteration (when available).
-}
-\examples{
-data(agaricus.train, package='xgboost')
-train <- agaricus.train
-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

@@ -1,42 +0,0 @@
-% 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')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = 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

@@ -1,39 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
-\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{
-slice(object, ...)
-
-\method{slice}{xgb.DMatrix}(object, idxset, ...)
-
-\method{[}{xgb.DMatrix}(object, idxset, colset = NULL)
-}
-\arguments{
-\item{object}{Object of class "xgb.DMatrix"}
-
-\item{...}{other parameters (currently not used)}
-
-\item{idxset}{a integer vector of indices of rows needed}
-
-\item{colset}{currently not used (columns subsetting is not available)}
-}
-\description{
-Get a new DMatrix containing the specified rows of
-original xgb.DMatrix object
-}
-\examples{
-data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-
-dsub <- slice(dtrain, 1:42)
-labels1 <- getinfo(dsub, 'label')
-dsub <- dtrain[1:42, ]
-labels2 <- getinfo(dsub, 'label')
-all.equal(labels1, labels2)
-
-}