Release 1.2.0

* Fix sklearn doc. (#5980)

* Enforce tree order in JSON. (#5974)

* Make JSON model IO more future proof by using tree id in model loading.

* Fix dask predict shape infer. (#5989)

* [Breaking] Fix .predict() method and add .predict_proba() in xgboost.dask.DaskXGBClassifier (#5986)

.clang-format

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

.github/FUNDING.yml

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

.github/workflows/jvm_tests.yml

@@ -1,74 +0,0 @@
-name: XGBoost-JVM-Tests
-
-on: [push, pull_request]
-
-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-10.15]
-
-    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

@@ -6,224 +6,133 @@ name: XGBoost-CI
 # events but only for the master branch
 on: [push, pull_request]
 
+env:
+  R_PACKAGES: c('XML', 'igraph', 'data.table', 'magrittr', 'stringi', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools')
+
 # 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)
+  test-with-jvm:
+    name: Test JVM on OS ${{ matrix.os }}
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-10.15]
+        os: [windows-latest, windows-2016, ubuntu-latest]
+
     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 }}
+    - uses: actions/setup-java@v1
+      with:
+        java-version: 1.8
+
+    - 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 JVM packages
+      run: |
+        cd jvm-packages
+        mvn test -pl :xgboost4j_2.12
+
+
+  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: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
+    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@master
+      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 }}-1-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+
+    - name: Run lintr
+      run: |
+        cd R-package
+        R.exe CMD INSTALL .
+        Rscript.exe tests/run_lint.R
+
+
+  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:
-        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
+        config:
+          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'autotools'}
+          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'autotools'}
+          - {os: windows-latest, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
+          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
+    env:
+      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
+      RSPM: ${{ matrix.config.rspm }}
 
-  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 Python and C++
-    steps:
-    - uses: actions/checkout@v2
+    - uses: r-lib/actions/setup-r@master
       with:
-        submodules: 'true'
+        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 }}-1-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+
     - uses: actions/setup-python@v2
       with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
-      run: |
-        python -m pip install wheel setuptools
-        python -m pip install pylint cpplint numpy scipy scikit-learn
-    - name: Run lint
-      run: |
-        make lint
+        python-version: '3.6' # Version range or exact version of a Python version to use, using SemVer's version range syntax
+        architecture: 'x64' # optional x64 or x86. Defaults to x64 if not specified
 
-  mypy:
-    runs-on: ubuntu-latest
-    name: Type checking for Python
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install Python packages
+    - name: Test R
       run: |
-        python -m pip install wheel setuptools mypy pandas dask[complete] distributed
-    - name: Run mypy
-      run: |
-        make mypy
-
-  doxygen:
-    runs-on: ubuntu-latest
-    name: Generate C/C++ API doc using Doxygen
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends doxygen graphviz ninja-build
-        python -m pip install wheel setuptools
-        python -m pip install awscli
-    - name: Run Doxygen
-      run: |
-        mkdir build
-        cd build
-        cmake .. -DBUILD_C_DOC=ON -GNinja
-        ninja -v doc_doxygen
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Publish
-      run: |
-        cd build/
-        tar cvjf ${{ steps.extract_branch.outputs.branch }}.tar.bz2 doc_doxygen/
-        python -m awscli s3 cp ./${{ steps.extract_branch.outputs.branch }}.tar.bz2 s3://xgboost-docs/doxygen/ --acl public-read
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}
-
-  sphinx:
-    runs-on: ubuntu-latest
-    name: Build docs using Sphinx
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-        architecture: 'x64'
-    - name: Install system packages
-      run: |
-        sudo apt-get install -y --no-install-recommends graphviz
-        python -m pip install wheel setuptools
-        python -m pip install -r doc/requirements.txt
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Run Sphinx
-      run: |
-        make -C doc html
-      env:
-        SPHINX_GIT_BRANCH: ${{ steps.extract_branch.outputs.branch }}
+        python tests/ci_build/test_r_package.py --compiler="${{ matrix.config.compiler }}" --build-tool="${{ matrix.config.build }}"

.github/workflows/python_tests.yml

@@ -1,142 +0,0 @@
-name: XGBoost-Python-Tests
-
-on: [push, pull_request]
-
-jobs:
-  python-sdist-test:
-    runs-on: ${{ matrix.os }}
-    name: Test installing XGBoost Python source package on ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-10.15, windows-latest]
-        python-version: ["3.8"]
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-    - name: Install osx system dependencies
-      if: matrix.os == 'macos-10.15'
-      run: |
-        brew install ninja libomp
-    - name: Install Ubuntu system dependencies
-      if: matrix.os == 'ubuntu-latest'
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-    - name: Build and install XGBoost
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py sdist
-        pip install -v ./dist/xgboost-*.tar.gz
-        cd ..
-        python -c 'import xgboost'
-
-  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 }}
-    strategy:
-      matrix:
-        config:
-          - {os: macos-10.15, python-version "3.8" }
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.config.python-version }}
-        activate-environment: macos_test
-        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
-
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on macos
-      shell: bash -l {0}
-      run: |
-        brew install ninja
-
-        mkdir build
-        cd build
-        # Set prefix, to use OpenMP library from Conda env
-        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
-        # to learn why we don't use libomp from Homebrew.
-        cmake .. -GNinja -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja
-
-    - name: Install Python package
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py bdist_wheel --universal
-        pip install ./dist/*.whl
-
-    - name: Test Python package
-      shell: bash -l {0}
-      run: |
-        pytest -s -v ./tests/python

.github/workflows/python_wheels.yml

@@ -1,38 +0,0 @@
-name: XGBoost-Python-Wheels
-
-on: [push, pull_request]
-
-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: '3.9'
-    - name: Build wheels
-      run: bash tests/ci_build/build_python_wheels.sh ${{ matrix.platform_id }} ${{ github.sha }}
-    - name: Extract branch name
-      shell: bash
-      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      id: extract_branch
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-    - name: Upload Python wheel
-      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
-      run: |
-        python -m pip install awscli
-        python -m awscli s3 cp wheelhouse/*.whl s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
-      env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID_IAM_S3_UPLOADER }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY_IAM_S3_UPLOADER }}

.github/workflows/r_nold.yml

@@ -1,44 +0,0 @@
-# Run 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')
-
-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

@@ -1,149 +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 }}
-
-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: windows-latest, r: 'release', compiler: 'mingw', build: 'autotools'}
-    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@master
-      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 }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-    - 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.exe CMD INSTALL .
-        Rscript.exe tests/helper_scripts/run_lint.R
-
-  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@master
-      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 }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-    - name: Install igraph on Windows
-      shell: Rscript {0}
-      if: matrix.config.os == 'windows-latest'
-      run: |
-        install.packages('igraph', type='binary', dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7'
-        architecture: 'x64'
-
-    - name: Test R
-      run: |
-        python tests/ci_build/test_r_package.py --compiler='${{ matrix.config.compiler }}' --build-tool='${{ matrix.config.build }}'
-
-  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@master
-      with:
-        r-version: ${{ matrix.config.r }}
-
-    - uses: r-lib/actions/setup-tinytex@master
-
-    - name: Install system packages
-      run: |
-        sudo apt-get update && sudo apt-get install libcurl4-openssl-dev libssl-dev libssh2-1-dev libgit2-dev pandoc pandoc-citeproc libglpk-dev
-
-    - name: Cache R packages
-      uses: actions/cache@v2
-      with:
-        path: ${{ env.R_LIBS_USER }}
-        key: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-3-${{ hashFiles('R-package/DESCRIPTION') }}
-
-    - name: Install dependencies
-      shell: Rscript {0}
-      run: |
-        install.packages(${{ env.R_PACKAGES }},
-                         repos = 'http://cloud.r-project.org',
-                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
-        install.packages('igraph', repos = 'http://cloud.r-project.org', dependencies = c('Depends', 'Imports', 'LinkingTo'))
-
-    - name: Check R Package
-      run: |
-        # Print stacktrace upon success of failure
-        make Rcheck || tests/ci_build/print_r_stacktrace.sh fail
-        tests/ci_build/print_r_stacktrace.sh success

.gitignore

@@ -63,7 +63,6 @@ nb-configuration*
 # Eclipse
 .project
 .cproject
-.classpath
 .pydevproject
 .settings/
 build
@@ -72,7 +71,6 @@ build
 build_plugin
 recommonmark/
 tags
-TAGS
 *.class
 target
 *.swp
@@ -106,28 +104,4 @@ R-package/src/Makevars
 /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
+.gdb_history

.gitmodules

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

.travis.yml

@@ -1,30 +1,57 @@
+# disable sudo for container build.
 sudo: required
 
+# Enabling test OS X
+os:
+  - linux
+  - osx
+
+osx_image: xcode10.1
 dist: bionic
 
+# Use Build Matrix to do lint and build seperately
 env:
+  matrix:
+    # python package test
+    - TASK=python_test
+    # test installation of Python source distribution
+    - TASK=python_sdist_test
+    # java package test
+    - TASK=java_test
+    # cmake test
+    - TASK=cmake_test
+
   global:
-    - secure: "lqkL5SCM/CBwgVb1GWoOngpojsa0zCSGcvF0O3/45rBT1EpNYtQ4LRJ1+XcHi126vdfGoim/8i7AQhn5eOgmZI8yAPBeoUZ5zSrejD3RUpXr2rXocsvRRP25Z4mIuAGHD9VAHtvTdhBZRVV818W02pYduSzAeaY61q/lU3xmWsE="
-    - secure: "mzms6X8uvdhRWxkPBMwx+mDl3d+V1kUpZa7UgjT+dr4rvZMzvKtjKp/O0JZZVogdgZjUZf444B98/7AvWdSkGdkfz2QdmhWmXzNPfNuHtmfCYMdijsgFIGLuD3GviFL/rBiM2vgn32T3QqFiEJiC5StparnnXimPTc9TpXQRq5c="
+    - secure: "PR16i9F8QtNwn99C5NDp8nptAS+97xwDtXEJJfEiEVhxPaaRkOp0MPWhogCaK0Eclxk1TqkgWbdXFknwGycX620AzZWa/A1K3gAs+GrpzqhnPMuoBJ0Z9qxXTbSJvCyvMbYwVrjaxc/zWqdMU8waWz8A7iqKGKs/SqbQ3rO6v7c="
+    - secure: "dAGAjBokqm/0nVoLMofQni/fWIBcYSmdq4XvCBX1ZAMDsWnuOfz/4XCY6h2lEI1rVHZQ+UdZkc9PioOHGPZh5BnvE49/xVVWr9c4/61lrDOlkD01ZjSAeoV0fAZq+93V/wPl4QV+MM+Sem9hNNzFSbN5VsQLAiWCSapWsLdKzqA="
 
-
-jobs:
-  include:
+matrix:
+  exclude:
     - os: linux
-      arch: s390x
-      env: TASK=s390x_test
+      env: TASK=python_test
+    - os: linux
+      env: TASK=java_test
+    - os: linux
+      env: TASK=cmake_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
+      - cmake
+      - libomp
+      - graphviz
+      - openssl
+      - libgit2
+      - lz4
+      - wget
+      - r
+    update: true
 
 before_install:
   - source tests/travis/travis_setup_env.sh
+  - if [ "${TASK}" != "python_sdist_test" ]; then export PYTHONPATH=${PYTHONPATH}:${PWD}/python-package; fi
+  - echo "MAVEN_OPTS='-Xmx2g -XX:MaxPermSize=1024m -XX:ReservedCodeCacheSize=512m -Dorg.slf4j.simpleLogger.defaultLogLevel=error'" > ~/.mavenrc
 
 install:
   - source tests/travis/setup.sh

CMakeLists.txt

@@ -1,10 +1,9 @@
-cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.6.2)
+cmake_minimum_required(VERSION 3.13)
+project(xgboost LANGUAGES CXX C VERSION 1.2.0)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)
 cmake_policy(SET CMP0079 NEW)
-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))
@@ -24,12 +23,9 @@ 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)
@@ -41,7 +37,6 @@ option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC
 option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
 option(GOOGLE_TEST "Build google tests" OFF)
 option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
-option(USE_DEVICE_DEBUG "Generate CUDA 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)
@@ -50,7 +45,6 @@ option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
 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
@@ -64,10 +58,8 @@ set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
   "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
 address, leak, undefined and thread.")
 ## Plugins
+option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
 option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
-option(PLUGIN_RMM "Build with RAPIDS Memory Manager (RMM)" OFF)
-## 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
@@ -77,9 +69,6 @@ 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))
@@ -93,29 +82,11 @@ 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))
 
 #-- Sanitizer
 if (USE_SANITIZER)
@@ -124,22 +95,18 @@ if (USE_SANITIZER)
 endif (USE_SANITIZER)
 
 if (USE_CUDA)
-  set(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
+  SET(USE_OPENMP ON CACHE BOOL "CUDA requires OpenMP" FORCE)
   # `export CXX=' is ignored by CMake CUDA.
   set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
   message(STATUS "Configured CUDA host compiler: ${CMAKE_CUDA_HOST_COMPILER}")
 
   enable_language(CUDA)
-  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.1)
-    message(FATAL_ERROR "CUDA version must be at least 10.1!")
+  if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.0)
+    message(FATAL_ERROR "CUDA version must be at least 10.0!")
   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 ()
+  message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
 endif (USE_CUDA)
 
 if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
@@ -159,51 +126,70 @@ if (USE_OPENMP)
   find_package(OpenMP REQUIRED)
 endif (USE_OPENMP)
 
-if (USE_NCCL)
-  find_package(Nccl REQUIRED)
-endif (USE_NCCL)
+# core xgboost
+add_subdirectory(${xgboost_SOURCE_DIR}/src)
 
 # dmlc-core
 msvc_use_static_runtime()
-if (FORCE_SHARED_CRT)
-  set(DMLC_FORCE_SHARED_CRT ON)
-endif ()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-
+set_target_properties(dmlc PROPERTIES
+  CXX_STANDARD 14
+  CXX_STANDARD_REQUIRED ON
+  POSITION_INDEPENDENT_CODE ON)
 if (MSVC)
+  target_compile_options(dmlc PRIVATE
+                         -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
   if (TARGET dmlc_unit_tests)
     target_compile_options(dmlc_unit_tests PRIVATE
                            -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
   endif (TARGET dmlc_unit_tests)
 endif (MSVC)
+if (ENABLE_ALL_WARNINGS)
+  target_compile_options(dmlc PRIVATE -Wall -Wextra)
+endif (ENABLE_ALL_WARNINGS)
+target_link_libraries(objxgboost PUBLIC dmlc)
 
 # rabit
+set(RABIT_BUILD_DMLC OFF)
+set(DMLC_ROOT ${xgboost_SOURCE_DIR}/dmlc-core)
+set(RABIT_WITH_R_LIB ${R_LIB})
 add_subdirectory(rabit)
-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)
+if (RABIT_MOCK)
+  target_link_libraries(objxgboost PUBLIC rabit_mock_static)
+  if (MSVC)
+    target_compile_options(rabit_mock_static PRIVATE
+                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
+  endif (MSVC)
+else()
+  target_link_libraries(objxgboost PUBLIC rabit)
+  if (MSVC)
+    target_compile_options(rabit PRIVATE
+                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
+  endif (MSVC)
+endif(RABIT_MOCK)
+foreach(lib rabit rabit_base rabit_empty rabit_mock rabit_mock_static)
+  # Explicitly link dmlc to rabit, so that configured header (build_config.h)
+  # from dmlc is correctly applied to rabit.
+  if (TARGET ${lib})
+    target_link_libraries(${lib} dmlc ${CMAKE_THREAD_LIBS_INIT})
+    if (HIDE_CXX_SYMBOLS)  # Hide all C++ symbols from Rabit
+      set_target_properties(${lib} PROPERTIES CXX_VISIBILITY_PRESET hidden)
+    endif (HIDE_CXX_SYMBOLS)
+    if (ENABLE_ALL_WARNINGS)
+      target_compile_options(${lib} PRIVATE -Wall -Wextra)
+    endif (ENABLE_ALL_WARNINGS)
+  endif (TARGET ${lib})
+endforeach()
 
 # 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)
@@ -211,37 +197,47 @@ else (BUILD_STATIC_LIB)
   add_library(xgboost SHARED)
 endif (BUILD_STATIC_LIB)
 target_link_libraries(xgboost PRIVATE objxgboost)
+
+if (USE_NVTX)
+  enable_nvtx(xgboost)
+endif (USE_NVTX)
+
+#-- Hide all C++ symbols
+if (HIDE_CXX_SYMBOLS)
+  set_target_properties(objxgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
+  set_target_properties(xgboost PROPERTIES CXX_VISIBILITY_PRESET hidden)
+endif (HIDE_CXX_SYMBOLS)
+
 target_include_directories(xgboost
   INTERFACE
-  $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
+  $<INSTALL_INTERFACE:${CMAKE_INSTALL_PREFIX}/include>
   $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
+
+# This creates its own shared library `xgboost4j'.
+if (JVM_BINDINGS)
+  add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
+endif (JVM_BINDINGS)
 #-- End shared library
 
 #-- CLI for xgboost
 add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
 target_link_libraries(runxgboost PRIVATE objxgboost)
+if (USE_NVTX)
+  enable_nvtx(runxgboost)
+endif (USE_NVTX)
+
 target_include_directories(runxgboost
   PRIVATE
   ${xgboost_SOURCE_DIR}/include
   ${xgboost_SOURCE_DIR}/dmlc-core/include
-  ${xgboost_SOURCE_DIR}/rabit/include
-)
-set_target_properties(runxgboost PROPERTIES OUTPUT_NAME xgboost)
+  ${xgboost_SOURCE_DIR}/rabit/include)
+set_target_properties(
+  runxgboost PROPERTIES
+  OUTPUT_NAME xgboost
+  CXX_STANDARD 14
+  CXX_STANDARD_REQUIRED ON)
 #-- End CLI for xgboost
 
-# Common setup for all targets
-foreach(target xgboost objxgboost dmlc runxgboost)
-  xgboost_target_properties(${target})
-  xgboost_target_link_libraries(${target})
-  xgboost_target_defs(${target})
-endforeach()
-
-if (JVM_BINDINGS)
-  xgboost_target_properties(xgboost4j)
-  xgboost_target_link_libraries(xgboost4j)
-  xgboost_target_defs(xgboost4j)
-endif (JVM_BINDINGS)
-
 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
@@ -266,27 +262,12 @@ if (BUILD_C_DOC)
   run_doxygen()
 endif (BUILD_C_DOC)
 
-include(CPack)
-
 include(GNUInstallDirs)
 # Install all headers.  Please note that currently the C++ headers does not form an "API".
 install(DIRECTORY ${xgboost_SOURCE_DIR}/include/xgboost
   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}
+install(TARGETS xgboost runxgboost
   EXPORT XGBoostTargets
   ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
   LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
@@ -308,7 +289,7 @@ write_basic_package_version_file(
   COMPATIBILITY AnyNewerVersion)
 install(
   FILES
-  ${CMAKE_CURRENT_BINARY_DIR}/cmake/xgboost-config.cmake
+  ${CMAKE_BINARY_DIR}/cmake/xgboost-config.cmake
   ${CMAKE_BINARY_DIR}/cmake/xgboost-config-version.cmake
   DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/xgboost)
 
@@ -316,18 +297,12 @@ install(
 if (GOOGLE_TEST)
   enable_testing()
   # Unittests.
-  add_executable(testxgboost)
-  target_link_libraries(testxgboost PRIVATE objxgboost)
-  xgboost_target_properties(testxgboost)
-  xgboost_target_link_libraries(testxgboost)
-  xgboost_target_defs(testxgboost)
-
   add_subdirectory(${xgboost_SOURCE_DIR}/tests/cpp)
-
   add_test(
     NAME TestXGBoostLib
     COMMAND testxgboost
     WORKING_DIRECTORY ${xgboost_BINARY_DIR})
+
   # CLI tests
   configure_file(
     ${xgboost_SOURCE_DIR}/tests/cli/machine.conf.in

CONTRIBUTORS.md

@@ -10,8 +10,8 @@ The Project Management Committee(PMC) consists group of active committers that m
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [Michael Benesty](https://github.com/pommedeterresautee)
   - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Akuity
-  - Yuan is a founding engineer at Akuity. He contributed mostly in R and Python packages.
+* [Yuan Tang](https://github.com/terrytangyuan), Ant Group
+  - Yuan is a software engineer in Ant Group. He contributed mostly in R and Python packages.
 * [Nan Zhu](https://github.com/CodingCat), Uber
   - Nan is a software engineer in Uber. He contributed mostly in JVM packages.
 * [Jiaming Yuan](https://github.com/trivialfis)
@@ -43,7 +43,7 @@ Committers are people who have made substantial contribution to the project and
 
 Become a Committer
 ------------------
-XGBoost is a open source project and we are actively looking for new committers who are willing to help maintaining and lead the project.
+XGBoost is a opensource project and we are actively looking for new committers who are willing to help maintaining and lead the project.
 Committers comes from contributors who:
 * Made substantial contribution to the project.
 * Willing to spent time on maintaining and lead the project.
@@ -59,7 +59,7 @@ List of Contributors
 * [Skipper Seabold](https://github.com/jseabold)
   - Skipper is the major contributor to the scikit-learn module of XGBoost.
 * [Zygmunt Zając](https://github.com/zygmuntz)
-  - Zygmunt is the master behind the early stopping feature frequently used by Kagglers.
+  - Zygmunt is the master behind the early stopping feature frequently used by kagglers.
 * [Ajinkya Kale](https://github.com/ajkl)
 * [Boliang Chen](https://github.com/cblsjtu)
 * [Yangqing Men](https://github.com/yanqingmen)
@@ -91,7 +91,7 @@ List of Contributors
 * [Henry Gouk](https://github.com/henrygouk)
 * [Pierre de Sahb](https://github.com/pdesahb)
 * [liuliang01](https://github.com/liuliang01)
-  - liuliang01 added support for the qid column for LIBSVM input format. This makes ranking task easier in distributed setting.
+  - liuliang01 added support for the qid column for LibSVM input format. This makes ranking task easier in distributed setting.
 * [Andrew Thia](https://github.com/BlueTea88)
   - Andrew Thia implemented feature interaction constraints
 * [Wei Tian](https://github.com/weitian)

Jenkinsfile

@@ -7,7 +7,7 @@
 dockerRun = 'tests/ci_build/ci_build.sh'
 
 // Which CUDA version to use when building reference distribution wheel
-ref_cuda_ver = '11.0.3'
+ref_cuda_ver = '10.0'
 
 import groovy.transform.Field
 
@@ -38,15 +38,26 @@ pipeline {
       agent { label 'job_initializer' }
       steps {
         script {
-          def buildNumber = env.BUILD_NUMBER as int
-          if (buildNumber > 1) milestone(buildNumber - 1)
-          milestone(buildNumber)
-
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
         sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
+        milestone ordinal: 1
+      }
+    }
+    stage('Jenkins Linux: Formatting Check') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'clang-tidy': { ClangTidy() },
+            'lint': { Lint() },
+            'sphinx-doc': { SphinxDoc() },
+            'doxygen': { Doxygen() }
+          ])
+        }
+        milestone ordinal: 2
       }
     }
     stage('Jenkins Linux: Build') {
@@ -54,19 +65,22 @@ pipeline {
       steps {
         script {
           parallel ([
-            'clang-tidy': { ClangTidy() },
             'build-cpu': { BuildCPU() },
-            'build-cpu-arm64': { BuildCPUARM64() },
             'build-cpu-rabit-mock': { BuildCPUMock() },
-            // Build reference, distribution-ready Python wheel with CUDA 11.0
-            // using CentOS 7 image
-            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0.3', build_rmm: true) },
-            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '11.0.3') },
-            'build-jvm-packages-gpu-cuda11.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.1', cuda_version: '11.0.3') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.1') },
+            'build-cpu-non-omp': { BuildCPUNonOmp() },
+            // Build reference, distribution-ready Python wheel with CUDA 10.0
+            // using CentOS 6 image
+            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
+            // The build-gpu-* builds below use Ubuntu image
+            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
+            'build-gpu-cuda10.2': { BuildCUDA(cuda_version: '10.2') },
+            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0') },
+            'build-jvm-packages-gpu-cuda10.0': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '10.0') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
             'build-jvm-doc': { BuildJVMDoc() }
           ])
         }
+        milestone ordinal: 3
       }
     }
     stage('Jenkins Linux: Test') {
@@ -75,14 +89,20 @@ pipeline {
         script {
           parallel ([
             'test-python-cpu': { TestPythonCPU() },
-            'test-python-cpu-arm64': { TestPythonCPUARM64() },
-            // artifact_cuda_version doesn't apply to RMM tests; RMM tests will always match CUDA version between artifact and host env
-            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', test_rmm: true) },
-            'test-python-mgpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', multi_gpu: true, test_rmm: true) },
-            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0.3', host_cuda_version: '11.0.3', test_rmm: true) },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') }
+            'test-python-gpu-cuda10.2': { TestPythonGPU(host_cuda_version: '10.2') },
+            'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '11.0') },
+            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
+            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', multi_gpu: true) },
+            'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2') },
+            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
+            'test-jvm-jdk8-cuda10.0': { CrossTestJVMwithJDKGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.0') },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
+            'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
+            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
+            'test-r-3.5.3': { TestR(use_r35: true) }
           ])
         }
+        milestone ordinal: 4
       }
     }
     stage('Jenkins Linux: Deploy') {
@@ -93,6 +113,7 @@ pipeline {
             'deploy-jvm-packages': { DeployJVMPackages(spark_version: '3.0.0') }
           ])
         }
+        milestone ordinal: 5
       }
     }
   }
@@ -114,7 +135,7 @@ def checkoutSrcs() {
 }
 
 def GetCUDABuildContainerType(cuda_version) {
-  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos7' : 'gpu_build'
+  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos6' : 'gpu_build'
 }
 
 def ClangTidy() {
@@ -123,14 +144,58 @@ def ClangTidy() {
     echo "Running clang-tidy job..."
     def container_type = "clang_tidy"
     def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION_ARG=11.0.3"
+    def dockerArgs = "--build-arg CUDA_VERSION=10.1"
     sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py --cuda-archs 75
+    ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
     """
     deleteDir()
   }
 }
 
+def Lint() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running lint..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate cpu_test && make lint"
+    """
+    deleteDir()
+  }
+}
+
+def SphinxDoc() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running sphinx-doc..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
+    sh """#!/bin/bash
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate cpu_test && make -C doc html"
+    """
+    deleteDir()
+  }
+}
+
+def Doxygen() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Running doxygen..."
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
+    """
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading doc...'
+      s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
+    }
+    deleteDir()
+  }
+}
+
 def BuildCPU() {
   node('linux && cpu') {
     unstash name: 'srcs'
@@ -142,15 +207,15 @@ def BuildCPU() {
       # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
       # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
       # See discussion at https://github.com/dmlc/xgboost/issues/5510
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_DENSE_PARSER=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_LZ4=ON -DPLUGIN_DENSE_PARSER=ON
+    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
     """
     // Sanitizer test
     def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
       -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose"
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
     """
 
     stash name: 'xgboost_cli', includes: 'xgboost'
@@ -158,36 +223,6 @@ def BuildCPU() {
   }
 }
 
-def BuildCPUARM64() {
-  node('linux && arm64') {
-    unstash name: 'srcs'
-    echo "Build CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    def wheel_tag = "manylinux2014_aarch64"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh --conda-env=aarch64_test -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOL=ON
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl && python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}"
-    mv -v wheelhouse/*.whl python-package/dist/
-    # Make sure that libgomp.so is vendored in the wheel
-    ${dockerRun} ${container_type} ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp || exit -1"
-    """
-    echo 'Stashing Python wheel...'
-    stash name: "xgboost_whl_arm64_cpu", includes: 'python-package/dist/*.whl'
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      echo 'Uploading Python wheel...'
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} bash -c "source activate aarch64_test && python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress"
-      """
-    }
-    stash name: 'xgboost_cli_arm64', includes: 'xgboost'
-    deleteDir()
-  }
-}
-
 def BuildCPUMock() {
   node('linux && cpu') {
     unstash name: 'srcs'
@@ -203,77 +238,48 @@ def BuildCPUMock() {
   }
 }
 
+def BuildCPUNonOmp() {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Build CPU without OpenMP"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_OPENMP=OFF
+    """
+    echo "Running Non-OpenMP C++ test..."
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    """
+    deleteDir()
+  }
+}
+
 def BuildCUDA(args) {
   node('linux && cpu_build') {
     unstash name: 'srcs'
     echo "Build with CUDA ${args.cuda_version}"
     def container_type = GetCUDABuildContainerType(args.cuda_version)
     def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
     def arch_flag = ""
     if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
       arch_flag = "-DGPU_COMPUTE_VER=75"
     }
-    def wheel_tag = "manylinux2014_x86_64"
     sh """
     ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOLS=ON ${arch_flag}
     ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
     """
-    if (args.cuda_version == ref_cuda_ver) {
-      sh """
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}
-      mv -v wheelhouse/*.whl python-package/dist/
-      # Make sure that libgomp.so is vendored in the wheel
-      ${dockerRun} auditwheel_x86_64 ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
-      """
-    }
     echo 'Stashing Python wheel...'
     stash name: "xgboost_whl_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
     if (args.cuda_version == ref_cuda_ver && (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release'))) {
       echo 'Uploading Python wheel...'
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress
-      """
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
     }
     echo 'Stashing C++ test executable (testxgboost)...'
     stash name: "xgboost_cpp_tests_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    if (args.build_rmm) {
-      echo "Build with CUDA ${args.cuda_version} and RMM"
-      container_type = "rmm"
-      docker_binary = "docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-      sh """
-      rm -rf build/
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON -DUSE_NCCL=ON -DPLUGIN_RMM=ON -DBUILD_WITH_CUDA_CUB=ON ${arch_flag}
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2014_x86_64
-      """
-      echo 'Stashing Python wheel...'
-      stash name: "xgboost_whl_rmm_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
-      echo 'Stashing C++ test executable (testxgboost)...'
-      stash name: "xgboost_cpp_tests_rmm_cuda${args.cuda_version}", includes: 'build/testxgboost'
-    }
-    deleteDir()
-  }
-}
-
-def BuildRPackageWithCUDA(args) {
-  node('linux && cpu_build') {
-    unstash name: 'srcs'
-    def container_type = 'gpu_build_r_centos7'
-    def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_r_pkg_with_cuda.sh ${commit_id}
-      """
-      echo 'Uploading R tarball...'
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python -m awscli s3 cp xgboost_r_gpu_linux_*.tar.gz s3://xgboost-nightly-builds/${BRANCH_NAME}/ --acl public-read --no-progress
-      """
-    }
     deleteDir()
   }
 }
@@ -284,7 +290,7 @@ def BuildJVMPackagesWithCUDA(args) {
     echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
     def container_type = "jvm_gpu_build"
     def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
     def arch_flag = ""
     if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
       arch_flag = "-DGPU_COMPUTE_VER=75"
@@ -295,7 +301,7 @@ def BuildJVMPackagesWithCUDA(args) {
     ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
     """
     echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
-    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
+    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
     deleteDir()
   }
 }
@@ -328,9 +334,7 @@ def BuildJVMDoc() {
     """
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Uploading doc...'
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} python -m awscli s3 cp jvm-packages/${BRANCH_NAME}.tar.bz2 s3://xgboost-docs/${BRANCH_NAME}.tar.bz2 --acl public-read --no-progress
-      """
+      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
     }
     deleteDir()
   }
@@ -351,21 +355,6 @@ def TestPythonCPU() {
   }
 }
 
-def TestPythonCPUARM64() {
-  node('linux && arm64') {
-    unstash name: "xgboost_whl_arm64_cpu"
-    unstash name: 'srcs'
-    unstash name: 'xgboost_cli_arm64'
-    echo "Test Python CPU ARM64"
-    def container_type = "aarch64"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-arm64
-    """
-    deleteDir()
-  }
-}
-
 def TestPythonGPU(args) {
   def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
   def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
@@ -376,43 +365,67 @@ def TestPythonGPU(args) {
     echo "Test Python GPU: CUDA ${args.host_cuda_version}"
     def container_type = "gpu"
     def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    def mgpu_indicator = (args.multi_gpu) ? 'mgpu' : 'gpu'
-    // Allocate extra space in /dev/shm to enable NCCL
-    def docker_extra_params = (args.multi_gpu) ? "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'" : ''
-    sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator}"
-    if (args.test_rmm) {
-      sh "rm -rfv build/ python-package/dist/"
-      unstash name: "xgboost_whl_rmm_cuda${args.host_cuda_version}"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator} --use-rmm-pool"
+    def docker_args = "--build-arg CUDA_VERSION=${args.host_cuda_version}"
+    if (args.multi_gpu) {
+      echo "Using multiple GPUs"
+      // Allocate extra space in /dev/shm to enable NCCL
+      def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'"
+      sh """
+      ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
+      """
+    } else {
+      echo "Using a single GPU"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
+      """
     }
     deleteDir()
   }
 }
 
+def TestCppRabit() {
+  node(nodeReq) {
+    unstash name: 'xgboost_rabit_tests'
+    unstash name: 'srcs'
+    echo "Test C++, rabit mock on"
+    def container_type = "cpu"
+    def docker_binary = "docker"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/runxgb.sh xgboost tests/ci_build/approx.conf.in
+    """
+    deleteDir()
+  }
+}
+
 def TestCppGPU(args) {
   def nodeReq = 'linux && mgpu'
   def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
   node(nodeReq) {
     unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
     unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.host_cuda_version}, rmm: ${args.test_rmm}"
+    echo "Test C++, CUDA ${args.host_cuda_version}"
     def container_type = "gpu"
     def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION=${args.host_cuda_version}"
     sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
-    if (args.test_rmm) {
-      sh "rm -rfv build/"
-      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
-      echo "Test C++, CUDA ${args.host_cuda_version} with RMM"
-      container_type = "rmm"
-      docker_binary = "nvidia-docker"
-      docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "source activate gpu_test && build/testxgboost --use-rmm-pool"
-      """
+    deleteDir()
+  }
+}
+
+def CrossTestJVMwithJDKGPU(args) {
+  def nodeReq = 'linux && mgpu'
+  node(nodeReq) {
+    unstash name: "xgboost4j_jar_gpu"
+    unstash name: 'srcs'
+    if (args.spark_version != null) {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}, CUDA ${args.host_cuda_version}"
+    } else {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, CUDA ${args.host_cuda_version}"
     }
+    def container_type = "gpu_jvm"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION=${args.host_cuda_version}"
+    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_gpu_cross.sh"
     deleteDir()
   }
 }
@@ -439,13 +452,31 @@ def CrossTestJVMwithJDK(args) {
   }
 }
 
+def TestR(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    echo "Test R package"
+    def container_type = "rproject"
+    def docker_binary = "docker"
+    def use_r35_flag = (args.use_r35) ? "1" : "0"
+    def docker_args = "--build-arg USE_R35=${use_r35_flag}"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_test_rpkg.sh || tests/ci_build/print_r_stacktrace.sh
+    """
+    deleteDir()
+  }
+}
+
 def DeployJVMPackages(args) {
   node('linux && cpu') {
     unstash name: 'srcs'
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Deploying to xgboost-maven-repo S3 repo...'
       sh """
-      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=11.0.3 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      ${dockerRun} jvm docker tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 0
+      """
+      sh """
+      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 1
       """
     }
     deleteDir()

Jenkinsfile-win64

@@ -25,14 +25,12 @@ pipeline {
       agent { label 'job_initializer' }
       steps {
         script {
-          def buildNumber = env.BUILD_NUMBER as int
-          if (buildNumber > 1) milestone(buildNumber - 1)
-          milestone(buildNumber)
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
         sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
+        milestone ordinal: 1
       }
     }
     stage('Jenkins Win64: Build') {
@@ -40,10 +38,10 @@ pipeline {
       steps {
         script {
           parallel ([
-            'build-win64-cuda11.0': { BuildWin64() },
-            'build-rpkg-win64-cuda11.0': { BuildRPackageWithCUDAWin64() }
+            'build-win64-cuda10.1': { BuildWin64() }
           ])
         }
+        milestone ordinal: 2
       }
     }
     stage('Jenkins Win64: Test') {
@@ -51,9 +49,10 @@ pipeline {
       steps {
         script {
           parallel ([
-            'test-win64-cuda11.0': { TestWin64() },
+            'test-win64-cuda10.1': { TestWin64() },
           ])
         }
+        milestone ordinal: 3
       }
     }
   }
@@ -75,8 +74,7 @@ def checkoutSrcs() {
 }
 
 def BuildWin64() {
-  node('win64 && cuda11_unified') {
-    deleteDir()
+  node('win64 && cuda10_unified') {
     unstash name: 'srcs'
     echo "Building XGBoost for Windows AMD64 target..."
     bat "nvcc --version"
@@ -87,7 +85,7 @@ def BuildWin64() {
     bat """
     mkdir build
     cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON ${arch_flag} -DCMAKE_UNITY_BUILD=ON
+    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON ${arch_flag}
     """
     bat """
     cd build
@@ -107,7 +105,7 @@ def BuildWin64() {
     stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Uploading Python wheel...'
-      path = "${BRANCH_NAME}/"
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
       s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
     }
     echo 'Stashing C++ test executable (testxgboost)...'
@@ -117,26 +115,8 @@ def BuildWin64() {
   }
 }
 
-def BuildRPackageWithCUDAWin64() {
-  node('win64 && cuda11_unified') {
-    deleteDir()
-    unstash name: 'srcs'
-    bat "nvcc --version"
-    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
-      bat """
-      bash tests/ci_build/build_r_pkg_with_cuda_win64.sh ${commit_id}
-      """
-      echo 'Uploading R tarball...'
-      path = "${BRANCH_NAME}/"
-      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_win64_*.tar.gz'
-    }
-    deleteDir()
-  }
-}
-
 def TestWin64() {
-  node('win64 && cuda11_unified') {
-    deleteDir()
+  node('win64 && cuda10_unified') {
     unstash name: 'srcs'
     unstash name: 'xgboost_whl'
     unstash name: 'xgboost_cli'
@@ -147,15 +127,15 @@ def TestWin64() {
     bat "build\\testxgboost.exe"
     echo "Installing Python dependencies..."
     def env_name = 'win64_' + UUID.randomUUID().toString().replaceAll('-', '')
-    bat "conda activate && mamba env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
+    bat "conda env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
     echo "Installing Python wheel..."
     bat """
     conda activate ${env_name} && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
     """
     echo "Running Python tests..."
-    bat "conda activate ${env_name} && python -X faulthandler -m pytest -v -s -rxXs --fulltrace tests\\python"
+    bat "conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace tests\\python"
     bat """
-    conda activate ${env_name} && python -X faulthandler -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
+    conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu
     """
     bat "conda env remove --name ${env_name}"
     deleteDir()

Makefile

@@ -86,23 +86,6 @@ cover: check
 	)
 endif
 
-
-# dask is required to pass, others are not
-# If any of the dask tests failed, contributor won't see the other error.
-mypy:
-	cd python-package; \
-	mypy ./xgboost/dask.py && \
-	mypy ./xgboost/rabit.py && \
-	mypy ./xgboost/tracker.py && \
-	mypy ./xgboost/sklearn.py && \
-	mypy ../demo/guide-python/external_memory.py && \
-	mypy ../demo/guide-python/categorical.py && \
-	mypy ../demo/guide-python/cat_in_the_dat.py && \
-	mypy ../tests/python-gpu/test_gpu_with_dask.py && \
-	mypy ../tests/python/test_data_iterator.py && \
-	mypy ../tests/python-gpu/test_gpu_data_iterator.py  || exit 1; \
-	mypy . || true ;
-
 clean:
 	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
 	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
@@ -151,19 +134,14 @@ Rpack: clean_all
 	sed -i -e 's/@OPENMP_LIB@//g' xgboost/src/Makevars.win
 	rm -f xgboost/src/Makevars.win-e   # OSX sed create this extra file; remove it
 	bash R-package/remove_warning_suppression_pragma.sh
-	bash xgboost/remove_warning_suppression_pragma.sh
 	rm xgboost/remove_warning_suppression_pragma.sh
-	rm xgboost/CMakeLists.txt
-	rm -rfv xgboost/tests/helper_scripts/
-
-R ?= R
 
 Rbuild: Rpack
-	$(R) CMD build xgboost
+	R CMD build --no-build-vignettes xgboost
 	rm -rf xgboost
 
 Rcheck: Rbuild
-	$(R) CMD check --as-cran xgboost*.tar.gz
+	R CMD check xgboost*.tar.gz
 
 -include build/*.d
 -include build/*/*.d

NEWS.md

@@ -3,905 +3,6 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
-## v1.5.0 (2021 Oct 11)
-
-This release comes with many exciting new features and optimizations, along with some bug
-fixes.  We will describe the experimental categorical data support and the external memory
-interface independently. Package-specific new features will be listed in respective
-sections.
-
-### Development on categorical data support
-In version 1.3, XGBoost introduced an experimental feature for handling categorical data
-natively, without one-hot encoding. XGBoost can fit categorical splits in decision
-trees. (Currently, the generated splits will be of form `x \in {v}`, where the input is
-compared to a single category value. A future version of XGBoost will generate splits that
-compare the input against a list of multiple category values.)
-
-Most of the other features, including prediction, SHAP value computation, feature
-importance, and model plotting were revised to natively handle categorical splits.  Also,
-all Python interfaces including native interface with and without quantized `DMatrix`,
-scikit-learn interface, and Dask interface now accept categorical data with a wide range
-of data structures support including numpy/cupy array and cuDF/pandas/modin dataframe.  In
-practice, the following are required for enabling categorical data support during
-training:
-
-  - Use Python package.
-  - Use `gpu_hist` to train the model.
-  - Use JSON model file format for saving the model.
-
-Once the model is trained, it can be used with most of the features that are available on
-the Python package.  For a quick introduction, see
-https://xgboost.readthedocs.io/en/latest/tutorials/categorical.html
-
-Related PRs: (#7011, #7001, #7042, #7041, #7047, #7043, #7036, #7054, #7053, #7065, #7213, #7228, #7220, #7221, #7231, #7306)
-
-* Next steps
-
-	- Revise the CPU training algorithm to handle categorical data natively and generate categorical splits
-	- Extend the CPU and GPU algorithms to generate categorical splits of form `x \in S`
-	where the input is compared with multiple category values.  split. (#7081)
-
-### External memory
-This release features a brand-new interface and implementation for external memory (also
-known as out-of-core training).  (#6901, #7064, #7088, #7089, #7087, #7092, #7070,
-#7216). The new implementation leverages the data iterator interface, which is currently
-used to create `DeviceQuantileDMatrix`. For a quick introduction, see
-https://xgboost.readthedocs.io/en/latest/tutorials/external_memory.html#data-iterator
-. During the development of this new interface, `lz4` compression is removed. (#7076).
-Please note that external memory support is still experimental and not ready for
-production use yet.  All future development will focus on this new interface and users are
-advised to migrate. (You are using the old interface if you are using a URL suffix to use
-external memory.)
-
-### New features in Python package
-* Support numpy array interface and all numeric types from numpy in `DMatrix`
-  construction and `inplace_predict` (#6998, #7003).  Now XGBoost no longer makes data
-  copy when input is numpy array view.
-* The early stopping callback in Python has a new `min_delta` parameter to control the
-  stopping behavior (#7137)
-* Python package now supports calculating feature scores for the linear model, which is
-  also available on R package. (#7048)
-* Python interface now supports configuring constraints using feature names instead of
-  feature indices.
-* Typehint support for more Python code including scikit-learn interface and rabit
-  module. (#6799, #7240)
-* Add tutorial for XGBoost-Ray (#6884)
-
-### New features in R package
-* In 1.4 we have a new prediction function in the C API which is used by the Python
-  package.  This release revises the R package to use the new prediction function as well.
-  A new parameter `iteration_range` for the predict function is available, which can be
-  used for specifying the range of trees for running prediction. (#6819, #7126)
-* R package now supports the `nthread` parameter in `DMatrix` construction. (#7127)
-
-### New features in JVM packages
-* Support GPU dataframe and `DeviceQuantileDMatrix` (#7195).  Constructing `DMatrix`
-  with GPU data structures and the interface for quantized `DMatrix` were first
-  introduced in the Python package and are now available in the xgboost4j package.
-* JVM packages now support saving and getting early stopping attributes. (#7095) Here is a
-  quick [example](https://github.com/dmlc/xgboost/jvm-packages/xgboost4j-example/src/main/java/ml/dmlc/xgboost4j/java/example/EarlyStopping.java "example") in JAVA (#7252).
-
-### General new features
-* We now have a pre-built binary package for R on Windows with GPU support. (#7185)
-* CUDA compute capability 86 is now part of the default CMake build configuration with
-  newly added support for CUDA 11.4. (#7131, #7182, #7254)
-* XGBoost can be compiled using system CUB provided by CUDA 11.x installation. (#7232)
-
-### Optimizations
-The performance for both `hist` and `gpu_hist` has been significantly improved in 1.5
-with the following optimizations:
-* GPU multi-class model training now supports prediction cache. (#6860)
-* GPU histogram building is sped up and the overall training time is 2-3 times faster on
-  large datasets (#7180, #7198).  In addition, we removed the parameter `deterministic_histogram` and now
-  the GPU algorithm is always deterministic.
-* CPU hist has an optimized procedure for data sampling (#6922)
-* More performance optimization in regression and binary classification objectives on
-  CPU (#7206)
-* Tree model dump is now performed in parallel (#7040)
-
-### Breaking changes
-* `n_gpus` was deprecated in 1.0 release and is now removed.
-* Feature grouping in CPU hist tree method is removed, which was disabled long
-  ago. (#7018)
-* C API for Quantile DMatrix is changed to be consistent with the new external memory
-  implementation. (#7082)
-
-### Notable general bug fixes
-* XGBoost no long changes global CUDA device ordinal when `gpu_id` is specified (#6891,
-  #6987)
-* Fix `gamma` negative likelihood evaluation metric. (#7275)
-* Fix integer value of `verbose_eal` for `xgboost.cv` function in Python. (#7291)
-* Remove extra sync in CPU hist for dense data, which can lead to incorrect tree node
-  statistics. (#7120, #7128)
-* Fix a bug in GPU hist when data size is larger than `UINT32_MAX` with missing
-  values. (#7026)
-* Fix a thread safety issue in prediction with the `softmax` objective. (#7104)
-* Fix a thread safety issue in CPU SHAP value computation. (#7050) Please note that all
-  prediction functions in Python are thread-safe.
-* Fix model slicing. (#7149, #7078)
-* Workaround a bug in old GCC which can lead to segfault during construction of
-  DMatrix. (#7161)
-* Fix histogram truncation in GPU hist, which can lead to slightly-off results. (#7181)
-* Fix loading GPU linear model pickle files on CPU-only machine. (#7154)
-* Check input value is duplicated when CPU quantile queue is full (#7091)
-* Fix parameter loading with training continuation. (#7121)
-* Fix CMake interface for exposing C library by specifying dependencies. (#7099)
-* Callback and early stopping are explicitly disabled for the scikit-learn interface
-  random forest estimator. (#7236)
-* Fix compilation error on x86 (32-bit machine) (#6964)
-* Fix CPU memory usage with extremely sparse datasets (#7255)
-* Fix a bug in GPU multi-class AUC implementation with weighted data (#7300)
-
-### Python package
-Other than the items mentioned in the previous sections, there are some Python-specific
-improvements.
-* Change development release postfix to `dev` (#6988)
-* Fix early stopping behavior with MAPE metric (#7061)
-* Fixed incorrect feature mismatch error message (#6949)
-* Add predictor to skl constructor. (#7000, #7159)
-* Re-enable feature validation in predict proba. (#7177)
-* scikit learn interface regression estimator now can pass the scikit-learn estimator
-  check and is fully compatible with scikit-learn utilities.  `__sklearn_is_fitted__` is
-  implemented as part of the changes (#7130, #7230)
-* Conform the latest pylint. (#7071, #7241)
-* Support latest panda range index in DMatrix construction. (#7074)
-* Fix DMatrix construction from pandas series. (#7243)
-* Fix typo and grammatical mistake in error message (#7134)
-* [dask] disable work stealing explicitly for training tasks (#6794)
-* [dask] Set dataframe index in predict. (#6944)
-* [dask] Fix prediction on df with latest dask. (#6969)
-* [dask] Fix dask predict on `DaskDMatrix` with `iteration_range`. (#7005)
-* [dask] Disallow importing non-dask estimators from xgboost.dask (#7133)
-
-### R package
-Improvements other than new features on R package:
-* Optimization for updating R handles in-place (#6903)
-* Removed the magrittr dependency. (#6855, #6906, #6928)
-* The R package now hides all C++ symbols to avoid conflicts. (#7245)
-* Other maintenance including code cleanups, document updates. (#6863, #6915, #6930, #6966, #6967)
-
-### JVM packages
-Improvements other than new features on JVM packages:
-* Constructors with implicit missing value are deprecated due to confusing behaviors. (#7225)
-* Reduce scala-compiler, scalatest dependency scopes (#6730)
-* Making the Java library loader emit helpful error messages on missing dependencies. (#6926)
-* JVM packages now use the Python tracker in XGBoost instead of dmlc.  The one in XGBoost
-  is shared between JVM packages and Python Dask and enjoys better maintenance (#7132)
-* Fix "key not found: train" error (#6842)
-* Fix model loading from stream (#7067)
-
-### General document improvements
-* Overhaul the installation documents. (#6877)
-* A few demos are added for AFT with dask (#6853), callback with dask (#6995), inference
-  in C (#7151), `process_type`. (#7135)
-* Fix PDF format of document. (#7143)
-* Clarify the behavior of `use_rmm`. (#6808)
-* Clarify prediction function. (#6813)
-* Improve tutorial on feature interactions (#7219)
-* Add small example for dask sklearn interface. (#6970)
-* Update Python intro.  (#7235)
-* Some fixes/updates (#6810, #6856, #6935, #6948, #6976, #7084, #7097, #7170, #7173, #7174, #7226, #6979, #6809, #6796, #6979)
-
-### Maintenance
-* Some refactoring around CPU hist, which lead to better performance but are listed under general maintenance tasks:
-  - Extract evaluate splits from CPU hist. (#7079)
-  - Merge lossgude and depthwise strategies for CPU hist (#7007)
-  - Simplify sparse and dense CPU hist kernels (#7029)
-  - Extract histogram builder from CPU Hist. (#7152)
-
-* Others
-  - Fix `gpu_id` with custom objective. (#7015)
-  - Fix typos in AUC. (#6795)
-  - Use constexpr in `dh::CopyIf`. (#6828)
-  - Update dmlc-core. (#6862)
-  - Bump version to 1.5.0 snapshot in master. (#6875)
-  - Relax shotgun test. (#6900)
-  - Guard against index error in prediction. (#6982)
-  - Hide symbols in CI build + hide symbols for C and CUDA (#6798)
-  - Persist data in dask test. (#7077)
-  - Fix typo in arguments of PartitionBuilder::Init (#7113)
-  - Fix typo in src/common/hist.cc BuildHistKernel (#7116)
-  - Use upstream URI in distributed quantile tests. (#7129)
-  - Include cpack (#7160)
-  - Remove synchronization in monitor. (#7164)
-  - Remove unused code. (#7175)
-  - Fix building on CUDA 11.0. (#7187)
-  - Better error message for `ncclUnhandledCudaError`. (#7190)
-  - Add noexcept to JSON objects. (#7205)
-  - Improve wording for warning (#7248)
-  - Fix typo in release script. [skip ci] (#7238)
-  - Relax shotgun test. (#6918)
-  - Relax test for decision stump in distributed environment. (#6919)
-  -	[dask] speed up tests (#7020)
-
-### CI
-* [CI] Rotate access keys for uploading MacOS artifacts from Travis CI (#7253)
-* Reduce Travis environment setup time. (#6912)
-* Restore R cache on github action. (#6985)
-* [CI] Remove stray build artifact to avoid error in artifact packaging (#6994)
-* [CI] Move appveyor tests to action (#6986)
-* Remove appveyor badge. [skip ci] (#7035)
-* [CI] Configure RAPIDS, dask, modin (#7033)
-* Test on s390x. (#7038)
-* [CI] Upgrade to CMake 3.14 (#7060)
-* [CI] Update R cache. (#7102)
-* [CI] Pin libomp to 11.1.0  (#7107)
-* [CI] Upgrade build image to CentOS 7 + GCC 8; require CUDA 10.1 and later (#7141)
-* [dask] Work around segfault in prediction. (#7112)
-* [dask] Remove the workaround for segfault. (#7146)
-* [CI] Fix hanging Python setup in Windows CI (#7186)
-* [CI] Clean up in beginning of each task in Win CI (#7189)
-* Fix travis. (#7237)
-
-### Acknowledgement
-* **Contributors**: Adam Pocock (@Craigacp), Jeff H (@JeffHCross), Johan Hansson (@JohanWork), Jose Manuel Llorens (@JoseLlorensRipolles), Benjamin Szőke (@Livius90), @ReeceGoding, @ShvetsKS, Robert Zabel (@ZabelTech), Ali (@ali5h), Andrew Ziem (@az0), Andy Adinets (@canonizer), @david-cortes, Daniel Saxton (@dsaxton), Emil Sadek (@esadek), @farfarawayzyt, Gil Forsyth (@gforsyth), @giladmaya, @graue70, Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), José Morales (@jmoralez), Kai Fricke (@krfricke), Christian Lorentzen (@lorentzenchr), Mads R. B. Kristensen (@madsbk), Anton Kostin (@masguit42), Martin Petříček (@mpetricek-corp), @naveenkb, Taewoo Kim (@oOTWK), Viktor Szathmáry (@phraktle), Robert Maynard (@robertmaynard), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), Paul Taylor (@trxcllnt), @vslaykovsky, Bobby Wang (@wbo4958),
-* **Reviewers**: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Jose Manuel Llorens (@JoseLlorensRipolles), Kodi Arfer (@Kodiologist), Benjamin Szőke (@Livius90), Mark Guryanov (@MarkGuryanov), Rory Mitchell (@RAMitchell), @ReeceGoding, @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Andrew Ziem (@az0), @candalfigomoro, Andy Adinets (@canonizer), Dante Gama Dessavre (@dantegd), @david-cortes, Daniel Saxton (@dsaxton), @farfarawayzyt, Gil Forsyth (@gforsyth), Harutaka Kawamura (@harupy), Philip Hyunsu Cho (@hcho3), @jakirkham, James Lamb (@jameslamb), José Morales (@jmoralez), James Bourbeau (@jrbourbeau), Christian Lorentzen (@lorentzenchr), Martin Petříček (@mpetricek-corp), Nikolay Petrov (@napetrov), @naveenkb, Viktor Szathmáry (@phraktle), Robin Teuwens (@rteuwens), Yuan Tang (@terrytangyuan), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), @vkuzmin-uber, Bobby Wang (@wbo4958), William Hicks (@wphicks)
-
-
-## v1.4.2 (2021.05.13)
-This is a patch release for Python package with following fixes:
-
-* Handle the latest version of cupy.ndarray in inplace_predict. (#6933)
-* Ensure output array from predict_leaf is (n_samples, ) when there's only 1 tree. 1.4.0 outputs (n_samples, 1). (#6889)
-* Fix empty dataset handling with multi-class AUC. (#6947)
-* Handle object type from pandas in inplace_predict. (#6927)
-
-
-## v1.4.1 (2021.04.20)
-This is a bug fix release.
-
-* Fix GPU implementation of AUC on some large datasets. (#6866)
-
-## v1.4.0 (2021.04.12)
-
-### Introduction of pre-built binary package for R, with GPU support
-Starting with release 1.4.0, users now have the option of installing `{xgboost}` without
-having to build it from the source. This is particularly advantageous for users who want
-to take advantage of the GPU algorithm (`gpu_hist`), as previously they'd have to build
-`{xgboost}` from the source using CMake and NVCC. Now installing `{xgboost}` with GPU
-support is as easy as: `R CMD INSTALL ./xgboost_r_gpu_linux.tar.gz`. (#6827)
-
-See the instructions at https://xgboost.readthedocs.io/en/latest/build.html
-
-### Improvements on prediction functions
-XGBoost has many prediction types including shap value computation and inplace prediction.
-In 1.4 we overhauled the underlying prediction functions for C API and Python API with an
-unified interface. (#6777, #6693, #6653, #6662, #6648, #6668, #6804)
-* Starting with 1.4, sklearn interface prediction will use inplace predict by default when
-  input data is supported.
-* Users can use inplace predict with `dart` booster and enable GPU acceleration just
-  like `gbtree`.
-* Also all prediction functions with tree models are now thread-safe.  Inplace predict is
-  improved with `base_margin` support.
-* A new set of C predict functions are exposed in the public interface.
-* A user-visible change is a newly added parameter called `strict_shape`.  See
-  https://xgboost.readthedocs.io/en/latest/prediction.html for more details.
-
-
-### Improvement on Dask interface
-* Starting with 1.4, the Dask interface is considered to be feature-complete, which means
-  all of the models found in the single node Python interface are now supported in Dask,
-  including but not limited to ranking and random forest.  Also, the prediction function
-  is significantly faster and supports shap value computation.
-  - Most of the parameters found in single node sklearn interface are supported by
-    Dask interface. (#6471, #6591)
-  - Implements learning to rank.  On the Dask interface, we use the newly added support of
-    query ID to enable group structure. (#6576)
-  - The Dask interface has Python type hints support. (#6519)
-  - All models can be safely pickled. (#6651)
-  - Random forest estimators are now supported. (#6602)
-  - Shap value computation is now supported. (#6575, #6645, #6614)
-  - Evaluation result is printed on the scheduler process. (#6609)
-  - `DaskDMatrix` (and device quantile dmatrix) now accepts all meta-information. (#6601)
-
-* Prediction optimization.  We enhanced and speeded up the prediction function for the
-  Dask interface.  See the latest Dask tutorial page in our document for an overview of
-  how you can optimize it even further. (#6650, #6645, #6648, #6668)
-
-* Bug fixes
-  - If you are using the latest Dask and distributed where `distributed.MultiLock` is
-    present, XGBoost supports training multiple models on the same cluster in
-    parallel. (#6743)
-  - A bug fix for when using `dask.client` to launch async task, XGBoost might use a
-    different client object internally. (#6722)
-
-* Other improvements on documents, blogs, tutorials, and demos. (#6389, #6366, #6687,
-  #6699, #6532, #6501)
-
-### Python package
-With changes from Dask and general improvement on prediction, we have made some
-enhancements on the general Python interface and IO for booster information.  Starting
-from 1.4, booster feature names and types can be saved into the JSON model.  Also some
-model attributes like `best_iteration`, `best_score` are restored upon model load.  On
-sklearn interface, some attributes are now implemented as Python object property with
-better documents.
-
-* Breaking change: All `data` parameters in prediction functions are renamed to `X`
-  for better compliance to sklearn estimator interface guidelines.
-* Breaking change: XGBoost used to generate some pseudo feature names with `DMatrix`
-  when inputs like `np.ndarray` don't have column names.  The procedure is removed to
-  avoid conflict with other inputs. (#6605)
-* Early stopping with training continuation is now supported. (#6506)
-* Optional import for Dask and cuDF are now lazy. (#6522)
-* As mentioned in the prediction improvement summary, the sklearn interface uses inplace
-  prediction whenever possible. (#6718)
-* Booster information like feature names and feature types are now saved into the JSON
-  model file. (#6605)
-* All `DMatrix` interfaces including `DeviceQuantileDMatrix` and counterparts in Dask
-  interface (as mentioned in the Dask changes summary) now accept all the meta-information
-  like `group` and `qid` in their constructor for better consistency. (#6601)
-* Booster attributes are restored upon model load so users don't have to call `attr`
-  manually. (#6593)
-* On sklearn interface, all models accept `base_margin` for evaluation datasets. (#6591)
-* Improvements over the setup script including smaller sdist size and faster installation
-  if the C++ library is already built (#6611, #6694, #6565).
-
-* Bug fixes for Python package:
-  - Don't validate feature when number of rows is 0. (#6472)
-  - Move metric configuration into booster. (#6504)
-  - Calling XGBModel.fit() should clear the Booster by default (#6562)
-  - Support `_estimator_type`. (#6582)
-  - [dask, sklearn] Fix predict proba. (#6566, #6817)
-  - Restore unknown data support. (#6595)
-  - Fix learning rate scheduler with cv. (#6720)
-  - Fixes small typo in sklearn documentation (#6717)
-  - [python-package] Fix class Booster: feature_types = None (#6705)
-  - Fix divide by 0 in feature importance when no split is found. (#6676)
-
-
-### JVM package
-* [jvm-packages] fix early stopping doesn't work even without custom_eval setting (#6738)
-* fix potential TaskFailedListener's callback won't be called (#6612)
-* [jvm] Add ability to load booster direct from byte array (#6655)
-* [jvm-packages] JVM library loader extensions (#6630)
-
-### R package
-* R documentation: Make construction of DMatrix consistent.
-* Fix R documentation for xgb.train. (#6764)
-
-### ROC-AUC
-We re-implemented the ROC-AUC metric in XGBoost.  The new implementation supports
-multi-class classification and has better support for learning to rank tasks that are not
-binary.  Also, it has a better-defined average on distributed environments with additional
-handling for invalid datasets. (#6749, #6747, #6797)
-
-### Global configuration.
-Starting from 1.4, XGBoost's Python, R and C interfaces support a new global configuration
-model where users can specify some global parameters.  Currently, supported parameters are
-`verbosity` and `use_rmm`.  The latter is experimental, see rmm plugin demo and
-related README file for details. (#6414, #6656)
-
-### Other New features.
-* Better handling for input data types that support `__array_interface__`.  For some
-  data types including GPU inputs and `scipy.sparse.csr_matrix`, XGBoost employs
-  `__array_interface__` for processing the underlying data.  Starting from 1.4, XGBoost
-  can accept arbitrary array strides (which means column-major is supported) without
-  making data copies, potentially reducing a significant amount of memory consumption.
-  Also version 3 of `__cuda_array_interface__` is now supported.  (#6776, #6765, #6459,
-  #6675)
-* Improved parameter validation, now feeding XGBoost with parameters that contain
-  whitespace will trigger an error. (#6769)
-* For Python and R packages, file paths containing the home indicator `~` are supported.
-* As mentioned in the Python changes summary, the JSON model can now save feature
-  information of the trained booster.  The JSON schema is updated accordingly. (#6605)
-* Development of categorical data support is continued.  Newly added weighted data support
-  and `dart` booster support. (#6508, #6693)
-* As mentioned in Dask change summary, ranking now supports the `qid` parameter for
-  query groups. (#6576)
-* `DMatrix.slice` can now consume a numpy array. (#6368)
-
-### Other breaking changes
-* Aside from the feature name generation, there are 2 breaking changes:
-  - Drop saving binary format for memory snapshot. (#6513, #6640)
-  - Change default evaluation metric for binary:logitraw objective to logloss (#6647)
-
-### CPU Optimization
-* Aside from the general changes on predict function, some optimizations are applied on
-  CPU implementation. (#6683, #6550, #6696, #6700)
-* Also performance for sampling initialization in `hist` is improved. (#6410)
-
-### Notable fixes in the core library
-These fixes do not reside in particular language bindings:
-* Fixes for gamma regression.  This includes checking for invalid input values, fixes for
-  gamma deviance metric, and better floating point guard for gamma negative log-likelihood
-  metric. (#6778, #6537, #6761)
-* Random forest with `gpu_hist` might generate low accuracy in previous versions. (#6755)
-* Fix a bug in GPU sketching when data size exceeds limit of 32-bit integer. (#6826)
-* Memory consumption fix for row-major adapters (#6779)
-* Don't estimate sketch batch size when rmm is used. (#6807) (#6830)
-* Fix in-place predict with missing value. (#6787)
-* Re-introduce double buffer in UpdatePosition, to fix perf regression in gpu_hist (#6757)
-* Pass correct split_type to GPU predictor (#6491)
-* Fix DMatrix feature names/types IO. (#6507)
-* Use view for `SparsePage` exclusively to avoid some data access races. (#6590)
-* Check for invalid data. (#6742)
-* Fix relocatable include in CMakeList (#6734) (#6737)
-* Fix DMatrix slice with feature types. (#6689)
-
-### Other deprecation notices:
-
-* This release will be the last release to support CUDA 10.0. (#6642)
-
-* Starting in the next release, the Python package will require Pip 19.3+ due to the use
-  of manylinux2014 tag. Also, CentOS 6, RHEL 6 and other old distributions will not be
-  supported.
-
-### Known issue:
-
-MacOS build of the JVM packages doesn't support multi-threading out of the box. To enable
-multi-threading with JVM packages, MacOS users will need to build the JVM packages from
-the source. See https://xgboost.readthedocs.io/en/latest/jvm/index.html#installation-from-source
-
-
-### Doc
-* Dedicated page for `tree_method` parameter is added. (#6564, #6633)
-* [doc] Add FLAML as a fast tuning tool for XGBoost  (#6770)
-* Add document for tests directory. [skip ci] (#6760)
-* Fix doc string of config.py to use correct `versionadded` (#6458)
-* Update demo for prediction. (#6789)
-* [Doc] Document that AUCPR is for binary classification/ranking (#5899)
-* Update the C API comments (#6457)
-* Fix document. [skip ci] (#6669)
-
-### Maintenance: Testing, continuous integration
-* Use CPU input for test_boost_from_prediction. (#6818)
-* [CI] Upload xgboost4j.dll to S3 (#6781)
-* Update dmlc-core submodule (#6745)
-* [CI] Use manylinux2010_x86_64 container to vendor libgomp (#6485)
-* Add conda-forge badge (#6502)
-* Fix merge conflict. (#6512)
-* [CI] Split up main.yml, add mypy. (#6515)
-* [Breaking] Upgrade cuDF and RMM to 0.18 nightlies; require RMM 0.18+ for RMM plugin (#6510)
-* "featue_map" typo changed to  "feature_map" (#6540)
-* Add script for generating release tarball. (#6544)
-* Add credentials to .gitignore (#6559)
-* Remove warnings in tests. (#6554)
-* Update dmlc-core submodule and conform to new API (#6431)
-* Suppress hypothesis health check for dask client. (#6589)
-* Fix pylint. (#6714)
-* [CI] Clear R package cache (#6746)
-* Exclude dmlc test on github action. (#6625)
-* Tests for regression metrics with weights. (#6729)
-* Add helper script and doc for releasing pip package. (#6613)
-* Support pylint 2.7.0 (#6726)
-* Remove R cache in github action. (#6695)
-* [CI] Do not mix up stashed executable built for ARM and x86_64 platforms (#6646)
-* [CI] Add ARM64 test to Jenkins pipeline (#6643)
-* Disable s390x and arm64 tests on travis for now. (#6641)
-* Move sdist test to action. (#6635)
-* [dask] Rework base margin test. (#6627)
-
-
-### Maintenance: Refactor code for legibility and maintainability
-* Improve OpenMP exception handling (#6680)
-* Improve string view to reduce string allocation. (#6644)
-* Simplify Span checks. (#6685)
-* Use generic dispatching routine for array interface. (#6672)
-
-
-## v1.3.0 (2020.12.08)
-
-### XGBoost4J-Spark: Exceptions should cancel jobs gracefully instead of killing SparkContext (#6019).
-* By default, exceptions in XGBoost4J-Spark causes the whole SparkContext to shut down, necessitating the restart of the Spark cluster. This behavior is often a major inconvenience.
-* Starting from 1.3.0 release, XGBoost adds a new parameter `killSparkContextOnWorkerFailure` to optionally prevent killing SparkContext. If this parameter is set, exceptions will gracefully cancel training jobs instead of killing SparkContext.
-
-### GPUTreeSHAP: GPU acceleration of the TreeSHAP algorithm (#6038, #6064, #6087, #6099, #6163, #6281, #6332)
-* [SHAP (SHapley Additive exPlanations)](https://github.com/slundberg/shap) is a game theoretic approach to explain predictions of machine learning models. It computes feature importance scores for individual examples, establishing how each feature influences a particular prediction. TreeSHAP is an optimized SHAP algorithm specifically designed for decision tree ensembles.
-* Starting with 1.3.0 release, it is now possible to leverage CUDA-capable GPUs to accelerate the TreeSHAP algorithm. Check out [the demo notebook](https://github.com/dmlc/xgboost/blob/master/demo/gpu_acceleration/shap.ipynb).
-* The CUDA implementation of the TreeSHAP algorithm is hosted at [rapidsai/GPUTreeSHAP](https://github.com/rapidsai/gputreeshap). XGBoost imports it as a Git submodule.
-
-### New style Python callback API (#6199, #6270, #6320, #6348, #6376, #6399, #6441)
-* The XGBoost Python package now offers a re-designed callback API. The new callback API lets you design various extensions of training in idomatic Python. In addition, the new callback API allows you to use early stopping with the native Dask API (`xgboost.dask`). Check out [the tutorial](https://xgboost.readthedocs.io/en/release_1.3.0/python/callbacks.html) and [the demo](https://github.com/dmlc/xgboost/blob/master/demo/guide-python/callbacks.py).
-
-### Enable the use of `DeviceQuantileDMatrix` / `DaskDeviceQuantileDMatrix` with large data (#6201, #6229, #6234).
-* `DeviceQuantileDMatrix` can achieve memory saving by avoiding extra copies of the training data, and the saving is bigger for large data. Unfortunately, large data with more than 2^31 elements was triggering integer overflow bugs in CUB and Thrust. Tracking issue: #6228.
-* This release contains a series of work-arounds to allow the use of `DeviceQuantileDMatrix` with large data:
-  - Loop over `copy_if` (#6201)
-  - Loop over `thrust::reduce` (#6229)
-  - Implement the inclusive scan algorithm in-house, to handle large offsets (#6234)
-
-### Support slicing of tree models (#6302)
-* Accessing the best iteration of a model after the application of early stopping used to be error-prone, need to manually pass the `ntree_limit` argument to the `predict()` function.
-* Now we provide a simple interface to slice tree models by specifying a range of boosting rounds. The tree ensemble can be split into multiple sub-ensembles via the slicing interface. Check out [an example](https://xgboost.readthedocs.io/en/release_1.3.0/python/model.html).
-* In addition, the early stopping callback now supports `save_best` option. When enabled, XGBoost will save (persist) the model at the best boosting round and discard the trees that were fit subsequent to the best round.
-
-### Weighted subsampling of features (columns) (#5962)
-* It is now possible to sample features (columns) via weighted subsampling, in which features with higher weights are more likely to be selected in the sample. Weighted subsampling allows you to encode domain knowledge by emphasizing a particular set of features in the choice of tree splits. In addition, you can prevent particular features from being used in any splits, by assigning them zero weights.
-* Check out [the demo](https://github.com/dmlc/xgboost/blob/master/demo/guide-python/feature_weights.py).
-
-### Improved integration with Dask
-* Support reverse-proxy environment such as Google Kubernetes Engine (#6343, #6475)
-* An XGBoost training job will no longer use all available workers. Instead, it will only use the workers that contain input data (#6343).
-* The new callback API works well with the Dask training API.
-* The `predict()` and `fit()` function of `DaskXGBClassifier` and `DaskXGBRegressor` now accept a base margin (#6155).
-* Support more meta data in the Dask API (#6130, #6132, #6333).
-* Allow passing extra keyword arguments as `kwargs` in `predict()` (#6117)
-* Fix typo in dask interface: `sample_weights` -> `sample_weight` (#6240)
-* Allow empty data matrix in AFT survival, as Dask may produce empty partitions (#6379)
-* Speed up prediction by overlapping prediction jobs in all workers (#6412)
-
-### Experimental support for direct splits with categorical features (#6028, #6128, #6137, #6140, #6164, #6165, #6166, #6179, #6194, #6219)
-* Currently, XGBoost requires users to one-hot-encode categorical variables. This has adverse performance implications, as the creation of many dummy variables results into higher memory consumption and may require fitting deeper trees to achieve equivalent model accuracy.
-* The 1.3.0 release of XGBoost contains an experimental support for direct handling of categorical variables in test nodes. Each test node will have the condition of form `feature_value \in match_set`, where the `match_set` on the right hand side contains one or more matching categories. The matching categories in `match_set` represent the condition for traversing to the right child node. Currently, XGBoost will only generate categorical splits with only a single matching category ("one-vs-rest split"). In a future release, we plan to remove this restriction and produce splits with multiple matching categories in `match_set`.
-* The categorical split requires the use of JSON model serialization. The legacy binary serialization method cannot be used to save (persist) models with categorical splits.
-* Note. This feature is currently highly experimental. Use it at your own risk. See the detailed list of limitations at [#5949](https://github.com/dmlc/xgboost/pull/5949).
-
-### Experimental plugin for RAPIDS Memory Manager (#5873, #6131, #6146, #6150, #6182)
-* RAPIDS Memory Manager library ([rapidsai/rmm](https://github.com/rapidsai/rmm)) provides a collection of efficient memory allocators for NVIDIA GPUs. It is now possible to use XGBoost with memory allocators provided by RMM, by enabling the RMM integration plugin. With this plugin, XGBoost is now able to share a common GPU memory pool with other applications using RMM, such as the RAPIDS data science packages.
-* See [the demo](https://github.com/dmlc/xgboost/blob/master/demo/rmm_plugin/README.md) for a working example, as well as directions for building XGBoost with the RMM plugin.
-* The plugin will be soon considered non-experimental, once #6297 is resolved.
-
-### Experimental plugin for oneAPI programming model (#5825)
-* oneAPI is a programming interface developed by Intel aimed at providing one programming model for many types of hardware such as CPU, GPU, FGPA and other hardware accelerators.
-* XGBoost now includes an experimental plugin for using oneAPI for the predictor and objective functions. The plugin is hosted in the directory `plugin/updater_oneapi`.
-* Roadmap: #5442
-
-### Pickling the XGBoost model will now trigger JSON serialization (#6027)
-* The pickle will now contain the JSON string representation of the XGBoost model, as well as related configuration.
-
-### Performance improvements
-* Various performance improvement on multi-core CPUs
-  - Optimize DMatrix build time by up to 3.7x. (#5877)
-  - CPU predict performance improvement, by up to 3.6x. (#6127)
-  - Optimize CPU sketch allreduce for sparse data (#6009)
-  - Thread local memory allocation for BuildHist, leading to speedup up to 1.7x. (#6358)
-  - Disable hyperthreading for DMatrix creation (#6386). This speeds up DMatrix creation by up to 2x.
-  - Simple fix for static shedule in predict (#6357)
-* Unify thread configuration, to make it easy to utilize all CPU cores (#6186)
-* [jvm-packages] Clean the way deterministic paritioning is computed (#6033)
-* Speed up JSON serialization by implementing an intrusive pointer class (#6129). It leads to 1.5x-2x performance boost.
-
-### API additions
-* [R] Add SHAP summary plot using ggplot2 (#5882)
-* Modin DataFrame can now be used as input (#6055)
-* [jvm-packages] Add `getNumFeature` method (#6075)
-* Add MAPE metric (#6119)
-* Implement GPU predict leaf. (#6187)
-* Enable cuDF/cuPy inputs in `XGBClassifier` (#6269)
-* Document tree method for feature weights. (#6312)
-* Add `fail_on_invalid_gpu_id` parameter, which will cause XGBoost to terminate upon seeing an invalid value of `gpu_id` (#6342)
-
-### Breaking: the default evaluation metric for classification is changed to `logloss` / `mlogloss` (#6183)
-* The default metric used to be accuracy, and it is not statistically consistent to perform early stopping with the accuracy metric when we are really optimizing the log loss for the `binary:logistic` objective.
-* For statistical consistency, the default metric for classification has been changed to `logloss`. Users may choose to preserve the old behavior by explicitly specifying `eval_metric`.
-
-### Breaking: `skmaker` is now removed (#5971)
-* The `skmaker` updater has not been documented nor tested.
-
-### Breaking: the JSON model format no longer stores the leaf child count (#6094).
-* The leaf child count field has been deprecated and is not used anywhere in the XGBoost codebase.
-
-### Breaking: XGBoost now requires MacOS 10.14 (Mojave) and later.
-* Homebrew has dropped support for MacOS 10.13 (High Sierra), so we are not able to install the OpenMP runtime (`libomp`) from Homebrew on MacOS 10.13. Please use MacOS 10.14 (Mojave) or later.
-
-### Deprecation notices
-* The use of `LabelEncoder` in `XGBClassifier` is now deprecated and will be removed in the next minor release (#6269). The deprecation is necessary to support multiple types of inputs, such as cuDF data frames or cuPy arrays.
-* The use of certain positional arguments in the Python interface is deprecated (#6365). Users will use deprecation warnings for the use of position arguments for certain function parameters. New code should use keyword arguments as much as possible. We have not yet decided when we will fully require the use of keyword arguments.
-
-### Bug-fixes
-* On big-endian arch, swap the byte order in the binary serializer to enable loading models that were produced by a little-endian machine (#5813).
-* [jvm-packages] Fix deterministic partitioning with dataset containing Double.NaN (#5996)
-* Limit tree depth for GPU hist to 31 to prevent integer overflow (#6045)
-* [jvm-packages] Set `maxBins` to 256 to align with the default value in the C++ code (#6066)
-* [R] Fix CRAN check (#6077)
-* Add back support for `scipy.sparse.coo_matrix` (#6162)
-* Handle duplicated values in sketching. (#6178)
-* Catch all standard exceptions in C API. (#6220)
-* Fix linear GPU input (#6255)
-* Fix inplace prediction interval. (#6259)
-* [R] allow `xgb.plot.importance()` calls to fill a grid (#6294)
-* Lazy import dask libraries. (#6309)
-* Deterministic data partitioning for external memory (#6317)
-* Avoid resetting seed for every configuration. (#6349)
-* Fix label errors in graph visualization (#6369)
-* [jvm-packages] fix potential unit test suites aborted issue due to race condition (#6373)
-* [R] Fix warnings from `R check --as-cran` (#6374)
-* [R] Fix a crash that occurs with noLD R (#6378)
-* [R] Do not convert continuous labels to factors (#6380)
-* [R] remove uses of `exists()` (#6387)
-* Propagate parameters to the underlying `Booster` handle from `XGBClassifier.set_param` / `XGBRegressor.set_param`. (#6416)
-* [R] Fix R package installation via CMake (#6423)
-* Enforce row-major order in cuPy array (#6459)
-* Fix filtering callable objects in the parameters passed to the scikit-learn API. (#6466)
-
-### Maintenance: Testing, continuous integration, build system
-* [CI] Improve JVM test in GitHub Actions (#5930)
-* Refactor plotting test so that it can run independently (#6040)
-* [CI] Cancel builds on subsequent pushes (#6011)
-* Fix Dask Pytest fixture (#6024)
-* [CI] Migrate linters to GitHub Actions (#6035)
-* [CI] Remove win2016 JVM test from GitHub Actions (#6042)
-* Fix CMake build with `BUILD_STATIC_LIB` option (#6090)
-* Don't link imported target in CMake (#6093)
-* Work around a compiler bug in MacOS AppleClang 11 (#6103)
-* [CI] Fix CTest by running it in a correct directory (#6104)
-* [R] Check warnings explicitly for model compatibility tests (#6114)
-* [jvm-packages] add xgboost4j-gpu/xgboost4j-spark-gpu module to facilitate release (#6136)
-* [CI] Time GPU tests. (#6141)
-* [R] remove warning in configure.ac (#6152)
-* [CI] Upgrade cuDF and RMM to 0.16 nightlies; upgrade to Ubuntu 18.04 (#6157)
-* [CI] Test C API demo (#6159)
-* Option for generating device debug info. (#6168)
-* Update `.gitignore` (#6175, #6193, #6346)
-* Hide C++ symbols from dmlc-core (#6188)
-* [CI] Added arm64 job in Travis-CI (#6200)
-* [CI] Fix Docker build for CUDA 11 (#6202)
-* [CI] Move non-OpenMP gtest to GitHub Actions (#6210)
-* [jvm-packages] Fix up build for xgboost4j-gpu, xgboost4j-spark-gpu (#6216)
-* Add more tests for categorical data support (#6219)
-* [dask] Test for data initializaton. (#6226)
-* Bump junit from 4.11 to 4.13.1 in /jvm-packages/xgboost4j (#6230)
-* Bump junit from 4.11 to 4.13.1 in /jvm-packages/xgboost4j-gpu (#6233)
-* [CI] Reduce testing load with RMM (#6249)
-* [CI] Build a Python wheel for aarch64 platform (#6253)
-* [CI] Time the CPU tests on Jenkins. (#6257)
-* [CI] Skip Dask tests on ARM. (#6267)
-* Fix a typo in `is_arm()` in testing.py (#6271)
-* [CI] replace `egrep` with `grep -E` (#6287)
-* Support unity build. (#6295)
-* [CI] Mark flaky tests as XFAIL (#6299)
-* [CI] Use separate Docker cache for each CUDA version (#6305)
-* Added `USE_NCCL_LIB_PATH` option to enable user to set `NCCL_LIBRARY` during build  (#6310)
-* Fix flaky data initialization test. (#6318)
-* Add a badge for GitHub Actions (#6321)
-* Optional `find_package` for sanitizers. (#6329)
-* Use pytest conventions consistently in Python tests (#6337)
-* Fix missing space in warning message (#6340)
-* Update `custom_metric_obj.rst` (#6367)
-* [CI] Run R check with `--as-cran` flag on GitHub Actions (#6371)
-* [CI] Remove R check from Jenkins (#6372)
-* Mark GPU external memory test as XFAIL. (#6381)
-* [CI] Add noLD R test (#6382)
-* Fix MPI build. (#6403)
-* [CI] Upgrade to MacOS Mojave image (#6406)
-* Fix flaky sparse page dmatrix test. (#6417)
-* [CI] Upgrade cuDF and RMM to 0.17 nightlies (#6434)
-* [CI] Fix CentOS 6 Docker images (#6467)
-* [CI] Vendor libgomp in the manylinux Python wheel (#6461)
-* [CI] Hot fix for libgomp vendoring (#6482)
-
-### Maintenance: Clean up and merge the Rabit submodule (#6023, #6095, #6096, #6105, #6110, #6262, #6275, #6290)
-* The Rabit submodule is now maintained as part of the XGBoost codebase.
-* Tests for Rabit are now part of the test suites of XGBoost.
-* Rabit can now be built on the Windows platform.
-* We made various code re-formatting for the C++ code with clang-tidy.
-* Public headers of XGBoost no longer depend on Rabit headers.
-* Unused CMake targets for Rabit were removed.
-* Single-point model recovery has been dropped and removed from Rabit, simplifying the Rabit code greatly. The single-point model recovery feature has not been adequately maintained over the years.
-* We removed the parts of Rabit that were not useful for XGBoost.
-
-### Maintenance: Refactor code for legibility and maintainability
-* Unify CPU hist sketching (#5880)
-* [R] fix uses of 1:length(x) and other small things (#5992)
-* Unify evaluation functions. (#6037)
-* Make binary bin search reusable. (#6058)
-* Unify set index data. (#6062)
-* [R] Remove `stringi` dependency (#6109)
-* Merge extract cuts into QuantileContainer. (#6125)
-* Reduce C++ compiler warnings (#6197, #6198, #6213, #6286, #6325)
-* Cleanup Python code. (#6223)
-* Small cleanup to evaluator. (#6400)
-
-### Usability Improvements, Documentation
-* [jvm-packages] add example to handle missing value other than 0 (#5677)
-* Add DMatrix usage examples to the C API demo (#5854)
-* List `DaskDeviceQuantileDMatrix` in the doc. (#5975)
-* Update Python custom objective demo. (#5981)
-* Update the JSON model schema to document more objective functions. (#5982)
-* [Python] Fix warning when `missing` field is not used. (#5969)
-* Fix typo in tracker logging (#5994)
-* Move a warning about empty dataset, so that it's shown for all objectives and metrics (#5998)
-* Fix the instructions for installing the nightly build. (#6004)
-* [Doc] Add dtreeviz as a showcase example of integration with 3rd-party software (#6013)
-* [jvm-packages] [doc] Update install doc for JVM packages (#6051)
-* Fix typo in `xgboost.callback.early_stop` docstring (#6071)
-* Add cache suffix to the files used in the external memory demo. (#6088)
-* [Doc] Document the parameter `kill_spark_context_on_worker_failure` (#6097)
-* Fix link to the demo for custom objectives (#6100)
-* Update Dask doc. (#6108)
-* Validate weights are positive values. (#6115)
-* Document the updated CMake version requirement. (#6123)
-* Add demo for `DaskDeviceQuantileDMatrix`. (#6156)
-* Cosmetic fixes in `faq.rst` (#6161)
-* Fix error message. (#6176)
-* [Doc] Add list of winning solutions in data science competitions using XGBoost (#6177)
-* Fix a comment in demo to use correct reference (#6190)
-* Update the list of winning solutions using XGBoost (#6192)
-* Consistent style for build status badge (#6203)
-* [Doc] Add info on GPU compiler (#6204)
-* Update the list of winning solutions (#6222, #6254)
-* Add link to XGBoost's Twitter handle (#6244)
-* Fix minor typos in XGBClassifier methods' docstrings (#6247)
-* Add sponsors link to FUNDING.yml (#6252)
-* Group CLI demo into subdirectory. (#6258)
-* Reduce warning messages from `gbtree`. (#6273)
-* Create a tutorial for using the C API in a C/C++ application (#6285)
-* Update plugin instructions for CMake build (#6289)
-* [doc] make Dask distributed example copy-pastable (#6345)
-* [Python] Add option to use `libxgboost.so` from the system path (#6362)
-* Fixed few grammatical mistakes in doc (#6393)
-* Fix broken link in CLI doc (#6396)
-* Improve documentation for the Dask API (#6413)
-* Revise misleading exception information: no such param of `allow_non_zero_missing` (#6418)
-* Fix CLI ranking demo. (#6439)
-* Fix broken links. (#6455)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), @FelixYBW, Jack Dunn (@JackDunnNZ), Jean Lescut-Muller (@JeanLescut),  Boris Feld (@Lothiraldan), Nikhil Choudhary (@Nikhil1O1), Rory Mitchell (@RAMitchell), @ShvetsKS, Anthony D'Amato (@Totoketchup), @Wittty-Panda, neko (@akiyamaneko), Alexander Gugel (@alexanderGugel), @dependabot[bot], DIVYA CHAUHAN (@divya661), Daniel Steinberg (@dstein64), Akira Funahashi (@funasoul), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), Hristo Iliev (@hiliev), Honza Sterba (@honzasterba), @hzy001, Igor Moura (@igormp), @jameskrach, James Lamb (@jameslamb), Naveed Ahmed Saleem Janvekar (@janvekarnaveed), Kyle Nicholson (@kylejn27), lacrosse91 (@lacrosse91), Christian Lorentzen (@lorentzenchr), Manikya Bardhan (@manikyabard), @nabokovas, John Quitto-Graham (@nvidia-johnq), @odidev, Qi Zhang (@qzhang90), Sergio Gavilán (@sgavil), Tanuja Kirthi Doddapaneni (@tanuja3), Cuong Duong (@tcuongd), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), vcarpani (@vcarpani), Vladislav Epifanov (@vepifanov), Vitalie Spinu (@vspinu), Bobby Wang (@wbo4958), Zeno Gantner (@zenogantner), zhang_jf (@zuston)
-
-**Reviewers**: Nan Zhu (@CodingCat), John Zedlewski (@JohnZed), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Anthony D'Amato (@Totoketchup), @Wittty-Panda, Alexander Gugel (@alexanderGugel), Codecov Comments Bot (@codecov-commenter), Codecov (@codecov-io), DIVYA CHAUHAN (@divya661), Devin Robison (@drobison00), Geoffrey Blake (@geoffreyblake), Mark Harris (@harrism), Philip Hyunsu Cho (@hcho3), Honza Sterba (@honzasterba), Igor Moura (@igormp), @jakirkham, @jameskrach, James Lamb (@jameslamb), Janakarajan Natarajan (@janaknat), Jake Hemstad (@jrhemstad), Keith Kraus (@kkraus14), Kyle Nicholson (@kylejn27), Christian Lorentzen (@lorentzenchr), Michael Mayer (@mayer79), Nikolay Petrov (@napetrov), @odidev, PSEUDOTENSOR / Jonathan McKinney (@pseudotensor), Qi Zhang (@qzhang90), Sergio Gavilán (@sgavil), Scott Lundberg (@slundberg), Cuong Duong (@tcuongd), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), vcarpani (@vcarpani), Vladislav Epifanov (@vepifanov), Vincent Nijs (@vnijs), Vitalie Spinu (@vspinu), Bobby Wang (@wbo4958), William Hicks (@wphicks)
-
-## v1.2.0 (2020.08.22)
-
-### XGBoost4J-Spark now supports the GPU algorithm (#5171)
-* Now XGBoost4J-Spark is able to leverage NVIDIA GPU hardware to speed up training.
-* There is on-going work for accelerating the rest of the data pipeline with NVIDIA GPUs (#5950, #5972).
-
-### XGBoost now supports CUDA 11 (#5808)
-* It is now possible to build XGBoost with CUDA 11. Note that we do not yet distribute pre-built binaries built with CUDA 11; all current distributions use CUDA 10.0.
-
-### Better guidance for persisting XGBoost models in an R environment (#5940, #5964)
-* Users are strongly encouraged to use `xgb.save()` and `xgb.save.raw()` instead of `saveRDS()`. This is so that the persisted models can be accessed with future releases of XGBoost.
-* The previous release (1.1.0) had problems loading models that were saved with `saveRDS()`. This release adds a compatibility layer to restore access to the old RDS files. Note that this is meant to be a temporary measure; users are advised to stop using `saveRDS()` and migrate to `xgb.save()` and `xgb.save.raw()`.
-
-### New objectives and metrics
-* The pseudo-Huber loss `reg:pseudohubererror` is added (#5647). The corresponding metric is `mphe`. Right now, the slope is hard-coded to 1.
-* The Accelerated Failure Time objective for survival analysis (`survival:aft`) is now accelerated on GPUs (#5714, #5716). The survival metrics `aft-nloglik` and `interval-regression-accuracy` are also accelerated on GPUs.
-
-### Improved integration with scikit-learn
-* Added `n_features_in_` attribute to the scikit-learn interface to store the number of features used (#5780). This is useful for integrating with some scikit-learn features such as `StackingClassifier`.  See [this link](https://scikit-learn-enhancement-proposals.readthedocs.io/en/latest/slep010/proposal.html) for more details.
-* `XGBoostError` now inherits `ValueError`, which conforms scikit-learn's exception requirement (#5696).
-
-### Improved integration with Dask
-* The XGBoost Dask API now exposes an asynchronous interface (#5862). See [the document](https://xgboost.readthedocs.io/en/latest/tutorials/dask.html#working-with-asyncio) for details.
-* Zero-copy ingestion of GPU arrays via `DaskDeviceQuantileDMatrix` (#5623, #5799, #5800, #5803, #5837, #5874, #5901): Previously, the Dask interface had to make 2 data copies: one for concatenating the Dask partition/block into a single block and another for internal representation. To save memory, we introduce `DaskDeviceQuantileDMatrix`. As long as Dask partitions are resident in the GPU memory, `DaskDeviceQuantileDMatrix` is able to ingest them directly without making copies. This matrix type wraps `DeviceQuantileDMatrix`.
-* The prediction function now returns GPU Series type if the input is from Dask-cuDF (#5710). This is to preserve the input data type.
-
-### Robust handling of external data types (#5689, #5893)
-- As we support more and more external data types, the handling logic has proliferated all over the code base and became hard to keep track. It also became unclear how missing values and threads are handled. We refactored the Python package code to collect all data handling logic to a central location, and now we have an explicit list of of all supported data types.
-
-### Improvements in GPU-side data matrix (`DeviceQuantileDMatrix`)
-* The GPU-side data matrix now implements its own quantile sketching logic, so that data don't have to be transported back to the main memory (#5700, #5747, #5760, #5846, #5870, #5898). The GK sketching algorithm is also now better documented.
-  - Now we can load extremely sparse dataset like URL, although performance is still sub-optimal.
-* The GPU-side data matrix now exposes an iterative interface (#5783), so that users are able to construct a matrix from a data iterator. See the [Python demo](https://github.com/dmlc/xgboost/blob/release_1.2.0/demo/guide-python/data_iterator.py).
-
-### New language binding: Swift (#5728)
-* Visit https://github.com/kongzii/SwiftXGBoost for more details.
-
-### Robust model serialization with JSON (#5772, #5804, #5831, #5857, #5934)
-* We continue efforts from the 1.0.0 release to adopt JSON as the format to save and load models robustly.
-* JSON model IO is significantly faster and produces smaller model files.
-* Round-trip reproducibility is guaranteed, via the introduction of an efficient float-to-string conversion algorithm known as [the Ryū algorithm](https://dl.acm.org/doi/10.1145/3192366.3192369). The conversion is locale-independent, producing consistent numeric representation regardless of the locale setting of the user's machine.
-* We fixed an issue in loading large JSON files to memory.
-* It is now possible to load a JSON file from a remote source such as S3.
-
-### Performance improvements
-* CPU hist tree method optimization
-  - Skip missing lookup in hist row partitioning if data is dense. (#5644)
-  - Specialize training procedures for CPU hist tree method on distributed environment. (#5557)
-  - Add single point histogram for CPU hist.  Previously gradient histogram for CPU hist is hard coded to be 64 bit, now users can specify the parameter `single_precision_histogram` to use 32 bit histogram instead for faster training performance. (#5624, #5811)
-* GPU hist tree method optimization
-  - Removed some unnecessary synchronizations and better memory allocation pattern. (#5707)
-  - Optimize GPU Hist for wide dataset.  Previously for wide dataset the atomic operation is performed on global memory, now it can run on shared memory for faster histogram building. But there's a known small regression on GeForce cards with dense data. (#5795, #5926, #5948, #5631)
-
-### API additions
-* Support passing fmap to importance plot (#5719). Now importance plot can show actual names of features instead of default ones.
-* Support 64bit seed. (#5643)
-* A new C API `XGBoosterGetNumFeature` is added for getting number of features in booster (#5856).
-* Feature names and feature types are now stored in C++ core and saved in binary DMatrix (#5858).
-
-### Breaking: The `predict()` method of `DaskXGBClassifier` now produces class predictions (#5986). Use `predict_proba()` to obtain probability predictions.
-* Previously, `DaskXGBClassifier.predict()` produced probability predictions. This is inconsistent with the behavior of other scikit-learn classifiers, where `predict()` returns class predictions. We make a breaking change in 1.2.0 release so that `DaskXGBClassifier.predict()` now correctly produces class predictions and thus behave like other scikit-learn classifiers. Furthermore, we introduce the `predict_proba()` method for obtaining probability predictions, again to be in line with other scikit-learn classifiers.
-
-### Breaking: Custom evaluation metric now receives raw prediction (#5954)
-* Previously, the custom evaluation metric received a transformed prediction result when used with a classifier. Now the custom metric will receive a raw (untransformed) prediction and will need to transform the prediction itself.  See [demo/guide-python/custom\_softmax.py](https://github.com/dmlc/xgboost/blob/release_1.2.0/demo/guide-python/custom_softmax.py) for an example.
-* This change is to make the custom metric behave consistently with the custom objective, which already receives raw prediction (#5564).
-
-### Breaking: XGBoost4J-Spark now requires Spark 3.0 and Scala 2.12 (#5836, #5890)
-* Starting with version 3.0, Spark can manage GPU resources and allocate them among executors.
-* Spark 3.0 dropped support for Scala 2.11 and now only supports Scala 2.12. Thus, XGBoost4J-Spark also only supports Scala 2.12.
-
-### Breaking: XGBoost Python package now requires Python 3.6 and later (#5715)
-* Python 3.6 has many useful features such as f-strings.
-
-### Breaking: XGBoost now adopts the C++14 standard (#5664)
-* Make sure to use a sufficiently modern C++ compiler that supports C++14, such as Visual Studio 2017, GCC 5.0+, and Clang 3.4+.
-
-### Bug-fixes
-* Fix a data race in the prediction function (#5853). As a byproduct, the prediction function now uses a thread-local data store and became thread-safe.
-* Restore capability to run prediction when the test input has fewer features than the training data (#5955). This capability is necessary to support predicting with LIBSVM inputs. The previous release (1.1) had broken this capability, so we restore it in this version with better tests.
-* Fix OpenMP build with CMake for R package, to support CMake 3.13 (#5895).
-* Fix Windows 2016 build (#5902, #5918).
-* Fix edge cases in scikit-learn interface with Pandas input by disabling feature validation. (#5953)
-* [R] Enable weighted learning to rank (#5945)
-* [R] Fix early stopping with custom objective (#5923)
-* Fix NDK Build (#5886)
-* Add missing explicit template specializations for greater portability (#5921)
-* Handle empty rows in data iterators correctly (#5929). This bug affects file loader and JVM data frames.
-* Fix `IsDense` (#5702)
-* [jvm-packages] Fix wrong method name `setAllowZeroForMissingValue` (#5740)
-* Fix shape inference for Dask predict (#5989)
-
-### Usability Improvements, Documentation
-* [Doc] Document that CUDA 10.0 is required (#5872)
-* Refactored command line interface (CLI). Now CLI is able to handle user errors and output basic document. (#5574)
-* Better error handling in Python: use `raise from` syntax to preserve full stacktrace (#5787).
-* The JSON model dump now has a formal schema (#5660, #5818). The benefit is to prevent `dump_model()` function from breaking. See [this document](https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html#difference-between-saving-model-and-dumping-model) to understand the difference between saving and dumping models.
-* Add a reference to the GPU external memory paper (#5684)
-* Document more objective parameters in the R package (#5682)
-* Document the existence of pre-built binary wheels for MacOS (#5711)
-* Remove `max.depth` in the R gblinear example. (#5753)
-* Added conda environment file for building docs (#5773)
-* Mention dask blog post in the doc, which introduces using Dask with GPU and some internal workings. (#5789)
-* Fix rendering of Markdown docs (#5821)
-* Document new objectives and metrics available on GPUs (#5909)
-* Better message when no GPU is found. (#5594)
-* Remove the use of `silent` parameter from R demos. (#5675)
-* Don't use masked array in array interface. (#5730)
-* Update affiliation of @terrytangyuan: Ant Financial -> Ant Group (#5827)
-* Move dask tutorial closer other distributed tutorials (#5613)
-* Update XGBoost + Dask overview documentation (#5961)
-* Show `n_estimators` in the docstring of the scikit-learn interface (#6041)
-* Fix a type in a doctring of the scikit-learn interface (#5980)
-
-### Maintenance: testing, continuous integration, build system
-* [CI] Remove CUDA 9.0 from CI (#5674, #5745)
-* Require CUDA 10.0+ in CMake build (#5718)
-* [R] Remove dependency on gendef for Visual Studio builds (fixes #5608) (#5764). This enables building XGBoost with GPU support with R 4.x.
-* [R-package] Reduce duplication in configure.ac (#5693)
-* Bump com.esotericsoftware to 4.0.2 (#5690)
-* Migrate some tests from AppVeyor to GitHub Actions to speed up the tests. (#5911, #5917, #5919, #5922, #5928)
-* Reduce cost of the Jenkins CI server (#5884, #5904, #5892). We now enforce a daily budget via an automated monitor. We also dramatically reduced the workload for the Windows platform, since the cloud VM cost is vastly greater for Windows.
-* [R] Set up automated R linter (#5944)
-* [R] replace uses of T and F with TRUE and FALSE (#5778)
-* Update Docker container 'CPU' (#5956)
-* Simplify CMake build with modern CMake techniques (#5871)
-* Use `hypothesis` package for testing (#5759, #5835, #5849).
-* Define `_CRT_SECURE_NO_WARNINGS` to remove unneeded warnings in MSVC (#5434)
-* Run all Python demos in CI, to ensure that they don't break (#5651)
-* Enhance nvtx support (#5636). Now we can use unified timer between CPU and GPU. Also CMake is able to find nvtx automatically.
-* Speed up python test. (#5752)
-* Add helper for generating batches of data. (#5756)
-* Add c-api-demo to .gitignore (#5855)
-* Add option to enable all compiler warnings in GCC/Clang (#5897)
-* Make Python model compatibility test runnable locally (#5941)
-* Add cupy to Windows CI (#5797)
-* [CI] Fix cuDF install; merge 'gpu' and 'cudf' test suite (#5814)
-* Update rabit submodule (#5680, #5876)
-* Force colored output for Ninja build. (#5959)
-* [CI] Assign larger /dev/shm to NCCL (#5966)
-* Add missing Pytest marks to AsyncIO unit test (#5968)
-* [CI] Use latest cuDF and dask-cudf (#6048)
-* Add CMake flag to log C API invocations, to aid debugging (#5925)
-* Fix a unit test on CLI, to handle RC versions (#6050)
-* [CI] Use mgpu machine to run gpu hist unit tests (#6050)
-* [CI] Build GPU-enabled JAR artifact and deploy to xgboost-maven-repo (#6050)
-
-### Maintenance: Refactor code for legibility and maintainability
-* Remove dead code in DMatrix initialization. (#5635)
-* Catch dmlc error by ref. (#5678)
-* Refactor the `gpu_hist` split evaluation in preparation for batched nodes enumeration. (#5610)
-* Remove column major specialization. (#5755)
-* Remove unused imports in Python (#5776)
-* Avoid including `c_api.h` in header files. (#5782)
-* Remove unweighted GK quantile, which is unused. (#5816)
-* Add Python binding for rabit ops. (#5743)
-* Implement `Empty` method for host device vector. (#5781)
-* Remove print (#5867)
-* Enforce tree order in JSON (#5974)
-
-### Acknowledgement
-**Contributors**: Nan Zhu (@CodingCat), @LionOrCatThatIsTheQuestion, Dmitry Mottl (@Mottl), Rory Mitchell (@RAMitchell), @ShvetsKS, Alex Wozniakowski (@a-wozniakowski), Alexander Gugel (@alexanderGugel), @anttisaukko, @boxdot, Andy Adinets (@canonizer), Ram Rachum (@cool-RR), Elliot Hershberg (@elliothershberg), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), @jameskrach, James Lamb (@jameslamb), James Bourbeau (@jrbourbeau), Peter Jung (@kongzii), Lorenz Walthert (@lorenzwalthert), Oleksandr Kuvshynov (@okuvshynov), Rong Ou (@rongou), Shaochen Shi (@shishaochen), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10)
-
-**Reviewers**: Nan Zhu (@CodingCat), @LionOrCatThatIsTheQuestion, Hao Yang (@QuantHao), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Alex Wozniakowski (@a-wozniakowski), Amit Kumar (@aktech), Avinash Barnwal (@avinashbarnwal), @boxdot, Andy Adinets (@canonizer), Chandra Shekhar Reddy (@chandrureddy), Ram Rachum (@cool-RR), Cristiano Goncalves (@cristianogoncalves), Elliot Hershberg (@elliothershberg), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), James Lamb (@jameslamb), James Bourbeau (@jrbourbeau), Lee Drake (@leedrake5), DougM (@mengdong), Oleksandr Kuvshynov (@okuvshynov), RongOu (@rongou), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), Yuan Tang (@terrytangyuan), Theodore Vasiloudis (@thvasilo), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10)
-
-## v1.1.1 (2020.06.06)
-This patch release applies the following patches to 1.1.0 release:
-
-* CPU performance improvement in the PyPI wheels (#5720)
-* Fix loading old model (#5724)
-* Install pkg-config file (#5744)
-
 ## v1.1.0 (2020.05.17)
 
 ### Better performance on multi-core CPUs (#5244, #5334, #5522)
@@ -1102,16 +203,6 @@ Upgrading to latest pip allows us to depend on newer versions of system librarie
 
 **Reviewers**: Nan Zhu (@CodingCat), @LeZhengThu, Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Steve Bronder (@SteveBronder), Nikita Titov (@StrikerRUS), Andrew Kane (@ankane), Avinash Barnwal (@avinashbarnwal), @brydag, Andy Adinets (@canonizer), Chandra Shekhar Reddy (@chandrureddy), Chen Qin (@chenqin), Codecov (@codecov-io), David Díaz Vico (@daviddiazvico), Darby Payne (@dpayne), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), @johnny-cat, Mu Li (@mli), Mate Soos (@msoos), @rnyak, Rong Ou (@rongou), Sriram Chandramouli (@sriramch), Toby Dylan Hocking (@tdhock), Yuan Tang (@terrytangyuan), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Liang-Chi Hsieh (@viirya), Bobby Wang (@wbo4958),
 
-## v1.0.2 (2020.03.03)
-This patch release applies the following patches to 1.0.0 release:
-
-* Fix a small typo in sklearn.py that broke multiple eval metrics (#5341)
-* Restore loading model from buffer (#5360)
-* Use type name for data type check (#5364)
-
-## v1.0.1 (2020.02.21)
-This release is identical to the 1.0.0 release, except that it fixes a small bug that rendered 1.0.0 incompatible with Python 3.5. See #5328.
-
 ## v1.0.0 (2020.02.19)
 This release marks a major milestone for the XGBoost project.
 
@@ -1349,7 +440,7 @@ This release marks a major milestone for the XGBoost project.
 * Specify version macro in CMake. (#4730)
 * Include dmlc-tracker into XGBoost Python package (#4731)
 * [CI] Use long key ID for Ubuntu repository fingerprints. (#4783)
-* Remove plugin, CUDA related code in automake & autoconf files (#4789)
+* Remove plugin, cuda related code in automake & autoconf files (#4789)
 * Skip related tests when scikit-learn is not installed. (#4791)
 * Ignore vscode and clion files (#4866)
 * Use bundled Google Test by default (#4900)
@@ -1380,7 +471,7 @@ This release marks a major milestone for the XGBoost project.
 ### Usability Improvements, Documentation
 * Add Random Forest API to Python API doc (#4500)
 * Fix Python demo and doc. (#4545)
-* Remove doc about not supporting CUDA 10.1 (#4578)
+* Remove doc about not supporting cuda 10.1 (#4578)
 * Address some sphinx warnings and errors, add doc for building doc. (#4589)
 * Add instruction to run formatting checks locally (#4591)
 * Fix docstring for `XGBModel.predict()` (#4592)
@@ -1395,7 +486,7 @@ This release marks a major milestone for the XGBoost project.
 * Update XGBoost4J-Spark doc (#4804)
 * Regular formatting for evaluation metrics (#4803)
 * [jvm-packages] Refine documentation for handling missing values in XGBoost4J-Spark (#4805)
-* Monitor for distributed environment (#4829). This is useful for identifying performance bottleneck.
+* Monitor for distributed envorinment (#4829). This is useful for identifying performance bottleneck.
 * Add check for length of weights and produce a good error message (#4872)
 * Fix DMatrix doc (#4884)
 * Export C++ headers in CMake installation (#4897)
@@ -1867,7 +958,7 @@ This release is packed with many new features and bug fixes.
 ### Known issues
 * Quantile sketcher fails to produce any quantile for some edge cases (#2943)
 * The `hist` algorithm leaks memory when used with learning rate decay callback (#3579)
-* Using custom evaluation function together with early stopping causes assertion failure in XGBoost4J-Spark (#3595)
+* Using custom evaluation funciton together with early stopping causes assertion failure in XGBoost4J-Spark (#3595)
 * Early stopping doesn't work with `gblinear` learner (#3789)
 * Label and weight vectors are not reshared upon the change in number of GPUs (#3794). To get around this issue, delete the `DMatrix` object and re-load.
 * The `DMatrix` Python objects are initialized with incorrect values when given array slices (#3841)
@@ -1961,7 +1052,7 @@ This version is only applicable for the Python package. The content is identical
   - Add scripts to cross-build and deploy artifacts (#3276, #3307)
   - Fix a compilation error for Scala 2.10 (#3332)
 * BREAKING CHANGES
-  - `XGBClassifier.predict_proba()` no longer accepts parameter `output_margin`. The parameter makes no sense for `predict_proba()` because the method is to predict class probabilities, not raw margin scores.
+  - `XGBClassifier.predict_proba()` no longer accepts paramter `output_margin`. The paramater makes no sense for `predict_proba()` because the method is to predict class probabilities, not raw margin scores.
 
 ## v0.71 (2018.04.11)
 * This is a minor release, mainly motivated by issues concerning `pip install`, e.g. #2426, #3189, #3118, and #3194.
@@ -1977,7 +1068,7 @@ This version is only applicable for the Python package. The content is identical
   - AUC-PR metric for ranking task (#3172)
   - Monotonic constraints for 'hist' algorithm (#3085)
 * GPU support
-    - Create an abstract 1D vector class that moves data seamlessly between the main and GPU memory (#2935, #3116, #3068). This eliminates unnecessary PCIe data transfer during training time.
+  - Create an abtract 1D vector class that moves data seamlessly between the main and GPU memory (#2935, #3116, #3068). This eliminates unnecessary PCIe data transfer during training time.
   - Fix minor bugs (#3051, #3217)
   - Fix compatibility error for CUDA 9.1 (#3218)
 * Python package:
@@ -2005,7 +1096,7 @@ This version is only applicable for the Python package. The content is identical
 * Refactored gbm to allow more friendly cache strategy
   - Specialized some prediction routine
 * Robust `DMatrix` construction from a sparse matrix
-* Faster construction of `DMatrix` from 2D NumPy matrices: elide copies, use of multiple threads
+* Faster consturction of `DMatrix` from 2D NumPy matrices: elide copies, use of multiple threads
 * Automatically remove nan from input data when it is sparse.
   - This can solve some of user reported problem of istart != hist.size
 * Fix the single-instance prediction function to obtain correct predictions
@@ -2033,7 +1124,7 @@ This version is only applicable for the Python package. The content is identical
   - Faster, histogram-based tree algorithm (`tree_method='hist'`) .
   - GPU/CUDA accelerated tree algorithms (`tree_method='gpu_hist'` or `'gpu_exact'`), including the GPU-based predictor.
   - Monotonic constraints: when other features are fixed, force the prediction to be monotonic increasing with respect to a certain specified feature.
-  - Faster gradient calculation using AVX SIMD
+  - Faster gradient caculation using AVX SIMD
   - Ability to export models in JSON format
   - Support for Tweedie regression
   - Additional dropout options for DART: binomial+1, epsilon

R-package/DESCRIPTION

@@ -1,12 +1,12 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.6.2.1
-Date: 2022-03-29
+Version: 1.2.0.1
+Date: 2020-02-21
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
-  person("Tong", "He", role = c("aut"),
+  person("Tong", "He", role = c("aut", "cre"),
          email = "hetong007@gmail.com"),
   person("Michael", "Benesty", role = c("aut"),
          email = "michael@benesty.fr"),
@@ -26,12 +26,9 @@ Authors@R: c(
   person("Min", "Lin", role = c("aut")),
   person("Yifeng", "Geng", role = c("aut")),
   person("Yutian", "Li", role = c("aut")),
-  person("Jiaming", "Yuan", role = c("aut", "cre"),
-         email = "jm.yuan@outlook.com"),
   person("XGBoost contributors", role = c("cph"),
          comment = "base XGBoost implementation")
   )
-Maintainer: Jiaming Yuan <jm.yuan@outlook.com>
 Description: Extreme Gradient Boosting, which is an efficient implementation
     of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
     This package is its R interface. The package includes efficient linear
@@ -56,15 +53,16 @@ Suggests:
     testthat,
     lintr,
     igraph (>= 1.0.1),
+    jsonlite,
     float,
-    crayon,
-    titanic
+    crayon
 Depends:
     R (>= 3.3.0)
 Imports:
     Matrix (>= 1.1-0),
     methods,
     data.table (>= 1.9.6),
-    jsonlite (>= 1.0),
+    magrittr (>= 1.5),
+    stringi (>= 0.5.2)
 RoxygenNote: 7.1.1
 SystemRequirements: GNU make, C++14

R-package/NAMESPACE

@@ -36,10 +36,8 @@ 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)
@@ -48,12 +46,10 @@ 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)
@@ -80,10 +76,14 @@ importFrom(graphics,lines)
 importFrom(graphics,par)
 importFrom(graphics,points)
 importFrom(graphics,title)
-importFrom(jsonlite,fromJSON)
-importFrom(jsonlite,toJSON)
+importFrom(magrittr,"%>%")
 importFrom(stats,median)
 importFrom(stats,predict)
+importFrom(stringi,stri_detect_regex)
+importFrom(stringi,stri_match_first_regex)
+importFrom(stringi,stri_replace_all_regex)
+importFrom(stringi,stri_replace_first_regex)
+importFrom(stringi,stri_split_regex)
 importFrom(utils,head)
 importFrom(utils,object.size)
 importFrom(utils,str)

R-package/R/callbacks.R

@@ -188,7 +188,7 @@ cb.reset.parameters <- function(new_params) {
   pnames <- gsub("\\.", "_", names(new_params))
   nrounds <- NULL
 
-  # run some checks in the beginning
+  # run some checks in the begining
   init <- function(env) {
     nrounds <<- env$end_iteration - env$begin_iteration + 1
 
@@ -263,7 +263,10 @@ cb.reset.parameters <- function(new_params) {
 #' \itemize{
 #' \item \code{best_score} the evaluation score at the best iteration
 #' \item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
+#' \item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
+#'      It differs from \code{best_iteration} in multiclass or random forest settings.
 #' }
+#'
 #' The Same values are also stored as xgb-attributes:
 #' \itemize{
 #' \item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)
@@ -349,15 +352,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
   finalizer <- function(env) {
     if (!is.null(env$bst)) {
       attr_best_score <- as.numeric(xgb.attr(env$bst$handle, 'best_score'))
-      if (best_score != attr_best_score) {
-        # If the difference is too big, throw an error
-        if (abs(best_score - attr_best_score) >= 1e-14) {
-          stop("Inconsistent 'best_score' values between the closure state: ", best_score,
-               " and the xgb.attr: ", attr_best_score)
-        }
-        # If the difference is due to floating-point truncation, update best_score
-        best_score <- attr_best_score
-      }
+      if (best_score != attr_best_score)
+        stop("Inconsistent 'best_score' values between the closure state: ", best_score,
+             " and the xgb.attr: ", attr_best_score)
       env$bst$best_iteration <- best_iteration
       env$bst$best_ntreelimit <- best_ntreelimit
       env$bst$best_score <- best_score
@@ -495,12 +492,13 @@ cb.cv.predict <- function(save_models = FALSE) {
         rep(NA_real_, N)
       }
 
-    iterationrange <- c(1, NVL(env$basket$best_iteration, env$end_iteration) + 1)
+    ntreelimit <- NVL(env$basket$best_ntreelimit,
+                      env$end_iteration * env$num_parallel_tree)
     if (NVL(env$params[['booster']], '') == 'gblinear') {
-      iterationrange <- c(1, 1)  # must be 0 for gblinear
+      ntreelimit <- 0 # must be 0 for gblinear
     }
     for (fd in env$bst_folds) {
-      pr <- predict(fd$bst, fd$watchlist[[2]], iterationrange = iterationrange, reshape = TRUE)
+      pr <- predict(fd$bst, fd$watchlist[[2]], ntreelimit = ntreelimit, reshape = TRUE)
       if (is.matrix(pred)) {
         pred[fd$index, ] <- pr
       } else {
@@ -529,7 +527,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' Callback closure for collecting the model coefficients history of a gblinear booster
 #' during its training.
 #'
-#' @param sparse when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
+#' @param sparse when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
 #'       Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 #'       when using the "thrifty" feature selector with fairly small number of top features
 #'       selected per iteration.
@@ -556,6 +554,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' #
 #' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
 #' # without considering the 2nd order interactions:
+#' require(magrittr)
 #' x <- model.matrix(Species ~ .^2, iris)[,-1]
 #' colnames(x)
 #' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
@@ -576,7 +575,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
 #'                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
 #'                  callbacks = list(cb.gblinear.history()))
-#' matplot(xgb.gblinear.history(bst), type = 'l')
+#' xgb.gblinear.history(bst) %>% matplot(type = 'l')
 #' #  Componentwise boosting is known to have similar effect to Lasso regularization.
 #' # Try experimenting with various values of top_k, eta, nrounds,
 #' # as well as different feature_selectors.
@@ -585,7 +584,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
 #'              callbacks = list(cb.gblinear.history()))
 #' # coefficients in the CV fold #3
-#' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
+#' xgb.gblinear.history(bst)[[3]] %>% matplot(type = 'l')
 #'
 #'
 #' #### Multiclass classification:
@@ -598,15 +597,15 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
 #'                  callbacks = list(cb.gblinear.history()))
 #' # Will plot the coefficient paths separately for each class:
-#' matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
-#' matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
-#' matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
+#' xgb.gblinear.history(bst, class_index = 0) %>% matplot(type = 'l')
+#' xgb.gblinear.history(bst, class_index = 1) %>% matplot(type = 'l')
+#' xgb.gblinear.history(bst, class_index = 2) %>% matplot(type = 'l')
 #'
 #' # CV:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
 #'               callbacks = list(cb.gblinear.history(FALSE)))
-#' # 1st fold of 1st class
-#' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
+#' # 1st forld of 1st class
+#' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l')
 #'
 #' @export
 cb.gblinear.history <- function(sparse=FALSE) {
@@ -637,14 +636,9 @@ cb.gblinear.history <- function(sparse=FALSE) {
     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
-      )
+      # first lapply transposes the list
+      coefs <<- lapply(seq_along(coefs[[1]]), function(i) lapply(coefs, "[[", i)) %>%
+                lapply(function(x) list2mat(x))
     }
   }
 

R-package/R/utils.R

@@ -1,6 +1,6 @@
 #
-# This file is for the low level reusable utility functions
-# that are not supposed to be visible to a user.
+# This file is for the low level reuseable utility functions
+# that are not supposed to be visibe to a user.
 #
 
 #
@@ -20,12 +20,6 @@ NVL <- function(x, val) {
   stop("typeof(x) == ", typeof(x), " is not supported by NVL")
 }
 
-# List of classification and ranking objectives
-.CLASSIFICATION_OBJECTIVES <- function() {
-  return(c('binary:logistic', 'binary:logitraw', 'binary:hinge', 'multi:softmax',
-           'multi:softprob', 'rank:pairwise', 'rank:ndcg', 'rank:map'))
-}
-
 
 #
 # Low-level functions for boosting --------------------------------------------
@@ -173,13 +167,13 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = 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, ])
+    msg <- stri_split_regex(msg, '(\\s+|:|\\s+)')[[1]][-1]
+    res <- as.numeric(msg[c(FALSE, TRUE)]) # even indices are the values
+    names(res) <- msg[c(TRUE, FALSE)]      # odds are the names
   } else {
     res <- sapply(seq_along(watchlist), function(j) {
       w <- watchlist[[j]]
-      ## predict using all trees
-      preds <- predict(booster_handle, w, outputmargin = TRUE, iterationrange = c(1, 1))
+      preds <- predict(booster_handle, w, outputmargin = TRUE, ntreelimit = 0) # predict using all trees
       eval_res <- feval(preds, w)
       out <- eval_res$value
       names(out) <- paste0(evnames[j], "-", eval_res$metric)
@@ -194,23 +188,13 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
 # 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$objective
-  if (is.character(objective) && strtrim(objective, 5) == 'rank:') {
+  if (exists('objective', where = params) &&
+      is.character(params$objective) &&
+      strtrim(params$objective, 5) == 'rank:') {
     stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
          "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
   }
@@ -223,16 +207,19 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
     #  - For classification, need to convert y labels to factor before making the folds,
     #    and then do stratification by factor levels.
     #  - For regression, leave y numeric and do stratification by quantiles.
-    if (is.character(objective)) {
-      y <- convert.labels(y, params$objective)
+    if (exists('objective', where = params) &&
+        is.character(params$objective)) {
+      # If 'objective' provided in params, assume that y is a classification label
+      # unless objective is reg:squarederror
+      if (params$objective != 'reg:squarederror')
+        y <- factor(y)
     } else {
       # If no 'objective' given in params, it means that user either wants to
       # use the default 'reg:squarederror' objective or has provided a custom
       # obj function.  Here, assume classification setting when y has 5 or less
       # unique values:
-      if (length(unique(y)) <= 5) {
+      if (length(unique(y)) <= 5)
         y <- factor(y)
-      }
     }
     folds <- xgb.createFolds(y, nfold)
   } else {
@@ -285,7 +272,7 @@ xgb.createFolds <- function(y, k = 10)
     for (i in seq_along(numInClass)) {
       ## create a vector of integers from 1:k as many times as possible without
       ## going over the number of samples in the class. Note that if the number
-      ## of samples in a class is less than k, nothing is produced here.
+      ## of samples in a class is less than k, nothing is producd here.
       seqVector <- rep(seq_len(k), numInClass[i] %/% k)
       ## add enough random integers to get  length(seqVector) == numInClass[i]
       if (numInClass[i] %% k > 0) seqVector <- c(seqVector, sample.int(k, numInClass[i] %% k))
@@ -362,7 +349,6 @@ NULL
 #' # 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)
@@ -378,7 +364,6 @@ NULL
 #' 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

R-package/R/xgb.Booster.R

@@ -1,7 +1,7 @@
 # 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) {
+                               modelfile = NULL) {
   if (typeof(cachelist) != "list" ||
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
@@ -11,7 +11,6 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(),
     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) {
@@ -20,7 +19,7 @@ xgb.Booster.handle <- function(params = list(), cachelist = list(),
       return(handle)
     } else if (typeof(modelfile) == "raw") {
       ## A memory buffer
-      bst <- xgb.unserialize(modelfile, handle)
+      bst <- xgb.unserialize(modelfile)
       xgb.parameters(bst) <- params
       return (bst)
     } else if (inherits(modelfile, "xgb.Booster")) {
@@ -129,7 +128,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
     stop("argument type must be xgb.Booster")
 
   if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(modelfile = object$raw, handle = object$handle)
+    object$handle <- xgb.Booster.handle(modelfile = object$raw)
   } else {
     if (is.null(object$raw) && saveraw) {
       object$raw <- xgb.serialize(object$handle)
@@ -162,17 +161,14 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' Predicted values based on either xgboost model or model handle object.
 #'
 #' @param object Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}
-#' @param newdata takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-#'        local data file or \code{xgb.DMatrix}.
-#'
-#'        For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-#'        a sparse vector, it will take it as a row vector.
+#' @param newdata takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.
 #' @param missing Missing is only used when input is dense matrix. Pick a float value that represents
 #'        missing values in data (e.g., sometimes 0 or some other extreme value is used).
 #' @param outputmargin whether the prediction should be returned in the for of original untransformed
 #'        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 ntreelimit limit the number of model's trees or boosting iterations used in prediction (see Details).
+#'        It will use all the trees by default (\code{NULL} value).
 #' @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).
@@ -182,19 +178,16 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #'        or predinteraction flags is TRUE.
 #' @param training whether is the prediction result used for training.  For dart booster,
 #'        training predicting will perform dropout.
-#' @param iterationrange Specifies which layer of trees are used in prediction.  For
-#'        example, if a random forest is trained with 100 rounds.  Specifying
-#'        `iterationrange=(1, 21)`, then only the forests built during [1, 21) (half open set)
-#'        rounds are used in this prediction.  It's 1-based index just like R vector.  When set
-#'        to \code{c(1, 1)} XGBoost will use all trees.
-#' @param strict_shape  Default is \code{FALSE}. When it's set to \code{TRUE}, output
-#'        type and shape of prediction are invariant to model type.
-#'
 #' @param ... Parameters passed to \code{predict.xgb.Booster}
 #'
 #' @details
+#' Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
+#' and it is not necessarily equal to the number of trees in a model.
+#' E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
+#' But for multiclass classification, while there are multiple trees per iteration,
+#' \code{ntreelimit} limits the number of boosting iterations.
 #'
-#' Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
+#' Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
 #' since gblinear doesn't keep its boosting history.
 #'
 #' One possible practical applications of the \code{predleaf} option is to use the model
@@ -215,8 +208,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' 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 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.
@@ -238,13 +230,6 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 #' such an array.
 #'
-#' When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
-#' normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
-#'
-#' For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
-#' For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
-#' For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
-#'
 #' @seealso
 #' \code{\link{xgb.train}}.
 #'
@@ -267,7 +252,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' # use all trees by default
 #' pred <- predict(bst, test$data)
 #' # use only the 1st tree
-#' pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
+#' pred1 <- predict(bst, test$data, ntreelimit = 1)
 #'
 #' # Predicting tree leafs:
 #' # the result is an nsamples X ntrees matrix
@@ -319,14 +304,31 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' all.equal(pred, pred_labels)
 #' # prediction from using only 5 iterations should result
 #' # in the same error as seen in iteration 5:
-#' pred5 <- predict(bst, as.matrix(iris[, -5]), iterationrange=c(1, 6))
+#' pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
 #' sum(pred5 != lb)/length(lb)
 #'
+#'
+#' ## random forest-like model of 25 trees for binary classification:
+#'
+#' set.seed(11)
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
+#'                nthread = 2, nrounds = 1, objective = "binary:logistic",
+#'                num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
+#' # Inspect the prediction error vs number of trees:
+#' lb <- test$label
+#' dtest <- xgb.DMatrix(test$data, label=lb)
+#' err <- sapply(1:25, function(n) {
+#'   pred <- predict(bst, dtest, ntreelimit=n)
+#'   sum((pred > 0.5) != lb)/length(lb)
+#' })
+#' plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
+#'
 #' @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, ...) {
+                                reshape = FALSE, training = FALSE, ...) {
+
   object <- xgb.Booster.complete(object, saveraw = FALSE)
   if (!inherits(newdata, "xgb.DMatrix"))
     newdata <- xgb.DMatrix(newdata, missing = missing)
@@ -334,136 +336,62 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       !is.null(colnames(newdata)) &&
       !identical(object[["feature_names"]], colnames(newdata)))
     stop("Feature names stored in `object` and `newdata` are different!")
-
-  if (NVL(object$params[['booster']], '') == 'gblinear' || is.null(ntreelimit))
+  if (is.null(ntreelimit))
+    ntreelimit <- NVL(object$best_ntreelimit, 0)
+  if (NVL(object$params[['booster']], '') == 'gblinear')
     ntreelimit <- 0
+  if (ntreelimit < 0)
+    stop("ntreelimit cannot be negative")
 
-  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)
-  }
+  option <- 0L + 1L * as.logical(outputmargin) + 2L * as.logical(predleaf) + 4L * as.logical(predcontrib) +
+    8L * as.logical(approxcontrib) + 16L * as.logical(predinteraction)
 
-  ## 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
+  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1],
+               as.integer(ntreelimit), as.integer(training))
 
   n_ret <- length(ret)
   n_row <- nrow(newdata)
-  if (n_row != shape[1]) {
-    stop("Incorrect predict shape.")
-  }
+  npred_per_case <- n_ret / n_row
 
-  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 (n_ret %% n_row != 0)
+    stop("prediction length ", n_ret, " is not multiple of nrows(newdata) ", n_row)
 
   if (predleaf) {
-    ## Predict leaf
-    arr <- if (n_ret == n_row) {
-      matrix(arr, ncol = 1)
+    ret <- if (n_ret == n_row) {
+      matrix(ret, ncol = 1)
     } else {
-      matrix(arr, nrow = n_row, byrow = TRUE)
+      matrix(ret, 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, , ])
+    n_col1 <- ncol(newdata) + 1
+    n_group <- npred_per_case / n_col1
+    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+    ret <- if (n_ret == n_row) {
+      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
+    } else if (n_group == 1) {
+      matrix(ret, nrow = n_row, byrow = TRUE, dimnames = list(NULL, cnames))
     } 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]))
+      arr <- array(ret, c(n_col1, n_group, n_row),
+                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2, 3, 1)) # [group, row, col]
+      lapply(seq_len(n_group), function(g) arr[g, , ])
     }
   } 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, , , ])
+    n_col1 <- ncol(newdata) + 1
+    n_group <- npred_per_case / n_col1^2
+    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+    ret <- if (n_ret == n_row) {
+      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
+    } else if (n_group == 1) {
+      array(ret, c(n_col1, n_col1, n_row), dimnames = list(cnames, cnames, NULL)) %>% aperm(c(3, 1, 2))
     } 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)
+      arr <- array(ret, c(n_col1, n_col1, n_group, n_row),
+                   dimnames = list(cnames, cnames, NULL, NULL)) %>% aperm(c(3, 4, 1, 2)) # [group, row, col1, col2]
+      lapply(seq_len(n_group), function(g) arr[g, , , ])
     }
+  } else if (reshape && npred_per_case > 1) {
+    ret <- matrix(ret, nrow = n_row, byrow = TRUE)
   }
-  return(arr)
+  return(ret)
 }
 
 #' @rdname predict.xgb.Booster

R-package/R/xgb.DMatrix.R

@@ -1,55 +1,39 @@
 #' Construct xgb.DMatrix object
 #'
 #' Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-#' Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
+#' Supported input file formats are either a libsvm text file or a binary file that was created previously by
 #' \code{\link{xgb.DMatrix.save}}).
 #'
-#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object,
-#'        a \code{dgRMatrix} object (only when making predictions from a fitted model),
-#'        a \code{dsparseVector} object (only when making predictions from a fitted model, will be
-#'        interpreted as a row vector), or a character string representing a filename.
+#' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
+#'        string representing a filename.
 #' @param info a named list of additional information to store in the \code{xgb.DMatrix} object.
 #'        See \code{\link{setinfo}} for the specific allowed kinds of
 #' @param missing a float value to represents missing values in data (used only when input is a dense matrix).
 #'        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))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
-xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthread = NULL, ...) {
+xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
   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)))
+    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing)
     cnames <- colnames(data)
   } else if (inherits(data, "dgCMatrix")) {
-    handle <- .Call(
-      XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data), as.integer(NVL(nthread, -1))
-    )
+    handle <- .Call(XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data))
     cnames <- colnames(data)
-  } else if (inherits(data, "dgRMatrix")) {
-    handle <- .Call(
-      XGDMatrixCreateFromCSR_R, data@p, data@j, data@x, ncol(data), as.integer(NVL(nthread, -1))
-    )
-    cnames <- colnames(data)
-  } else if (inherits(data, "dsparseVector")) {
-    indptr <- c(0L, as.integer(length(data@i)))
-    ind <- as.integer(data@i) - 1L
-    handle <- .Call(
-      XGDMatrixCreateFromCSR_R, indptr, ind, data@x, length(data), as.integer(NVL(nthread, -1))
-    )
   } else {
     stop("xgb.DMatrix does not support construction from ", typeof(data))
   }
@@ -67,12 +51,12 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthre
 
 # get dmatrix from data, label
 # internal helper method
-xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nthread = NULL) {
+xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = 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)
+    dtrain <- xgb.DMatrix(data, label = label, missing = missing)
     if (!is.null(weight)){
       setinfo(dtrain, "weight", weight)
     }
@@ -81,7 +65,6 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nth
       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
@@ -177,9 +160,9 @@ dimnames.xgb.DMatrix <- function(x) {
 #' The \code{name} field can be one of the following:
 #'
 #' \itemize{
-#'     \item \code{label}: label XGBoost learn from ;
+#'     \item \code{label}: label Xgboost learn from ;
 #'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
+#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
 #'     \item \code{nrow}: number of rows of the \code{xgb.DMatrix}.
 #'
 #' }
@@ -188,7 +171,8 @@ dimnames.xgb.DMatrix <- function(x) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -232,15 +216,16 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #' The \code{name} field can be one of the following:
 #'
 #' \itemize{
-#'     \item \code{label}: label XGBoost learn from ;
+#'     \item \code{label}: label Xgboost learn from ;
 #'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
+#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
 #'     \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
 #' }
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -287,13 +272,6 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
     .Call(XGDMatrixSetInfo_R, object, name, as.integer(info))
     return(TRUE)
   }
-  if (name == "feature_weights") {
-    if (length(info) != ncol(object)) {
-      stop("The number of feature weights must equal to the number of columns in the input data")
-    }
-    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
-    return(TRUE)
-  }
   stop("setinfo: unknown info name ", name)
   return(FALSE)
 }
@@ -312,7 +290,8 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #'
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -368,7 +347,8 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #'
 #' dtrain
 #' print(dtrain, verbose=TRUE)
@@ -377,7 +357,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #' @export
 print.xgb.DMatrix <- function(x, verbose = FALSE, ...) {
   cat('xgb.DMatrix  dim:', nrow(x), 'x', ncol(x), ' info: ')
-  infos <- character(0)
+  infos <- c()
   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')

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

@@ -7,7 +7,8 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' train <- agaricus.train
+#' dtrain <- xgb.DMatrix(train$data, label=train$label)
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
@@ -18,7 +19,6 @@ xgb.DMatrix.save <- function(dmatrix, fname) {
   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

@@ -18,7 +18,7 @@
 #'
 #' International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
 #'
-#' \url{https://research.facebook.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+#' \url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
 #'
 #' Extract explaining the method:
 #'
@@ -48,8 +48,8 @@
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' 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, silent=1, objective='binary:logistic')
 #' nrounds = 4

R-package/R/xgb.cv.R

@@ -36,8 +36,6 @@
 #'   \item \code{error} binary classification error rate
 #'   \item \code{rmse} Rooted mean square error
 #'   \item \code{logloss} negative log-likelihood function
-#'   \item \code{mae} Mean absolute error
-#'   \item \code{mape} Mean absolute percentage error
 #'   \item \code{auc} Area under curve
 #'   \item \code{aucpr} Area under PR curve
 #'   \item \code{merror} Exact matching error, used to evaluate multi-class classification
@@ -81,7 +79,7 @@
 #'
 #' All observations are used for both training and validation.
 #'
-#' Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
+#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
 #'
 #' @return
 #' An object of class \code{xgb.cv.synchronous} with the following elements:
@@ -101,7 +99,9 @@
 #'         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{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+#'         which could further be used in \code{predict} method
+#'         (only available with early stopping).
 #'   \item \code{pred} CV prediction values available when \code{prediction} is set.
 #'         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
 #'   \item \code{models} a list of the CV folds' models. It is only available with the explicit
@@ -110,7 +110,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
 #'                   max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)

R-package/R/xgb.dump.R

@@ -6,6 +6,8 @@
 #' @param fname the name of the text file where to save the model text dump.
 #'        If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.
 #' @param fmap feature map file representing feature types.
+#'        Detailed description could be found at
+#'        \url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
 #'        See demo/ for walkthrough example in R, and
 #'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
 #'        for example Format.
@@ -54,17 +56,16 @@ xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
                       as.character(dump_format))
 
   if (is.null(fname))
-    model_dump <- gsub('\t', '', model_dump, fixed = TRUE)
+    model_dump <- stri_replace_all_regex(model_dump, '\t', '')
 
   if (dump_format == "text")
-    model_dump <- unlist(strsplit(model_dump, '\n', fixed = TRUE))
+    model_dump <- unlist(stri_split_regex(model_dump, '\n'))
 
   model_dump <- grep('^\\s*$', model_dump, invert = TRUE, value = TRUE)
 
   if (is.null(fname)) {
     return(model_dump)
   } else {
-    fname <- path.expand(fname)
     writeLines(model_dump, fname[1])
     return(TRUE)
   }

R-package/R/xgb.ggplot.R

@@ -99,84 +99,6 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
   }
 }
 
-#' @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
@@ -209,5 +131,5 @@ multiplot <- function(..., cols = 1) {
 
 globalVariables(c(
   "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight", "feature"
+  "element_blank", "element_text", "V1", "Weight"
 ))

R-package/R/xgb.importance.R

@@ -96,44 +96,40 @@ xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
   if (!(is.null(feature_names) || is.character(feature_names)))
     stop("feature_names: Has to be a character vector")
 
-  model <- 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))]
+  model_text_dump <- xgb.dump(model = model, with_stats = TRUE)
+
+  # linear model
+  if (model_text_dump[2] == "bias:"){
+    weights <- which(model_text_dump == "weight:") %>%
+               {model_text_dump[(. + 1):length(model_text_dump)]} %>%
+               as.numeric
+
+    num_class <- NVL(model$params$num_class, 1)
+    if (is.null(feature_names))
+      feature_names <- seq(to = length(weights) / num_class) - 1
+    if (length(feature_names) * num_class != length(weights))
+      stop("feature_names length does not match the number of features used in the model")
+
+    result <- if (num_class == 1) {
+      data.table(Feature = feature_names, Weight = weights)[order(-abs(Weight))]
     } else {
-      data.table(
-        Feature = rep(results$features, each = n_classes), Weight = results$weight, Class = seq_len(n_classes) - 1
-      )[order(Class, -abs(Weight))]
+      data.table(Feature = rep(feature_names, each = num_class),
+                 Weight = weights,
+                 Class = seq_len(num_class) - 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)]
+  } else { # tree model
+      result <- xgb.model.dt.tree(feature_names = feature_names,
+                                  text = model_text_dump,
+                                  trees = trees)[
+          Feature != "Leaf", .(Gain = sum(Quality),
+                               Cover = sum(Cover),
+                               Frequency = .N), by = Feature][
+        , `:=`(Gain = Gain / sum(Gain),
+               Cover = Cover / sum(Cover),
+               Frequency = Frequency / sum(Frequency))][
+          order(Gain, decreasing = TRUE)]
   }
-  importance
+  result
 }
 
 # Avoid error messages during CRAN check.

R-package/R/xgb.load.R

@@ -5,7 +5,7 @@
 #' @param modelfile the name of the binary input file.
 #'
 #' @details
-#' The input file is expected to contain a model saved in an xgboost model format
+#' The input file is expected to contain a model saved in an xgboost-internal binary format
 #' using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
 #' appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 #' saved from there in xgboost format, could be loaded from R.
@@ -38,13 +38,6 @@ xgb.load <- function(modelfile) {
   handle <- xgb.Booster.handle(modelfile = modelfile)
   # re-use modelfile if it is raw so we do not need to serialize
   if (typeof(modelfile) == "raw") {
-    warning(
-      paste(
-        "The support for loading raw booster with `xgb.load` will be ",
-        "discontinued in upcoming release. Use `xgb.load.raw` or",
-        " `xgb.unserialize` instead. "
-      )
-    )
     bst <- xgb.handleToBooster(handle, modelfile)
   } else {
     bst <- xgb.handleToBooster(handle, NULL)

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

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

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

@@ -87,11 +87,11 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   }
 
   if (length(text) < 2 ||
-      sum(grepl('leaf=(\\d+)', text)) < 1) {
+      sum(stri_detect_regex(text, 'yes=(\\d+),no=(\\d+)')) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
 
-  position <- which(grepl("booster", text, fixed = TRUE))
+  position <- which(!is.na(stri_match_first_regex(text, "booster")))
 
   add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
 
@@ -108,36 +108,23 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   }
   td <- td[Tree %in% trees & !grepl('^booster', t)]
 
-  td[, Node := as.integer(sub("^([0-9]+):.*", "\\1", t))]
+  td[, Node := stri_match_first_regex(t, "(\\d+):")[, 2] %>% as.integer]
   if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := grepl("leaf", t, fixed = TRUE)]
+  td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
 
   # parse branch lines
   branch_rx <- 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))
+  td[isLeaf == FALSE,
+     (branch_cols) := {
       # skip some indices with spurious capture groups from anynumber_regex
-      xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
+      xtr <- stri_match_first_regex(t, branch_rx)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
       xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
-      if (length(xtr) == 0) {
-        as.data.table(
-          list(Feature = "NA", Split = "NA", Yes = "NA", No = "NA", Missing = "NA", Quality = "NA", Cover = "NA")
-        )
-      } else {
-        as.data.table(xtr)
-      }
-    }
-  ]
-
+      lapply(seq_len(ncol(xtr)), function(i) xtr[, i])
+    }]
   # assign feature_names when available
-  is_stump <- function() {
-    return(length(td$Feature) == 1 && is.na(td$Feature))
-  }
-  if (!is.null(feature_names) && !is_stump()) {
+  if (!is.null(feature_names)) {
     if (length(feature_names) <= max(as.numeric(td$Feature), na.rm = TRUE))
       stop("feature_names has less elements than there are features used in the model")
     td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1]]
@@ -146,18 +133,11 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
   # parse leaf lines
   leaf_rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   leaf_cols <- c("Feature", "Quality", "Cover")
-  td[
-    isLeaf == TRUE,
-    (leaf_cols) := {
-      matches <- regmatches(t, regexec(leaf_rx, t))
-      xtr <- do.call(rbind, matches)[, c(2, 4)]
-      if (length(xtr) == 2) {
-        c("Leaf", as.data.table(xtr[1]), as.data.table(xtr[2]))
-      } else {
-        c("Leaf", as.data.table(xtr))
-      }
-    }
-  ]
+  td[isLeaf == TRUE,
+     (leaf_cols) := {
+      xtr <- stri_match_first_regex(t, leaf_rx)[, c(2, 4)]
+      c("Leaf", lapply(seq_len(ncol(xtr)), function(i) xtr[, i]))
+    }]
 
   # convert some columns to numeric
   numeric_cols <- c("Split", "Quality", "Cover")

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

@@ -99,20 +99,21 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
   }
 
   if (plot) {
-    original_mar <- par()$mar
-
-    # reset margins so this function doesn't have side effects
-    on.exit({par(mar = original_mar)})
-
-    mar <- original_mar
+    op <- par(no.readonly = TRUE)
+    mar <- op$mar
     if (!is.null(left_margin))
       mar[2] <- left_margin
     par(mar = mar)
 
     # reverse the order of rows to have the highest ranked at the top
-    importance_matrix[rev(seq_len(nrow(importance_matrix))),
+    importance_matrix[nrow(importance_matrix):1,
                       barplot(Importance, horiz = TRUE, border = NA, cex.names = cex,
                               names.arg = Feature, las = 1, ...)]
+    grid(NULL, NA)
+    # redraw over the grid
+    importance_matrix[nrow(importance_matrix):1,
+                      barplot(Importance, horiz = TRUE, border = NA, add = TRUE)]
+    par(op)
   }
 
   invisible(importance_matrix)

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

@@ -67,7 +67,7 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
 
   # first number of the path represents the tree, then the following numbers are related to the path to follow
   # root init
-  root.nodes <- tree.matrix[Node == 0, ID]
+  root.nodes <- tree.matrix[stri_detect_regex(ID, "\\d+-0"), ID]
   tree.matrix[ID %in% root.nodes, abs.node.position := root.nodes]
 
   precedent.nodes <- root.nodes
@@ -75,8 +75,8 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
   while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
     yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
     no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
-    yes.nodes.abs.pos <- paste0(yes.row.nodes[, abs.node.position], "_0")
-    no.nodes.abs.pos <- paste0(no.row.nodes[, abs.node.position], "_1")
+    yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
+    no.nodes.abs.pos <- no.row.nodes[, abs.node.position] %>% paste0("_1")
 
     tree.matrix[ID %in% yes.row.nodes[, Yes], abs.node.position := yes.nodes.abs.pos]
     tree.matrix[ID %in% no.row.nodes[, No], abs.node.position := no.nodes.abs.pos]
@@ -86,34 +86,28 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
   tree.matrix[!is.na(Yes), Yes := paste0(abs.node.position, "_0")]
   tree.matrix[!is.na(No), No := paste0(abs.node.position, "_1")]
 
-  for (nm in c("abs.node.position", "Yes", "No"))
-    data.table::set(tree.matrix, j = nm, value = sub("^\\d+-", "", tree.matrix[[nm]]))
+  remove.tree <- . %>% stri_replace_first_regex(pattern = "^\\d+-", replacement = "")
+
+  tree.matrix[, `:=`(abs.node.position = remove.tree(abs.node.position),
+                     Yes = remove.tree(Yes),
+                     No = remove.tree(No))]
 
   nodes.dt <- tree.matrix[
         , .(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
-      ]
+      ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
+                          " (",
+                          format(Quality[1:min(length(Quality), features_keep)], digits = 5),
+                          ")") %>%
+                   paste0(collapse = "\n"))
+        , by = abs.node.position]
 
-  edges.dt <- 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]
+  edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
+    list(tree.matrix[Feature != "Leaf", .(abs.node.position, No)]) %>%
+    rbindlist() %>%
+    setnames(c("From", "To")) %>%
+    .[, .N, .(From, To)] %>%
+    .[, N := NULL]
 
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
@@ -129,25 +123,21 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "node",
       attr  = c("color", "fillcolor", "style", "shape", "fontname"),
       value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica")
-  )
+      value = c("DimGray", "1.5", "vee", "Helvetica"))
 
   if (!render) return(invisible(graph))
 

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

@@ -33,7 +33,7 @@
 #' @param col_loess a color to use for the loess curves.
 #' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
 #' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
-#' @param plot whether a plot should be drawn. If FALSE, only a list of matrices is returned.
+#' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
 #' @param ... other parameters passed to \code{plot}.
 #'
 #' @details
@@ -81,7 +81,6 @@
 #' 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
@@ -100,7 +99,6 @@
 #'               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
@@ -111,33 +109,69 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
                           plot_NA = TRUE, col_NA = rgb(0.7, 0, 1, 0.6), pch_NA = '.', pos_NA = 1.07,
                           plot_loess = TRUE, col_loess = 2, span_loess = 0.5,
                           which = c("1d", "2d"), plot = TRUE, ...) {
-  data_list <- xgb.shap.data(
-    data = data,
-    shap_contrib = shap_contrib,
-    features = features,
-    top_n = top_n,
-    model = model,
-    trees = trees,
-    target_class = target_class,
-    approxcontrib = approxcontrib,
-    subsample = subsample,
-    max_observations = 100000
-  )
-  data <- data_list[["data"]]
-  shap_contrib <- data_list[["shap_contrib"]]
-  features <- colnames(data)
+
+  if (!is.matrix(data) && !inherits(data, "dgCMatrix"))
+    stop("data: must be either matrix or dgCMatrix")
+
+  if (is.null(shap_contrib) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when shap_contrib is not provided, one must provide an xgb.Booster model")
+
+  if (is.null(features) && (is.null(model) || !inherits(model, "xgb.Booster")))
+    stop("when features are not provided, one must provide an xgb.Booster model to rank the features")
+
+  if (!is.null(shap_contrib) &&
+      (!is.matrix(shap_contrib) || nrow(shap_contrib) != nrow(data) || ncol(shap_contrib) != ncol(data) + 1))
+    stop("shap_contrib is not compatible with the provided data")
+
+  nsample <- if (is.null(subsample)) min(100000, nrow(data)) else as.integer(subsample * nrow(data))
+  idx <- sample(1:nrow(data), nsample)
+  data <- data[idx, ]
+
+  if (is.null(shap_contrib)) {
+    shap_contrib <- predict(model, data, predcontrib = TRUE, approxcontrib = approxcontrib)
+  } else {
+    shap_contrib <- shap_contrib[idx, ]
+  }
 
   which <- match.arg(which)
   if (which == "2d")
     stop("2D plots are not implemented yet")
 
+  if (is.null(features)) {
+    imp <- xgb.importance(model = model, trees = trees)
+    top_n <- as.integer(top_n[1])
+    if (top_n < 1 && top_n > 100)
+      stop("top_n: must be an integer within [1, 100]")
+    features <- imp$Feature[1:min(top_n, NROW(imp))]
+  }
+
+  if (is.character(features)) {
+    if (is.null(colnames(data)))
+      stop("Either provide `data` with column names or provide `features` as column indices")
+    features <- match(features, colnames(data))
+  }
+
   if (n_col > length(features)) n_col <- length(features)
+
+  if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
+    shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]]
+                    else Reduce("+", lapply(shap_contrib, abs))
+  }
+
+  shap_contrib <- shap_contrib[, features, drop = FALSE]
+  data <- data[, features, drop = FALSE]
+  cols <- colnames(data)
+  if (is.null(cols)) cols <- colnames(shap_contrib)
+  if (is.null(cols)) cols <- paste0('X', 1:ncol(data))
+  colnames(data) <- cols
+  colnames(shap_contrib) <- cols
+
   if (plot && which == "1d") {
     op <- par(mfrow = c(ceiling(length(features) / n_col), n_col),
               oma = c(0, 0, 0, 0) + 0.2,
               mar = c(3.5, 3.5, 0, 0) + 0.1,
               mgp = c(1.7, 0.6, 0))
-    for (f in features) {
+    for (f in cols) {
       ord <- order(data[, f])
       x <- data[, f][ord]
       y <- shap_contrib[, f][ord]
@@ -157,7 +191,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       plot(x2plot, y, pch = pch, xlab = f, col = col, xlim = x_lim, ylim = y_lim, ylab = ylab, ...)
       grid()
       if (plot_loess) {
-        # compress x to 3 digits, and mean-aggregate y
+        # compress x to 3 digits, and mean-aggredate y
         zz <- data.table(x = signif(x, 3), y)[, .(.N, y = mean(y)), x]
         if (nrow(zz) <= 5) {
           lines(zz$x, zz$y, col = col_loess)
@@ -182,108 +216,3 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
   }
   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

@@ -98,46 +98,34 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
     data      = dt$Feature,
     fontcolor = "black")
 
-  if (nrow(dt[Feature != "Leaf"]) != 0) {
-    edges <- DiagrammeR::create_edge_df(
-      from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
-      to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-      label = c(
-        dt[Feature != "Leaf", paste("<", Split)],
-        rep("", nrow(dt[Feature != "Leaf"]))
-      ),
-      style = c(
-        dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
-        dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
-      ),
-      rel   = "leading_to")
-  } else {
-    edges <- NULL
-  }
+  edges <- DiagrammeR::create_edge_df(
+    from  = match(dt[Feature != "Leaf", c(ID)] %>% rep(2), dt$ID),
+    to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
+    label = dt[Feature != "Leaf", paste("<", Split)] %>%
+            c(rep("", nrow(dt[Feature != "Leaf"]))),
+    style = dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")] %>%
+            c(dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]),
+    rel   = "leading_to")
 
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "node",
       attr  = c("color", "style", "fontname"),
       value = c("DimGray", "filled", "Helvetica")
-  )
-  graph <- DiagrammeR::add_global_graph_attrs(
-      graph = graph,
+      ) %>%
+    DiagrammeR::add_global_graph_attrs(
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica")
-  )
+      value = c("DimGray", "1.5", "vee", "Helvetica"))
 
   if (!render) return(invisible(graph))
 

R-package/R/xgb.save.R

@@ -42,7 +42,6 @@ xgb.save <- function(model, fname) {
          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

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

R-package/R/xgb.train.R

@@ -15,7 +15,7 @@
 #'
 #' 2. Booster Parameters
 #'
-#' 2.1. Parameters for Tree Booster
+#' 2.1. Parameter for Tree Booster
 #'
 #' \itemize{
 #'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
@@ -24,14 +24,12 @@
 #'   \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{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
 #'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
 #'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 #' }
 #'
-#' 2.2. Parameters for Linear Booster
+#' 2.2. Parameter for Linear Booster
 #'
 #' \itemize{
 #'   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -51,10 +49,10 @@
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
 #'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-#'     \item \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+#'     \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \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{aft_loss_distribution}: Probabilty 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.
@@ -126,24 +124,22 @@
 #' Parallelization is automatically enabled if \code{OpenMP} is present.
 #' Number of threads can also be manually specified via \code{nthread} parameter.
 #'
-#' The evaluation metric is chosen automatically by XGBoost (according to the objective)
+#' The evaluation metric is chosen automatically by Xgboost (according to the objective)
 #' when the \code{eval_metric} parameter is not provided.
 #' User may set one or several \code{eval_metric} parameters.
 #' Note that when using a customized metric, only this single metric can be used.
-#' The following is the list of built-in metrics for which XGBoost provides optimized implementation:
+#' The following is the list of built-in metrics for which Xgboost provides optimized implementation:
 #'   \itemize{
-#'      \item \code{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
-#'      \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
-#'      \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
+#'      \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
+#'      \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
+#'      \item \code{mlogloss} multiclass logloss. \url{http://wiki.fast.ai/index.php/Log_Loss}
 #'      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
 #'            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
 #'            Different threshold (e.g., 0.) could be specified as "error@0."
 #'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'      \item \code{mae} Mean absolute error
-#'      \item \code{mape} Mean absolute percentage error
-#'      \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+#'      \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
 #'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
+#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
 #'   }
 #'
 #' The following callbacks are automatically created when certain parameters are set:
@@ -171,6 +167,9 @@
 #'         explicitly passed.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
+#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+#'         which could further be used in \code{predict} method
+#'         (only available with early stopping).
 #'   \item \code{best_score} the best evaluation metric value during early stopping.
 #'         (only available with early stopping).
 #'   \item \code{feature_names} names of the training dataset features
@@ -192,8 +191,8 @@
 #' 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))
+#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+#' dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 #' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:

R-package/R/xgb.unserialize.R

@@ -1,21 +1,11 @@
 #' 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) {
+xgb.unserialize <- function(buffer) {
   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)
-  }
+  handle <- .Call(XGBoosterCreate_R, cachelist)
   tryCatch(
     .Call(XGBoosterUnserializeFromBuffer_R, handle, buffer),
     error = function(e) {

R-package/R/xgboost.R

@@ -9,8 +9,8 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
                     early_stopping_rounds = NULL, maximize = NULL,
                     save_period = NULL, save_name = "xgboost.model",
                     xgb_model = NULL, callbacks = list(), ...) {
-  merged <- check.booster.params(params, ...)
-  dtrain <- xgb.get.DMatrix(data, label, missing, weight, nthread = merged$nthread)
+
+  dtrain <- xgb.get.DMatrix(data, label, missing, weight)
 
   watchlist <- list(train = dtrain)
 
@@ -90,8 +90,12 @@ NULL
 #' @importFrom data.table setkey
 #' @importFrom data.table setkeyv
 #' @importFrom data.table setnames
-#' @importFrom jsonlite fromJSON
-#' @importFrom jsonlite toJSON
+#' @importFrom magrittr %>%
+#' @importFrom stringi stri_detect_regex
+#' @importFrom stringi stri_match_first_regex
+#' @importFrom stringi stri_replace_first_regex
+#' @importFrom stringi stri_replace_all_regex
+#' @importFrom stringi stri_split_regex
 #' @importFrom utils object.size str tail
 #' @importFrom stats predict
 #' @importFrom stats median

R-package/README.md

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

R-package/cleanup

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

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for xgboost 1.6-0.
+# Generated by GNU Autoconf 2.69 for xgboost 0.6-3.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -576,8 +576,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='1.6-0'
-PACKAGE_STRING='xgboost 1.6-0'
+PACKAGE_VERSION='0.6-3'
+PACKAGE_STRING='xgboost 0.6-3'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1195,7 +1195,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures xgboost 1.6-0 to adapt to many kinds of systems.
+\`configure' configures xgboost 0.6-3 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1257,7 +1257,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 1.6-0:";;
+     short | recursive ) echo "Configuration of xgboost 0.6-3:";;
    esac
   cat <<\_ACEOF
 
@@ -1336,7 +1336,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 1.6-0
+xgboost configure 0.6-3
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1479,7 +1479,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by xgboost $as_me 1.6-0, which was
+It was created by xgboost $as_me 0.6-3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2725,14 +2725,14 @@ main ()
   return 0;
 }
 _ACEOF
-  ${CC} -o conftest conftest.c ${CPPFLAGS} ${LDFLAGS} ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
+  ${CC} -o conftest conftest.c ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   { $as_echo "$as_me:${as_lineno-$LINENO}: result: ${ac_pkg_openmp}" >&5
 $as_echo "${ac_pkg_openmp}" >&6; }
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''
     OPENMP_LIB=''
     echo '*****************************************************************************************'
-    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
+    echo 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
     echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
     echo '             brew install libomp'
     echo '*****************************************************************************************'
@@ -3287,7 +3287,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by xgboost $as_me 1.6-0, which was
+This file was extended by xgboost $as_me 0.6-3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3340,7 +3340,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-xgboost config.status 1.6-0
+xgboost config.status 0.6-3
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 
@@ -3900,3 +3900,4 @@ if test -n "$ac_unrecognized_opts" && test "$enable_option_checking" != no; then
 $as_echo "$as_me: WARNING: unrecognized options: $ac_unrecognized_opts" >&2;}
 fi
 
+

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[1.6-0],[],[xgboost],[])
+AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
 # Use this line to set CC variable to a C compiler
 AC_PROG_CC
@@ -33,13 +33,13 @@ then
   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
+  ${CC} -o conftest conftest.c ${OPENMP_LIB} ${OPENMP_CXXFLAGS} 2>/dev/null && ./conftest && ac_pkg_openmp=yes
   AC_MSG_RESULT([${ac_pkg_openmp}])
   if test "${ac_pkg_openmp}" = no; then
     OPENMP_CXXFLAGS=''
     OPENMP_LIB=''
     echo '*****************************************************************************************'
-    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
+    echo 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
     echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
     echo '             brew install libomp'
     echo '*****************************************************************************************'
@@ -52,3 +52,4 @@ AC_SUBST(ENDIAN_FLAG)
 AC_SUBST(BACKTRACE_LIB)
 AC_CONFIG_FILES([src/Makevars])
 AC_OUTPUT
+

R-package/demo/00Index

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

R-package/demo/README.md

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

R-package/demo/basic_walkthrough.R

@@ -40,7 +40,7 @@ print("Train xgboost with verbose 2, also print information about tree")
 bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
                nthread = 2, objective = "binary:logistic", verbose = 2)
 
-# you can also specify data as file path to a LIBSVM format input
+# you can also specify data as file path to a LibSVM format input
 # since we do not have this file with us, the following line is just for illustration
 # bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nrounds = 2,objective = "binary:logistic")
 
@@ -63,7 +63,7 @@ print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
 # save model to R's raw vector
 raw <- xgb.save.raw(bst)
 # load binary model to R
-bst3 <- xgb.load.raw(raw)
+bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
 print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))

R-package/demo/create_sparse_matrix.R

@@ -2,17 +2,17 @@ require(xgboost)
 require(Matrix)
 require(data.table)
 if (!require(vcd)) {
-  install.packages('vcd') #Available in CRAN. Used for its dataset with categorical values.
+  install.packages('vcd') #Available in Cran. Used for its dataset with categorical values.
   require(vcd)
 }
-# According to its documentation, XGBoost works only on numbers.
+# According to its documentation, Xgboost works only on numbers.
 # Sometimes the dataset we have to work on have categorical data.
 # A categorical variable is one which have a fixed number of values. By example, if for each observation a variable called "Colour" can have only "red", "blue" or "green" as value, it is a categorical variable.
 #
 # In R, categorical variable is called Factor.
 # Type ?factor in console for more information.
 #
-# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in XGBoost.
+# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in Xgboost.
 # The method we are going to see is usually called "one hot encoding".
 
 #load Arthritis dataset in memory.
@@ -25,13 +25,13 @@ df <- data.table(Arthritis, keep.rownames = FALSE)
 cat("Print the dataset\n")
 print(df)
 
-# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
+# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values wich can be ordered, here: None > Some > Marked).
 cat("Structure of the dataset\n")
 str(df)
 
 # Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 
-# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independent values.
+# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as 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!).

R-package/demo/cross_validation.R

@@ -22,10 +22,10 @@ xgb.cv(param, dtrain, nrounds, nfold = 5,
        metrics = 'error', showsd = FALSE)
 
 ###
-# you can also do cross validation with customized loss function
+# you can also do cross validation with cutomized loss function
 # See custom_objective.R
 ##
-print ('running cross validation, with customized loss function')
+print ('running cross validation, with cutomsized loss function')
 
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/custom_objective.R

@@ -12,7 +12,7 @@ watchlist <- list(eval = dtest, train = dtrain)
 num_round <- 2
 
 # user define objective function, given prediction, return gradient and second order gradient
-# this is log likelihood loss
+# this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
   preds <- 1 / (1 + exp(-preds))
@@ -23,9 +23,9 @@ logregobj <- function(preds, dtrain) {
 
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make builtin evaluation metric not function properly
+# this may make buildin evalution metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
+# the buildin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/early_stopping.R

@@ -11,7 +11,7 @@ param <- list(max_depth = 2, eta = 1, nthread = 2, verbosity = 0)
 watchlist <- list(eval = dtest)
 num_round <- 20
 # user define objective function, given prediction, return gradient and second order gradient
-# this is log likelihood loss
+# this is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
   preds <- 1 / (1 + exp(-preds))
@@ -21,9 +21,9 @@ logregobj <- function(preds, dtrain) {
 }
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make builtin evaluation metric not function properly
+# this may make buildin evalution metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the builtin evaluation error assumes input is after logistic transformation
+# the buildin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")

R-package/demo/interaction_constraints.R

@@ -36,7 +36,7 @@ treeInteractions <- function(input_tree, input_max_depth) {
   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_trees_split <- split(interaction_trees, 1:nrow(interaction_trees))
   interaction_list <- lapply(interaction_trees_split, as.character)
 
   # Remove NAs (no parent interaction)
@@ -101,8 +101,8 @@ bst3_interactions <- treeInteractions(bst3_tree, 4)
 
 # Show monotonic constraints still apply by checking scores after incrementing V1
 x1 <- sort(unique(x[['V1']]))
-for (i in seq_along(x1)){
-  testdata <- copy(x[, - ('V1')])
+for (i in 1:length(x1)){
+  testdata <- copy(x[, -c('V1')])
   testdata[['V1']] <- x1[i]
   testdata <- testdata[, paste0('V', 1:10), with = FALSE]
   pred <- predict(bst3, as.matrix(testdata))

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

@@ -43,7 +43,6 @@ 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)
@@ -59,6 +58,5 @@ saveRDS(obj, 'my_object.rds')
 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/cb.early.stop.Rd

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

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

@@ -8,7 +8,7 @@ during its training.}
 cb.gblinear.history(sparse = FALSE)
 }
 \arguments{
-\item{sparse}{when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
+\item{sparse}{when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
 Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 when using the "thrifty" feature selector with fairly small number of top features
 selected per iteration.}
@@ -36,6 +36,7 @@ Callback function expects the following values to be set in its calling frame:
 #
 # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
 # without considering the 2nd order interactions:
+require(magrittr)
 x <- model.matrix(Species ~ .^2, iris)[,-1]
 colnames(x)
 dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
@@ -56,7 +57,7 @@ matplot(coef_path, type = 'l')
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
                  callbacks = list(cb.gblinear.history()))
-matplot(xgb.gblinear.history(bst), type = 'l')
+xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
 #  Componentwise boosting is known to have similar effect to Lasso regularization.
 # Try experimenting with various values of top_k, eta, nrounds,
 # as well as different feature_selectors.
@@ -65,7 +66,7 @@ matplot(xgb.gblinear.history(bst), type = 'l')
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
              callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
-matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
+xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
 
 
 #### Multiclass classification:
@@ -78,15 +79,15 @@ param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
                  callbacks = list(cb.gblinear.history()))
 # Will plot the coefficient paths separately for each class:
-matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
-matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
-matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
+xgb.gblinear.history(bst, class_index = 0) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 1) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 2) \%>\% matplot(type = 'l')
 
 # CV:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
               callbacks = list(cb.gblinear.history(FALSE)))
-# 1st fold of 1st class
-matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
+# 1st forld of 1st class
+xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
 
 }
 \seealso{

R-package/man/getinfo.Rd

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

R-package/man/normalize.Rd

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

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

@@ -17,8 +17,6 @@
   predinteraction = FALSE,
   reshape = FALSE,
   training = FALSE,
-  iterationrange = NULL,
-  strict_shape = FALSE,
   ...
 )
 
@@ -27,11 +25,7 @@
 \arguments{
 \item{object}{Object of class \code{xgb.Booster} or \code{xgb.Booster.handle}}
 
-\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, \code{dgRMatrix}, \code{dsparseVector},
-       local data file or \code{xgb.DMatrix}.
-
-       For single-row predictions on sparse data, it's recommended to use CSR format. If passing
-       a sparse vector, it will take it as a row vector.}
+\item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or \code{xgb.DMatrix}.}
 
 \item{missing}{Missing is only used when input is dense matrix. Pick a float value that represents
 missing values in data (e.g., sometimes 0 or some other extreme value is used).}
@@ -40,7 +34,8 @@ missing values in data (e.g., sometimes 0 or some other extreme value is used).}
 sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
 logistic regression would result in predictions for log-odds instead of probabilities.}
 
-\item{ntreelimit}{Deprecated, use \code{iterationrange} instead.}
+\item{ntreelimit}{limit the number of model's trees or boosting iterations used in prediction (see Details).
+It will use all the trees by default (\code{NULL} value).}
 
 \item{predleaf}{whether predict leaf index.}
 
@@ -57,20 +52,10 @@ 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 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.
@@ -91,19 +76,18 @@ two dimensions. The "+ 1" columns corresponds to bias. Summing this array along
 produce practically the same result as predict with \code{predcontrib = TRUE}.
 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 such an array.
-
-When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
-normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
-
-For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
-For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
-For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
 }
 \description{
 Predicted values based on either xgboost model or model handle object.
 }
 \details{
-Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
+Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
+and it is not necessarily equal to the number of trees in a model.
+E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
+But for multiclass classification, while there are multiple trees per iteration,
+\code{ntreelimit} limits the number of boosting iterations.
+
+Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
 since gblinear doesn't keep its boosting history.
 
 One possible practical applications of the \code{predleaf} option is to use the model
@@ -136,7 +120,7 @@ bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 # use all trees by default
 pred <- predict(bst, test$data)
 # use only the 1st tree
-pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
+pred1 <- predict(bst, test$data, ntreelimit = 1)
 
 # Predicting tree leafs:
 # the result is an nsamples X ntrees matrix
@@ -188,9 +172,25 @@ 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))
+pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
 sum(pred5 != lb)/length(lb)
 
+
+## random forest-like model of 25 trees for binary classification:
+
+set.seed(11)
+bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
+               nthread = 2, nrounds = 1, objective = "binary:logistic",
+               num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
+# Inspect the prediction error vs number of trees:
+lb <- test$label
+dtest <- xgb.DMatrix(test$data, label=lb)
+err <- sapply(1:25, function(n) {
+  pred <- predict(bst, dtest, ntreelimit=n)
+  sum((pred > 0.5) != lb)/length(lb)
+})
+plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
+
 }
 \references{
 Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}

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

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

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

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

R-package/man/setinfo.Rd

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

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

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

R-package/man/xgb.DMatrix.Rd

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

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

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

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

@@ -29,7 +29,7 @@ Joaquin Quinonero Candela)}
 
 International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
 
-\url{https://research.facebook.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
+\url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
 
 Extract explaining the method:
 
@@ -59,8 +59,8 @@ a rule on certain features."
 \examples{
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+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, silent=1, objective='binary:logistic')
 nrounds = 4

R-package/man/xgb.cv.Rd

@@ -70,8 +70,6 @@ from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callb
   \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
@@ -135,7 +133,9 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
         parameter or randomly generated.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
-  \item \code{best_ntreelimit} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
+  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+        which could further be used in \code{predict} method
+        (only available with early stopping).
   \item \code{pred} CV prediction values available when \code{prediction} is set.
         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
   \item \code{models} a list of the CV folds' models. It is only available with the explicit
@@ -154,11 +154,11 @@ The cross-validation process is then repeated \code{nrounds} times, with each of
 
 All observations are used for both training and validation.
 
-Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
+Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
                   max_depth = 3, eta = 1, objective = "binary:logistic")
 print(cv)

R-package/man/xgb.dump.Rd

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

R-package/man/xgb.load.Rd

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

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

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

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

@@ -87,7 +87,7 @@ more than 5 distinct values.}
 
 \item{which}{whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.}
 
-\item{plot}{whether a plot should be drawn. If FALSE, only a list of matrices is returned.}
+\item{plot}{whether a plot should be drawn. If FALSE, only a lits of matrices is returned.}
 
 \item{...}{other parameters passed to \code{plot}.}
 }
@@ -131,7 +131,6 @@ bst <- xgboost(agaricus.train$data, agaricus.train$label, nrounds = 50,
 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
@@ -150,7 +149,6 @@ 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
 
 }
 \references{

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

@@ -1,78 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.ggplot.R, R/xgb.plot.shap.R
-\name{xgb.ggplot.shap.summary}
-\alias{xgb.ggplot.shap.summary}
-\alias{xgb.plot.shap.summary}
-\title{SHAP contribution dependency summary plot}
-\usage{
-xgb.ggplot.shap.summary(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 10,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL
-)
-
-xgb.plot.shap.summary(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 10,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL
-)
-}
-\arguments{
-\item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
-
-\item{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}.}
-
-\item{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.}
-
-\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.}
-
-\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-or \code{features} is missing.}
-
-\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.}
-
-\item{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.}
-
-\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.}
-
-\item{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.}
-}
-\value{
-A \code{ggplot2} object.
-}
-\description{
-Compare SHAP contributions of different features.
-}
-\details{
-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.
-}
-\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}
-}

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

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

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

@@ -1,55 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.plot.shap.R
-\name{xgb.shap.data}
-\alias{xgb.shap.data}
-\title{Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-Internal utility function.}
-\usage{
-xgb.shap.data(
-  data,
-  shap_contrib = NULL,
-  features = NULL,
-  top_n = 1,
-  model = NULL,
-  trees = NULL,
-  target_class = NULL,
-  approxcontrib = FALSE,
-  subsample = NULL,
-  max_observations = 1e+05
-)
-}
-\arguments{
-\item{data}{data as a \code{matrix} or \code{dgCMatrix}.}
-
-\item{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}.}
-
-\item{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.}
-
-\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.}
-
-\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib}
-or \code{features} is missing.}
-
-\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.}
-
-\item{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.}
-
-\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.}
-
-\item{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.}
-}
-\value{
-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.
-}
-\description{
-Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc.
-Internal utility function.
-}
-\keyword{internal}

R-package/man/xgb.train.Rd

@@ -54,7 +54,7 @@ xgboost(
 
 2. Booster Parameters
 
-2.1. Parameters for Tree Booster
+2.1. Parameter for Tree Booster
 
 \itemize{
   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
@@ -63,14 +63,12 @@ xgboost(
   \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{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 }
 
-2.2. Parameters for Linear Booster
+2.2. Parameter for Linear Booster
 
 \itemize{
   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -90,10 +88,10 @@ xgboost(
     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
-    \item \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+    \item \code{count:poisson}: poisson regression for count data, output mean of poisson distribution. \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{aft_loss_distribution}: Probabilty 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.
@@ -187,6 +185,9 @@ An object of class \code{xgb.Booster} with the following elements:
         explicitly passed.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
+  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
+        which could further be used in \code{predict} method
+        (only available with early stopping).
   \item \code{best_score} the best evaluation metric value during early stopping.
         (only available with early stopping).
   \item \code{feature_names} names of the training dataset features
@@ -208,24 +209,22 @@ than the \code{xgboost} interface.
 Parallelization is automatically enabled if \code{OpenMP} is present.
 Number of threads can also be manually specified via \code{nthread} parameter.
 
-The evaluation metric is chosen automatically by XGBoost (according to the objective)
+The evaluation metric is chosen automatically by Xgboost (according to the objective)
 when the \code{eval_metric} parameter is not provided.
 User may set one or several \code{eval_metric} parameters.
 Note that when using a customized metric, only this single metric can be used.
-The following is the list of built-in metrics for which XGBoost provides optimized implementation:
+The following is the list of built-in metrics for which Xgboost provides optimized implementation:
   \itemize{
-     \item \code{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
-     \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
-     \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
+     \item \code{rmse} root mean square error. \url{http://en.wikipedia.org/wiki/Root_mean_square_error}
+     \item \code{logloss} negative log-likelihood. \url{http://en.wikipedia.org/wiki/Log-likelihood}
+     \item \code{mlogloss} multiclass logloss. \url{http://wiki.fast.ai/index.php/Log_Loss}
      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
            Different threshold (e.g., 0.) could be specified as "error@0."
      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-     \item \code{mae} Mean absolute error
-     \item \code{mape} Mean absolute percentage error
-     \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+     \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-     \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
+     \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
   }
 
 The following callbacks are automatically created when certain parameters are set:
@@ -241,8 +240,8 @@ The following callbacks are automatically created when certain parameters are se
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:

R-package/man/xgb.unserialize.Rd

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

R-package/man/xgbConfig.Rd

@@ -1,39 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xgb.config.R
-\name{xgb.set.config, xgb.get.config}
-\alias{xgb.set.config, xgb.get.config}
-\alias{xgb.set.config}
-\alias{xgb.get.config}
-\title{Set and get global configuration}
-\usage{
-xgb.set.config(...)
-
-xgb.get.config()
-}
-\arguments{
-\item{...}{List of parameters to be set, as keyword arguments}
-}
-\value{
-\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.
-}
-\description{
-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}).
-}
-\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)
-}

R-package/src/Makevars.in

@@ -8,7 +8,7 @@ CXX_STD = CXX14
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\
            -DDMLC_LOG_CUSTOMIZE=1 -DXGBOOST_CUSTOMIZE_LOGGER=1\
-           -DRABIT_CUSTOMIZE_MSG_
+           -DRABIT_CUSTOMIZE_MSG_ -DRABIT_STRICT_CXX98_
 
 # disable the use of thread_local for 32 bit windows:
 ifeq ($(R_OSTYPE)$(WIN),windows)
@@ -17,9 +17,8 @@ endif
 $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
-PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ @ENDIAN_FLAG@ -pthread $(CXX_VISIBILITY)
+PKG_CXXFLAGS= @OPENMP_CXXFLAGS@ @ENDIAN_FLAG@ -pthread
 PKG_LIBS = @OPENMP_CXXFLAGS@ @OPENMP_LIB@ @ENDIAN_FLAG@ @BACKTRACE_LIB@ -pthread
-OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o \
-         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o \
-         $(PKGROOT)/rabit/src/engine.o $(PKGROOT)/rabit/src/rabit_c_api.o \
-         $(PKGROOT)/rabit/src/allreduce_base.o
+OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o\
+         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o\
+         $(PKGROOT)/rabit/src/engine_empty.o $(PKGROOT)/rabit/src/c_api.o

R-package/src/Makevars.win

@@ -3,7 +3,7 @@ PKGROOT=./
 ENABLE_STD_THREAD=0
 # _*_ mode: Makefile; _*_
 
-# This file is only used for Windows compilation from GitHub
+# This file is only used for windows compilation from github
 # It will be replaced with Makevars.in for the CRAN version
 .PHONY: all xgblib
 all: $(SHLIB)
@@ -20,7 +20,7 @@ CXX_STD = CXX14
 XGB_RFLAGS = -DXGBOOST_STRICT_R_MODE=1 -DDMLC_LOG_BEFORE_THROW=0\
            -DDMLC_ENABLE_STD_THREAD=$(ENABLE_STD_THREAD) -DDMLC_DISABLE_STDIN=1\
            -DDMLC_LOG_CUSTOMIZE=1 -DXGBOOST_CUSTOMIZE_LOGGER=1\
-           -DRABIT_CUSTOMIZE_MSG_
+           -DRABIT_CUSTOMIZE_MSG_ -DRABIT_STRICT_CXX98_
 
 # disable the use of thread_local for 32 bit windows:
 ifeq ($(R_OSTYPE)$(WIN),windows)
@@ -31,9 +31,8 @@ $(foreach v, $(XGB_RFLAGS), $(warning $(v)))
 PKG_CPPFLAGS=  -I$(PKGROOT)/include -I$(PKGROOT)/dmlc-core/include -I$(PKGROOT)/rabit/include -I$(PKGROOT) $(XGB_RFLAGS)
 PKG_CXXFLAGS= $(SHLIB_OPENMP_CXXFLAGS) $(SHLIB_PTHREAD_FLAGS)
 PKG_LIBS = $(SHLIB_OPENMP_CXXFLAGS) $(SHLIB_PTHREAD_FLAGS)
-OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o \
-         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o \
-         $(PKGROOT)/rabit/src/engine.o $(PKGROOT)/rabit/src/rabit_c_api.o \
-         $(PKGROOT)/rabit/src/allreduce_base.o
+OBJECTS= ./xgboost_R.o ./xgboost_custom.o ./xgboost_assert.o ./init.o\
+         $(PKGROOT)/amalgamation/xgboost-all0.o $(PKGROOT)/amalgamation/dmlc-minimum0.o\
+         $(PKGROOT)/rabit/src/engine_empty.o $(PKGROOT)/rabit/src/c_api.o
 
 $(OBJECTS) : xgblib

R-package/src/init.c

@@ -9,7 +9,6 @@
 #include <Rinternals.h>
 #include <stdlib.h>
 #include <R_ext/Rdynload.h>
-#include <R_ext/Visibility.h>
 
 /* FIXME:
 Check these declarations against the C/Fortran source code.
@@ -18,81 +17,69 @@ Check these declarations against the C/Fortran source code.
 /* .Call calls */
 extern SEXP XGBoosterBoostOneIter_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterCreate_R(SEXP);
-extern SEXP XGBoosterCreateInEmptyObj_R(SEXP, SEXP);
 extern SEXP XGBoosterDumpModel_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterEvalOneIter_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGBoosterGetAttrNames_R(SEXP);
 extern SEXP XGBoosterGetAttr_R(SEXP, SEXP);
 extern SEXP XGBoosterLoadModelFromRaw_R(SEXP, SEXP);
-extern SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP config);
 extern SEXP XGBoosterLoadModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSaveJsonConfig_R(SEXP handle);
 extern SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value);
 extern SEXP XGBoosterSerializeToBuffer_R(SEXP handle);
 extern SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw);
+extern SEXP XGBoosterModelToRaw_R(SEXP);
 extern SEXP XGBoosterPredict_R(SEXP, SEXP, SEXP, SEXP, SEXP);
-extern SEXP XGBoosterPredictFromDMatrix_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSaveModel_R(SEXP, SEXP);
 extern SEXP XGBoosterSetAttr_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterSetParam_R(SEXP, SEXP, SEXP);
 extern SEXP XGBoosterUpdateOneIter_R(SEXP, SEXP, SEXP);
 extern SEXP XGCheckNullPtr_R(SEXP);
-extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP, SEXP);
-extern SEXP XGDMatrixCreateFromCSR_R(SEXP, SEXP, SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromCSC_R(SEXP, SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixCreateFromFile_R(SEXP, SEXP);
-extern SEXP XGDMatrixCreateFromMat_R(SEXP, SEXP, SEXP);
+extern SEXP XGDMatrixCreateFromMat_R(SEXP, SEXP);
 extern SEXP XGDMatrixGetInfo_R(SEXP, SEXP);
 extern SEXP XGDMatrixNumCol_R(SEXP);
 extern SEXP XGDMatrixNumRow_R(SEXP);
 extern SEXP XGDMatrixSaveBinary_R(SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixSetInfo_R(SEXP, SEXP, SEXP);
 extern SEXP XGDMatrixSliceDMatrix_R(SEXP, SEXP);
-extern SEXP XGBSetGlobalConfig_R(SEXP);
-extern SEXP XGBGetGlobalConfig_R();
-extern SEXP XGBoosterFeatureScore_R(SEXP, SEXP);
 
 static const R_CallMethodDef CallEntries[] = {
   {"XGBoosterBoostOneIter_R",     (DL_FUNC) &XGBoosterBoostOneIter_R,     4},
   {"XGBoosterCreate_R",           (DL_FUNC) &XGBoosterCreate_R,           1},
-  {"XGBoosterCreateInEmptyObj_R", (DL_FUNC) &XGBoosterCreateInEmptyObj_R, 2},
   {"XGBoosterDumpModel_R",        (DL_FUNC) &XGBoosterDumpModel_R,        4},
   {"XGBoosterEvalOneIter_R",      (DL_FUNC) &XGBoosterEvalOneIter_R,      4},
   {"XGBoosterGetAttrNames_R",     (DL_FUNC) &XGBoosterGetAttrNames_R,     1},
   {"XGBoosterGetAttr_R",          (DL_FUNC) &XGBoosterGetAttr_R,          2},
   {"XGBoosterLoadModelFromRaw_R", (DL_FUNC) &XGBoosterLoadModelFromRaw_R, 2},
-  {"XGBoosterSaveModelToRaw_R",   (DL_FUNC) &XGBoosterSaveModelToRaw_R,   2},
   {"XGBoosterLoadModel_R",        (DL_FUNC) &XGBoosterLoadModel_R,        2},
   {"XGBoosterSaveJsonConfig_R",   (DL_FUNC) &XGBoosterSaveJsonConfig_R,   1},
   {"XGBoosterLoadJsonConfig_R",   (DL_FUNC) &XGBoosterLoadJsonConfig_R,   2},
   {"XGBoosterSerializeToBuffer_R",     (DL_FUNC) &XGBoosterSerializeToBuffer_R,     1},
   {"XGBoosterUnserializeFromBuffer_R", (DL_FUNC) &XGBoosterUnserializeFromBuffer_R, 2},
+  {"XGBoosterModelToRaw_R",       (DL_FUNC) &XGBoosterModelToRaw_R,       1},
   {"XGBoosterPredict_R",          (DL_FUNC) &XGBoosterPredict_R,          5},
-  {"XGBoosterPredictFromDMatrix_R", (DL_FUNC) &XGBoosterPredictFromDMatrix_R, 3},
   {"XGBoosterSaveModel_R",        (DL_FUNC) &XGBoosterSaveModel_R,        2},
   {"XGBoosterSetAttr_R",          (DL_FUNC) &XGBoosterSetAttr_R,          3},
   {"XGBoosterSetParam_R",         (DL_FUNC) &XGBoosterSetParam_R,         3},
   {"XGBoosterUpdateOneIter_R",    (DL_FUNC) &XGBoosterUpdateOneIter_R,    3},
   {"XGCheckNullPtr_R",            (DL_FUNC) &XGCheckNullPtr_R,            1},
-  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    5},
-  {"XGDMatrixCreateFromCSR_R",    (DL_FUNC) &XGDMatrixCreateFromCSR_R,    5},
+  {"XGDMatrixCreateFromCSC_R",    (DL_FUNC) &XGDMatrixCreateFromCSC_R,    4},
   {"XGDMatrixCreateFromFile_R",   (DL_FUNC) &XGDMatrixCreateFromFile_R,   2},
-  {"XGDMatrixCreateFromMat_R",    (DL_FUNC) &XGDMatrixCreateFromMat_R,    3},
+  {"XGDMatrixCreateFromMat_R",    (DL_FUNC) &XGDMatrixCreateFromMat_R,    2},
   {"XGDMatrixGetInfo_R",          (DL_FUNC) &XGDMatrixGetInfo_R,          2},
   {"XGDMatrixNumCol_R",           (DL_FUNC) &XGDMatrixNumCol_R,           1},
   {"XGDMatrixNumRow_R",           (DL_FUNC) &XGDMatrixNumRow_R,           1},
   {"XGDMatrixSaveBinary_R",       (DL_FUNC) &XGDMatrixSaveBinary_R,       3},
   {"XGDMatrixSetInfo_R",          (DL_FUNC) &XGDMatrixSetInfo_R,          3},
   {"XGDMatrixSliceDMatrix_R",     (DL_FUNC) &XGDMatrixSliceDMatrix_R,     2},
-  {"XGBSetGlobalConfig_R",        (DL_FUNC) &XGBSetGlobalConfig_R,        1},
-  {"XGBGetGlobalConfig_R",        (DL_FUNC) &XGBGetGlobalConfig_R,        0},
-  {"XGBoosterFeatureScore_R",     (DL_FUNC) &XGBoosterFeatureScore_R,     2},
   {NULL, NULL, 0}
 };
 
 #if defined(_WIN32)
 __declspec(dllexport)
 #endif  // defined(_WIN32)
-void attribute_visible R_init_xgboost(DllInfo *dll) {
+void R_init_xgboost(DllInfo *dll) {
   R_registerRoutines(dll, NULL, CallEntries, NULL, NULL);
   R_useDynamicSymbols(dll, FALSE);
 }

R-package/src/xgboost-win.def

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

R-package/src/xgboost_R.cc

@@ -1,23 +1,13 @@
-/**
- * Copyright 2014-2022 by XGBoost Contributors
- */
-#include <dmlc/common.h>
+// Copyright (c) 2014 by Contributors
+#include <dmlc/logging.h>
 #include <dmlc/omp.h>
 #include <xgboost/c_api.h>
-#include <xgboost/data.h>
-#include <xgboost/generic_parameters.h>
-#include <xgboost/logging.h>
-
-#include <cstdio>
-#include <cstring>
-#include <sstream>
+#include <vector>
 #include <string>
 #include <utility>
-#include <vector>
-
-#include "../../src/c_api/c_api_error.h"
-#include "../../src/common/threading_utils.h"
-
+#include <cstring>
+#include <cstdio>
+#include <sstream>
 #include "./xgboost_R.h"
 
 /*!
@@ -44,27 +34,14 @@
     error(XGBGetLastError());                   \
   }
 
-using dmlc::BeginPtr;
 
-xgboost::GenericParameter const *BoosterCtx(BoosterHandle handle) {
-  CHECK_HANDLE();
-  auto *learner = static_cast<xgboost::Learner *>(handle);
-  CHECK(learner);
-  return learner->Ctx();
-}
+using namespace dmlc;
 
-xgboost::GenericParameter const *DMatrixCtx(DMatrixHandle handle) {
-  CHECK_HANDLE();
-  auto p_m = static_cast<std::shared_ptr<xgboost::DMatrix> *>(handle);
-  CHECK(p_m);
-  return p_m->get()->Ctx();
-}
-
-XGB_DLL SEXP XGCheckNullPtr_R(SEXP handle) {
+SEXP XGCheckNullPtr_R(SEXP handle) {
   return ScalarLogical(R_ExternalPtrAddr(handle) == NULL);
 }
 
-XGB_DLL void _DMatrixFinalizer(SEXP ext) {
+void _DMatrixFinalizer(SEXP ext) {
   R_API_BEGIN();
   if (R_ExternalPtrAddr(ext) == NULL) return;
   CHECK_CALL(XGDMatrixFree(R_ExternalPtrAddr(ext)));
@@ -72,22 +49,7 @@ XGB_DLL void _DMatrixFinalizer(SEXP ext) {
   R_API_END();
 }
 
-XGB_DLL SEXP XGBSetGlobalConfig_R(SEXP json_str) {
-  R_API_BEGIN();
-  CHECK_CALL(XGBSetGlobalConfig(CHAR(asChar(json_str))));
-  R_API_END();
-  return R_NilValue;
-}
-
-XGB_DLL SEXP XGBGetGlobalConfig_R() {
-  const char* json_str;
-  R_API_BEGIN();
-  CHECK_CALL(XGBGetGlobalConfig(&json_str));
-  R_API_END();
-  return mkString(json_str);
-}
-
-XGB_DLL SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
+SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
   SEXP ret;
   R_API_BEGIN();
   DMatrixHandle handle;
@@ -99,7 +61,8 @@ XGB_DLL SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
+SEXP XGDMatrixCreateFromMat_R(SEXP mat,
+                              SEXP missing) {
   SEXP ret;
   R_API_BEGIN();
   SEXP dim = getAttrib(mat, R_DimSymbol);
@@ -114,16 +77,14 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
     din = REAL(mat);
   }
   std::vector<float> data(nrow * ncol);
-  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
-
-  xgboost::common::ParallelFor(nrow, threads, [&](xgboost::omp_ulong i) {
+  #pragma omp parallel for schedule(static)
+  for (omp_ulong i = 0; i < nrow; ++i) {
     for (size_t j = 0; j < ncol; ++j) {
-      data[i * ncol + j] = is_int ? static_cast<float>(iin[i + nrow * j]) : din[i + nrow * j];
+      data[i * ncol +j] = is_int ? static_cast<float>(iin[i + nrow * j]) : din[i + nrow * j];
     }
-  });
+  }
   DMatrixHandle handle;
-  CHECK_CALL(XGDMatrixCreateFromMat_omp(BeginPtr(data), nrow, ncol,
-                                        asReal(missing), &handle, threads));
+  CHECK_CALL(XGDMatrixCreateFromMat(BeginPtr(data), nrow, ncol, asReal(missing), &handle));
   ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
   R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
   R_API_END();
@@ -131,8 +92,10 @@ XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat, SEXP missing, SEXP n_threads) {
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
-                                      SEXP num_row, SEXP n_threads) {
+SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
+                              SEXP indices,
+                              SEXP data,
+                              SEXP num_row) {
   SEXP ret;
   R_API_BEGIN();
   const int *p_indptr = INTEGER(indptr);
@@ -148,11 +111,11 @@ XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
   for (size_t i = 0; i < nindptr; ++i) {
     col_ptr_[i] = static_cast<size_t>(p_indptr[i]);
   }
-  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
-  xgboost::common::ParallelFor(ndata, threads, [&](xgboost::omp_ulong i) {
+  #pragma omp parallel for schedule(static)
+  for (int64_t i = 0; i < static_cast<int64_t>(ndata); ++i) {
     indices_[i] = static_cast<unsigned>(p_indices[i]);
     data_[i] = static_cast<float>(p_data[i]);
-  });
+  }
   DMatrixHandle handle;
   CHECK_CALL(XGDMatrixCreateFromCSCEx(BeginPtr(col_ptr_), BeginPtr(indices_),
                                       BeginPtr(data_), nindptr, ndata,
@@ -164,40 +127,7 @@ XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data,
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data,
-                                      SEXP num_col, SEXP n_threads) {
-  SEXP ret;
-  R_API_BEGIN();
-  const int *p_indptr = INTEGER(indptr);
-  const int *p_indices = INTEGER(indices);
-  const double *p_data = REAL(data);
-  size_t nindptr = static_cast<size_t>(length(indptr));
-  size_t ndata = static_cast<size_t>(length(data));
-  size_t ncol = static_cast<size_t>(INTEGER(num_col)[0]);
-  std::vector<size_t> row_ptr_(nindptr);
-  std::vector<unsigned> indices_(ndata);
-  std::vector<float> data_(ndata);
-
-  for (size_t i = 0; i < nindptr; ++i) {
-    row_ptr_[i] = static_cast<size_t>(p_indptr[i]);
-  }
-  int32_t threads = xgboost::common::OmpGetNumThreads(asInteger(n_threads));
-  xgboost::common::ParallelFor(ndata, threads, [&](xgboost::omp_ulong i) {
-    indices_[i] = static_cast<unsigned>(p_indices[i]);
-    data_[i] = static_cast<float>(p_data[i]);
-  });
-  DMatrixHandle handle;
-  CHECK_CALL(XGDMatrixCreateFromCSREx(BeginPtr(row_ptr_), BeginPtr(indices_),
-                                      BeginPtr(data_), nindptr, ndata,
-                                      ncol, &handle));
-  ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
-  R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
-  R_API_END();
-  UNPROTECT(1);
-  return ret;
-}
-
-XGB_DLL SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
+SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
   SEXP ret;
   R_API_BEGIN();
   int len = length(idxset);
@@ -217,7 +147,7 @@ XGB_DLL SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
+SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixSaveBinary(R_ExternalPtrAddr(handle),
                                  CHAR(asChar(fname)),
@@ -226,30 +156,34 @@ XGB_DLL SEXP XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
+SEXP XGDMatrixSetInfo_R(SEXP handle, SEXP field, SEXP array) {
   R_API_BEGIN();
   int len = length(array);
   const char *name = CHAR(asChar(field));
-  auto ctx = DMatrixCtx(R_ExternalPtrAddr(handle));
   if (!strcmp("group", name)) {
     std::vector<unsigned> vec(len);
-    xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
+    #pragma omp parallel for schedule(static)
+    for (int i = 0; i < len; ++i) {
       vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
-    });
-    CHECK_CALL(
-        XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
+    }
+    CHECK_CALL(XGDMatrixSetUIntInfo(R_ExternalPtrAddr(handle),
+                                    CHAR(asChar(field)),
+                                    BeginPtr(vec), len));
   } else {
     std::vector<float> vec(len);
-    xgboost::common::ParallelFor(len, ctx->Threads(),
-                                 [&](xgboost::omp_ulong i) { vec[i] = REAL(array)[i]; });
-    CHECK_CALL(
-        XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle), CHAR(asChar(field)), BeginPtr(vec), len));
+    #pragma omp parallel for schedule(static)
+    for (int i = 0; i < len; ++i) {
+      vec[i] = REAL(array)[i];
+    }
+    CHECK_CALL(XGDMatrixSetFloatInfo(R_ExternalPtrAddr(handle),
+                                     CHAR(asChar(field)),
+                                     BeginPtr(vec), len));
   }
   R_API_END();
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
+SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong olen;
@@ -267,7 +201,7 @@ XGB_DLL SEXP XGDMatrixGetInfo_R(SEXP handle, SEXP field) {
   return ret;
 }
 
-XGB_DLL SEXP XGDMatrixNumRow_R(SEXP handle) {
+SEXP XGDMatrixNumRow_R(SEXP handle) {
   bst_ulong nrow;
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixNumRow(R_ExternalPtrAddr(handle), &nrow));
@@ -275,7 +209,7 @@ XGB_DLL SEXP XGDMatrixNumRow_R(SEXP handle) {
   return ScalarInteger(static_cast<int>(nrow));
 }
 
-XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle) {
+SEXP XGDMatrixNumCol_R(SEXP handle) {
   bst_ulong ncol;
   R_API_BEGIN();
   CHECK_CALL(XGDMatrixNumCol(R_ExternalPtrAddr(handle), &ncol));
@@ -290,7 +224,7 @@ void _BoosterFinalizer(SEXP ext) {
   R_ClearExternalPtr(ext);
 }
 
-XGB_DLL SEXP XGBoosterCreate_R(SEXP dmats) {
+SEXP XGBoosterCreate_R(SEXP dmats) {
   SEXP ret;
   R_API_BEGIN();
   int len = length(dmats);
@@ -307,22 +241,7 @@ XGB_DLL SEXP XGBoosterCreate_R(SEXP dmats) {
   return ret;
 }
 
-XGB_DLL SEXP XGBoosterCreateInEmptyObj_R(SEXP dmats, SEXP R_handle) {
-  R_API_BEGIN();
-  int len = length(dmats);
-  std::vector<void*> dvec;
-  for (int i = 0; i < len; ++i) {
-    dvec.push_back(R_ExternalPtrAddr(VECTOR_ELT(dmats, i)));
-  }
-  BoosterHandle handle;
-  CHECK_CALL(XGBoosterCreate(BeginPtr(dvec), dvec.size(), &handle));
-  R_SetExternalPtrAddr(R_handle, handle);
-  R_RegisterCFinalizerEx(R_handle, _BoosterFinalizer, TRUE);
-  R_API_END();
-  return R_NilValue;
-}
-
-XGB_DLL SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
+SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterSetParam(R_ExternalPtrAddr(handle),
                                CHAR(asChar(name)),
@@ -331,7 +250,7 @@ XGB_DLL SEXP XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
+SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterUpdateOneIter(R_ExternalPtrAddr(handle),
                                   asInteger(iter),
@@ -340,17 +259,17 @@ XGB_DLL SEXP XGBoosterUpdateOneIter_R(SEXP handle, SEXP iter, SEXP dtrain) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP hess) {
+SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP hess) {
   R_API_BEGIN();
   CHECK_EQ(length(grad), length(hess))
       << "gradient and hess must have same length";
   int len = length(grad);
   std::vector<float> tgrad(len), thess(len);
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong j) {
+  #pragma omp parallel for schedule(static)
+  for (int j = 0; j < len; ++j) {
     tgrad[j] = REAL(grad)[j];
     thess[j] = REAL(hess)[j];
-  });
+  }
   CHECK_CALL(XGBoosterBoostOneIter(R_ExternalPtrAddr(handle),
                                  R_ExternalPtrAddr(dtrain),
                                  BeginPtr(tgrad), BeginPtr(thess),
@@ -359,7 +278,7 @@ XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP h
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
+SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames) {
   const char *ret;
   R_API_BEGIN();
   CHECK_EQ(length(dmats), length(evnames))
@@ -384,8 +303,8 @@ XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evn
   return mkString(ret);
 }
 
-XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
-                                SEXP ntree_limit, SEXP training) {
+SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
+                        SEXP ntree_limit, SEXP training) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong olen;
@@ -405,59 +324,36 @@ XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
   return ret;
 }
 
-XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_config)  {
-  SEXP r_out_shape;
-  SEXP r_out_result;
-  SEXP r_out;
-
-  R_API_BEGIN();
-  char const *c_json_config = CHAR(asChar(json_config));
-
-  bst_ulong out_dim;
-  bst_ulong const *out_shape;
-  float const *out_result;
-  CHECK_CALL(XGBoosterPredictFromDMatrix(R_ExternalPtrAddr(handle),
-                                         R_ExternalPtrAddr(dmat), c_json_config,
-                                         &out_shape, &out_dim, &out_result));
-
-  r_out_shape = PROTECT(allocVector(INTSXP, out_dim));
-  size_t len = 1;
-  for (size_t i = 0; i < out_dim; ++i) {
-    INTEGER(r_out_shape)[i] = out_shape[i];
-    len *= out_shape[i];
-  }
-  r_out_result = PROTECT(allocVector(REALSXP, len));
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
-    REAL(r_out_result)[i] = out_result[i];
-  });
-
-  r_out = PROTECT(allocVector(VECSXP, 2));
-
-  SET_VECTOR_ELT(r_out, 0, r_out_shape);
-  SET_VECTOR_ELT(r_out, 1, r_out_result);
-
-  R_API_END();
-  UNPROTECT(3);
-
-  return r_out;
-}
-
-XGB_DLL SEXP XGBoosterLoadModel_R(SEXP handle, SEXP fname) {
+SEXP XGBoosterLoadModel_R(SEXP handle, SEXP fname) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadModel(R_ExternalPtrAddr(handle), CHAR(asChar(fname))));
   R_API_END();
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
+SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterSaveModel(R_ExternalPtrAddr(handle), CHAR(asChar(fname))));
   R_API_END();
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
+SEXP XGBoosterModelToRaw_R(SEXP handle) {
+  SEXP ret;
+  R_API_BEGIN();
+  bst_ulong olen;
+  const char *raw;
+  CHECK_CALL(XGBoosterGetModelRaw(R_ExternalPtrAddr(handle), &olen, &raw));
+  ret = PROTECT(allocVector(RAWSXP, olen));
+  if (olen != 0) {
+    memcpy(RAW(ret), raw, olen);
+  }
+  R_API_END();
+  UNPROTECT(1);
+  return ret;
+}
+
+SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadModelFromBuffer(R_ExternalPtrAddr(handle),
                                           RAW(raw),
@@ -466,23 +362,7 @@ XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP json_config) {
-  SEXP ret;
-  R_API_BEGIN();
-  bst_ulong olen;
-  char const *c_json_config = CHAR(asChar(json_config));
-  char const *raw;
-  CHECK_CALL(XGBoosterSaveModelToBuffer(R_ExternalPtrAddr(handle), c_json_config, &olen, &raw))
-  ret = PROTECT(allocVector(RAWSXP, olen));
-  if (olen != 0) {
-    std::memcpy(RAW(ret), raw, olen);
-  }
-  R_API_END();
-  UNPROTECT(1);
-  return ret;
-}
-
-XGB_DLL SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
+SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
   const char* ret;
   R_API_BEGIN();
   bst_ulong len {0};
@@ -493,14 +373,14 @@ XGB_DLL SEXP XGBoosterSaveJsonConfig_R(SEXP handle) {
   return mkString(ret);
 }
 
-XGB_DLL SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
+SEXP XGBoosterLoadJsonConfig_R(SEXP handle, SEXP value) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterLoadJsonConfig(R_ExternalPtrAddr(handle), CHAR(asChar(value))));
   R_API_END();
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
+SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
   SEXP ret;
   R_API_BEGIN();
   bst_ulong out_len;
@@ -515,7 +395,7 @@ XGB_DLL SEXP XGBoosterSerializeToBuffer_R(SEXP handle) {
   return ret;
 }
 
-XGB_DLL SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
+SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
   R_API_BEGIN();
   CHECK_CALL(XGBoosterUnserializeFromBuffer(R_ExternalPtrAddr(handle),
                                  RAW(raw),
@@ -524,7 +404,7 @@ XGB_DLL SEXP XGBoosterUnserializeFromBuffer_R(SEXP handle, SEXP raw) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_format) {
+SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP dump_format) {
   SEXP out;
   R_API_BEGIN();
   bst_ulong olen;
@@ -561,7 +441,7 @@ XGB_DLL SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats, SEXP
   return out;
 }
 
-XGB_DLL SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
+SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
   SEXP out;
   R_API_BEGIN();
   int success;
@@ -581,7 +461,7 @@ XGB_DLL SEXP XGBoosterGetAttr_R(SEXP handle, SEXP name) {
   return out;
 }
 
-XGB_DLL SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
+SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
   R_API_BEGIN();
   const char *v = isNull(val) ? nullptr : CHAR(asChar(val));
   CHECK_CALL(XGBoosterSetAttr(R_ExternalPtrAddr(handle),
@@ -590,7 +470,7 @@ XGB_DLL SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val) {
   return R_NilValue;
 }
 
-XGB_DLL SEXP XGBoosterGetAttrNames_R(SEXP handle) {
+SEXP XGBoosterGetAttrNames_R(SEXP handle) {
   SEXP out;
   R_API_BEGIN();
   bst_ulong len;
@@ -609,50 +489,3 @@ XGB_DLL SEXP XGBoosterGetAttrNames_R(SEXP handle) {
   UNPROTECT(1);
   return out;
 }
-
-XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config) {
-  SEXP out_features_sexp;
-  SEXP out_scores_sexp;
-  SEXP out_shape_sexp;
-  SEXP r_out;
-
-  R_API_BEGIN();
-  char const *c_json_config = CHAR(asChar(json_config));
-  bst_ulong out_n_features;
-  char const **out_features;
-
-  bst_ulong out_dim;
-  bst_ulong const *out_shape;
-  float const *out_scores;
-
-  CHECK_CALL(XGBoosterFeatureScore(R_ExternalPtrAddr(handle), c_json_config,
-                                   &out_n_features, &out_features,
-                                   &out_dim, &out_shape, &out_scores));
-  out_shape_sexp = PROTECT(allocVector(INTSXP, out_dim));
-  size_t len = 1;
-  for (size_t i = 0; i < out_dim; ++i) {
-    INTEGER(out_shape_sexp)[i] = out_shape[i];
-    len *= out_shape[i];
-  }
-
-  out_scores_sexp = PROTECT(allocVector(REALSXP, len));
-  auto ctx = BoosterCtx(R_ExternalPtrAddr(handle));
-  xgboost::common::ParallelFor(len, ctx->Threads(), [&](xgboost::omp_ulong i) {
-    REAL(out_scores_sexp)[i] = out_scores[i];
-  });
-
-  out_features_sexp = PROTECT(allocVector(STRSXP, out_n_features));
-  for (size_t i = 0; i < out_n_features; ++i) {
-    SET_STRING_ELT(out_features_sexp, i, mkChar(out_features[i]));
-  }
-
-  r_out = PROTECT(allocVector(VECSXP, 3));
-  SET_VECTOR_ELT(r_out, 0, out_features_sexp);
-  SET_VECTOR_ELT(r_out, 1, out_shape_sexp);
-  SET_VECTOR_ELT(r_out, 2, out_scores_sexp);
-
-  R_API_END();
-  UNPROTECT(4);
-
-  return r_out;
-}

R-package/src/xgboost_R.h

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2014-2022 by XGBoost Contributors
+ * Copyright 2014 (c) by Contributors
  * \file xgboost_R.h
  * \author Tianqi Chen
  * \brief R wrapper of xgboost
@@ -21,19 +21,6 @@
  */
 XGB_DLL SEXP XGCheckNullPtr_R(SEXP handle);
 
-/*!
- * \brief Set global configuration
- * \param json_str a JSON string representing the list of key-value pairs
- * \return R_NilValue
- */
-XGB_DLL SEXP XGBSetGlobalConfig_R(SEXP json_str);
-
-/*!
- * \brief Get global configuration
- * \return JSON string
- */
-XGB_DLL SEXP XGBGetGlobalConfig_R();
-
 /*!
  * \brief load a data matrix
  * \param fname name of the content
@@ -47,35 +34,22 @@ XGB_DLL SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent);
  * This assumes the matrix is stored in column major format
  * \param data R Matrix object
  * \param missing which value to represent missing value
- * \param n_threads Number of threads used to construct DMatrix from dense matrix.
  * \return created dmatrix
  */
 XGB_DLL SEXP XGDMatrixCreateFromMat_R(SEXP mat,
-                                      SEXP missing,
-                                      SEXP n_threads);
+                                      SEXP missing);
 /*!
  * \brief create a matrix content from CSC format
  * \param indptr pointer to column headers
  * \param indices row indices
  * \param data content of the data
  * \param num_row numer of rows (when it's set to 0, then guess from data)
- * \param n_threads Number of threads used to construct DMatrix from csc matrix.
  * \return created dmatrix
  */
-XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_row,
-                                      SEXP n_threads);
-
-/*!
- * \brief create a matrix content from CSR format
- * \param indptr pointer to row headers
- * \param indices column indices
- * \param data content of the data
- * \param num_col numer of columns (when it's set to 0, then guess from data)
- * \param n_threads Number of threads used to construct DMatrix from csr matrix.
- * \return created dmatrix
- */
-XGB_DLL SEXP XGDMatrixCreateFromCSR_R(SEXP indptr, SEXP indices, SEXP data, SEXP num_col,
-                                      SEXP n_threads);
+XGB_DLL SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
+                                      SEXP indices,
+                                      SEXP data,
+                                      SEXP num_row);
 
 /*!
  * \brief create a new dmatrix from sliced content of existing matrix
@@ -129,14 +103,6 @@ XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle);
  */
 XGB_DLL SEXP XGBoosterCreate_R(SEXP dmats);
 
-
-/*!
- * \brief create xgboost learner, saving the pointer into an existing R object
- * \param dmats a list of dmatrix handles that will be cached
- * \param R_handle a clean R external pointer (not holding any object)
- */
-XGB_DLL SEXP XGBoosterCreateInEmptyObj_R(SEXP dmats, SEXP R_handle);
-
 /*!
  * \brief set parameters
  * \param handle handle
@@ -177,7 +143,7 @@ XGB_DLL SEXP XGBoosterBoostOneIter_R(SEXP handle, SEXP dtrain, SEXP grad, SEXP h
 XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evnames);
 
 /*!
- * \brief (Deprecated) make prediction based on dmat
+ * \brief make prediction based on dmat
  * \param handle handle
  * \param dmat data matrix
  * \param option_mask output_margin:1 predict_leaf:2
@@ -186,16 +152,6 @@ XGB_DLL SEXP XGBoosterEvalOneIter_R(SEXP handle, SEXP iter, SEXP dmats, SEXP evn
  */
 XGB_DLL SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask,
                                 SEXP ntree_limit, SEXP training);
-
-/*!
- * \brief Run prediction on DMatrix, replacing `XGBoosterPredict_R`
- * \param handle handle
- * \param dmat data matrix
- * \param json_config See `XGBoosterPredictFromDMatrix` in xgboost c_api.h
- *
- * \return A list containing 2 vectors, first one for shape while second one for prediction result.
- */
-XGB_DLL SEXP XGBoosterPredictFromDMatrix_R(SEXP handle, SEXP dmat, SEXP json_config);
 /*!
  * \brief load model from existing file
  * \param handle handle
@@ -220,21 +176,11 @@ XGB_DLL SEXP XGBoosterSaveModel_R(SEXP handle, SEXP fname);
 XGB_DLL SEXP XGBoosterLoadModelFromRaw_R(SEXP handle, SEXP raw);
 
 /*!
- * \brief Save model into R's raw array
- *
+ * \brief save model into R's raw array
  * \param handle handle
- * \param json_config JSON encoded string storing parameters for the function.  Following
- *                    keys are expected in the JSON document:
- *
- *     "format": str
- *       - json: Output booster will be encoded as JSON.
- *       - ubj:  Output booster will be encoded as Univeral binary JSON.
- *       - deprecated: Output booster will be encoded as old custom binary format.  Do now use
- *         this format except for compatibility reasons.
- *
- * \return Raw array
+ * \return raw array
  */
-XGB_DLL SEXP XGBoosterSaveModelToRaw_R(SEXP handle, SEXP json_config);
+XGB_DLL SEXP XGBoosterModelToRaw_R(SEXP handle);
 
 /*!
  * \brief Save internal parameters as a JSON string
@@ -298,12 +244,4 @@ XGB_DLL SEXP XGBoosterSetAttr_R(SEXP handle, SEXP name, SEXP val);
  */
 XGB_DLL SEXP XGBoosterGetAttrNames_R(SEXP handle);
 
-/*!
- * \brief Get feature scores from the model.
- * \param json_config See `XGBoosterFeatureScore` in xgboost c_api.h
- * \return A vector with the first element as feature names, second element as shape of
- *         feature scores and thrid element as feature scores.
- */
-XGB_DLL SEXP XGBoosterFeatureScore_R(SEXP handle, SEXP json_config);
-
 #endif  // XGBOOST_WRAPPER_R_H_ // NOLINT(*)

R-package/src/xgboost_custom.cc

@@ -13,10 +13,27 @@ void CustomLogMessage::Log(const std::string& msg) {
 }
 }  // namespace dmlc
 
+// implements rabit error handling.
+extern "C" {
+  void XGBoostAssert_R(int exp, const char *fmt, ...);
+  void XGBoostCheck_R(int exp, const char *fmt, ...);
+}
+
+namespace rabit {
+namespace utils {
+extern "C" {
+  void (*Printf)(const char *fmt, ...) = Rprintf;
+  void (*Assert)(int exp, const char *fmt, ...) = XGBoostAssert_R;
+  void (*Check)(int exp, const char *fmt, ...) = XGBoostCheck_R;
+  void (*Error)(const char *fmt, ...) = error;
+}
+}
+}
+
 namespace xgboost {
 ConsoleLogger::~ConsoleLogger() {
   if (cur_verbosity_ == LogVerbosity::kIgnore ||
-      cur_verbosity_ <= GlobalVerbosity()) {
+      cur_verbosity_ <= global_verbosity_) {
     dmlc::CustomLogMessage::Log(log_stream_.str());
   }
 }

R-package/tests/generate_models.R

@@ -2,16 +2,10 @@
 # of saved model files from XGBoost version 0.90 and 1.0.x.
 library(xgboost)
 library(Matrix)
+source('./generate_models_params.R')
 
 set.seed(0)
-metadata <- list(
-  kRounds = 2,
-  kRows = 1000,
-  kCols = 4,
-  kForests = 2,
-  kMaxDepth = 2,
-  kClasses = 3
-)
+metadata <- model_generator_metadata()
 X <- Matrix(data = rnorm(metadata$kRows * metadata$kCols), nrow = metadata$kRows,
             ncol = metadata$kCols, sparse = TRUE)
 w <- runif(metadata$kRows)
@@ -52,16 +46,11 @@ generate_logistic_model <- function () {
   y <- sample(0:1, size = metadata$kRows, replace = TRUE)
   stopifnot(max(y) == 1, min(y) == 0)
 
-  objective <- c('binary:logistic', 'binary:logitraw')
-  name <- c('logit', 'logitraw')
-
-  for (i in seq_len(length(objective))) {
-    data <- xgb.DMatrix(X, label = y, weight = w)
-    params <- list(tree_method = 'hist', num_parallel_tree = metadata$kForests,
-                   max_depth = metadata$kMaxDepth, objective = objective[i])
-    booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-    save_booster(booster, name[i])
-  }
+  data <- xgb.DMatrix(X, label = y, weight = w)
+  params <- list(tree_method = 'hist', num_parallel_tree = metadata$kForests,
+                 max_depth = metadata$kMaxDepth, objective = 'binary:logistic')
+  booster <- xgb.train(params, data, nrounds = metadata$kRounds)
+  save_booster(booster, 'logit')
 }
 
 generate_classification_model <- function () {

R-package/tests/generate_models_params.R

@@ -0,0 +1,10 @@
+model_generator_metadata <- function() {
+  return (list(
+    kRounds = 2,
+    kRows = 1000,
+    kCols = 4,
+    kForests = 2,
+    kMaxDepth = 2,
+    kClasses = 3
+  ))
+}

R-package/tests/run_lint.R

@@ -6,21 +6,21 @@ my_linters <- list(
   assignment_linter = lintr::assignment_linter,
   closed_curly_linter = lintr::closed_curly_linter,
   commas_linter = lintr::commas_linter,
-  equals_na = lintr::equals_na_linter,
+  # commented_code_linter = lintr::commented_code_linter,
   infix_spaces_linter = lintr::infix_spaces_linter,
   line_length_linter = lintr::line_length_linter,
   no_tab_linter = lintr::no_tab_linter,
   object_usage_linter = lintr::object_usage_linter,
+  # snake_case_linter = lintr::snake_case_linter,
+  # multiple_dots_linter = lintr::multiple_dots_linter,
   object_length_linter = lintr::object_length_linter,
   open_curly_linter = lintr::open_curly_linter,
-  semicolon = lintr::semicolon_terminator_linter,
-  seq = lintr::seq_linter,
+  # single_quotes_linter = lintr::single_quotes_linter,
   spaces_inside_linter = lintr::spaces_inside_linter,
   spaces_left_parentheses_linter = lintr::spaces_left_parentheses_linter,
   trailing_blank_lines_linter = lintr::trailing_blank_lines_linter,
   trailing_whitespace_linter = lintr::trailing_whitespace_linter,
-  true_false = lintr::T_and_F_symbol_linter,
-  unneeded_concatenation = lintr::unneeded_concatenation_linter
+  true_false = lintr::T_and_F_symbol_linter
 )
 
 results <- lapply(

R-package/tests/testthat/test_basic.R

@@ -1,5 +1,4 @@
 require(xgboost)
-library(Matrix)
 
 context("basic functions")
 
@@ -18,8 +17,7 @@ test_that("train and predict binary classification", {
   nrounds <- 2
   expect_output(
     bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-                  eta = 1, nthread = 2, nrounds = nrounds, objective = "binary:logistic",
-                  eval_metric = "error")
+                  eta = 1, nthread = 2, nrounds = nrounds, objective = "binary:logistic")
   , "train-error")
   expect_equal(class(bst), "xgb.Booster")
   expect_equal(bst$niter, nrounds)
@@ -35,10 +33,6 @@ test_that("train and predict binary classification", {
   err_pred1 <- sum((pred1 > 0.5) != train$label) / length(train$label)
   err_log <- bst$evaluation_log[1, train_error]
   expect_lt(abs(err_pred1 - err_log), 10e-6)
-
-  pred2 <- predict(bst, train$data, iterationrange = c(1, 2))
-  expect_length(pred1, 6513)
-  expect_equal(pred1, pred2)
 })
 
 test_that("parameter validation works", {
@@ -71,7 +65,7 @@ test_that("parameter validation works", {
       xgb.train(params = params, data = dtrain, nrounds = nrounds))
     print(output)
   }
-  expect_output(incorrect(), '\\\\"bar\\\\", \\\\"foo\\\\"')
+  expect_output(incorrect(), "bar, foo")
 })
 
 
@@ -128,7 +122,7 @@ test_that("train and predict softprob", {
   expect_output(
     bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                    max_depth = 3, eta = 0.5, nthread = 2, nrounds = 5,
-                   objective = "multi:softprob", num_class = 3, eval_metric = "merror")
+                   objective = "multi:softprob", num_class = 3)
   , "train-merror")
   expect_false(is.null(bst$evaluation_log))
   expect_lt(bst$evaluation_log[, min(train_merror)], 0.025)
@@ -148,24 +142,6 @@ test_that("train and predict softprob", {
   pred_labels <- max.col(mpred) - 1
   err <- sum(pred_labels != lb) / length(lb)
   expect_equal(bst$evaluation_log[1, train_merror], err, tolerance = 5e-6)
-
-  mpred1 <- predict(bst, as.matrix(iris[, -5]), reshape = TRUE, iterationrange = c(1, 2))
-  expect_equal(mpred, mpred1)
-
-  d <- cbind(
-    x1 = rnorm(100),
-    x2 = rnorm(100),
-    x3 = rnorm(100)
-  )
-  y <- sample.int(10, 100, replace = TRUE) - 1
-  dtrain <- xgb.DMatrix(data = d, info = list(label = y))
-  booster <- xgb.train(
-    params = list(tree_method = "hist"), data = dtrain, nrounds = 4, num_class = 10,
-    objective = "multi:softprob"
-  )
-  predt <- predict(booster, as.matrix(d), reshape = TRUE, strict_shape = FALSE)
-  expect_equal(ncol(predt), 10)
-  expect_equal(rowSums(predt), rep(1, 100), tolerance = 1e-7)
 })
 
 test_that("train and predict softmax", {
@@ -174,7 +150,7 @@ test_that("train and predict softmax", {
   expect_output(
     bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                    max_depth = 3, eta = 0.5, nthread = 2, nrounds = 5,
-                   objective = "multi:softmax", num_class = 3, eval_metric = "merror")
+                   objective = "multi:softmax", num_class = 3)
   , "train-merror")
   expect_false(is.null(bst$evaluation_log))
   expect_lt(bst$evaluation_log[, min(train_merror)], 0.025)
@@ -191,7 +167,7 @@ test_that("train and predict RF", {
   lb <- train$label
   # single iteration
   bst <- xgboost(data = train$data, label = lb, max_depth = 5,
-                 nthread = 2, nrounds = 1, objective = "binary:logistic", eval_metric = "error",
+                 nthread = 2, nrounds = 1, objective = "binary:logistic",
                  num_parallel_tree = 20, subsample = 0.6, colsample_bytree = 0.1)
   expect_equal(bst$niter, 1)
   expect_equal(xgb.ntree(bst), 20)
@@ -205,8 +181,10 @@ test_that("train and predict RF", {
   pred_err_20 <- sum((pred > 0.5) != lb) / length(lb)
   expect_equal(pred_err_20, pred_err)
 
-  pred1 <- predict(bst, train$data, iterationrange = c(1, 2))
-  expect_equal(pred, pred1)
+  #pred <- predict(bst, train$data, ntreelimit = 1)
+  #pred_err_1 <- sum((pred > 0.5) != lb)/length(lb)
+  #expect_lt(pred_err, pred_err_1)
+  #expect_lt(pred_err, 0.08)
 })
 
 test_that("train and predict RF with softprob", {
@@ -215,8 +193,7 @@ test_that("train and predict RF with softprob", {
   set.seed(11)
   bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
                  max_depth = 3, eta = 0.9, nthread = 2, nrounds = nrounds,
-                 objective = "multi:softprob", eval_metric = "merror",
-                 num_class = 3, verbose = 0,
+                 objective = "multi:softprob", num_class = 3, verbose = 0,
                  num_parallel_tree = 4, subsample = 0.5, colsample_bytree = 0.5)
   expect_equal(bst$niter, 15)
   expect_equal(xgb.ntree(bst), 15 * 3 * 4)
@@ -268,12 +245,11 @@ test_that("training continuation works", {
     expect_equal(bst$raw, bst2$raw)
   expect_equal(dim(bst2$evaluation_log), c(2, 2))
   # test continuing from a model in file
-  xgb.save(bst1, "xgboost.json")
-  bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0, xgb_model = "xgboost.json")
+  xgb.save(bst1, "xgboost.model")
+  bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0, xgb_model = "xgboost.model")
   if (!windows_flag && !solaris_flag)
     expect_equal(bst$raw, bst2$raw)
   expect_equal(dim(bst2$evaluation_log), c(2, 2))
-  file.remove("xgboost.json")
 })
 
 test_that("model serialization works", {
@@ -297,7 +273,7 @@ test_that("xgb.cv works", {
   expect_output(
     cv <- xgb.cv(data = train$data, label = train$label, max_depth = 2, nfold = 5,
                  eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
-                 eval_metric = "error", verbose = TRUE)
+                 verbose = TRUE)
   , "train-error:")
   expect_is(cv, 'xgb.cv.synchronous')
   expect_false(is.null(cv$evaluation_log))
@@ -322,7 +298,7 @@ test_that("xgb.cv works with stratified folds", {
                 eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
                 verbose = TRUE, stratified = TRUE)
   # Stratified folds should result in a different evaluation logs
-  expect_true(all(cv$evaluation_log[, test_logloss_mean] != cv2$evaluation_log[, test_logloss_mean]))
+  expect_true(all(cv$evaluation_log[, test_error_mean] != cv2$evaluation_log[, test_error_mean]))
 })
 
 test_that("train and predict with non-strict classes", {
@@ -352,7 +328,7 @@ test_that("train and predict with non-strict classes", {
   expect_error(pr <- predict(bst, train_dense), regexp = NA)
   expect_equal(pr0, pr)
 
-  # when someone inherits from xgb.Booster, it should still be possible to use it as xgb.Booster
+  # when someone inhertis from xgb.Booster, it should still be possible to use it as xgb.Booster
   class(bst) <- c('super.Booster', 'xgb.Booster')
   expect_error(pr <- predict(bst, train_dense), regexp = NA)
   expect_equal(pr0, pr)
@@ -367,7 +343,7 @@ test_that("max_delta_step works", {
   bst1 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1)
   # model with restricted max_delta_step
   bst2 <- xgb.train(param, dtrain, nrounds, watchlist, verbose = 1, max_delta_step = 1)
-  # the no-restriction model is expected to have consistently lower loss during the initial iterations
+  # the no-restriction model is expected to have consistently lower loss during the initial interations
   expect_true(all(bst1$evaluation_log$train_logloss < bst2$evaluation_log$train_logloss))
   expect_lt(mean(bst1$evaluation_log$train_logloss) / mean(bst2$evaluation_log$train_logloss), 0.8)
 })
@@ -406,72 +382,3 @@ test_that("Configuration works", {
   reloaded_config <- xgb.config(bst)
   expect_equal(config, reloaded_config);
 })
-
-test_that("strict_shape works", {
-  n_rounds <- 2
-
-  test_strict_shape <- function(bst, X, n_groups) {
-    predt <- predict(bst, X, strict_shape = TRUE)
-    margin <- predict(bst, X, outputmargin = TRUE, strict_shape = TRUE)
-    contri <- predict(bst, X, predcontrib = TRUE, strict_shape = TRUE)
-    interact <- predict(bst, X, predinteraction = TRUE, strict_shape = TRUE)
-    leaf <- predict(bst, X, predleaf = TRUE, strict_shape = TRUE)
-
-    n_rows <- nrow(X)
-    n_cols <- ncol(X)
-
-    expect_equal(dim(predt), c(n_groups, n_rows))
-    expect_equal(dim(margin), c(n_groups, n_rows))
-    expect_equal(dim(contri), c(n_cols + 1, n_groups, n_rows))
-    expect_equal(dim(interact), c(n_cols + 1, n_cols + 1, n_groups, n_rows))
-    expect_equal(dim(leaf), c(1, n_groups, n_rounds, n_rows))
-
-    if (n_groups != 1) {
-      for (g in seq_len(n_groups)) {
-        expect_lt(max(abs(colSums(contri[, g, ]) - margin[g, ])), 1e-5)
-      }
-    }
-  }
-
-  test_iris <- function() {
-    y <- as.numeric(iris$Species) - 1
-    X <- as.matrix(iris[, -5])
-
-    bst <- xgboost(data = X, label = y,
-                   max_depth = 2, nrounds = n_rounds,
-                   objective = "multi:softprob", num_class = 3, eval_metric = "merror")
-
-    test_strict_shape(bst, X, 3)
-  }
-
-
-  test_agaricus <- function() {
-    data(agaricus.train, package = 'xgboost')
-    X <- agaricus.train$data
-    y <- agaricus.train$label
-
-    bst <- xgboost(data = X, label = y, max_depth = 2,
-                   nrounds = n_rounds, objective = "binary:logistic",
-                   eval_metric = 'error', eval_metric = 'auc', eval_metric = "logloss")
-
-    test_strict_shape(bst, X, 1)
-  }
-
-  test_iris()
-  test_agaricus()
-})
-
-test_that("'predict' accepts CSR data", {
-  X <- agaricus.train$data
-  y <- agaricus.train$label
-  x_csc <- as(X[1L, , drop = FALSE], "CsparseMatrix")
-  x_csr <- as(x_csc, "RsparseMatrix")
-  x_spv <- as(x_csc, "sparseVector")
-  bst <- xgboost(data = X, label = y, objective = "binary:logistic",
-                 nrounds = 5L, verbose = FALSE)
-  p_csc <- predict(bst, x_csc)
-  p_csr <- predict(bst, x_csr)
-  p_spv <- predict(bst, x_spv)
-  expect_equal(p_csc, p_csr)
-  expect_equal(p_csc, p_spv)
-})

R-package/tests/testthat/test_callbacks.R

@@ -2,7 +2,6 @@
 
 require(xgboost)
 require(data.table)
-require(titanic)
 
 context("callbacks")
 
@@ -27,8 +26,7 @@ watchlist <- list(train = dtrain, test = dtest)
 
 err <- function(label, pr) sum((pr > 0.5) != label) / length(label)
 
-param <- list(objective = "binary:logistic", eval_metric = "error",
-              max_depth = 2, nthread = 2)
+param <- list(objective = "binary:logistic", max_depth = 2, nthread = 2)
 
 
 test_that("cb.print.evaluation works as expected", {
@@ -107,8 +105,7 @@ test_that("cb.evaluation.log works as expected", {
 })
 
 
-param <- list(objective = "binary:logistic", eval_metric = "error",
-              max_depth = 4, nthread = 2)
+param <- list(objective = "binary:logistic", max_depth = 4, nthread = 2)
 
 test_that("can store evaluation_log without printing", {
   expect_silent(
@@ -176,16 +173,16 @@ test_that("cb.reset.parameters works as expected", {
 })
 
 test_that("cb.save.model works as expected", {
-  files <- c('xgboost_01.json', 'xgboost_02.json', 'xgboost.json')
+  files <- c('xgboost_01.model', 'xgboost_02.model', 'xgboost.model')
   for (f in files) if (file.exists(f)) file.remove(f)
 
   bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, eta = 1, verbose = 0,
-                   save_period = 1, save_name = "xgboost_%02d.json")
-  expect_true(file.exists('xgboost_01.json'))
-  expect_true(file.exists('xgboost_02.json'))
-  b1 <- xgb.load('xgboost_01.json')
+                   save_period = 1, save_name = "xgboost_%02d.model")
+  expect_true(file.exists('xgboost_01.model'))
+  expect_true(file.exists('xgboost_02.model'))
+  b1 <- xgb.load('xgboost_01.model')
   expect_equal(xgb.ntree(b1), 1)
-  b2 <- xgb.load('xgboost_02.json')
+  b2 <- xgb.load('xgboost_02.model')
   expect_equal(xgb.ntree(b2), 2)
 
   xgb.config(b2) <- xgb.config(bst)
@@ -194,9 +191,9 @@ test_that("cb.save.model works as expected", {
 
   # save_period = 0 saves the last iteration's model
   bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, eta = 1, verbose = 0,
-                   save_period = 0, save_name = 'xgboost.json')
-  expect_true(file.exists('xgboost.json'))
-  b2 <- xgb.load('xgboost.json')
+                   save_period = 0)
+  expect_true(file.exists('xgboost.model'))
+  b2 <- xgb.load('xgboost.model')
   xgb.config(b2) <- xgb.config(bst)
   expect_equal(bst$raw, b2$raw)
 
@@ -239,7 +236,7 @@ test_that("early stopping xgb.train works", {
 test_that("early stopping using a specific metric works", {
   set.seed(11)
   expect_output(
-    bst <- xgb.train(param[-2], dtrain, nrounds = 20, watchlist, eta = 0.6,
+    bst <- xgb.train(param, dtrain, nrounds = 20, watchlist, eta = 0.6,
                      eval_metric = "logloss", eval_metric = "auc",
                      callbacks = list(cb.early.stop(stopping_rounds = 3, maximize = FALSE,
                                                     metric_name = 'test_logloss')))
@@ -255,26 +252,6 @@ test_that("early stopping using a specific metric works", {
   expect_equal(logloss_log, logloss_pred, tolerance = 1e-5)
 })
 
-test_that("early stopping works with titanic", {
-  # This test was inspired by https://github.com/dmlc/xgboost/issues/5935
-  # It catches possible issues on noLD R
-  titanic <- titanic::titanic_train
-  titanic$Pclass <-  as.factor(titanic$Pclass)
-  dtx <- model.matrix(~ 0 + ., data = titanic[, c("Pclass", "Sex")])
-  dty <- titanic$Survived
-
-  xgboost::xgboost(
-    data = dtx,
-    label = dty,
-    objective = "binary:logistic",
-    eval_metric = "auc",
-    nrounds = 100,
-    early_stopping_rounds = 3
-  )
-
-  expect_true(TRUE)  # should not crash
-})
-
 test_that("early stopping xgb.cv works", {
   set.seed(11)
   expect_output(

R-package/tests/testthat/test_config.R

@@ -1,21 +0,0 @@
-context('Test global configuration')
-
-test_that('Global configuration works with verbosity', {
-  old_verbosity <- xgb.get.config()$verbosity
-  for (v in c(0, 1, 2, 3)) {
-    xgb.set.config(verbosity = v)
-    expect_equal(xgb.get.config()$verbosity, v)
-  }
-  xgb.set.config(verbosity = old_verbosity)
-  expect_equal(xgb.get.config()$verbosity, old_verbosity)
-})
-
-test_that('Global configuration works with use_rmm flag', {
-  old_use_rmm_flag <- xgb.get.config()$use_rmm
-  for (v in c(TRUE, FALSE)) {
-    xgb.set.config(use_rmm = v)
-    expect_equal(xgb.get.config()$use_rmm, v)
-  }
-  xgb.set.config(use_rmm = old_use_rmm_flag)
-  expect_equal(xgb.get.config()$use_rmm, old_use_rmm_flag)
-})

R-package/tests/testthat/test_custom_objective.R

@@ -47,7 +47,7 @@ test_that("custom objective with early stop works", {
   bst <- xgb.train(param, dtrain, 10, watchlist)
   expect_equal(class(bst), "xgb.Booster")
   train_log <- bst$evaluation_log$train_error
-  expect_true(all(diff(train_log) <= 0))
+  expect_true(all(diff(train_log)) <= 0)
 })
 
 test_that("custom objective using DMatrix attr works", {

R-package/tests/testthat/test_dmatrix.R

@@ -27,7 +27,6 @@ test_that("xgb.DMatrix: saving, loading", {
   # save to a local file
   dtest1 <- xgb.DMatrix(test_data, label = test_label)
   tmp_file <- tempfile('xgb.DMatrix_')
-  on.exit(unlink(tmp_file))
   expect_true(xgb.DMatrix.save(dtest1, tmp_file))
   # read from a local file
   expect_output(dtest3 <- xgb.DMatrix(tmp_file), "entries loaded from")
@@ -42,6 +41,7 @@ test_that("xgb.DMatrix: saving, loading", {
   dtest4 <- xgb.DMatrix(tmp_file, silent = TRUE)
   expect_equal(dim(dtest4), c(3, 4))
   expect_equal(getinfo(dtest4, 'label'), c(0, 1, 0))
+  unlink(tmp_file)
 })
 
 test_that("xgb.DMatrix: getinfo & setinfo", {
@@ -64,8 +64,8 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
   expect_true(setinfo(dtest, 'group', c(50, 50)))
   expect_error(setinfo(dtest, 'group', test_label))
 
-  # providing character values will give an error
-  expect_error(setinfo(dtest, 'weight', rep('a', nrow(test_data))))
+  # providing character values will give a warning
+  expect_warning(setinfo(dtest, 'weight', rep('a', nrow(test_data))))
 
   # any other label should error
   expect_error(setinfo(dtest, 'asdf', test_label))
@@ -99,7 +99,7 @@ test_that("xgb.DMatrix: colnames", {
   dtest <- xgb.DMatrix(test_data, label = test_label)
   expect_equal(colnames(dtest), colnames(test_data))
   expect_error(colnames(dtest) <- 'asdf')
-  new_names <- make.names(seq_len(ncol(test_data)))
+  new_names <- make.names(1:ncol(test_data))
   expect_silent(colnames(dtest) <- new_names)
   expect_equal(colnames(dtest), new_names)
   expect_silent(colnames(dtest) <- NULL)

R-package/tests/testthat/test_feature_weights.R

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

R-package/tests/testthat/test_gc_safety.R

@@ -9,8 +9,7 @@ test_that("train and prediction when gctorture is on", {
   test <- agaricus.test
   gctorture(TRUE)
   bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
-                 eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+  eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
   pred <- predict(bst, test$data)
   gctorture(FALSE)
-  expect_length(pred, length(test$label))
 })

R-package/tests/testthat/test_glm.R

@@ -8,7 +8,7 @@ test_that("gblinear works", {
   dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
   dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
-  param <- list(objective = "binary:logistic", eval_metric = "error", booster = "gblinear",
+  param <- list(objective = "binary:logistic", booster = "gblinear",
                 nthread = 2, eta = 0.8, alpha = 0.0001, lambda = 0.0001)
   watchlist <- list(eval = dtest, train = dtrain)
 
@@ -46,31 +46,3 @@ test_that("gblinear works", {
   expect_equal(dim(h), c(n, ncol(dtrain) + 1))
   expect_s4_class(h, "dgCMatrix")
 })
-
-test_that("gblinear early stopping works", {
-  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(
-    objective = "binary:logistic", eval_metric = "error", booster = "gblinear",
-    nthread = 2, eta = 0.8, alpha = 0.0001, lambda = 0.0001,
-    updater = "coord_descent"
-  )
-
-  es_round <- 1
-  n <- 10
-  booster <- xgb.train(
-    param, dtrain, n, list(eval = dtest, train = dtrain), early_stopping_rounds = es_round
-  )
-  expect_equal(booster$best_iteration, 5)
-  predt_es <- predict(booster, dtrain)
-
-  n <- booster$best_iteration + es_round
-  booster <- xgb.train(
-    param, dtrain, n, list(eval = dtest, train = dtrain), early_stopping_rounds = es_round
-  )
-  predt <- predict(booster, dtrain)
-  expect_equal(predt_es, predt)
-})

R-package/tests/testthat/test_helpers.R

@@ -1,4 +1,3 @@
-library(testthat)
 context('Test helper functions')
 
 require(xgboost)
@@ -111,7 +110,7 @@ test_that("predict feature contributions works", {
   pred <- predict(bst.GLM, sparse_matrix, outputmargin = TRUE)
   expect_lt(max(abs(rowSums(pred_contr) - pred)), 1e-5)
   # manual calculation of linear terms
-  coefs <- as.numeric(xgb.dump(bst.GLM)[-c(1, 2, 4)])
+  coefs <- xgb.dump(bst.GLM)[-c(1, 2, 4)] %>% as.numeric
   coefs <- c(coefs[-1], coefs[1]) # intercept must be the last
   pred_contr_manual <- sweep(cbind(sparse_matrix, 1), 2, coefs, FUN = "*")
   expect_equal(as.numeric(pred_contr), as.numeric(pred_contr_manual),
@@ -131,11 +130,7 @@ test_that("predict feature contributions works", {
   pred <- predict(mbst.GLM, as.matrix(iris[, -5]), outputmargin = TRUE, reshape = TRUE)
   pred_contr <- predict(mbst.GLM, as.matrix(iris[, -5]), predcontrib = TRUE)
   expect_length(pred_contr, 3)
-  coefs_all <- matrix(
-    data = as.numeric(xgb.dump(mbst.GLM)[-c(1, 2, 6)]),
-    ncol = 3,
-    byrow = TRUE
-  )
+  coefs_all <- xgb.dump(mbst.GLM)[-c(1, 2, 6)] %>% as.numeric %>% matrix(ncol = 3, byrow = TRUE)
   for (g in seq_along(pred_contr)) {
     expect_equal(colnames(pred_contr[[g]]), c(colnames(iris[, -5]), "BIAS"))
     expect_lt(max(abs(rowSums(pred_contr[[g]]) - pred[, g])), float_tolerance)
@@ -179,7 +174,7 @@ test_that("SHAPs sum to predictions, with or without DART", {
 
     expect_equal(rowSums(shap), pred, tol = tol)
     expect_equal(apply(shapi, 1, sum), pred, tol = tol)
-    for (i in seq_len(nrow(d)))
+    for (i in 1 : nrow(d))
       for (f in list(rowSums, colSums))
         expect_equal(f(shapi[i, , ]), shap[i, ], tol = tol)
   }
@@ -228,7 +223,7 @@ if (grepl('Windows', Sys.info()[['sysname']]) ||
       X <- 10^runif(100, -20, 20)
       if (capabilities('long.double')) {
           X2X <- as.numeric(format(X, digits = 17))
-          expect_equal(X, X2X, tolerance = float_tolerance)
+          expect_identical(X, X2X)
       }
       # retrieved attributes to be the same as written
       for (x in X) {
@@ -243,13 +238,12 @@ if (grepl('Windows', Sys.info()[['sysname']]) ||
 test_that("xgb.Booster serializing as R object works", {
   saveRDS(bst.Tree, 'xgb.model.rds')
   bst <- readRDS('xgb.model.rds')
+  if (file.exists('xgb.model.rds')) file.remove('xgb.model.rds')
   dtrain <- xgb.DMatrix(sparse_matrix, label = label)
   expect_equal(predict(bst.Tree, dtrain), predict(bst, dtrain), tolerance = float_tolerance)
   expect_equal(xgb.dump(bst.Tree), xgb.dump(bst))
   xgb.save(bst, 'xgb.model')
   if (file.exists('xgb.model')) file.remove('xgb.model')
-  bst <- readRDS('xgb.model.rds')
-  if (file.exists('xgb.model.rds')) file.remove('xgb.model.rds')
   nil_ptr <- new("externalptr")
   class(nil_ptr) <- "xgb.Booster.handle"
   expect_true(identical(bst$handle, nil_ptr))
@@ -311,45 +305,7 @@ test_that("xgb.importance works with and without feature names", {
   # for multiclass
   imp.Tree <- xgb.importance(model = mbst.Tree)
   expect_equal(dim(imp.Tree), c(4, 4))
-
-  trees <- seq(from = 0, by = 2, length.out = 2)
-  importance <- xgb.importance(feature_names = feature.names, model = bst.Tree, trees = trees)
-
-  importance_from_dump <- function() {
-    model_text_dump <- xgb.dump(model = bst.Tree, with_stats = TRUE, trees = trees)
-    imp <- xgb.model.dt.tree(
-      feature_names = feature.names,
-      text = model_text_dump,
-      trees = trees
-    )[
-      Feature != "Leaf", .(
-        Gain = sum(Quality),
-        Cover = sum(Cover),
-        Frequency = .N
-      ),
-      by = Feature
-    ][
-      , `:=`(
-        Gain = Gain / sum(Gain),
-        Cover = Cover / sum(Cover),
-        Frequency = Frequency / sum(Frequency)
-      )
-    ][
-      order(Gain, decreasing = TRUE)
-    ]
-    imp
-  }
-  expect_equal(importance_from_dump(), importance, tolerance = 1e-6)
-
-  ## decision stump
-  m <- xgboost::xgboost(
-    data = as.matrix(data.frame(x = c(0, 1))),
-    label = c(1, 2),
-    nrounds = 1
-  )
-  df <- xgb.model.dt.tree(model = m)
-  expect_equal(df$Feature, "Leaf")
-  expect_equal(df$Cover, 2)
+  xgb.importance(model = mbst.Tree, trees = seq(from = 0, by = nclass, length.out = nrounds))
 })
 
 test_that("xgb.importance works with GLM model", {
@@ -379,8 +335,8 @@ test_that("xgb.model.dt.tree and xgb.importance work with a single split model",
 })
 
 test_that("xgb.plot.tree works with and without feature names", {
-  expect_silent(xgb.plot.tree(feature_names = feature.names, model = bst.Tree))
-  expect_silent(xgb.plot.tree(model = bst.Tree))
+  xgb.plot.tree(feature_names = feature.names, model = bst.Tree)
+  xgb.plot.tree(model = bst.Tree)
 })
 
 test_that("xgb.plot.multi.trees works with and without feature names", {
@@ -395,47 +351,11 @@ test_that("xgb.plot.deepness works", {
   xgb.ggplot.deepness(model = bst.Tree)
 })
 
-test_that("xgb.shap.data works when top_n is provided", {
-  data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2)
-  expect_equal(names(data_list), c("data", "shap_contrib"))
-  expect_equal(NCOL(data_list$data), 2)
-  expect_equal(NCOL(data_list$shap_contrib), 2)
-  expect_equal(NROW(data_list$data), NROW(data_list$shap_contrib))
-  expect_gt(length(colnames(data_list$data)), 0)
-  expect_gt(length(colnames(data_list$shap_contrib)), 0)
-
-  # for multiclass without target class provided
-  data_list <- xgb.shap.data(data = as.matrix(iris[, -5]), model = mbst.Tree, top_n = 2)
-  expect_equal(dim(data_list$shap_contrib), c(nrow(iris), 2))
-  # for multiclass with target class provided
-  data_list <- xgb.shap.data(data = as.matrix(iris[, -5]), model = mbst.Tree, top_n = 2, target_class = 0)
-  expect_equal(dim(data_list$shap_contrib), c(nrow(iris), 2))
-})
-
-test_that("xgb.shap.data works with subsampling", {
-  data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2, subsample = 0.8)
-  expect_equal(NROW(data_list$data), as.integer(0.8 * nrow(sparse_matrix)))
-  expect_equal(NROW(data_list$data), NROW(data_list$shap_contrib))
-})
-
-test_that("prepare.ggplot.shap.data works", {
-  data_list <- xgb.shap.data(data = sparse_matrix, model = bst.Tree, top_n = 2)
-  plot_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
-  expect_s3_class(plot_data, "data.frame")
-  expect_equal(names(plot_data), c("id", "feature", "feature_value", "shap_value"))
-  expect_s3_class(plot_data$feature, "factor")
-  # Each observation should have 1 row for each feature
-  expect_equal(nrow(plot_data), nrow(sparse_matrix) * 2)
-})
-
 test_that("xgb.plot.shap works", {
   sh <- xgb.plot.shap(data = sparse_matrix, model = bst.Tree, top_n = 2, col = 4)
   expect_equal(names(sh), c("data", "shap_contrib"))
-})
-
-test_that("xgb.plot.shap.summary works", {
-  expect_silent(xgb.plot.shap.summary(data = sparse_matrix, model = bst.Tree, top_n = 2))
-  expect_silent(xgb.ggplot.shap.summary(data = sparse_matrix, model = bst.Tree, top_n = 2))
+  expect_equal(NCOL(sh$data), 2)
+  expect_equal(NCOL(sh$shap_contrib), 2)
 })
 
 test_that("check.deprecation works", {
@@ -454,26 +374,3 @@ test_that("check.deprecation works", {
   , "\'dumm\' was partially matched to \'dummy\'")
   expect_equal(res, list(a = 1, DUMMY = 22))
 })
-
-test_that('convert.labels works', {
-  y <- c(0, 1, 0, 0, 1)
-  for (objective in c('binary:logistic', 'binary:logitraw', 'binary:hinge')) {
-    res <- xgboost:::convert.labels(y, objective_name = objective)
-    expect_s3_class(res, 'factor')
-    expect_equal(res, factor(res))
-  }
-  y <- c(0, 1, 3, 2, 1, 4)
-  for (objective in c('multi:softmax', 'multi:softprob', 'rank:pairwise', 'rank:ndcg',
-                      'rank:map')) {
-    res <- xgboost:::convert.labels(y, objective_name = objective)
-    expect_s3_class(res, 'factor')
-    expect_equal(res, factor(res))
-  }
-  y <- c(1.2, 3.0, -1.0, 10.0)
-  for (objective in c('reg:squarederror', 'reg:squaredlogerror', 'reg:logistic',
-                      'reg:pseudohubererror', 'count:poisson', 'survival:cox', 'survival:aft',
-                      'reg:gamma', 'reg:tweedie')) {
-    res <- xgboost:::convert.labels(y, objective_name = objective)
-    expect_equal(class(res), 'numeric')
-  }
-})

R-package/tests/testthat/test_interactions.R

@@ -1,6 +1,7 @@
 context('Test prediction of feature interactions')
 
 require(xgboost)
+require(magrittr)
 
 set.seed(123)
 
@@ -31,7 +32,7 @@ test_that("predict feature interactions works", {
   cont <- predict(b, dm, predcontrib = TRUE)
   expect_equal(dim(cont), c(N, P + 1))
   # make sure for each row they add up to marginal predictions
-  expect_lt(max(abs(rowSums(cont) - pred)), 0.001)
+  max(abs(rowSums(cont) - pred)) %>% expect_lt(0.001)
   # Hand-construct the 'ground truth' feature contributions:
   gt_cont <- cbind(
       2. * X[, 1],
@@ -51,24 +52,21 @@ test_that("predict feature interactions works", {
   expect_equal(dimnames(intr), list(NULL, cn, cn))
 
   # check the symmetry
-  expect_lt(max(abs(aperm(intr, c(1, 3, 2)) - intr)), 0.00001)
+  max(abs(aperm(intr, c(1, 3, 2)) - intr)) %>% expect_lt(0.00001)
 
   # sums WRT columns must be close to feature contributions
-  expect_lt(max(abs(apply(intr, c(1, 2), sum) - cont)), 0.00001)
+  max(abs(apply(intr, c(1, 2), sum) - cont)) %>% expect_lt(0.00001)
 
   # diagonal terms for features 3,4,5 must be close to zero
-  expect_lt(Reduce(max, sapply(3:P, function(i) max(abs(intr[, i, i])))), 0.05)
+  Reduce(max, sapply(3:P, function(i) max(abs(intr[, i, i])))) %>% expect_lt(0.05)
 
   # BIAS must have no interactions
-  expect_lt(max(abs(intr[, 1:P, P + 1])), 0.00001)
+  max(abs(intr[, 1:P, P + 1])) %>% expect_lt(0.00001)
 
   # interactions other than 2 x 3 must be close to zero
   intr23 <- intr
   intr23[, 2, 3] <- 0
-  expect_lt(
-    Reduce(max, sapply(1:P, function(i) max(abs(intr23[, i, (i + 1):(P + 1)])))),
-    0.05
-  )
+  Reduce(max, sapply(1:P, function(i) max(abs(intr23[, i, (i + 1):(P + 1)])))) %>% expect_lt(0.05)
 
   # Construct the 'ground truth' contributions of interactions directly from the linear terms:
   gt_intr <- array(0, c(N, P + 1, P + 1))
@@ -121,64 +119,23 @@ test_that("multiclass feature interactions work", {
   dm <- xgb.DMatrix(as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1)
   param <- list(eta = 0.1, max_depth = 4, objective = 'multi:softprob', num_class = 3)
   b <- xgb.train(param, dm, 40)
-  pred <- t(
-    array(
-      data = predict(b, dm, outputmargin = TRUE),
-      dim = c(3, 150)
-    )
-  )
+  pred <- predict(b, dm, outputmargin = TRUE) %>% array(c(3, 150)) %>% t
 
   # SHAP contributions:
   cont <- predict(b, dm, predcontrib = TRUE)
   expect_length(cont, 3)
   # rewrap them as a 3d array
-  cont <- array(
-    data = unlist(cont),
-    dim = c(150, 5,  3)
-  )
-
+  cont <- unlist(cont) %>% array(c(150, 5, 3))
   # make sure for each row they add up to marginal predictions
-  expect_lt(max(abs(apply(cont, c(1, 3), sum) - pred)), 0.001)
+  max(abs(apply(cont, c(1, 3), sum) - pred)) %>% expect_lt(0.001)
 
   # SHAP interaction contributions:
   intr <- predict(b, dm, predinteraction = TRUE)
   expect_length(intr, 3)
   # rewrap them as a 4d array
-  intr <- aperm(
-    a = array(
-      data = unlist(intr),
-      dim = c(150, 5, 5, 3)
-    ),
-    perm = c(4, 1, 2, 3)  # [grp, row, col, col]
-  )
-
+  intr <- unlist(intr) %>% array(c(150, 5, 5, 3)) %>% aperm(c(4, 1, 2, 3)) # [grp, row, col, col]
   # check the symmetry
-  expect_lt(max(abs(aperm(intr, c(1, 2, 4, 3)) - intr)), 0.00001)
+  max(abs(aperm(intr, c(1, 2, 4, 3)) - intr)) %>% expect_lt(0.00001)
   # sums WRT columns must be close to feature contributions
-  expect_lt(max(abs(apply(intr, c(1, 2, 3), sum) - aperm(cont, c(3, 1, 2)))), 0.00001)
-})
-
-
-test_that("SHAP single sample works", {
-  train <- agaricus.train
-  test <- agaricus.test
-  booster <- xgboost(
-    data = train$data,
-    label = train$label,
-    max_depth = 2,
-    nrounds = 4,
-    objective = "binary:logistic",
-  )
-
-  predt <- predict(
-    booster,
-    newdata = train$data[1, , drop = FALSE], predcontrib = TRUE
-  )
-  expect_equal(dim(predt), c(1, dim(train$data)[2] + 1))
-
-  predt <- predict(
-    booster,
-    newdata = train$data[1, , drop = FALSE], predinteraction = TRUE
-  )
-  expect_equal(dim(predt), c(1, dim(train$data)[2] + 1, dim(train$data)[2] + 1))
+  max(abs(apply(intr, c(1, 2, 3), sum) - aperm(cont, c(3, 1, 2)))) %>% expect_lt(0.00001)
 })

R-package/tests/testthat/test_io.R

@@ -1,30 +0,0 @@
-context("Test model IO.")
-## some other tests are in test_basic.R
-require(xgboost)
-require(testthat)
-
-data(agaricus.train, package = "xgboost")
-data(agaricus.test, package = "xgboost")
-train <- agaricus.train
-test <- agaricus.test
-
-test_that("load/save raw works", {
-  nrounds <- 8
-  booster <- xgboost(
-    data = train$data, label = train$label,
-    nrounds = nrounds, objective = "binary:logistic"
-  )
-
-  json_bytes <- xgb.save.raw(booster, raw_format = "json")
-  ubj_bytes <- xgb.save.raw(booster, raw_format = "ubj")
-  old_bytes <- xgb.save.raw(booster, raw_format = "deprecated")
-
-  from_json <- xgb.load.raw(json_bytes, as_booster = TRUE)
-  from_ubj <- xgb.load.raw(ubj_bytes, as_booster = TRUE)
-
-  json2old <- xgb.save.raw(from_json, raw_format = "deprecated")
-  ubj2old <- xgb.save.raw(from_ubj, raw_format = "deprecated")
-
-  expect_equal(json2old, ubj2old)
-  expect_equal(json2old, old_bytes)
-})

R-package/tests/testthat/test_model_compatibility.R

@@ -1,16 +1,10 @@
 require(xgboost)
 require(jsonlite)
+source('../generate_models_params.R')
 
 context("Models from previous versions of XGBoost can be loaded")
 
-metadata <- list(
-  kRounds = 2,
-  kRows = 1000,
-  kCols = 4,
-  kForests = 2,
-  kMaxDepth = 2,
-  kClasses = 3
-)
+metadata <- model_generator_metadata()
 
 run_model_param_check <- function (config) {
   testthat::expect_equal(config$learner$learner_model_param$num_feature, '4')
@@ -39,10 +33,6 @@ run_booster_check <- function (booster, name) {
     testthat::expect_equal(config$learner$learner_train_param$objective, 'multi:softmax')
     testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class),
                            metadata$kClasses)
-  } else if (name == 'logitraw') {
-    testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
-    testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
-    testthat::expect_equal(config$learner$learner_train_param$objective, 'binary:logitraw')
   } else if (name == 'logit') {
     testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
     testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
@@ -65,7 +55,7 @@ test_that("Models from previous versions of XGBoost can be loaded", {
   zipfile <- file.path(getwd(), file_name)
   model_dir <- file.path(getwd(), 'models')
   download.file(paste('https://', bucket, '.s3-', region, '.amazonaws.com/', file_name, sep = ''),
-                destfile = zipfile, mode = 'wb', quiet = TRUE)
+                destfile = zipfile, mode = 'wb')
   unzip(zipfile, overwrite = TRUE)
 
   pred_data <- xgb.DMatrix(matrix(c(0, 0, 0, 0), nrow = 1, ncol = 4))
@@ -76,35 +66,13 @@ test_that("Models from previous versions of XGBoost can be loaded", {
     m <- regmatches(model_file, m)[[1]]
     model_xgb_ver <- m[2]
     name <- m[3]
-    is_rds <- endsWith(model_file, '.rds')
 
-    cpp_warning <- capture.output({
-      # Expect an R warning when a model is loaded from RDS and it was generated by version < 1.1.x
-      if (is_rds && compareVersion(model_xgb_ver, '1.1.1.1') < 0) {
-        booster <- readRDS(model_file)
-        expect_warning(predict(booster, newdata = pred_data))
-        booster <- readRDS(model_file)
-        expect_warning(run_booster_check(booster, name))
-      } else {
-        if (is_rds) {
-          booster <- readRDS(model_file)
-        } else {
-          booster <- xgb.load(model_file)
-        }
-        predict(booster, newdata = pred_data)
-        run_booster_check(booster, name)
-      }
-    })
-    if (compareVersion(model_xgb_ver, '1.0.0.0') < 0) {
-      # Expect a C++ warning when a model was generated in version < 1.0.x
-      m <- grepl(paste0('.*Loading model from XGBoost < 1\\.0\\.0, consider saving it again for ',
-                        'improved compatibility.*'), cpp_warning, perl = TRUE)
-      expect_true(length(m) > 0 && all(m))
-    } else if (is_rds && model_xgb_ver == '1.1.1.1') {
-      # Expect a C++ warning when a model is loaded from RDS and it was generated by version 1.1.x
-      m <- grepl(paste0('.*Attempted to load internal configuration for a model file that was ',
-                        'generated by a previous version of XGBoost.*'), cpp_warning, perl = TRUE)
-      expect_true(length(m) > 0 && all(m))
+    if (endsWith(model_file, '.rds')) {
+      booster <- readRDS(model_file)
+    } else {
+      booster <- xgb.load(model_file)
     }
+    predict(booster, newdata = pred_data)
+    run_booster_check(booster, name)
   })
 })