Change version to 1.5.0. (#7258)

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>

.clang-tidy

@@ -1,21 +1,21 @@
 Checks: 'modernize-*,-modernize-make-*,-modernize-use-auto,-modernize-raw-string-literal,-modernize-avoid-c-arrays,-modernize-use-trailing-return-type,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
 CheckOptions:
-  - { key: readability-identifier-naming.ClassCase,           value: CamelCase  }
-  - { key: readability-identifier-naming.StructCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypeAliasCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypedefCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.TypeTemplateParameterCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.MemberCase,          value: lower_case  }
-  - { key: readability-identifier-naming.PrivateMemberSuffix,    value: '_'  }
-  - { key: readability-identifier-naming.ProtectedMemberSuffix,  value: '_'  }
-  - { key: readability-identifier-naming.EnumCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstant,          value: CamelCase  }
-  - { key: readability-identifier-naming.EnumConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.GlobalConstantCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.GlobalConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.StaticConstantCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.StaticConstantPrefix,          value: k  }
-  - { key: readability-identifier-naming.ConstexprVariableCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.ConstexprVariablePrefix,          value: k  }
-  - { key: readability-identifier-naming.FunctionCase,          value: CamelCase  }
-  - { key: readability-identifier-naming.NamespaceCase,       value: lower_case }
+  - { key: readability-identifier-naming.ClassCase,                 value: CamelCase  }
+  - { key: readability-identifier-naming.StructCase,                value: CamelCase  }
+  - { key: readability-identifier-naming.TypeAliasCase,             value: CamelCase  }
+  - { key: readability-identifier-naming.TypedefCase,               value: CamelCase  }
+  - { key: readability-identifier-naming.TypeTemplateParameterCase, value: CamelCase  }
+  - { key: readability-identifier-naming.MemberCase,                value: lower_case }
+  - { key: readability-identifier-naming.PrivateMemberSuffix,       value: '_'        }
+  - { key: readability-identifier-naming.ProtectedMemberSuffix,     value: '_'        }
+  - { key: readability-identifier-naming.EnumCase,                  value: CamelCase  }
+  - { key: readability-identifier-naming.EnumConstant,              value: CamelCase  }
+  - { key: readability-identifier-naming.EnumConstantPrefix,        value: k          }
+  - { key: readability-identifier-naming.GlobalConstantCase,        value: CamelCase  }
+  - { key: readability-identifier-naming.GlobalConstantPrefix,      value: k          }
+  - { key: readability-identifier-naming.StaticConstantCase,        value: CamelCase  }
+  - { key: readability-identifier-naming.StaticConstantPrefix,      value: k          }
+  - { key: readability-identifier-naming.ConstexprVariableCase,     value: CamelCase  }
+  - { key: readability-identifier-naming.ConstexprVariablePrefix,   value: k          }
+  - { key: readability-identifier-naming.FunctionCase,              value: CamelCase  }
+  - { key: readability-identifier-naming.NamespaceCase,             value: lower_case }

.github/FUNDING.yml

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

.github/workflows/jvm_tests.yml

@@ -0,0 +1,74 @@
+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]
+
+    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

@@ -0,0 +1,232 @@
+# This is a basic workflow to help you get started with Actions
+
+name: XGBoost-CI
+
+# Controls when the action will run. Triggers the workflow on push or pull request
+# events but only for the master branch
+on: [push, pull_request]
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  gtest-cpu:
+    name: Test Google C++ test (CPU)
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-10.15]
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - name: Install system packages
+      run: |
+        # Use libomp 11.1.0: https://github.com/dmlc/xgboost/issues/7039
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
+        brew install ninja libomp
+        brew pin libomp
+    - name: Build gtest binary
+      run: |
+        mkdir build
+        cd build
+        cmake .. -DGOOGLE_TEST=ON -DUSE_OPENMP=ON -DUSE_DMLC_GTEST=ON -DPLUGIN_DENSE_PARSER=ON -GNinja
+        ninja -v
+    - name: Run gtest binary
+      run: |
+        cd build
+        ./testxgboost
+        ctest -R TestXGBoostCLI --extra-verbose
+
+  gtest-cpu-nonomp:
+    name: Test Google C++ unittest (CPU Non-OMP)
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - name: Install system packages
+      run: |
+        sudo apt-get install -y --no-install-recommends ninja-build
+    - name: Build and install XGBoost
+      shell: bash -l {0}
+      run: |
+        mkdir build
+        cd build
+        cmake .. -GNinja -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON -DUSE_OPENMP=OFF
+        ninja -v
+    - name: Run gtest binary
+      run: |
+        cd build
+        ctest --extra-verbose
+
+  c-api-demo:
+    name: Test installing XGBoost lib + building the C API demo
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"]
+        python-version: ["3.8"]
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - name: Install system packages
+      run: |
+        sudo apt-get install -y --no-install-recommends ninja-build
+    - uses: conda-incubator/setup-miniconda@v2
+      with:
+        auto-update-conda: true
+        python-version: ${{ matrix.python-version }}
+        activate-environment: test
+    - name: Display Conda env
+      shell: bash -l {0}
+      run: |
+        conda info
+        conda list
+    - name: Build and install XGBoost static library
+      shell: bash -l {0}
+      run: |
+        mkdir build
+        cd build
+        cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
+        ninja -v install
+        cd -
+    - name: Build and run C API demo with static
+      shell: bash -l {0}
+      run: |
+        pushd .
+        cd demo/c-api/
+        mkdir build
+        cd build
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        ninja -v
+        ctest
+        cd ..
+        rm -rf ./build
+        popd
+    - name: Build and install XGBoost shared library
+      shell: bash -l {0}
+      run: |
+        cd build
+        cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
+        ninja -v install
+        cd -
+    - name: Build and run C API demo with shared
+      shell: bash -l {0}
+      run: |
+        pushd .
+        cd demo/c-api/
+        mkdir build
+        cd build
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        ninja -v
+        ctest
+        popd
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
+
+  lint:
+    runs-on: ubuntu-latest
+    name: Code linting for Python and C++
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+        architecture: 'x64'
+    - name: Install Python packages
+      run: |
+        python -m pip install wheel setuptools
+        python -m pip install pylint cpplint numpy scipy scikit-learn
+    - name: Run lint
+      run: |
+        make lint
+
+  mypy:
+    runs-on: ubuntu-latest
+    name: Type checking for Python
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+        architecture: 'x64'
+    - name: Install Python packages
+      run: |
+        python -m pip install wheel setuptools mypy pandas dask[complete] distributed
+    - name: Run mypy
+      run: |
+        make mypy
+
+  doxygen:
+    runs-on: ubuntu-latest
+    name: Generate C/C++ API doc using Doxygen
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+        architecture: 'x64'
+    - name: Install system packages
+      run: |
+        sudo apt-get install -y --no-install-recommends doxygen graphviz ninja-build
+        python -m pip install wheel setuptools
+        python -m pip install awscli
+    - name: Run Doxygen
+      run: |
+        mkdir build
+        cd build
+        cmake .. -DBUILD_C_DOC=ON -GNinja
+        ninja -v doc_doxygen
+    - name: Extract branch name
+      shell: bash
+      run: echo "##[set-output name=branch;]$(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 }}

.github/workflows/python_tests.yml

@@ -0,0 +1,94 @@
+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: |
+        # Use libomp 11.1.0: https://github.com/dmlc/xgboost/issues/7039
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
+        brew install ninja libomp
+        brew pin libomp
+    - name: 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:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    strategy:
+      matrix:
+        config:
+          - {os: windows-2016, compiler: 'msvc', 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_test
+        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 with msvc
+      shell: bash -l {0}
+      if: matrix.config.compiler == 'msvc'
+      run: |
+        mkdir build_msvc
+        cd build_msvc
+        cmake .. -G"Visual Studio 15 2017" -DCMAKE_CONFIGURATION_TYPES="Release" -A x64 -DGOOGLE_TEST=ON  -DUSE_DMLC_GTEST=ON
+        cmake --build . --config Release --parallel $(nproc)
+
+    - name: Install Python package
+      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/r_nold.yml

@@ -0,0 +1,44 @@
+# 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

@@ -0,0 +1,138 @@
+name: XGBoost-R-Tests
+
+on: [push, pull_request]
+
+env:
+  R_PACKAGES: c('XML', 'igraph', '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 }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+
+    - name: 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-2016, r: 'release', compiler: 'mingw', build: 'autotools'}
+          - {os: windows-2016, r: 'release', compiler: 'msvc', build: 'cmake'}
+          - {os: windows-2016, r: 'release', compiler: 'mingw', build: 'cmake'}
+    env:
+      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
+      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 }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         repos = 'http://cloud.r-project.org',
+                         dependencies = c('Depends', 'Imports', 'LinkingTo'))
+
+    - 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
+
+    - name: Cache R packages
+      uses: actions/cache@v2
+      with:
+        path: ${{ env.R_LIBS_USER }}
+        key: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+        restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-2-${{ hashFiles('R-package/DESCRIPTION') }}
+
+    - name: Install dependencies
+      shell: Rscript {0}
+      run: |
+        install.packages(${{ env.R_PACKAGES }},
+                         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

@@ -51,6 +51,7 @@ Debug
 #.Rbuildignore
 R-package.Rproj
 *.cache*
+.mypy_cache/
 # java
 java/xgboost4j/target
 java/xgboost4j/tmp
@@ -65,12 +66,12 @@ nb-configuration*
 .pydevproject
 .settings/
 build
-config.mk
 /xgboost
 *.data
 build_plugin
 recommonmark/
 tags
+TAGS
 *.class
 target
 *.swp
@@ -93,6 +94,7 @@ metastore_db
 # files from R-package source install
 **/config.status
 R-package/src/Makevars
+*.lib
 
 # Visual Studio Code
 /.vscode/
@@ -101,3 +103,25 @@ R-package/src/Makevars
 .idea
 *.iml
 /cmake-build-debug/
+
+# GDB
+.gdb_history
+
+# Python joblib.Memory used in pytest.
+cachedir/
+
+# Files from local Dask work
+dask-worker-space/
+
+# Jupyter notebook checkpoints
+.ipynb_checkpoints/
+
+# credentials and key material
+config
+credentials
+credentials.csv
+*.env
+*.pem
+*.pub
+*.rdp
+*_rsa

.gitmodules

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

.travis.yml

@@ -1,50 +1,38 @@
-# disable sudo for container build.
 sudo: required
 
-# Enabling test OS X
-os:
-  - linux
-  - osx
-
-osx_image: xcode10.3
 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="
 
-matrix:
-  exclude:
-    - os: linux
+
+jobs:
+  include:
+    - os: osx
+      arch: amd64
+      osx_image: xcode10.2
       env: TASK=python_test
-    - os: linux
+    - os: osx
+      arch: amd64
+      osx_image: xcode10.2
       env: TASK=java_test
     - os: linux
-      env: TASK=cmake_test
+      arch: s390x
+      env: TASK=s390x_test
 
 # dependent brew packages
+# the dependencies from homebrew is installed manually from setup script due to outdated image from travis.
 addons:
   homebrew:
+    update: false
+  apt:
     packages:
-      - cmake
-      - libomp
-      - graphviz
-      - openssl
-      - libgit2
-      - wget
-      - r
-    update: true
+      - unzip
 
 before_install:
-  - source dmlc-core/scripts/travis/travis_setup_env.sh
+  - 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
 
@@ -60,7 +48,7 @@ cache:
     - ${HOME}/.cache/pip
 
 before_cache:
-  - dmlc-core/scripts/travis/travis_before_cache.sh
+  - tests/travis/travis_before_cache.sh
 
 after_failure:
   - tests/travis/travis_after_failure.sh

CMakeLists.txt

@@ -1,8 +1,11 @@
-cmake_minimum_required(VERSION 3.12)
-project(xgboost LANGUAGES CXX C VERSION 1.0.0)
+cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
+project(xgboost LANGUAGES CXX C VERSION 1.5.0)
 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))
   cmake_policy(SET CMP0077 NEW)
@@ -21,23 +24,32 @@ 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(RABIT_BUILD_MPI "Build MPI" OFF)
 ## Bindings
 option(JVM_BINDINGS "Build JVM bindings" OFF)
 option(R_LIB "Build shared library for R package" OFF)
 ## Dev
 option(USE_DEBUG_OUTPUT "Dump internal training results like gradients and predictions to stdout.
 Should only be used for debugging." OFF)
+option(FORCE_COLORED_OUTPUT "Force colored output from compilers, useful when ninja is used instead of make." OFF)
+option(ENABLE_ALL_WARNINGS "Enable all compiler warnings. Only effective for GCC/Clang" OFF)
+option(LOG_CAPI_INVOCATION "Log all C API invocations for debugging" OFF)
 option(GOOGLE_TEST "Build google tests" OFF)
 option(USE_DMLC_GTEST "Use google tests bundled with dmlc-core submodule" OFF)
+option(USE_DEVICE_DEBUG "Generate CUDA device debug info." OFF)
 option(USE_NVTX "Build with cuda profiling annotations. Developers only." OFF)
 set(NVTX_HEADER_DIR "" CACHE PATH "Path to the stand-alone nvtx header")
 option(RABIT_MOCK "Build rabit with mock" OFF)
+option(HIDE_CXX_SYMBOLS "Build shared library and hide all C++ symbols" OFF)
 ## CUDA
 option(USE_CUDA  "Build with GPU acceleration" OFF)
 option(USE_NCCL  "Build with NCCL to enable distributed GPU support." OFF)
 option(BUILD_WITH_SHARED_NCCL "Build with shared NCCL library." OFF)
+option(BUILD_WITH_CUDA_CUB "Build with cub in CUDA installation" OFF)
 set(GPU_COMPUTE_VER "" CACHE STRING
   "Semicolon separated list of compute versions to be built against, e.g. '35;61'")
 ## Copied From dmlc
@@ -49,10 +61,13 @@ option(USE_SANITIZER "Use santizer flags" OFF)
 option(SANITIZER_PATH "Path to sanitizes.")
 set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
   "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
-address, leak and thread.")
+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
 if (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
@@ -61,6 +76,9 @@ 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))
@@ -74,6 +92,29 @@ 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)
@@ -82,17 +123,28 @@ 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 (${CMAKE_CUDA_COMPILER_VERSION} VERSION_LESS 10.1)
+    message(FATAL_ERROR "CUDA version must be at least 10.1!")
+  endif()
   set(GEN_CODE "")
   format_gencode_flags("${GPU_COMPUTE_VER}" GEN_CODE)
-  message(STATUS "CUDA GEN_CODE: ${GEN_CODE}")
+  add_subdirectory(${PROJECT_SOURCE_DIR}/gputreeshap)
 endif (USE_CUDA)
 
+if (FORCE_COLORED_OUTPUT AND (CMAKE_GENERATOR STREQUAL "Ninja") AND
+    ((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") OR
+      (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")))
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-color=always")
+endif()
+
+find_package(Threads REQUIRED)
+
 if (USE_OPENMP)
   if (APPLE)
     # Require CMake 3.16+ on Mac OSX, as previous versions of CMake had trouble locating
@@ -102,67 +154,82 @@ if (USE_OPENMP)
   find_package(OpenMP REQUIRED)
 endif (USE_OPENMP)
 
+if (USE_NCCL)
+  find_package(Nccl REQUIRED)
+endif (USE_NCCL)
+
 # dmlc-core
 msvc_use_static_runtime()
 add_subdirectory(${xgboost_SOURCE_DIR}/dmlc-core)
-set_target_properties(dmlc PROPERTIES
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON
-  POSITION_INDEPENDENT_CODE ON)
-list(APPEND LINKED_LIBRARIES_PRIVATE dmlc)
+
+if (MSVC)
+  if (TARGET dmlc_unit_tests)
+    target_compile_options(dmlc_unit_tests PRIVATE
+                           -D_CRT_SECURE_NO_WARNINGS -D_CRT_SECURE_NO_DEPRECATE)
+  endif (TARGET dmlc_unit_tests)
+endif (MSVC)
 
 # rabit
-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)
 
-if (RABIT_MOCK)
-  list(APPEND LINKED_LIBRARIES_PRIVATE rabit_mock_static)
-else()
-  list(APPEND LINKED_LIBRARIES_PRIVATE rabit)
-endif(RABIT_MOCK)
+# core xgboost
+add_subdirectory(${xgboost_SOURCE_DIR}/src)
+target_link_libraries(objxgboost PUBLIC dmlc)
 
 # Exports some R specific definitions and objects
 if (R_LIB)
   add_subdirectory(${xgboost_SOURCE_DIR}/R-package)
 endif (R_LIB)
 
-# core xgboost
-add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
-add_subdirectory(${xgboost_SOURCE_DIR}/src)
-set(XGBOOST_OBJ_SOURCES "${XGBOOST_OBJ_SOURCES};$<TARGET_OBJECTS:objxgboost>")
-
-#-- Shared library
-add_library(xgboost SHARED ${XGBOOST_OBJ_SOURCES})
-target_include_directories(xgboost
-  INTERFACE
-  $<INSTALL_INTERFACE:${CMAKE_INSTALL_PREFIX}/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
-target_link_libraries(xgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
-
 # This creates its own shared library `xgboost4j'.
 if (JVM_BINDINGS)
   add_subdirectory(${xgboost_SOURCE_DIR}/jvm-packages)
 endif (JVM_BINDINGS)
+
+# Plugin
+add_subdirectory(${xgboost_SOURCE_DIR}/plugin)
+
+#-- library
+if (BUILD_STATIC_LIB)
+  add_library(xgboost STATIC)
+else (BUILD_STATIC_LIB)
+  add_library(xgboost SHARED)
+endif (BUILD_STATIC_LIB)
+target_link_libraries(xgboost PRIVATE objxgboost)
+target_include_directories(xgboost
+  INTERFACE
+  $<INSTALL_INTERFACE:$<INSTALL_PREFIX>/include>
+  $<BUILD_INTERFACE:${CMAKE_CURRENT_LIST_DIR}/include>)
 #-- End shared library
 
 #-- CLI for xgboost
-add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc ${XGBOOST_OBJ_SOURCES})
-
+add_executable(runxgboost ${xgboost_SOURCE_DIR}/src/cli_main.cc)
+target_link_libraries(runxgboost PRIVATE objxgboost)
 target_include_directories(runxgboost
   PRIVATE
   ${xgboost_SOURCE_DIR}/include
   ${xgboost_SOURCE_DIR}/dmlc-core/include
-  ${xgboost_SOURCE_DIR}/rabit/include)
-target_link_libraries(runxgboost PRIVATE ${LINKED_LIBRARIES_PRIVATE})
-set_target_properties(
-  runxgboost PROPERTIES
-  OUTPUT_NAME xgboost
-  CXX_STANDARD 11
-  CXX_STANDARD_REQUIRED ON)
+  ${xgboost_SOURCE_DIR}/rabit/include
+)
+set_target_properties(runxgboost PROPERTIES OUTPUT_NAME xgboost)
 #-- End CLI for xgboost
 
+# Common setup for all targets
+foreach(target xgboost objxgboost dmlc runxgboost)
+  xgboost_target_properties(${target})
+  xgboost_target_link_libraries(${target})
+  xgboost_target_defs(${target})
+endforeach()
+
+if (JVM_BINDINGS)
+  xgboost_target_properties(xgboost4j)
+  xgboost_target_link_libraries(xgboost4j)
+  xgboost_target_defs(xgboost4j)
+endif (JVM_BINDINGS)
+
 set_output_directory(runxgboost ${xgboost_SOURCE_DIR})
 set_output_directory(xgboost ${xgboost_SOURCE_DIR}/lib)
 # Ensure these two targets do not build simultaneously, as they produce outputs with conflicting names
@@ -170,11 +237,12 @@ add_dependencies(xgboost runxgboost)
 
 #-- Installing XGBoost
 if (R_LIB)
+  include(cmake/RPackageInstallTargetSetup.cmake)
   set_target_properties(xgboost PROPERTIES PREFIX "")
   if (APPLE)
     set_target_properties(xgboost PROPERTIES SUFFIX ".so")
   endif (APPLE)
-  setup_rpackage_install_target(xgboost ${CMAKE_CURRENT_BINARY_DIR})
+  setup_rpackage_install_target(xgboost "${CMAKE_CURRENT_BINARY_DIR}/R-package-install")
   set(CMAKE_INSTALL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/dummy_inst")
 endif (R_LIB)
 if (MINGW)
@@ -186,12 +254,27 @@ 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(TARGETS xgboost runxgboost
+# Install libraries. If `xgboost` is a static lib, specify `objxgboost` also, to avoid the
+# following error:
+#
+#  > install(EXPORT ...) includes target "xgboost" which requires target "objxgboost" that is not
+#  > in any export set.
+#
+# https://github.com/dmlc/xgboost/issues/6085
+if (BUILD_STATIC_LIB)
+  set(INSTALL_TARGETS xgboost runxgboost objxgboost dmlc)
+else (BUILD_STATIC_LIB)
+  set(INSTALL_TARGETS xgboost runxgboost)
+endif (BUILD_STATIC_LIB)
+
+install(TARGETS ${INSTALL_TARGETS}
   EXPORT XGBoostTargets
   ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
   LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
@@ -221,12 +304,18 @@ install(
 if (GOOGLE_TEST)
   enable_testing()
   # Unittests.
+  add_executable(testxgboost)
+  target_link_libraries(testxgboost PRIVATE objxgboost)
+  xgboost_target_properties(testxgboost)
+  xgboost_target_link_libraries(testxgboost)
+  xgboost_target_defs(testxgboost)
+
   add_subdirectory(${xgboost_SOURCE_DIR}/tests/cpp)
+
   add_test(
     NAME TestXGBoostLib
     COMMAND testxgboost
     WORKING_DIRECTORY ${xgboost_BINARY_DIR})
-
   # CLI tests
   configure_file(
     ${xgboost_SOURCE_DIR}/tests/cli/machine.conf.in
@@ -245,3 +334,12 @@ endif (GOOGLE_TEST)
 # replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
 # for issues caused by mixing of /MD and /MT flags
 msvc_use_static_runtime()
+
+# Add xgboost.pc
+if (ADD_PKGCONFIG)
+  configure_file(${xgboost_SOURCE_DIR}/cmake/xgboost.pc.in ${xgboost_BINARY_DIR}/xgboost.pc @ONLY)
+
+  install(
+    FILES ${xgboost_BINARY_DIR}/xgboost.pc
+    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
+endif (ADD_PKGCONFIG)

CONTRIBUTORS.md

@@ -10,14 +10,14 @@ The Project Management Committee(PMC) consists group of active committers that m
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
 * [Michael Benesty](https://github.com/pommedeterresautee)
   - Michael is a lawyer and data scientist in France. He is the creator of XGBoost interactive analysis module in R.
-* [Yuan Tang](https://github.com/terrytangyuan), Ant Financial
-  - Yuan is a software engineer in Ant Financial. 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)
   - Jiaming contributed to the GPU algorithms. He has also introduced new abstractions to improve the quality of the C++ codebase.
-* [Hyunsu Cho](http://hyunsu-cho.io/), Amazon AI
-  - Hyunsu is an applied scientist in Amazon AI. He is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater.   
+* [Hyunsu Cho](http://hyunsu-cho.io/), NVIDIA
+  - Hyunsu is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater.
 * [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
   - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
 * [Hongliang Liu](https://github.com/phunterlau)
@@ -37,11 +37,13 @@ Committers are people who have made substantial contribution to the project and
   - Sergei is a software engineer in Criteo. He contributed mostly in JVM packages.
 * [Scott Lundberg](http://scottlundberg.com/), University of Washington
   - Scott is a Ph.D. student at University of Washington. He is the creator of SHAP, a unified approach to explain the output of machine learning models such as decision tree ensembles. He also helps maintain the XGBoost Julia package.
+* [Egor Smirnov](https://github.com/SmirnovEgorRu), Intel
+  - Egor has led a major effort to improve the performance of XGBoost on multi-core CPUs.
 
 
 Become a Committer
 ------------------
-XGBoost is a opensource project and we are actively looking for new committers who are willing to help maintaining and lead the project.
+XGBoost is a open source project and we are actively looking for new committers who are willing to help maintaining and lead the project.
 Committers comes from contributors who:
 * Made substantial contribution to the project.
 * Willing to spent time on maintaining and lead the project.
@@ -57,7 +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)
@@ -89,7 +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

@@ -6,6 +6,9 @@
 // Command to run command inside a docker container
 dockerRun = 'tests/ci_build/ci_build.sh'
 
+// Which CUDA version to use when building reference distribution wheel
+ref_cuda_ver = '10.1'
+
 import groovy.transform.Field
 
 @Field
@@ -31,29 +34,19 @@ pipeline {
 
   // Build stages
   stages {
-    stage('Jenkins Linux: Get sources') {
-      agent { label 'linux && cpu' }
+    stage('Jenkins Linux: Initialize') {
+      agent { label 'job_initializer' }
       steps {
         script {
+          def buildNumber = env.BUILD_NUMBER as int
+          if (buildNumber > 1) milestone(buildNumber - 1)
+          milestone(buildNumber)
+
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
+        sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
-        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') {
@@ -61,16 +54,21 @@ pipeline {
       steps {
         script {
           parallel ([
+            'clang-tidy': { ClangTidy() },
             'build-cpu': { BuildCPU() },
+            'build-cpu-arm64': { BuildCPUARM64() },
             'build-cpu-rabit-mock': { BuildCPUMock() },
-            'build-gpu-cuda9.0': { BuildCUDA(cuda_version: '9.0') },
-            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
+            // Build reference, distribution-ready Python wheel with CUDA 10.1
+            // using CentOS 7 image
             'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
+            // The build-gpu-* builds below use Ubuntu image
+            'build-gpu-cuda11.0': { BuildCUDA(cuda_version: '11.0', build_rmm: true) },
+            'build-gpu-rpkg': { BuildRPackageWithCUDA(cuda_version: '10.1') },
+            'build-jvm-packages-gpu-cuda10.1': { BuildJVMPackagesWithCUDA(spark_version: '3.0.0', cuda_version: '11.0') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '3.0.0') },
             'build-jvm-doc': { BuildJVMDoc() }
           ])
         }
-        milestone ordinal: 3
       }
     }
     stage('Jenkins Linux: Test') {
@@ -79,20 +77,27 @@ pipeline {
         script {
           parallel ([
             'test-python-cpu': { TestPythonCPU() },
-            'test-python-gpu-cuda9.0': { TestPythonGPU(cuda_version: '9.0') },
-            'test-python-gpu-cuda10.0': { TestPythonGPU(cuda_version: '10.0') },
-            'test-python-gpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1') },
-            'test-python-mgpu-cuda10.1': { TestPythonGPU(cuda_version: '10.1', multi_gpu: true) },
-            'test-cpp-gpu': { TestCppGPU(cuda_version: '10.1') },
-            'test-cpp-mgpu': { TestCppGPU(cuda_version: '10.1', multi_gpu: true) },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '2.4.3') },
+            'test-python-cpu-arm64': { TestPythonCPUARM64() },
+            // artifact_cuda_version doesn't apply to RMM tests; RMM tests will always match CUDA version between artifact and host env
+            'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.1', host_cuda_version: '11.0', test_rmm: true) },
+            'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
+            'test-python-mgpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '10.1', host_cuda_version: '11.0', multi_gpu: true, test_rmm: true) },
+            'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0', test_rmm: true) },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
             'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
-            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
-            'test-r-3.4.4': { TestR(use_r35: false) },
-            'test-r-3.5.3': { TestR(use_r35: true) }
+            'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') }
+          ])
+        }
+      }
+    }
+    stage('Jenkins Linux: Deploy') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '3.0.0') }
           ])
         }
-        milestone ordinal: 4
       }
     }
   }
@@ -113,13 +118,17 @@ def checkoutSrcs() {
   }
 }
 
+def GetCUDABuildContainerType(cuda_version) {
+  return (cuda_version == ref_cuda_ver) ? 'gpu_build_centos7' : 'gpu_build'
+}
+
 def ClangTidy() {
-  node('linux && cpu') {
+  node('linux && cpu_build') {
     unstash name: 'srcs'
     echo "Running clang-tidy job..."
     def container_type = "clang_tidy"
     def docker_binary = "docker"
-    def dockerArgs = "--build-arg CUDA_VERSION=9.2"
+    def dockerArgs = "--build-arg CUDA_VERSION_ARG=10.1"
     sh """
     ${dockerRun} ${container_type} ${docker_binary} ${dockerArgs} python3 tests/ci_build/tidy.py
     """
@@ -127,48 +136,6 @@ def ClangTidy() {
   }
 }
 
-def Lint() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running lint..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} make lint
-    """
-    deleteDir()
-  }
-}
-
-def SphinxDoc() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running sphinx-doc..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e SPHINX_GIT_BRANCH=${BRANCH_NAME}'"
-    sh """#!/bin/bash
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} make -C doc html
-    """
-    deleteDir()
-  }
-}
-
-def Doxygen() {
-  node('linux && cpu') {
-    unstash name: 'srcs'
-    echo "Running doxygen..."
-    def container_type = "cpu"
-    def docker_binary = "docker"
-    sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
-    """
-    echo 'Uploading doc...'
-    s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
-    deleteDir()
-  }
-}
-
 def BuildCPU() {
   node('linux && cpu') {
     unstash name: 'srcs'
@@ -176,17 +143,51 @@ def BuildCPU() {
     def container_type = "cpu"
     def docker_binary = "docker"
     sh """
-    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh
-    ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    ${dockerRun} ${container_type} ${docker_binary} rm -fv dmlc-core/include/dmlc/build_config_default.h
+      # This step is not necessary, but here we include it, to ensure that DMLC_CORE_USE_CMAKE flag is correctly propagated
+      # We want to make sure that we use the configured header build/dmlc/build_config.h instead of include/dmlc/build_config_default.h.
+      # See discussion at https://github.com/dmlc/xgboost/issues/5510
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DPLUGIN_DENSE_PARSER=ON
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
     """
     // Sanitizer test
     def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='-e ASAN_SYMBOLIZER_PATH=/usr/bin/llvm-symbolizer -e ASAN_OPTIONS=symbolize=1 -e UBSAN_OPTIONS=print_stacktrace=1:log_path=ubsan_error.log --cap-add SYS_PTRACE'"
-    def docker_args = "--build-arg CMAKE_VERSION=3.12"
     sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak;undefined" \
       -DCMAKE_BUILD_TYPE=Debug -DSANITIZER_PATH=/usr/lib/x86_64-linux-gnu/
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} build/testxgboost
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --exclude-regex AllTestsInDMLCUnitTests --extra-verbose"
     """
+
+    stash name: 'xgboost_cli', includes: 'xgboost'
+    deleteDir()
+  }
+}
+
+def BuildCPUARM64() {
+  node('linux && arm64') {
+    unstash name: 'srcs'
+    echo "Build CPU ARM64"
+    def container_type = "aarch64"
+    def docker_binary = "docker"
+    def wheel_tag = "manylinux2014_aarch64"
+    sh """
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_via_cmake.sh --conda-env=aarch64_test -DOPEN_MP:BOOL=ON -DHIDE_CXX_SYMBOL=ON
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd build && ctest --extra-verbose"
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
+    ${dockerRun} ${container_type} ${docker_binary} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl && python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}"
+    mv -v wheelhouse/*.whl python-package/dist/
+    # Make sure that libgomp.so is vendored in the wheel
+    ${dockerRun} ${container_type} ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp || exit -1"
+    """
+    echo 'Stashing Python wheel...'
+    stash name: "xgboost_whl_arm64_cpu", includes: 'python-package/dist/*.whl'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading Python wheel...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    }
+    stash name: 'xgboost_cli_arm64', includes: 'xgboost'
     deleteDir()
   }
 }
@@ -200,34 +201,103 @@ def BuildCPUMock() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_mock_cmake.sh
     """
-     echo 'Stashing rabit C++ test executable (xgboost)...'
+    echo 'Stashing rabit C++ test executable (xgboost)...'
     stash name: 'xgboost_rabit_tests', includes: 'xgboost'
     deleteDir()
   }
 }
 
-
 def BuildCUDA(args) {
-  node('linux && cpu') {
+  node('linux && cpu_build') {
     unstash name: 'srcs'
     echo "Build with CUDA ${args.cuda_version}"
-    def container_type = "gpu_build"
+    def container_type = GetCUDABuildContainerType(args.cuda_version)
     def docker_binary = "docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def arch_flag = ""
+    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
+      arch_flag = "-DGPU_COMPUTE_VER=75"
+    }
+    def wheel_tag = "manylinux2014_x86_64"
     sh """
-    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON
+    ${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} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux1_x86_64
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} ${wheel_tag}
     """
-    // Stash wheel for CUDA 9.0 target
-    if (args.cuda_version == '9.0') {
-      echo 'Stashing Python wheel...'
-      stash name: 'xgboost_whl_cuda9', includes: 'python-package/dist/*.whl'
+    if (args.cuda_version == ref_cuda_ver) {
+      sh """
+      ${dockerRun} auditwheel_x86_64 ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py wheelhouse/*.whl ${commit_id} ${wheel_tag}
+      mv -v wheelhouse/*.whl python-package/dist/
+      # Make sure that libgomp.so is vendored in the wheel
+      ${dockerRun} auditwheel_x86_64 ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
+      """
+    }
+    echo 'Stashing Python wheel...'
+    stash name: "xgboost_whl_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
+    if (args.cuda_version == ref_cuda_ver && (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release'))) {
+      echo 'Uploading Python wheel...'
       path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
       s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
-      echo 'Stashing C++ test executable (testxgboost)...'
-      stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost'
     }
+    echo 'Stashing C++ test executable (testxgboost)...'
+    stash name: "xgboost_cpp_tests_cuda${args.cuda_version}", includes: 'build/testxgboost'
+    if (args.build_rmm) {
+      echo "Build with CUDA ${args.cuda_version} and RMM"
+      container_type = "rmm"
+      docker_binary = "docker"
+      docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+      sh """
+      rm -rf build/
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON -DUSE_NCCL=ON -DPLUGIN_RMM=ON -DBUILD_WITH_CUDA_CUB=ON ${arch_flag}
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2014_x86_64
+      """
+      echo 'Stashing Python wheel...'
+      stash name: "xgboost_whl_rmm_cuda${args.cuda_version}", includes: 'python-package/dist/*.whl'
+      echo 'Stashing C++ test executable (testxgboost)...'
+      stash name: "xgboost_cpp_tests_rmm_cuda${args.cuda_version}", includes: 'build/testxgboost'
+    }
+    deleteDir()
+  }
+}
+
+def BuildRPackageWithCUDA(args) {
+  node('linux && cpu_build') {
+    unstash name: 'srcs'
+    def container_type = 'gpu_build_r_centos7'
+    def docker_binary = "docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_r_pkg_with_cuda.sh ${commit_id}
+      """
+      echo 'Uploading R tarball...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_linux_*.tar.gz'
+    }
+    deleteDir()
+  }
+}
+
+def BuildJVMPackagesWithCUDA(args) {
+  node('linux && mgpu') {
+    unstash name: 'srcs'
+    echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
+    def container_type = "jvm_gpu_build"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.cuda_version}"
+    def arch_flag = ""
+    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
+      arch_flag = "-DGPU_COMPUTE_VER=75"
+    }
+    // Use only 4 CPU cores
+    def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
+    sh """
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
+    """
+    echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
+    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
     deleteDir()
   }
 }
@@ -244,7 +314,7 @@ def BuildJVMPackages(args) {
     ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
     """
     echo 'Stashing XGBoost4J JAR...'
-    stash name: 'xgboost4j_jar', includes: 'jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar'
+    stash name: 'xgboost4j_jar', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
     deleteDir()
   }
 }
@@ -258,16 +328,19 @@ def BuildJVMDoc() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
     """
-    echo 'Uploading doc...'
-    s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading doc...'
+      s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
+    }
     deleteDir()
   }
 }
 
 def TestPythonCPU() {
   node('linux && cpu') {
-    unstash name: 'xgboost_whl_cuda9'
+    unstash name: "xgboost_whl_cuda${ref_cuda_ver}"
     unstash name: 'srcs'
+    unstash name: 'xgboost_cli'
     echo "Test Python CPU"
     def container_type = "cpu"
     def docker_binary = "docker"
@@ -278,66 +351,67 @@ def TestPythonCPU() {
   }
 }
 
-def TestPythonGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
-  node(nodeReq) {
-    unstash name: 'xgboost_whl_cuda9'
+def TestPythonCPUARM64() {
+  node('linux && arm64') {
+    unstash name: "xgboost_whl_arm64_cpu"
     unstash name: 'srcs'
-    echo "Test Python GPU: CUDA ${args.cuda_version}"
-    def container_type = "gpu"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh mgpu
-      """
-    } else {
-      echo "Using a single GPU"
-      sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh gpu
-      """
-    }
-    // For CUDA 10.0 target, run cuDF tests too
-    if (args.cuda_version == '10.0') {
-      echo "Running tests with cuDF..."
-      sh """
-      ${dockerRun} cudf ${docker_binary} ${docker_args} tests/ci_build/test_python.sh cudf
-      """
-    }
-    deleteDir()
-  }
-}
-
-def TestCppRabit() {
-  node(nodeReq) {
-    unstash name: 'xgboost_rabit_tests'
-    unstash name: 'srcs'
-    echo "Test C++, rabit mock on"
-    def container_type = "cpu"
+    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/runxgb.sh xgboost tests/ci_build/approx.conf.in
+    ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/test_python.sh cpu-arm64
     """
     deleteDir()
   }
 }
 
-def TestCppGPU(args) {
-  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
+def TestPythonGPU(args) {
+  def nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
+  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
   node(nodeReq) {
-    unstash name: 'xgboost_cpp_tests'
+    unstash name: "xgboost_whl_cuda${artifact_cuda_version}"
+    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
     unstash name: 'srcs'
-    echo "Test C++, CUDA ${args.cuda_version}"
+    echo "Test Python GPU: CUDA ${args.host_cuda_version}"
     def container_type = "gpu"
     def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION=${args.cuda_version}"
-    if (args.multi_gpu) {
-      echo "Using multiple GPUs"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=*.MGPU_*"
-    } else {
-      echo "Using a single GPU"
-      sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost --gtest_filter=-*.MGPU_*"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+    def mgpu_indicator = (args.multi_gpu) ? 'mgpu' : 'gpu'
+    // Allocate extra space in /dev/shm to enable NCCL
+    def docker_extra_params = (args.multi_gpu) ? "CI_DOCKER_EXTRA_PARAMS_INIT='--shm-size=4g'" : ''
+    sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator}"
+    if (args.test_rmm) {
+      sh "rm -rfv build/ python-package/dist/"
+      unstash name: "xgboost_whl_rmm_cuda${args.host_cuda_version}"
+      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
+      sh "${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_python.sh ${mgpu_indicator} --use-rmm-pool"
+    }
+    deleteDir()
+  }
+}
+
+def TestCppGPU(args) {
+  def nodeReq = 'linux && mgpu'
+  def artifact_cuda_version = (args.artifact_cuda_version) ?: ref_cuda_ver
+  node(nodeReq) {
+    unstash name: "xgboost_cpp_tests_cuda${artifact_cuda_version}"
+    unstash name: 'srcs'
+    echo "Test C++, CUDA ${args.host_cuda_version}"
+    def container_type = "gpu"
+    def docker_binary = "nvidia-docker"
+    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} build/testxgboost"
+    if (args.test_rmm) {
+      sh "rm -rfv build/"
+      unstash name: "xgboost_cpp_tests_rmm_cuda${args.host_cuda_version}"
+      echo "Test C++, CUDA ${args.host_cuda_version} with RMM"
+      container_type = "rmm"
+      docker_binary = "nvidia-docker"
+      docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "source activate gpu_test && build/testxgboost --use-rmm-pool --gtest_filter=-*DeathTest.*"
+      """
     }
     deleteDir()
   }
@@ -365,17 +439,15 @@ def CrossTestJVMwithJDK(args) {
   }
 }
 
-def TestR(args) {
+def DeployJVMPackages(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
-    """
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Deploying to xgboost-maven-repo S3 repo...'
+      sh """
+      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.1 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      """
+    }
     deleteDir()
   }
 }

Jenkinsfile-win64

@@ -10,17 +10,29 @@ def commit_id   // necessary to pass a variable from one stage to another
 
 pipeline {
   agent none
+
+  // Setup common job properties
+  options {
+    timestamps()
+    timeout(time: 240, unit: 'MINUTES')
+    buildDiscarder(logRotator(numToKeepStr: '10'))
+    preserveStashes()
+  }
+
   // Build stages
   stages {
-    stage('Jenkins Win64: Get sources') {
-      agent { label 'win64 && build' }
+    stage('Jenkins Win64: Initialize') {
+      agent { label 'job_initializer' }
       steps {
         script {
+          def buildNumber = env.BUILD_NUMBER as int
+          if (buildNumber > 1) milestone(buildNumber - 1)
+          milestone(buildNumber)
           checkoutSrcs()
           commit_id = "${GIT_COMMIT}"
         }
+        sh 'python3 tests/jenkins_get_approval.py'
         stash name: 'srcs'
-        milestone ordinal: 1
       }
     }
     stage('Jenkins Win64: Build') {
@@ -28,10 +40,10 @@ pipeline {
       steps {
         script {
           parallel ([
-            'build-win64-cuda9.0': { BuildWin64() }
+            'build-win64-cuda10.1': { BuildWin64() },
+            'build-rpkg-win64-cuda10.1': { BuildRPackageWithCUDAWin64() }
           ])
         }
-        milestone ordinal: 2
       }
     }
     stage('Jenkins Win64: Test') {
@@ -39,13 +51,9 @@ pipeline {
       steps {
         script {
           parallel ([
-            'test-win64-cpu': { TestWin64CPU() },
-            'test-win64-gpu-cuda9.0': { TestWin64GPU(cuda_target: 'cuda9') },
-            'test-win64-gpu-cuda10.0': { TestWin64GPU(cuda_target: 'cuda10_0') },
-            'test-win64-gpu-cuda10.1': { TestWin64GPU(cuda_target: 'cuda10_1') }
+            'test-win64-cuda10.1': { TestWin64() },
           ])
         }
-        milestone ordinal: 3
       }
     }
   }
@@ -67,14 +75,19 @@ def checkoutSrcs() {
 }
 
 def BuildWin64() {
-  node('win64 && build') {
+  node('win64 && cuda10_unified') {
+    deleteDir()
     unstash name: 'srcs'
     echo "Building XGBoost for Windows AMD64 target..."
     bat "nvcc --version"
+    def arch_flag = ""
+    if (env.BRANCH_NAME != 'master' && !(env.BRANCH_NAME.startsWith('release'))) {
+      arch_flag = "-DGPU_COMPUTE_VER=75"
+    }
     bat """
     mkdir build
     cd build
-    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON
+    cmake .. -G"Visual Studio 15 2017 Win64" -DUSE_CUDA=ON -DCMAKE_VERBOSE_MAKEFILE=ON -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON ${arch_flag} -DCMAKE_UNITY_BUILD=ON
     """
     bat """
     cd build
@@ -92,50 +105,59 @@ def BuildWin64() {
     """
     echo 'Stashing Python wheel...'
     stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
-    s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Uploading Python wheel...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
+    }
     echo 'Stashing C++ test executable (testxgboost)...'
     stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
+    stash name: 'xgboost_cli', includes: 'xgboost.exe'
     deleteDir()
   }
 }
 
-def TestWin64CPU() {
-  node('win64 && cpu') {
+def BuildRPackageWithCUDAWin64() {
+  node('win64 && cuda10_unified') {
+    deleteDir()
     unstash name: 'srcs'
-    unstash name: 'xgboost_whl'
-    echo "Test Win64 CPU"
-    echo "Installing Python wheel..."
-    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
-    bat """
-    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
-    """
-    echo "Running Python tests..."
-    bat "conda activate && python -m pytest -v -s --fulltrace tests\\python"
-    bat "conda activate && python -m pip uninstall -y xgboost"
+    bat "nvcc --version"
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      bat """
+      bash tests/ci_build/build_r_pkg_with_cuda_win64.sh ${commit_id}
+      """
+      echo 'Uploading R tarball...'
+      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', includePathPattern:'xgboost_r_gpu_win64_*.tar.gz'
+    }
     deleteDir()
   }
 }
 
-def TestWin64GPU(args) {
-  node("win64 && gpu && ${args.cuda_target}") {
+def TestWin64() {
+  node('win64 && cuda10_unified') {
+    deleteDir()
     unstash name: 'srcs'
     unstash name: 'xgboost_whl'
+    unstash name: 'xgboost_cli'
     unstash name: 'xgboost_cpp_tests'
-    echo "Test Win64 GPU (${args.cuda_target})"
+    echo "Test Win64"
     bat "nvcc --version"
     echo "Running C++ tests..."
     bat "build\\testxgboost.exe"
+    echo "Installing Python dependencies..."
+    def env_name = 'win64_' + UUID.randomUUID().toString().replaceAll('-', '')
+    bat "conda activate && mamba env create -n ${env_name} --file=tests/ci_build/conda_env/win64_test.yml"
     echo "Installing Python wheel..."
-    bat "conda activate && (python -m pip uninstall -y xgboost || cd .)"
     bat """
-    conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
+    conda activate ${env_name} && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
     """
     echo "Running Python tests..."
+    bat "conda activate ${env_name} && python -m pytest -v -s -rxXs --fulltrace tests\\python"
     bat """
-    conda activate && python -m pytest -v -s --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 activate && python -m pip uninstall -y xgboost"
+    bat "conda env remove --name ${env_name}"
     deleteDir()
   }
 }

Makefile

@@ -1,11 +1,3 @@
-ifndef config
-ifneq ("$(wildcard ./config.mk)","")
-	config = config.mk
-else
-	config = make/config.mk
-endif
-endif
-
 ifndef DMLC_CORE
 	DMLC_CORE = dmlc-core
 endif
@@ -30,16 +22,6 @@ ifndef MAKE_OK
 endif
 $(warning MAKE [$(MAKE)] - $(if $(MAKE_OK),checked OK,PROBLEM))
 
-ifeq ($(OS), Windows_NT)
-	UNAME="Windows"
-else
-	UNAME=$(shell uname)
-endif
-
-include $(config)
-ifeq ($(USE_OPENMP), 0)
-	export NO_OPENMP = 1
-endif
 include $(DMLC_CORE)/make/dmlc.mk
 
 # set compiler defaults for OSX versus *nix
@@ -62,75 +44,21 @@ export CXX = g++
 endif
 endif
 
-export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS)
-export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
+export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++14 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS)
 CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
-#java include path
-export JAVAINCFLAGS = -I${JAVA_HOME}/include -I./java
 
 ifeq ($(TEST_COVER), 1)
 	CFLAGS += -g -O0 -fprofile-arcs -ftest-coverage
 else
 	CFLAGS += -O3 -funroll-loops
-ifeq ($(USE_SSE), 1)
-	CFLAGS += -msse2
-endif
 endif
 
 ifndef LINT_LANG
 	LINT_LANG= "all"
 endif
 
-ifeq ($(UNAME), Windows)
-	XGBOOST_DYLIB = lib/xgboost.dll
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/win32
-else
-ifeq ($(UNAME), Darwin)
-	XGBOOST_DYLIB = lib/libxgboost.dylib
-	CFLAGS += -fPIC
-else
-	XGBOOST_DYLIB = lib/libxgboost.so
-	CFLAGS += -fPIC
-endif
-endif
-
-ifeq ($(UNAME), Linux)
-	LDFLAGS += -lrt
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/linux
-endif
-
-ifeq ($(UNAME), Darwin)
-	JAVAINCFLAGS += -I${JAVA_HOME}/include/darwin
-endif
-
-OPENMP_FLAGS =
-ifeq ($(USE_OPENMP), 1)
-	OPENMP_FLAGS = -fopenmp
-else
-	OPENMP_FLAGS = -DDISABLE_OPENMP
-endif
-CFLAGS += $(OPENMP_FLAGS)
-
 # specify tensor path
-.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck java pylint
-
-all: lib/libxgboost.a $(XGBOOST_DYLIB) xgboost
-
-$(DMLC_CORE)/libdmlc.a: $(wildcard $(DMLC_CORE)/src/*.cc $(DMLC_CORE)/src/*/*.cc)
-	+ cd $(DMLC_CORE); "$(MAKE)" libdmlc.a config=$(ROOTDIR)/$(config); cd $(ROOTDIR)
-
-$(RABIT)/lib/$(LIB_RABIT): $(wildcard $(RABIT)/src/*.cc)
-	+ cd $(RABIT); "$(MAKE)" lib/$(LIB_RABIT) USE_SSE=$(USE_SSE); cd $(ROOTDIR)
-
-jvm: jvm-packages/lib/libxgboost4j.so
-
-SRC = $(wildcard src/*.cc src/*/*.cc)
-ALL_OBJ = $(patsubst src/%.cc, build/%.o, $(SRC))
-AMALGA_OBJ = amalgamation/xgboost-all0.o
-LIB_DEP = $(DMLC_CORE)/libdmlc.a $(RABIT)/lib/$(LIB_RABIT)
-ALL_DEP = $(filter-out build/cli_main.o, $(ALL_OBJ)) $(LIB_DEP)
-CLI_OBJ = build/cli_main.o
-include tests/cpp/xgboost_test.mk
+.PHONY: clean all lint clean_all doxygen rcpplint pypack Rpack Rbuild Rcheck
 
 build/%.o: src/%.cc
 	@mkdir -p $(@D)
@@ -141,27 +69,6 @@ build/%.o: src/%.cc
 amalgamation/xgboost-all0.o: amalgamation/xgboost-all0.cc
 	$(CXX) -c $(CFLAGS) $< -o $@
 
-# Equivalent to lib/libxgboost_all.so
-lib/libxgboost_all.so: $(AMALGA_OBJ) $(LIB_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %.a, $^) $(LDFLAGS)
-
-lib/libxgboost.a: $(ALL_DEP)
-	@mkdir -p $(@D)
-	ar crv $@ $(filter %.o, $?)
-
-lib/xgboost.dll lib/libxgboost.so lib/libxgboost.dylib: $(ALL_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %a,  $^) $(LDFLAGS)
-
-jvm-packages/lib/libxgboost4j.so: jvm-packages/xgboost4j/src/native/xgboost4j.cpp $(ALL_DEP)
-	@mkdir -p $(@D)
-	$(CXX) $(CFLAGS) $(JAVAINCFLAGS) -shared -o $@ $(filter %.cpp %.o %.a, $^) $(LDFLAGS)
-
-
-xgboost: $(CLI_OBJ) $(ALL_DEP)
-	$(CXX) $(CFLAGS) -o $@  $(filter %.o %.a, $^)  $(LDFLAGS)
-
 rcpplint:
 	python3 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
 
@@ -172,16 +79,6 @@ lint: rcpplint
 	  python-package/xgboost/src --pylint-rc ${PWD}/python-package/.pylintrc xgboost \
 	  ${LINT_LANG} include src python-package
 
-pylint:
-	flake8 --ignore E501 python-package
-	flake8 --ignore E501 tests/python
-
-test: $(ALL_TEST)
-	$(ALL_TEST)
-
-check: test
-	./tests/cpp/xgboost_test
-
 ifeq ($(TEST_COVER), 1)
 cover: check
 	@- $(foreach COV_OBJ, $(COVER_OBJ), \
@@ -189,6 +86,20 @@ cover: check
 	)
 endif
 
+
+# dask is required to pass, others are not
+# If any of the dask tests failed, contributor won't see the other error.
+mypy:
+	cd python-package; \
+	mypy ./xgboost/dask.py && \
+	mypy ./xgboost/rabit.py && \
+	mypy ../demo/guide-python/external_memory.py && \
+	mypy ../tests/python-gpu/test_gpu_with_dask.py && \
+	mypy ../tests/python/test_data_iterator.py && \
+	mypy ../tests/python-gpu/test_gpu_data_iterator.py && \
+	mypy ./xgboost/sklearn.py || exit 1; \
+	mypy . || true ;
+
 clean:
 	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ */*.o */*/*.o */*/*/*.o #xgboost
 	$(RM) -rf build_tests *.gcov tests/cpp/xgboost_test
@@ -202,38 +113,9 @@ clean_all: clean
 	cd $(DMLC_CORE); "$(MAKE)" clean; cd $(ROOTDIR)
 	cd $(RABIT); "$(MAKE)" clean; cd $(ROOTDIR)
 
-doxygen:
-	doxygen doc/Doxyfile
-
-# create standalone python tar file.
-pypack: ${XGBOOST_DYLIB}
-	cp ${XGBOOST_DYLIB} python-package/xgboost
-	cd python-package; tar cf xgboost.tar xgboost; cd ..
-
 # create pip source dist (sdist) pack for PyPI
 pippack: clean_all
-	rm -rf xgboost-python
-# remove symlinked directories in python-package/xgboost
-	rm -rf python-package/xgboost/lib
-	rm -rf python-package/xgboost/dmlc-core
-	rm -rf python-package/xgboost/include
-	rm -rf python-package/xgboost/make
-	rm -rf python-package/xgboost/rabit
-	rm -rf python-package/xgboost/src
-	cp -r python-package xgboost-python
-	cp -r CMakeLists.txt xgboost-python/xgboost/
-	cp -r cmake xgboost-python/xgboost/
-	cp -r plugin xgboost-python/xgboost/
-	cp -r make xgboost-python/xgboost/
-	cp -r src xgboost-python/xgboost/
-	cp -r tests xgboost-python/xgboost/
-	cp -r include xgboost-python/xgboost/
-	cp -r dmlc-core xgboost-python/xgboost/
-	cp -r rabit xgboost-python/xgboost/
-# Use setup_pip.py instead of setup.py
-	mv xgboost-python/setup_pip.py xgboost-python/setup.py
-# Build sdist tarball
-	cd xgboost-python; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
+	cd python-package; python setup.py sdist; mv dist/*.tar.gz ..; cd ..
 
 # Script to make a clean installable R package.
 Rpack: clean_all
@@ -254,9 +136,9 @@ Rpack: clean_all
 	cp -r dmlc-core/include xgboost/src/dmlc-core/include
 	cp -r dmlc-core/src xgboost/src/dmlc-core/src
 	cp ./LICENSE xgboost
-	# Modify PKGROOT in Makevars.in
+# Modify PKGROOT in Makevars.in
 	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
-	# Configure Makevars.win (Windows-specific Makevars, likely using MinGW)
+# Configure Makevars.win (Windows-specific Makevars, likely using MinGW)
 	cp xgboost/src/Makevars.in xgboost/src/Makevars.win
 	cat xgboost/src/Makevars.in| sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.win
 	sed -i -e 's/@OPENMP_CXXFLAGS@/$$\(SHLIB_OPENMP_CXXFLAGS\)/g' xgboost/src/Makevars.win
@@ -266,14 +148,18 @@ 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 -rfv xgboost/tests/helper_scripts/
+
+R ?= R
 
 Rbuild: Rpack
-	R CMD build --no-build-vignettes xgboost
+	$(R) CMD build xgboost
 	rm -rf xgboost
 
 Rcheck: Rbuild
-	R CMD check xgboost*.tar.gz
+	$(R) CMD check --as-cran xgboost*.tar.gz
 
 -include build/*.d
 -include build/*/*.d

R-package/CMakeLists.txt

@@ -6,8 +6,11 @@ file(GLOB_RECURSE R_SOURCES
   ${CMAKE_CURRENT_LIST_DIR}/src/*.c)
 # Use object library to expose symbols
 add_library(xgboost-r OBJECT ${R_SOURCES})
-
-set(R_DEFINITIONS
+if (ENABLE_ALL_WARNINGS)
+  target_compile_options(xgboost-r PRIVATE -Wall -Wextra)
+endif (ENABLE_ALL_WARNINGS)
+target_compile_definitions(xgboost-r
+  PUBLIC
   -DXGBOOST_STRICT_R_MODE=1
   -DXGBOOST_CUSTOMIZE_GLOBAL_PRNG=1
   -DDMLC_LOG_BEFORE_THROW=0
@@ -15,20 +18,27 @@ set(R_DEFINITIONS
   -DDMLC_LOG_CUSTOMIZE=1
   -DRABIT_CUSTOMIZE_MSG_
   -DRABIT_STRICT_CXX98_)
-target_compile_definitions(xgboost-r
-  PRIVATE ${R_DEFINITIONS})
 target_include_directories(xgboost-r
   PRIVATE
   ${LIBR_INCLUDE_DIRS}
   ${PROJECT_SOURCE_DIR}/include
   ${PROJECT_SOURCE_DIR}/dmlc-core/include
   ${PROJECT_SOURCE_DIR}/rabit/include)
+target_link_libraries(xgboost-r PUBLIC ${LIBR_CORE_LIBRARY})
+if (USE_OPENMP)
+  find_package(OpenMP REQUIRED)
+  target_link_libraries(xgboost-r PUBLIC OpenMP::OpenMP_CXX OpenMP::OpenMP_C)
+endif (USE_OPENMP)
 set_target_properties(
   xgboost-r PROPERTIES
-  CXX_STANDARD 11
+  CXX_STANDARD 14
   CXX_STANDARD_REQUIRED ON
   POSITION_INDEPENDENT_CODE ON)
 
-set(XGBOOST_DEFINITIONS "${XGBOOST_DEFINITIONS};${R_DEFINITIONS}" PARENT_SCOPE)
-set(XGBOOST_OBJ_SOURCES $<TARGET_OBJECTS:xgboost-r> PARENT_SCOPE)
-set(LINKED_LIBRARIES_PRIVATE ${LINKED_LIBRARIES_PRIVATE} ${LIBR_CORE_LIBRARY} PARENT_SCOPE)
+# Get compilation and link flags of xgboost-r and propagate to objxgboost
+target_link_libraries(objxgboost PUBLIC xgboost-r)
+# Add all objects of xgboost-r to objxgboost
+target_sources(objxgboost INTERFACE $<TARGET_OBJECTS:xgboost-r>)
+
+set(LIBR_HOME "${LIBR_HOME}" PARENT_SCOPE)
+set(LIBR_EXECUTABLE "${LIBR_EXECUTABLE}" PARENT_SCOPE)

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.0.0.1
-Date: 2019-07-23
+Version: 1.5.0.1
+Date: 2021-09-25
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -31,9 +31,9 @@ Authors@R: c(
   )
 Description: Extreme Gradient Boosting, which is an efficient implementation
     of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
-    This package is its R interface. The package includes efficient linear 
-    model solver and tree learning algorithms. The package can automatically 
-    do parallel computation on a single machine which could be more than 10 
+    This package is its R interface. The package includes efficient linear
+    model solver and tree learning algorithms. The package can automatically
+    do parallel computation on a single machine which could be more than 10
     times faster than existing gradient boosting packages. It supports
     various objective functions, including regression, classification and ranking.
     The package is made to be extensible, so that users are also allowed to define
@@ -53,15 +53,15 @@ Suggests:
     testthat,
     lintr,
     igraph (>= 1.0.1),
-    jsonlite,
-    float
+    float,
+    crayon,
+    titanic
 Depends:
     R (>= 3.3.0)
 Imports:
     Matrix (>= 1.1-0),
     methods,
     data.table (>= 1.9.6),
-    magrittr (>= 1.5),
-    stringi (>= 0.5.2)
-RoxygenNote: 7.0.2
-SystemRequirements: GNU make, C++11
+    jsonlite (>= 1.0),
+RoxygenNote: 7.1.1
+SystemRequirements: GNU make, C++14

R-package/NAMESPACE

@@ -14,6 +14,7 @@ S3method(setinfo,xgb.DMatrix)
 S3method(slice,xgb.DMatrix)
 export("xgb.attr<-")
 export("xgb.attributes<-")
+export("xgb.config<-")
 export("xgb.parameters<-")
 export(cb.cv.predict)
 export(cb.early.stop)
@@ -30,23 +31,31 @@ export(xgb.DMatrix)
 export(xgb.DMatrix.save)
 export(xgb.attr)
 export(xgb.attributes)
+export(xgb.config)
 export(xgb.create.features)
 export(xgb.cv)
 export(xgb.dump)
 export(xgb.gblinear.history)
+export(xgb.get.config)
 export(xgb.ggplot.deepness)
 export(xgb.ggplot.importance)
+export(xgb.ggplot.shap.summary)
 export(xgb.importance)
 export(xgb.load)
+export(xgb.load.raw)
 export(xgb.model.dt.tree)
 export(xgb.plot.deepness)
 export(xgb.plot.importance)
 export(xgb.plot.multi.trees)
 export(xgb.plot.shap)
+export(xgb.plot.shap.summary)
 export(xgb.plot.tree)
 export(xgb.save)
 export(xgb.save.raw)
+export(xgb.serialize)
+export(xgb.set.config)
 export(xgb.train)
+export(xgb.unserialize)
 export(xgboost)
 import(methods)
 importClassesFrom(Matrix,dgCMatrix)
@@ -71,14 +80,10 @@ importFrom(graphics,lines)
 importFrom(graphics,par)
 importFrom(graphics,points)
 importFrom(graphics,title)
-importFrom(magrittr,"%>%")
+importFrom(jsonlite,fromJSON)
+importFrom(jsonlite,toJSON)
 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

@@ -62,11 +62,11 @@ cb.print.evaluation <- function(period = 1, showsd = TRUE) {
   callback <- function(env = parent.frame()) {
     if (length(env$bst_evaluation) == 0 ||
         period == 0 ||
-        NVL(env$rank, 0) != 0 )
+        NVL(env$rank, 0) != 0)
       return()
 
     i <- env$iteration
-    if ((i-1) %% period == 0 ||
+    if ((i - 1) %% period == 0 ||
         i == env$begin_iteration ||
         i == env$end_iteration) {
       stdev <- if (showsd) env$bst_evaluation_err else NULL
@@ -115,7 +115,7 @@ cb.evaluation.log <- function() {
       stop("bst_evaluation must have non-empty names")
 
     mnames <<- gsub('-', '_', names(env$bst_evaluation))
-    if(!is.null(env$bst_evaluation_err))
+    if (!is.null(env$bst_evaluation_err))
       mnames <<- c(paste0(mnames, '_mean'), paste0(mnames, '_std'))
   }
 
@@ -123,12 +123,12 @@ cb.evaluation.log <- function() {
     env$evaluation_log <- as.data.table(t(simplify2array(env$evaluation_log)))
     setnames(env$evaluation_log, c('iter', mnames))
 
-    if(!is.null(env$bst_evaluation_err)) {
+    if (!is.null(env$bst_evaluation_err)) {
       # rearrange col order from _mean,_mean,...,_std,_std,...
       # to be _mean,_std,_mean,_std,...
       len <- length(mnames)
-      means <- mnames[seq_len(len/2)]
-      stds <- mnames[(len/2 + 1):len]
+      means <- mnames[seq_len(len / 2)]
+      stds <- mnames[(len / 2 + 1):len]
       cnames <- numeric(len)
       cnames[c(TRUE, FALSE)] <- means
       cnames[c(FALSE, TRUE)] <- stds
@@ -144,7 +144,7 @@ cb.evaluation.log <- function() {
       return(finalizer(env))
 
     ev <- env$bst_evaluation
-    if(!is.null(env$bst_evaluation_err))
+    if (!is.null(env$bst_evaluation_err))
       ev <- c(ev, env$bst_evaluation_err)
     env$evaluation_log <- c(env$evaluation_log,
                             list(c(iter = env$iteration, ev)))
@@ -188,7 +188,7 @@ cb.reset.parameters <- function(new_params) {
   pnames <- gsub("\\.", "_", names(new_params))
   nrounds <- NULL
 
-  # run some checks in the begining
+  # run some checks in the beginning
   init <- function(env) {
     nrounds <<- env$end_iteration - env$begin_iteration + 1
 
@@ -263,10 +263,7 @@ cb.reset.parameters <- function(new_params) {
 #' \itemize{
 #' \item \code{best_score} the evaluation score at the best iteration
 #' \item \code{best_iteration} at which boosting iteration the best score has occurred (1-based index)
-#' \item \code{best_ntreelimit} to use with the \code{ntreelimit} parameter in \code{predict}.
-#'      It differs from \code{best_iteration} in multiclass or random forest settings.
 #' }
-#'
 #' The Same values are also stored as xgb-attributes:
 #' \itemize{
 #' \item \code{best_iteration} is stored as a 0-based iteration index (for interoperability of binary models)
@@ -351,13 +348,19 @@ 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$handle, 'best_score'))
-      if (best_score != attr_best_score)
-        stop("Inconsistent 'best_score' values between the closure state: ", best_score,
-             " and the xgb.attr: ", attr_best_score)
-      env$bst$best_iteration = best_iteration
-      env$bst$best_ntreelimit = best_ntreelimit
-      env$bst$best_score = best_score
+      attr_best_score <- as.numeric(xgb.attr(env$bst$handle, 'best_score'))
+      if (best_score != attr_best_score) {
+        # If the difference is too big, throw an error
+        if (abs(best_score - attr_best_score) >= 1e-14) {
+          stop("Inconsistent 'best_score' values between the closure state: ", best_score,
+               " and the xgb.attr: ", attr_best_score)
+        }
+        # If the difference is due to floating-point truncation, update best_score
+        best_score <- attr_best_score
+      }
+      env$bst$best_iteration <- best_iteration
+      env$bst$best_ntreelimit <- best_ntreelimit
+      env$bst$best_score <- best_score
     } else {
       env$basket$best_iteration <- best_iteration
       env$basket$best_ntreelimit <- best_ntreelimit
@@ -372,9 +375,9 @@ cb.early.stop <- function(stopping_rounds, maximize = FALSE,
       return(finalizer(env))
 
     i <- env$iteration
-    score = env$bst_evaluation[metric_idx]
+    score <- env$bst_evaluation[metric_idx]
 
-    if (( maximize && score > best_score) ||
+    if ((maximize && score > best_score) ||
         (!maximize && score < best_score)) {
 
       best_msg <<- format.eval.string(i, env$bst_evaluation, env$bst_evaluation_err)
@@ -492,15 +495,14 @@ cb.cv.predict <- function(save_models = FALSE) {
         rep(NA_real_, N)
       }
 
-    ntreelimit <- NVL(env$basket$best_ntreelimit,
-                      env$end_iteration * env$num_parallel_tree)
+    iterationrange <- c(1, NVL(env$basket$best_iteration, env$end_iteration) + 1)
     if (NVL(env$params[['booster']], '') == 'gblinear') {
-      ntreelimit <- 0 # must be 0 for gblinear
+      iterationrange <- c(1, 1)  # must be 0 for gblinear
     }
     for (fd in env$bst_folds) {
-      pr <- predict(fd$bst, fd$watchlist[[2]], ntreelimit = ntreelimit, reshape = TRUE)
+      pr <- predict(fd$bst, fd$watchlist[[2]], iterationrange = iterationrange, reshape = TRUE)
       if (is.matrix(pred)) {
-        pred[fd$index,] <- pr
+        pred[fd$index, ] <- pr
       } else {
         pred[fd$index] <- pr
       }
@@ -527,7 +529,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' Callback closure for collecting the model coefficients history of a gblinear booster
 #' during its training.
 #'
-#' @param sparse when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
+#' @param sparse when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
 #'       Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 #'       when using the "thrifty" feature selector with fairly small number of top features
 #'       selected per iteration.
@@ -554,7 +556,6 @@ 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"))
@@ -575,7 +576,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
 #'                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
 #'                  callbacks = list(cb.gblinear.history()))
-#' xgb.gblinear.history(bst) %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst), type = 'l')
 #' #  Componentwise boosting is known to have similar effect to Lasso regularization.
 #' # Try experimenting with various values of top_k, eta, nrounds,
 #' # as well as different feature_selectors.
@@ -584,7 +585,7 @@ 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
-#' xgb.gblinear.history(bst)[[3]] %>% matplot(type = 'l')
+#' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 #'
 #'
 #' #### Multiclass classification:
@@ -597,15 +598,15 @@ 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:
-#' 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')
+#' matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
+#' matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
 #'
 #' # CV:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
 #'               callbacks = list(cb.gblinear.history(FALSE)))
-#' # 1st forld of 1st class
-#' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l')
+#' # 1st fold of 1st class
+#' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
 #'
 #' @export
 cb.gblinear.history <- function(sparse=FALSE) {
@@ -613,9 +614,7 @@ cb.gblinear.history <- function(sparse=FALSE) {
 
   init <- function(env) {
     if (!is.null(env$bst)) { # xgb.train:
-      coef_path <- list()
     } else if (!is.null(env$bst_folds)) { # xgb.cv:
-      coef_path <- rep(list(), length(env$bst_folds))
     } else stop("Parent frame has neither 'bst' nor 'bst_folds'")
   }
 
@@ -638,9 +637,14 @@ cb.gblinear.history <- function(sparse=FALSE) {
     if (!is.null(env$bst)) { # # xgb.train:
       coefs <<- list2mat(coefs)
     } else { # xgb.cv:
-      # first lapply transposes the list
-      coefs <<- lapply(seq_along(coefs[[1]]), function(i) lapply(coefs, "[[", i)) %>%
-                lapply(function(x) list2mat(x))
+      # second lapply transposes the list
+      coefs <<- lapply(
+        X = lapply(
+          X = seq_along(coefs[[1]]),
+          FUN = function(i) lapply(coefs, "[[", i)
+        ),
+        FUN = list2mat
+      )
     }
   }
 
@@ -705,11 +709,11 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   if (!is_cv) {
     # extract num_class & num_feat from the internal model
     dmp <- xgb.dump(model)
-    if(length(dmp) < 2 || dmp[2] != "bias:")
+    if (length(dmp) < 2 || dmp[2] != "bias:")
       stop("It does not appear to be a gblinear model")
-    dmp <- dmp[-c(1,2)]
+    dmp <- dmp[-c(1, 2)]
     n <- which(dmp == 'weight:')
-    if(length(n) != 1)
+    if (length(n) != 1)
       stop("It does not appear to be a gblinear model")
     num_class <- n - 1
     num_feat <- (length(dmp) - 4) / num_class
@@ -732,9 +736,9 @@ xgb.gblinear.history <- function(model, class_index = NULL) {
   if (!is.null(class_index) && num_class > 1) {
     coef_path <- if (is.list(coef_path)) {
       lapply(coef_path,
-             function(x) x[, seq(1 + class_index, by=num_class, length.out=num_feat)])
+             function(x) x[, seq(1 + class_index, by = num_class, length.out = num_feat)])
     } else {
-      coef_path <- coef_path[, seq(1 + class_index, by=num_class, length.out=num_feat)]
+      coef_path <- coef_path[, seq(1 + class_index, by = num_class, length.out = num_feat)]
     }
   }
   coef_path

R-package/R/utils.R

@@ -1,6 +1,6 @@
 #
-# This file is for the low level reuseable utility functions
-# that are not supposed to be visibe to a user.
+# This file is for the low level reusable utility functions
+# that are not supposed to be visible to a user.
 #
 
 #
@@ -20,6 +20,12 @@ 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 --------------------------------------------
@@ -28,7 +34,7 @@ NVL <- function(x, val) {
 # Merges booster params with whatever is provided in ...
 # plus runs some checks
 check.booster.params <- function(params, ...) {
-  if (typeof(params) != "list")
+  if (!identical(class(params), "list"))
     stop("params must be a list")
 
   # in R interface, allow for '.' instead of '_' in parameter names
@@ -69,23 +75,23 @@ check.booster.params <- function(params, ...) {
 
   if (!is.null(params[['monotone_constraints']]) &&
       typeof(params[['monotone_constraints']]) != "character") {
-        vec2str = paste(params[['monotone_constraints']], collapse = ',')
-        vec2str = paste0('(', vec2str, ')')
-        params[['monotone_constraints']] = vec2str
+        vec2str <- paste(params[['monotone_constraints']], collapse = ',')
+        vec2str <- paste0('(', vec2str, ')')
+        params[['monotone_constraints']] <- vec2str
   }
 
   # interaction constraints parser (convert from list of column indices to string)
   if (!is.null(params[['interaction_constraints']]) &&
       typeof(params[['interaction_constraints']]) != "character"){
     # check input class
-    if (class(params[['interaction_constraints']]) != 'list') stop('interaction_constraints should be class list')
-    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric','integer'))) {
+    if (!identical(class(params[['interaction_constraints']]), 'list')) stop('interaction_constraints should be class list')
+    if (!all(unique(sapply(params[['interaction_constraints']], class)) %in% c('numeric', 'integer'))) {
       stop('interaction_constraints should be a list of numeric/integer vectors')
     }
 
     # recast parameter as string
-    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse=','), ']'))
-    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse=','), ']')
+    interaction_constraints <- sapply(params[['interaction_constraints']], function(x) paste0('[', paste(x, collapse = ','), ']'))
+    params[['interaction_constraints']] <- paste0('[', paste(interaction_constraints, collapse = ','), ']')
   }
   return(params)
 }
@@ -145,7 +151,8 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
   if (is.null(obj)) {
     .Call(XGBoosterUpdateOneIter_R, booster_handle, as.integer(iter), dtrain)
   } else {
-    pred <- predict(booster_handle, dtrain, training = TRUE)
+    pred <- predict(booster_handle, dtrain, outputmargin = TRUE, training = TRUE,
+                    ntreelimit = 0)
     gpair <- obj(pred, dtrain)
     .Call(XGBoosterBoostOneIter_R, booster_handle, dtrain, gpair$grad, gpair$hess)
   }
@@ -166,13 +173,13 @@ 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))
-    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
+    mat <- matrix(strsplit(msg, '\\s+|:')[[1]][-1], nrow = 2)
+    res <- structure(as.numeric(mat[2, ]), names = mat[1, ])
   } else {
     res <- sapply(seq_along(watchlist), function(j) {
       w <- watchlist[[j]]
-      preds <- predict(booster_handle, w) # predict using all trees
+      ## predict using all trees
+      preds <- predict(booster_handle, w, outputmargin = TRUE, iterationrange = c(1, 1))
       eval_res <- feval(preds, w)
       out <- eval_res$value
       names(out) <- paste0(evnames[j], "-", eval_res$metric)
@@ -187,13 +194,23 @@ 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
-  if (exists('objective', where = params) &&
-      is.character(params$objective) &&
-      strtrim(params$objective, 5) == 'rank:') {
+  objective <- params$objective
+  if (is.character(objective) && strtrim(objective, 5) == 'rank:') {
     stop("\n\tAutomatic generation of CV-folds is not implemented for ranking!\n",
          "\tConsider providing pre-computed CV-folds through the 'folds=' parameter.\n")
   }
@@ -206,19 +223,16 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
     #  - For classification, need to convert y labels to factor before making the folds,
     #    and then do stratification by factor levels.
     #  - For regression, leave y numeric and do stratification by quantiles.
-    if (exists('objective', where = params) &&
-        is.character(params$objective)) {
-      # If 'objective' provided in params, assume that y is a classification label
-      # unless objective is reg:squarederror
-      if (params$objective != 'reg:squarederror')
-        y <- factor(y)
+    if (is.character(objective)) {
+      y <- convert.labels(y, params$objective)
     } else {
       # If no 'objective' given in params, it means that user either wants to
       # use the default 'reg:squarederror' objective or has provided a custom
       # obj function.  Here, assume classification setting when y has 5 or less
       # unique values:
-      if (length(unique(y)) <= 5)
+      if (length(unique(y)) <= 5) {
         y <- factor(y)
+      }
     }
     folds <- xgb.createFolds(y, nfold)
   } else {
@@ -271,7 +285,7 @@ xgb.createFolds <- function(y, k = 10)
     for (i in seq_along(numInClass)) {
       ## create a vector of integers from 1:k as many times as possible without
       ## going over the number of samples in the class. Note that if the number
-      ## of samples in a class is less than k, nothing is producd here.
+      ## of samples in a class is less than k, nothing is produced here.
       seqVector <- rep(seq_len(k), numInClass[i] %/% k)
       ## add enough random integers to get  length(seqVector) == numInClass[i]
       if (numInClass[i] %% k > 0) seqVector <- c(seqVector, sample.int(k, numInClass[i] %% k))
@@ -307,6 +321,68 @@ xgb.createFolds <- function(y, k = 10)
 #' @name xgboost-deprecated
 NULL
 
+#' Do not use \code{\link[base]{saveRDS}} or \code{\link[base]{save}} for long-term archival of
+#' models. Instead, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}}.
+#'
+#' It is a common practice to use the built-in \code{\link[base]{saveRDS}} function (or
+#' \code{\link[base]{save}}) to persist R objects to the disk. While it is possible to persist
+#' \code{xgb.Booster} objects using \code{\link[base]{saveRDS}}, it is not advisable to do so if
+#' the model is to be accessed in the future. If you train a model with the current version of
+#' XGBoost and persist it with \code{\link[base]{saveRDS}}, the model is not guaranteed to be
+#' accessible in later releases of XGBoost. To ensure that your model can be accessed in future
+#' releases of XGBoost, use \code{\link{xgb.save}} or \code{\link{xgb.save.raw}} instead.
+#'
+#' @details
+#' Use \code{\link{xgb.save}} to save the XGBoost model as a stand-alone file. You may opt into
+#' the JSON format by specifying the JSON extension. To read the model back, use
+#' \code{\link{xgb.load}}.
+#'
+#' Use \code{\link{xgb.save.raw}} to save the XGBoost model as a sequence (vector) of raw bytes
+#' in a future-proof manner. Future releases of XGBoost will be able to read the raw bytes and
+#' re-construct the corresponding model. To read the model back, use \code{\link{xgb.load.raw}}.
+#' The \code{\link{xgb.save.raw}} function is useful if you'd like to persist the XGBoost model
+#' as part of another R object.
+#'
+#' Note: Do not use \code{\link{xgb.serialize}} to store models long-term. It persists not only the
+#' model but also internal configurations and parameters, and its format is not stable across
+#' multiple XGBoost versions. Use \code{\link{xgb.serialize}} only for checkpointing.
+#'
+#' For more details and explanation about model persistence and archival, consult the page
+#' \url{https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html}.
+#'
+#' @examples
+#' data(agaricus.train, package='xgboost')
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
+#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+#'
+#' # Save as a stand-alone file; load it with xgb.load()
+#' xgb.save(bst, 'xgb.model')
+#' bst2 <- xgb.load('xgb.model')
+#'
+#' # Save as a stand-alone file (JSON); load it with xgb.load()
+#' xgb.save(bst, 'xgb.model.json')
+#' bst2 <- xgb.load('xgb.model.json')
+#' if (file.exists('xgb.model.json')) file.remove('xgb.model.json')
+#'
+#' # Save as a raw byte vector; load it with xgb.load.raw()
+#' xgb_bytes <- xgb.save.raw(bst)
+#' bst2 <- xgb.load.raw(xgb_bytes)
+#'
+#' # Persist XGBoost model as part of another R object
+#' obj <- list(xgb_model_bytes = xgb.save.raw(bst), description = "My first XGBoost model")
+#' # Persist the R object. Here, saveRDS() is okay, since it doesn't persist
+#' # xgb.Booster directly. What's being persisted is the future-proof byte representation
+#' # as given by xgb.save.raw().
+#' saveRDS(obj, 'my_object.rds')
+#' # Read back the R object
+#' obj2 <- readRDS('my_object.rds')
+#' # Re-construct xgb.Booster object from the bytes
+#' bst2 <- xgb.load.raw(obj2$xgb_model_bytes)
+#' if (file.exists('my_object.rds')) file.remove('my_object.rds')
+#'
+#' @name a-compatibility-note-for-saveRDS-save
+NULL
+
 # Lookup table for the deprecated parameters bookkeeping
 depr_par_lut <- matrix(c(
   'print.every.n', 'print_every_n',
@@ -315,8 +391,8 @@ depr_par_lut <- matrix(c(
   'with.stats', 'with_stats',
   'numberOfClusters', 'n_clusters',
   'features.keep', 'features_keep',
-  'plot.height','plot_height',
-  'plot.width','plot_width',
+  'plot.height', 'plot_height',
+  'plot.width', 'plot_width',
   'n_first_tree', 'trees',
   'dummy', 'DUMMY'
 ), ncol = 2, byrow = TRUE)
@@ -329,20 +405,20 @@ colnames(depr_par_lut) <- c('old', 'new')
 check.deprecation <- function(..., env = parent.frame()) {
   pars <- list(...)
   # exact and partial matches
-  all_match <- pmatch(names(pars), depr_par_lut[,1])
+  all_match <- pmatch(names(pars), depr_par_lut[, 1])
   # indices of matched pars' names
   idx_pars <- which(!is.na(all_match))
   if (length(idx_pars) == 0) return()
   # indices of matched LUT rows
   idx_lut <- all_match[idx_pars]
   # which of idx_lut were the exact matches?
-  ex_match <- depr_par_lut[idx_lut,1] %in% names(pars)
+  ex_match <- depr_par_lut[idx_lut, 1] %in% names(pars)
   for (i in seq_along(idx_pars)) {
     pars_par <- names(pars)[idx_pars[i]]
     old_par <- depr_par_lut[idx_lut[i], 1]
     new_par <- depr_par_lut[idx_lut[i], 2]
     if (!ex_match[i]) {
-      warning("'", pars_par, "' was partially matched to '", old_par,"'")
+      warning("'", pars_par, "' was partially matched to '", old_par, "'")
     }
     .Deprecated(new_par, old = old_par, package = 'xgboost')
     if (new_par != 'NULL') {

R-package/R/xgb.Booster.R

@@ -1,24 +1,40 @@
 # Construct an internal xgboost Booster and return a handle to it.
 # internal utility function
-xgb.Booster.handle <- function(params = list(), cachelist = list(), modelfile = NULL) {
+xgb.Booster.handle <- function(params = list(), cachelist = list(),
+                               modelfile = NULL, handle = NULL) {
   if (typeof(cachelist) != "list" ||
       !all(vapply(cachelist, inherits, logical(1), what = 'xgb.DMatrix'))) {
     stop("cachelist must be a list of xgb.DMatrix objects")
   }
-
-  handle <- .Call(XGBoosterCreate_R, cachelist)
+  ## Load existing model, dispatch for on disk model file and in memory buffer
   if (!is.null(modelfile)) {
     if (typeof(modelfile) == "character") {
+      ## A filename
+      handle <- .Call(XGBoosterCreate_R, cachelist)
+      modelfile <- path.expand(modelfile)
       .Call(XGBoosterLoadModel_R, handle, modelfile[1])
+      class(handle) <- "xgb.Booster.handle"
+      if (length(params) > 0) {
+        xgb.parameters(handle) <- params
+      }
+      return(handle)
     } else if (typeof(modelfile) == "raw") {
-      .Call(XGBoosterLoadModelFromRaw_R, handle, modelfile)
+      ## A memory buffer
+      bst <- xgb.unserialize(modelfile, handle)
+      xgb.parameters(bst) <- params
+      return (bst)
     } else if (inherits(modelfile, "xgb.Booster")) {
+      ## A booster object
       bst <- xgb.Booster.complete(modelfile, saveraw = TRUE)
-      .Call(XGBoosterLoadModelFromRaw_R, handle, bst$raw)
+      bst <- xgb.unserialize(bst$raw)
+      xgb.parameters(bst) <- params
+      return (bst)
     } else {
       stop("modelfile must be either character filename, or raw booster dump, or xgb.Booster object")
     }
   }
+  ## Create new model
+  handle <- .Call(XGBoosterCreate_R, cachelist)
   class(handle) <- "xgb.Booster.handle"
   if (length(params) > 0) {
     xgb.parameters(handle) <- params
@@ -48,8 +64,8 @@ is.null.handle <- function(handle) {
   return(FALSE)
 }
 
-# Return a verified to be valid handle out of either xgb.Booster.handle or xgb.Booster
-# internal utility function
+# Return a verified to be valid handle out of either xgb.Booster.handle or
+# xgb.Booster internal utility function
 xgb.get.handle <- function(object) {
   if (inherits(object, "xgb.Booster")) {
     handle <- object$handle
@@ -96,6 +112,8 @@ xgb.get.handle <- function(object) {
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' saveRDS(bst, "xgb.model.rds")
 #'
+#' # Warning: The resulting RDS file is only compatible with the current XGBoost version.
+#' # Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 #' bst1 <- readRDS("xgb.model.rds")
 #' if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 #' # the handle is invalid:
@@ -111,11 +129,31 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
     stop("argument type must be xgb.Booster")
 
   if (is.null.handle(object$handle)) {
-    object$handle <- xgb.Booster.handle(modelfile = object$raw)
+    object$handle <- xgb.Booster.handle(modelfile = object$raw, handle = object$handle)
   } else {
-    if (is.null(object$raw) && saveraw)
-      object$raw <- xgb.save.raw(object$handle)
+    if (is.null(object$raw) && saveraw) {
+      object$raw <- xgb.serialize(object$handle)
+    }
   }
+
+  attrs <- xgb.attributes(object)
+  if (!is.null(attrs$best_ntreelimit)) {
+    object$best_ntreelimit <- as.integer(attrs$best_ntreelimit)
+  }
+  if (!is.null(attrs$best_iteration)) {
+    ## Convert from 0 based back to 1 based.
+    object$best_iteration <- as.integer(attrs$best_iteration) + 1
+  }
+  if (!is.null(attrs$best_score)) {
+    object$best_score <- as.numeric(attrs$best_score)
+  }
+  if (!is.null(attrs$best_msg)) {
+    object$best_msg <- attrs$best_msg
+  }
+  if (!is.null(attrs$niter)) {
+    object$niter <- as.integer(attrs$niter)
+  }
+
   return(object)
 }
 
@@ -130,8 +168,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' @param outputmargin whether the prediction should be returned in the for of original untransformed
 #'        sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
 #'        logistic regression would result in predictions for log-odds instead of probabilities.
-#' @param ntreelimit limit the number of model's trees or boosting iterations used in prediction (see Details).
-#'        It will use all the trees by default (\code{NULL} value).
+#' @param ntreelimit Deprecated, use \code{iterationrange} instead.
 #' @param predleaf whether predict leaf index.
 #' @param predcontrib whether to return feature contributions to individual predictions (see Details).
 #' @param approxcontrib whether to use a fast approximation for feature contributions (see Details).
@@ -139,16 +176,21 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' @param reshape whether to reshape the vector of predictions to a matrix form when there are several
 #'        prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
 #'        or predinteraction flags is TRUE.
+#' @param training whether is the prediction result used for training.  For dart booster,
+#'        training predicting will perform dropout.
+#' @param iterationrange Specifies which layer of trees are used in prediction.  For
+#'        example, if a random forest is trained with 100 rounds.  Specifying
+#'        `iteration_range=(1, 21)`, then only the forests built during [1, 21) (half open set)
+#'        rounds are used in this prediction.  It's 1-based index just like R vector.  When set
+#'        to \code{c(1, 1)} XGBoost will use all trees.
+#' @param strict_shape  Default is \code{FALSE}. When it's set to \code{TRUE}, output
+#'        type and shape of prediction are invariant to model type.
+#'
 #' @param ... Parameters passed to \code{predict.xgb.Booster}
 #'
 #' @details
-#' Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
-#' and it is not necessarily equal to the number of trees in a model.
-#' E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-#' But for multiclass classification, while there are multiple trees per iteration,
-#' \code{ntreelimit} limits the number of boosting iterations.
 #'
-#' Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
+#' Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
 #' since gblinear doesn't keep its boosting history.
 #'
 #' One possible practical applications of the \code{predleaf} option is to use the model
@@ -169,7 +211,8 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' of the most important features first. See below about the format of the returned results.
 #'
 #' @return
-#' For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
+#' The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
+#' for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
 #' For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
 #' a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
 #' the \code{reshape} value.
@@ -191,6 +234,13 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 #' such an array.
 #'
+#' When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
+#' normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
+#'
+#' For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
+#' For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
+#' For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
+#'
 #' @seealso
 #' \code{\link{xgb.train}}.
 #'
@@ -213,7 +263,7 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' # use all trees by default
 #' pred <- predict(bst, test$data)
 #' # use only the 1st tree
-#' pred1 <- predict(bst, test$data, ntreelimit = 1)
+#' pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
 #'
 #' # Predicting tree leafs:
 #' # the result is an nsamples X ntrees matrix
@@ -265,31 +315,14 @@ xgb.Booster.complete <- function(object, saveraw = TRUE) {
 #' all.equal(pred, pred_labels)
 #' # prediction from using only 5 iterations should result
 #' # in the same error as seen in iteration 5:
-#' pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
+#' pred5 <- predict(bst, as.matrix(iris[, -5]), iterationrange=c(1, 6))
 #' sum(pred5 != lb)/length(lb)
 #'
-#'
-#' ## random forest-like model of 25 trees for binary classification:
-#'
-#' set.seed(11)
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-#'                nthread = 2, nrounds = 1, objective = "binary:logistic",
-#'                num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-#' # Inspect the prediction error vs number of trees:
-#' lb <- test$label
-#' dtest <- xgb.DMatrix(test$data, label=lb)
-#' err <- sapply(1:25, function(n) {
-#'   pred <- predict(bst, dtest, ntreelimit=n)
-#'   sum((pred > 0.5) != lb)/length(lb)
-#' })
-#' plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-#'
 #' @rdname predict.xgb.Booster
 #' @export
 predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE, ntreelimit = NULL,
                                 predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, training = FALSE, ...) {
-
+                                reshape = FALSE, training = FALSE, iterationrange = NULL, strict_shape = FALSE, ...) {
   object <- xgb.Booster.complete(object, saveraw = FALSE)
   if (!inherits(newdata, "xgb.DMatrix"))
     newdata <- xgb.DMatrix(newdata, missing = missing)
@@ -297,62 +330,114 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       !is.null(colnames(newdata)) &&
       !identical(object[["feature_names"]], colnames(newdata)))
     stop("Feature names stored in `object` and `newdata` are different!")
-  if (is.null(ntreelimit))
-    ntreelimit <- NVL(object$best_ntreelimit, 0)
-  if (NVL(object$params[['booster']], '') == 'gblinear')
+
+  if (NVL(object$params[['booster']], '') == 'gblinear' || is.null(ntreelimit))
     ntreelimit <- 0
-  if (ntreelimit < 0)
-    stop("ntreelimit cannot be negative")
 
-  option <- 0L + 1L * as.logical(outputmargin) + 2L * as.logical(predleaf) + 4L * as.logical(predcontrib) +
-    8L * as.logical(approxcontrib) + 16L * as.logical(predinteraction)
-
-  ret <- .Call(XGBoosterPredict_R, object$handle, newdata, option[1],
-               as.integer(ntreelimit), as.integer(training))
-
-  n_ret <- length(ret)
-  n_row <- nrow(newdata)
-  npred_per_case <- n_ret / n_row
-
-  if (n_ret %% n_row != 0)
-    stop("prediction length ", n_ret, " is not multiple of nrows(newdata) ", n_row)
-
-  if (predleaf) {
-    ret <- if (n_ret == n_row) {
-      matrix(ret, ncol = 1)
+  if (ntreelimit != 0 && is.null(iterationrange)) {
+    ## only ntreelimit, initialize iteration range
+    iterationrange <- c(0, 0)
+  } else if (ntreelimit == 0 && !is.null(iterationrange)) {
+    ## only iteration range, handle 1-based indexing
+    iterationrange <- c(iterationrange[1] - 1, iterationrange[2] - 1)
+  } else if (ntreelimit != 0 && !is.null(iterationrange)) {
+    ## both are specified, let libgxgboost throw an error
+  } else {
+    ## no limit is supplied, use best
+    if (is.null(object$best_iteration)) {
+      iterationrange <- c(0, 0)
     } else {
-      matrix(ret, nrow = n_row, byrow = TRUE)
+      ## We don't need to + 1 as R is 1-based index.
+      iterationrange <- c(0, as.integer(object$best_iteration))
     }
-  } else if (predcontrib) {
-    n_col1 <- ncol(newdata) + 1
-    n_group <- npred_per_case / n_col1
-    cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
-    ret <- if (n_ret == n_row) {
-      matrix(ret, ncol = 1, dimnames = list(NULL, cnames))
-    } else if (n_group == 1) {
-      matrix(ret, nrow = n_row, byrow = TRUE, dimnames = list(NULL, cnames))
-    } else {
-      arr <- array(ret, c(n_col1, n_group, n_row),
-                   dimnames = list(cnames, NULL, NULL)) %>% aperm(c(2,3,1)) # [group, row, col]
-      lapply(seq_len(n_group), function(g) arr[g,,])
+  }
+  ## Handle the 0 length values.
+  box <- function(val) {
+    if (length(val) == 0) {
+      cval <- vector(, 1)
+      cval[0] <- val
+      return(cval)
+    }
+    return (val)
+  }
+
+  ## We set strict_shape to TRUE then drop the dimensions conditionally
+  args <- list(
+    training = box(training),
+    strict_shape = box(TRUE),
+    iteration_begin = box(as.integer(iterationrange[1])),
+    iteration_end = box(as.integer(iterationrange[2])),
+    ntree_limit = box(as.integer(ntreelimit)),
+    type = box(as.integer(0))
+  )
+
+  set_type <- function(type) {
+    if (args$type != 0) {
+      stop("One type of prediction at a time.")
+    }
+    return(box(as.integer(type)))
+  }
+  if (outputmargin) {
+    args$type <- set_type(1)
+  }
+  if (predcontrib) {
+    args$type <- set_type(if (approxcontrib) 3 else 2)
+  }
+  if (predinteraction) {
+    args$type <- set_type(if (approxcontrib) 5 else 4)
+  }
+  if (predleaf) {
+    args$type <- set_type(6)
+  }
+
+  predts <- .Call(
+    XGBoosterPredictFromDMatrix_R, object$handle, newdata, jsonlite::toJSON(args, auto_unbox = TRUE)
+  )
+  names(predts) <- c("shape", "results")
+  shape <- predts$shape
+  ret <- predts$results
+
+  n_row <- nrow(newdata)
+  if (n_row != shape[1]) {
+    stop("Incorrect predict shape.")
+  }
+
+  arr <- array(data = ret, dim = rev(shape))
+
+  cnames <- if (!is.null(colnames(newdata))) c(colnames(newdata), "BIAS") else NULL
+  if (predcontrib) {
+    dimnames(arr) <- list(cnames, NULL, NULL)
+    if (!strict_shape) {
+      arr <- aperm(a = arr, perm = c(2, 3, 1)) # [group, row, col]
     }
   } else if (predinteraction) {
-    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 {
-      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,,,])
+    dimnames(arr) <- list(cnames, cnames, NULL, NULL)
+    if (!strict_shape) {
+      arr <- aperm(a = arr, perm = c(3, 4, 1, 2)) # [group, row, col, col]
     }
-  } else if (reshape && npred_per_case > 1) {
-    ret <- matrix(ret, nrow = n_row, byrow = TRUE)
   }
-  return(ret)
+
+  if (!strict_shape) {
+    n_groups <- shape[2]
+    if (predleaf) {
+      arr <- matrix(arr, nrow = n_row, byrow = TRUE)
+    } else if (predcontrib && n_groups != 1) {
+      arr <- lapply(seq_len(n_groups), function(g) arr[g, , ])
+    } else if (predinteraction && n_groups != 1) {
+      arr <- lapply(seq_len(n_groups), function(g) arr[g, , , ])
+    } else if (!reshape && n_groups != 1) {
+      arr <- ret
+    } else if (reshape && n_groups != 1) {
+      arr <- matrix(arr, ncol = n_groups, byrow = TRUE)
+    }
+    arr <- drop(arr)
+    if (length(dim(arr)) == 1) {
+      arr <- as.vector(arr)
+    } else if (length(dim(arr)) == 2) {
+      arr <- as.matrix(arr)
+    }
+  }
+  return(arr)
 }
 
 #' @rdname predict.xgb.Booster
@@ -397,7 +482,7 @@ predict.xgb.Booster.handle <- function(object, ...) {
 #' That would only matter if attributes need to be set many times.
 #' Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
 #' the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-#' and it would be user's responsibility to call \code{xgb.save.raw} to update it.
+#' and it would be user's responsibility to call \code{xgb.serialize} to update it.
 #'
 #' The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
 #' but it doesn't delete the other existing attributes.
@@ -456,7 +541,7 @@ xgb.attr <- function(object, name) {
   }
   .Call(XGBoosterSetAttr_R, handle, as.character(name[1]), value)
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
+    object$raw <- xgb.serialize(object$handle)
   }
   object
 }
@@ -496,11 +581,41 @@ xgb.attributes <- function(object) {
     .Call(XGBoosterSetAttr_R, handle, names(a[i]), a[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
+    object$raw <- xgb.serialize(object$handle)
   }
   object
 }
 
+#' Accessors for model parameters as JSON string.
+#'
+#' @param object Object of class \code{xgb.Booster}
+#' @param value A JSON string.
+#'
+#' @examples
+#' data(agaricus.train, package='xgboost')
+#' train <- agaricus.train
+#'
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+#' config <- xgb.config(bst)
+#'
+#' @rdname xgb.config
+#' @export
+xgb.config <- function(object) {
+  handle <- xgb.get.handle(object)
+  .Call(XGBoosterSaveJsonConfig_R, handle);
+}
+
+#' @rdname xgb.config
+#' @export
+`xgb.config<-` <- function(object, value) {
+  handle <- xgb.get.handle(object)
+  .Call(XGBoosterLoadJsonConfig_R, handle, value)
+  object$raw <- NULL  # force renew the raw buffer
+  object <- xgb.Booster.complete(object)
+  object
+}
+
 #' Accessors for model parameters.
 #'
 #' Only the setter for xgboost parameters is currently implemented.
@@ -537,7 +652,7 @@ xgb.attributes <- function(object) {
     .Call(XGBoosterSetParam_R, handle, names(p[i]), p[[i]])
   }
   if (is(object, 'xgb.Booster') && !is.null(object$raw)) {
-    object$raw <- xgb.save.raw(object$handle)
+    object$raw <- xgb.serialize(object$handle)
   }
   object
 }
@@ -590,7 +705,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
 
   if (!is.null(x$params)) {
     cat('params (as set within xgb.train):\n')
-    cat( '  ',
+    cat('  ',
          paste(names(x$params),
                paste0('"', unlist(x$params), '"'),
                sep = ' = ', collapse = ', '), '\n', sep = '')
@@ -603,9 +718,9 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   if (length(attrs) > 0) {
     cat('xgb.attributes:\n')
     if (verbose) {
-      cat( paste(paste0('  ',names(attrs)),
-                 paste0('"', unlist(attrs), '"'),
-                 sep = ' = ', collapse = '\n'), '\n', sep = '')
+        cat(paste(paste0('  ', names(attrs)),
+                  paste0('"', unlist(attrs), '"'),
+                  sep = ' = ', collapse = '\n'), '\n', sep = '')
     } else {
       cat('  ', paste(names(attrs), collapse = ', '), '\n', sep = '')
     }
@@ -627,7 +742,7 @@ print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   #cat('ntree: ', xgb.ntree(x), '\n', sep='')
 
   for (n in setdiff(names(x), c('handle', 'raw', 'call', 'params', 'callbacks',
-                                'evaluation_log','niter','feature_names'))) {
+                                'evaluation_log', 'niter', 'feature_names'))) {
     if (is.atomic(x[[n]])) {
       cat(n, ':', x[[n]], '\n', sep = ' ')
     } else {

R-package/R/xgb.DMatrix.R

@@ -1,7 +1,7 @@
 #' Construct xgb.DMatrix object
 #'
 #' Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-#' Supported input file formats are either a libsvm text file or a binary file that was created previously by
+#' Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
 #' \code{\link{xgb.DMatrix.save}}).
 #'
 #' @param data a \code{matrix} object (either numeric or integer), a \code{dgCMatrix} object, or a character
@@ -15,21 +15,21 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
 #' @export
-xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...) {
+xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, nthread = NULL, ...) {
   cnames <- NULL
   if (typeof(data) == "character") {
     if (length(data) > 1)
       stop("'data' has class 'character' and length ", length(data),
            ".\n  'data' accepts either a numeric matrix or a single filename.")
+    data <- path.expand(data)
     handle <- .Call(XGDMatrixCreateFromFile_R, data, as.integer(silent))
   } else if (is.matrix(data)) {
-    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing)
+    handle <- .Call(XGDMatrixCreateFromMat_R, data, missing, as.integer(NVL(nthread, -1)))
     cnames <- colnames(data)
   } else if (inherits(data, "dgCMatrix")) {
     handle <- .Call(XGDMatrixCreateFromCSC_R, data@p, data@i, data@x, nrow(data))
@@ -51,12 +51,12 @@ xgb.DMatrix <- function(data, info = list(), missing = NA, silent = FALSE, ...)
 
 # get dmatrix from data, label
 # internal helper method
-xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
+xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nthread = NULL) {
   if (inherits(data, "dgCMatrix") || is.matrix(data)) {
     if (is.null(label)) {
       stop("label must be provided when data is a matrix")
     }
-    dtrain <- xgb.DMatrix(data, label = label, missing = missing)
+    dtrain <- xgb.DMatrix(data, label = label, missing = missing, nthread = nthread)
     if (!is.null(weight)){
       setinfo(dtrain, "weight", weight)
     }
@@ -65,6 +65,7 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
       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
@@ -160,9 +161,9 @@ 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}.
 #'
 #' }
@@ -171,8 +172,7 @@ dimnames.xgb.DMatrix <- function(x) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -188,9 +188,10 @@ getinfo <- function(object, ...) UseMethod("getinfo")
 getinfo.xgb.DMatrix <- function(object, name, ...) {
   if (typeof(name) != "character" ||
       length(name) != 1 ||
-      !name %in% c('label', 'weight', 'base_margin', 'nrow')) {
+      !name %in% c('label', 'weight', 'base_margin', 'nrow',
+                   'label_lower_bound', 'label_upper_bound')) {
     stop("getinfo: name must be one of the following\n",
-         "    'label', 'weight', 'base_margin', 'nrow'")
+         "    'label', 'weight', 'base_margin', 'nrow', 'label_lower_bound', 'label_upper_bound'")
   }
   if (name != "nrow"){
     ret <- .Call(XGDMatrixGetInfo_R, object, name)
@@ -215,16 +216,15 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #' The \code{name} field can be one of the following:
 #'
 #' \itemize{
-#'     \item \code{label}: label Xgboost learn from ;
+#'     \item \code{label}: label XGBoost learn from ;
 #'     \item \code{weight}: to do a weight rescale ;
-#'     \item \code{base_margin}: base margin is the base prediction Xgboost will boost from ;
+#'     \item \code{base_margin}: base margin is the base prediction XGBoost will boost from ;
 #'     \item \code{group}: number of rows in each group (to use with \code{rank:pairwise} objective).
 #' }
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -243,9 +243,19 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
     .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
     return(TRUE)
   }
-  if (name == "weight") {
+  if (name == "label_lower_bound") {
     if (length(info) != nrow(object))
-      stop("The length of weights must equal to the number of rows in the input data")
+      stop("The length of lower-bound labels must equal to the number of rows in the input data")
+    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
+    return(TRUE)
+  }
+  if (name == "label_upper_bound") {
+    if (length(info) != nrow(object))
+      stop("The length of upper-bound labels must equal to the number of rows in the input data")
+    .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
+    return(TRUE)
+  }
+  if (name == "weight") {
     .Call(XGDMatrixSetInfo_R, object, name, as.numeric(info))
     return(TRUE)
   }
@@ -279,8 +289,7 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -309,7 +318,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
     for (i in seq_along(ind)) {
       obj_attr <- attr(object, nms[i])
       if (NCOL(obj_attr) > 1) {
-        attr(ret, nms[i]) <- obj_attr[idxset,]
+        attr(ret, nms[i]) <- obj_attr[idxset, ]
       } else {
         attr(ret, nms[i]) <- obj_attr[idxset]
       }
@@ -336,8 +345,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #'
 #' dtrain
 #' print(dtrain, verbose=TRUE)
@@ -346,10 +354,10 @@ 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 <- 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')
+  infos <- character(0)
+  if (length(getinfo(x, 'label')) > 0) infos <- 'label'
+  if (length(getinfo(x, 'weight')) > 0) infos <- c(infos, 'weight')
+  if (length(getinfo(x, 'base_margin')) > 0) infos <- c(infos, 'base_margin')
   if (length(infos) == 0) infos <- 'NA'
   cat(infos)
   cnames <- colnames(x)

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

@@ -1,14 +1,13 @@
 #' Save xgb.DMatrix object to binary file
-#' 
+#'
 #' Save xgb.DMatrix object to binary file
-#' 
+#'
 #' @param dmatrix the \code{xgb.DMatrix} object
 #' @param fname the name of the file to write.
-#' 
+#'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
@@ -18,7 +17,8 @@ xgb.DMatrix.save <- function(dmatrix, fname) {
     stop("fname must be character")
   if (!inherits(dmatrix, "xgb.DMatrix"))
     stop("dmatrix must be xgb.DMatrix")
-  
+
+  fname <- path.expand(fname)
   .Call(XGDMatrixSaveBinary_R, dmatrix, fname[1], 0L)
   return(TRUE)
 }

R-package/R/xgb.config.R

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

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

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

R-package/R/xgb.cv.R

@@ -2,12 +2,15 @@
 #'
 #' The cross validation function of xgboost
 #'
-#' @param params the list of parameters. Commonly used ones are:
+#' @param params the list of parameters. The complete list of parameters is
+#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
+#'   is a shorter summary:
 #' \itemize{
 #'   \item \code{objective} objective function, common ones are
 #'   \itemize{
-#'     \item \code{reg:squarederror} Regression with squared loss
-#'     \item \code{binary:logistic} logistic regression for classification
+#'     \item \code{reg:squarederror} Regression with squared loss.
+#'     \item \code{binary:logistic} logistic regression for classification.
+#'     \item See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
 #'   }
 #'   \item \code{eta} step size of each boosting step
 #'   \item \code{max_depth} maximum depth of the tree
@@ -33,6 +36,8 @@
 #'   \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
@@ -76,7 +81,7 @@
 #'
 #' All observations are used for both training and validation.
 #'
-#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
+#' Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
 #'
 #' @return
 #' An object of class \code{xgb.cv.synchronous} with the following elements:
@@ -96,18 +101,16 @@
 #'         parameter or randomly generated.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
+#'   \item \code{best_ntreelimit} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
 #'   \item \code{pred} CV prediction values available when \code{prediction} is set.
 #'         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-#'   \item \code{models} a liost of the CV folds' models. It is only available with the explicit
+#'   \item \code{models} a list of the CV folds' models. It is only available with the explicit
 #'         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
 #' }
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
 #'                   max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
@@ -134,20 +137,20 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   #  stop("Either 'eval_metric' or 'feval' must be provided for CV")
 
   # Check the labels
-  if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
-       (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
+  if ((inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
+      (!inherits(data, 'xgb.DMatrix') && is.null(label))) {
     stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
   } else if (inherits(data, 'xgb.DMatrix')) {
     if (!is.null(label))
       warning("xgb.cv: label will be ignored, since data is of type xgb.DMatrix")
-    cv_label = getinfo(data, 'label')
+    cv_label <- getinfo(data, 'label')
   } else {
-    cv_label = label
+    cv_label <- label
   }
 
   # CV folds
-  if(!is.null(folds)) {
-    if(!is.list(folds) || length(folds) < 2)
+  if (!is.null(folds)) {
+    if (!is.list(folds) || length(folds) < 2)
       stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
     nfold <- length(folds)
   } else {
@@ -162,7 +165,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # verbosity & evaluation printing callback:
   params <- c(params, list(silent = 1))
-  print_every_n <- max( as.integer(print_every_n), 1L)
+  print_every_n <- max(as.integer(print_every_n), 1L)
   if (!has.callbacks(callbacks, 'cb.print.evaluation') && verbose) {
     callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n, showsd = showsd))
   }
@@ -193,20 +196,20 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   bst_folds <- lapply(seq_along(folds), function(k) {
     dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow
-    if(is.null(train_folds))
+    if (is.null(train_folds))
        dtrain <- slice(dall, unlist(folds[-k]))
     else
        dtrain <- slice(dall, train_folds[[k]])
     handle <- xgb.Booster.handle(params, list(dtrain, dtest))
-    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test=dtest), index = folds[[k]])
+    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, test = dtest), index = folds[[k]])
   })
   rm(dall)
   # a "basket" to collect some results from callbacks
   basket <- list()
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
-  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1)
-  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1)
+  num_class <- max(as.numeric(NVL(params[['num_class']], 1)), 1) # nolint
+  num_parallel_tree <- max(as.numeric(NVL(params[['num_parallel_tree']], 1)), 1) # nolint
 
   # those are fixed for CV (no training continuation)
   begin_iteration <- 1
@@ -223,7 +226,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
     })
     msg <- simplify2array(msg)
     bst_evaluation <- rowMeans(msg)
-    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
+    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2) # nolint
 
     for (f in cb$post_iter) f()
 
@@ -282,10 +285,10 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
     }
     if (!is.null(x$params)) {
       cat('params (as set within xgb.cv):\n')
-      cat( '  ',
-           paste(names(x$params),
-                 paste0('"', unlist(x$params), '"'),
-                 sep = ' = ', collapse = ', '), '\n', sep = '')
+      cat('  ',
+          paste(names(x$params),
+                paste0('"', unlist(x$params), '"'),
+                sep = ' = ', collapse = ', '), '\n', sep = '')
     }
     if (!is.null(x$callbacks) && length(x$callbacks) > 0) {
       cat('callbacks:\n')

R-package/R/xgb.dump.R

@@ -1,15 +1,15 @@
 #' Dump an xgboost model in text format.
-#' 
+#'
 #' Dump an xgboost model in text format.
-#' 
+#'
 #' @param model the model object.
-#' @param fname the name of the text file where to save the model text dump. 
+#' @param fname the name of the text file where to save the model text dump.
 #'        If not provided or set to \code{NULL}, the model is returned as a \code{character} vector.
 #' @param fmap feature map file representing feature types.
-#'        Detailed description could be found at 
+#'        Detailed description could be found at
 #'        \url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
 #'        See demo/ for walkthrough example in R, and
-#'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt} 
+#'        \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
 #'        for example Format.
 #' @param with_stats whether to dump some additional statistics about the splits.
 #'        When this option is on, the model dump contains two additional values:
@@ -27,18 +27,18 @@
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
 #' dump_path = file.path(tempdir(), 'model.dump')
 #' xgb.dump(bst, dump_path, with_stats = TRUE)
-#' 
+#'
 #' # print the model without saving it to a file
 #' print(xgb.dump(bst, with_stats = TRUE))
-#' 
+#'
 #' # print in JSON format:
 #' cat(xgb.dump(bst, with_stats = TRUE, dump_format='json'))
-#' 
+#'
 #' @export
 xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
                      dump_format = c("text", "json"), ...) {
@@ -50,22 +50,23 @@ xgb.dump <- function(model, fname = NULL, fmap = "", with_stats=FALSE,
     stop("fname: argument must be a character string (when provided)")
   if (!(is.null(fmap) || is.character(fmap)))
     stop("fmap: argument must be a character string (when provided)")
-  
+
   model <- xgb.Booster.complete(model)
   model_dump <- .Call(XGBoosterDumpModel_R, model$handle, NVL(fmap, "")[1], as.integer(with_stats),
                       as.character(dump_format))
 
-  if (is.null(fname)) 
-    model_dump <- stri_replace_all_regex(model_dump, '\t', '')
-  
+  if (is.null(fname))
+    model_dump <- gsub('\t', '', model_dump, fixed = TRUE)
+
   if (dump_format == "text")
-    model_dump <- unlist(stri_split_regex(model_dump, '\n'))
-  
+    model_dump <- unlist(strsplit(model_dump, '\n', fixed = TRUE))
+
   model_dump <- grep('^\\s*$', model_dump, invert = TRUE, value = TRUE)
-  
+
   if (is.null(fname)) {
     return(model_dump)
   } else {
+    fname <- path.expand(fname)
     writeLines(model_dump, fname[1])
     return(TRUE)
   }

R-package/R/xgb.ggplot.R

@@ -3,9 +3,9 @@
 
 #' @rdname xgb.plot.importance
 #' @export
-xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL, 
+xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measure = NULL,
                                   rel_to_first = FALSE, n_clusters = c(1:10), ...) {
-  
+
   importance_matrix <- xgb.plot.importance(importance_matrix, top_n = top_n, measure = measure,
                                            rel_to_first = rel_to_first, plot = FALSE, ...)
   if (!requireNamespace("ggplot2", quietly = TRUE)) {
@@ -14,21 +14,21 @@ xgb.ggplot.importance <- function(importance_matrix = NULL, top_n = NULL, measur
   if (!requireNamespace("Ckmeans.1d.dp", quietly = TRUE)) {
     stop("Ckmeans.1d.dp package is required", call. = FALSE)
   }
-  
+
   clusters <- suppressWarnings(
     Ckmeans.1d.dp::Ckmeans.1d.dp(importance_matrix$Importance, n_clusters)
   )
   importance_matrix[, Cluster := as.character(clusters$cluster)]
 
   plot <-
-    ggplot2::ggplot(importance_matrix, 
+    ggplot2::ggplot(importance_matrix,
                     ggplot2::aes(x = factor(Feature, levels = rev(Feature)), y = Importance, width = 0.5),
-                    environment = environment()) + 
-    ggplot2::geom_bar(ggplot2::aes(fill = Cluster), stat = "identity", position = "identity") + 
-    ggplot2::coord_flip() + 
-    ggplot2::xlab("Features") + 
-    ggplot2::ggtitle("Feature importance") + 
-    ggplot2::theme(plot.title = ggplot2::element_text(lineheight = .9, face = "bold"), 
+                    environment = environment()) +
+    ggplot2::geom_bar(ggplot2::aes(fill = Cluster), stat = "identity", position = "identity") +
+    ggplot2::coord_flip() +
+    ggplot2::xlab("Features") +
+    ggplot2::ggtitle("Feature importance") +
+    ggplot2::theme(plot.title = ggplot2::element_text(lineheight = .9, face = "bold"),
                    panel.grid.major.y = ggplot2::element_blank())
   return(plot)
 }
@@ -42,7 +42,7 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     stop("ggplot2 package is required for plotting the graph deepness.", call. = FALSE)
 
   which <- match.arg(which)
-  
+
   dt_depths <- xgb.plot.deepness(model = model, plot = FALSE)
   dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
   setkey(dt_summaries, 'Depth')
@@ -60,30 +60,30 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
         axis.ticks = ggplot2::element_blank(),
         axis.text.x = ggplot2::element_blank()
       )
-  
-    p2 <- 
+
+    p2 <-
       ggplot2::ggplot(dt_summaries) +
-      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") + 
+      ggplot2::geom_bar(ggplot2::aes(x = Depth, y = Cover), stat = "Identity") +
       ggplot2::xlab("Leaf depth") +
       ggplot2::ylab("Weighted cover")
-  
+
     multiplot(p1, p2, cols = 1)
     return(invisible(list(p1, p2)))
-    
+
   } else if (which == "max.depth") {
     p <-
       ggplot2::ggplot(dt_depths[, max(Depth), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
+                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Max tree leaf depth")
     return(p)
-    
+
   } else if (which == "med.depth") {
     p <-
       ggplot2::ggplot(dt_depths[, median(as.numeric(Depth)), Tree]) +
       ggplot2::geom_jitter(ggplot2::aes(x = Tree, y = V1),
-                           height = 0.15, alpha=0.4, size=3, stroke=0) + 
+                           height = 0.15, alpha = 0.4, size = 3, stroke = 0) +
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median tree leaf depth")
     return(p)
@@ -92,24 +92,102 @@ xgb.ggplot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med
     p <-
       ggplot2::ggplot(dt_depths[, median(abs(Weight)), Tree]) +
       ggplot2::geom_point(ggplot2::aes(x = Tree, y = V1),
-                          alpha=0.4, size=3, stroke=0) + 
+                          alpha = 0.4, size = 3, stroke = 0) +
       ggplot2::xlab("tree #") +
       ggplot2::ylab("Median absolute leaf weight")
     return(p)
   }
 }
 
+#' @rdname xgb.plot.shap.summary
+#' @export
+xgb.ggplot.shap.summary <- function(data, shap_contrib = NULL, features = NULL, top_n = 10, model = NULL,
+                                    trees = NULL, target_class = NULL, approxcontrib = FALSE, subsample = NULL) {
+  data_list <- xgb.shap.data(
+    data = data,
+    shap_contrib = shap_contrib,
+    features = features,
+    top_n = top_n,
+    model = model,
+    trees = trees,
+    target_class = target_class,
+    approxcontrib = approxcontrib,
+    subsample = subsample,
+    max_observations = 10000  # 10,000 samples per feature.
+  )
+  p_data <- prepare.ggplot.shap.data(data_list, normalize = TRUE)
+  # Reverse factor levels so that the first level is at the top of the plot
+  p_data[, "feature" := factor(feature, rev(levels(feature)))]
+  p <- ggplot2::ggplot(p_data, ggplot2::aes(x = feature, y = p_data$shap_value, colour = p_data$feature_value)) +
+    ggplot2::geom_jitter(alpha = 0.5, width = 0.1) +
+    ggplot2::scale_colour_viridis_c(limits = c(-3, 3), option = "plasma", direction = -1) +
+    ggplot2::geom_abline(slope = 0, intercept = 0, colour = "darkgrey") +
+    ggplot2::coord_flip()
+
+  p
+}
+
+#' Combine and melt feature values and SHAP contributions for sample
+#' observations.
+#'
+#' Conforms to data format required for ggplot functions.
+#'
+#' Internal utility function.
+#'
+#' @param data_list List containing 'data' and 'shap_contrib' returned by
+#'   \code{xgb.shap.data()}.
+#' @param normalize Whether to standardize feature values to have mean 0 and
+#'   standard deviation 1 (useful for comparing multiple features on the same
+#'   plot). Default \code{FALSE}.
+#'
+#' @return A data.table containing the observation ID, the feature name, the
+#'   feature value (normalized if specified), and the SHAP contribution value.
+prepare.ggplot.shap.data <- function(data_list, normalize = FALSE) {
+  data <- data_list[["data"]]
+  shap_contrib <- data_list[["shap_contrib"]]
+
+  data <- data.table::as.data.table(as.matrix(data))
+  if (normalize) {
+    data[, (names(data)) := lapply(.SD, normalize)]
+  }
+  data[, "id" := seq_len(nrow(data))]
+  data_m <- data.table::melt.data.table(data, id.vars = "id", variable.name = "feature", value.name = "feature_value")
+
+  shap_contrib <- data.table::as.data.table(as.matrix(shap_contrib))
+  shap_contrib[, "id" := seq_len(nrow(shap_contrib))]
+  shap_contrib_m <- data.table::melt.data.table(shap_contrib, id.vars = "id", variable.name = "feature", value.name = "shap_value")
+
+  p_data <- data.table::merge.data.table(data_m, shap_contrib_m, by = c("id", "feature"))
+
+  p_data
+}
+
+#' Scale feature value to have mean 0, standard deviation 1
+#'
+#' This is used to compare multiple features on the same plot.
+#' Internal utility function
+#'
+#' @param x Numeric vector
+#'
+#' @return Numeric vector with mean 0 and sd 1.
+normalize <- function(x) {
+  loc <- mean(x, na.rm = TRUE)
+  scale <- stats::sd(x, na.rm = TRUE)
+
+  (x - loc) / scale
+}
+
 # Plot multiple ggplot graph aligned by rows and columns.
 # ... the plots
 # cols number of columns
 # internal utility function
 multiplot <- function(..., cols = 1) {
   plots <- list(...)
-  num_plots = length(plots)
-  
+  num_plots <- length(plots)
+
   layout <- matrix(seq(1, cols * ceiling(num_plots / cols)),
                    ncol = cols, nrow = ceiling(num_plots / cols))
-  
+
   if (num_plots == 1) {
     print(plots[[1]])
   } else {
@@ -118,7 +196,7 @@ multiplot <- function(..., cols = 1) {
     for (i in 1:num_plots) {
       # Get the i,j matrix positions of the regions that contain this subplot
       matchidx <- as.data.table(which(layout == i, arr.ind = TRUE))
-      
+
       print(
         plots[[i]], vp = grid::viewport(
           layout.pos.row = matchidx$row,
@@ -131,5 +209,5 @@ multiplot <- function(..., cols = 1) {
 
 globalVariables(c(
   "Cluster", "ggplot", "aes", "geom_bar", "coord_flip", "xlab", "ylab", "ggtitle", "theme",
-  "element_blank", "element_text", "V1", "Weight"
+  "element_blank", "element_text", "V1", "Weight", "feature"
 ))

R-package/R/xgb.importance.R

@@ -1,66 +1,66 @@
 #' Importance of features in a model.
-#' 
+#'
 #' Creates a \code{data.table} of feature importances in a model.
-#' 
+#'
 #' @param feature_names character vector of feature names. If the model already
 #'       contains feature names, those would be used when \code{feature_names=NULL} (default value).
 #'       Non-null \code{feature_names} could be provided to override those in the model.
 #' @param model object of class \code{xgb.Booster}.
 #' @param trees (only for the gbtree booster) an integer vector of tree indices that should be included
 #'          into the importance calculation. If set to \code{NULL}, all trees of the model are parsed.
-#'          It could be useful, e.g., in multiclass classification to get feature importances 
+#'          It could be useful, e.g., in multiclass classification to get feature importances
 #'          for each class separately. IMPORTANT: the tree index in xgboost models
 #'          is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
 #' @param data deprecated.
 #' @param label deprecated.
 #' @param target deprecated.
 #'
-#' @details 
-#' 
+#' @details
+#'
 #' This function works for both linear and tree models.
-#' 
-#' For linear models, the importance is the absolute magnitude of linear coefficients. 
-#' For that reason, in order to obtain a meaningful ranking by importance for a linear model, 
-#' the features need to be on the same scale (which you also would want to do when using either 
+#'
+#' For linear models, the importance is the absolute magnitude of linear coefficients.
+#' For that reason, in order to obtain a meaningful ranking by importance for a linear model,
+#' the features need to be on the same scale (which you also would want to do when using either
 #' L1 or L2 regularization).
-#' 
+#'
 #' @return
-#' 
+#'
 #' For a tree model, a \code{data.table} with the following columns:
 #' \itemize{
 #'   \item \code{Features} names of the features used in the model;
 #'   \item \code{Gain} represents fractional contribution of each feature to the model based on
-#'        the total gain of this feature's splits. Higher percentage means a more important 
+#'        the total gain of this feature's splits. Higher percentage means a more important
 #'        predictive feature.
 #'   \item \code{Cover} metric of the number of observation related to this feature;
 #'   \item \code{Frequency} percentage representing the relative number of times
 #'        a feature have been used in trees.
 #' }
-#' 
+#'
 #' A linear model's importance \code{data.table} has the following columns:
 #' \itemize{
 #'   \item \code{Features} names of the features used in the model;
 #'   \item \code{Weight} the linear coefficient of this feature;
 #'   \item \code{Class} (only for multiclass models) class label.
 #' }
-#' 
-#' If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names}, 
+#'
+#' If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names},
 #' index of the features will be used instead. Because the index is extracted from the model dump
 #' (based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
-#' 
+#'
 #' @examples
-#' 
+#'
 #' # binomial classification using gbtree:
 #' data(agaricus.train, package='xgboost')
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' xgb.importance(model = bst)
-#' 
+#'
 #' # binomial classification using gblinear:
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear", 
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear",
 #'                eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
 #' xgb.importance(model = bst)
-#' 
+#'
 #' # multiclass classification using gbtree:
 #' nclass <- 3
 #' nrounds <- 10
@@ -73,7 +73,7 @@
 #' xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
 #' xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
 #' xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
-#' 
+#'
 #' # multiclass classification using gblinear:
 #' mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
 #'                booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
@@ -83,54 +83,57 @@
 #' @export
 xgb.importance <- function(feature_names = NULL, model = NULL, trees = NULL,
                            data = NULL, label = NULL, target = NULL){
-  
+
   if (!(is.null(data) && is.null(label) && is.null(target)))
     warning("xgb.importance: parameters 'data', 'label' and 'target' are deprecated")
-  
+
   if (!inherits(model, "xgb.Booster"))
     stop("model: must be an object of class xgb.Booster")
-  
+
   if (is.null(feature_names) && !is.null(model$feature_names))
     feature_names <- model$feature_names
-  
+
   if (!(is.null(feature_names) || is.character(feature_names)))
     stop("feature_names: Has to be a character vector")
 
-  model_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))]
+  model <- xgb.Booster.complete(model)
+  config <- jsonlite::fromJSON(xgb.config(model))
+  if (config$learner$gradient_booster$name == "gblinear") {
+    args <- list(importance_type = "weight", feature_names = feature_names)
+    results <- .Call(
+      XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
+    )
+    names(results) <- c("features", "shape", "weight")
+    n_classes <-  if (length(results$shape) == 2) { results$shape[2] } else { 0 }
+    importance <- if (n_classes == 0) {
+      data.table(Feature = results$features, Weight = results$weight)[order(-abs(Weight))]
     } else {
-      data.table(Feature = rep(feature_names, each = num_class),
-                 Weight = weights,
-                 Class = seq_len(num_class) - 1)[order(Class, -abs(Weight))]
+      data.table(
+        Feature = rep(results$features, each = n_classes), Weight = results$weight, Class = seq_len(n_classes) - 1
+      )[order(Class, -abs(Weight))]
     }
-  } 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)]
+  } else {
+    concatenated <- list()
+    output_names <- vector()
+    for (importance_type in c("weight", "gain", "cover")) {
+      args <- list(importance_type = importance_type, feature_names = feature_names)
+      results <- .Call(
+        XGBoosterFeatureScore_R, model$handle, jsonlite::toJSON(args, auto_unbox = TRUE, null = "null")
+      )
+      names(results) <- c("features", "shape", importance_type)
+      concatenated[
+        switch(importance_type, "weight" = "Frequency", "gain" = "Gain", "cover" = "Cover")
+      ] <- results[importance_type]
+      output_names <- results$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)]
   }
-  result
+  importance
 }
 
 # Avoid error messages during CRAN check.

R-package/R/xgb.load.R

@@ -1,30 +1,30 @@
 #' Load xgboost model from binary file
-#' 
-#' Load xgboost model from the binary model file. 
-#' 
+#'
+#' Load xgboost model from the binary model file.
+#'
 #' @param modelfile the name of the binary input file.
-#' 
-#' @details 
+#'
+#' @details
 #' 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 
+#' using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
+#' appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 #' saved from there in xgboost format, could be loaded from R.
-#' 
+#'
 #' Note: a model saved as an R-object, has to be loaded using corresponding R-methods,
 #' not \code{xgb.load}.
-#' 
-#' @return 
+#'
+#' @return
 #' An object of \code{xgb.Booster} class.
-#' 
-#' @seealso 
-#' \code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}. 
-#' 
+#'
+#' @seealso
+#' \code{\link{xgb.save}}, \code{\link{xgb.Booster.complete}}.
+#'
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' xgb.save(bst, 'xgb.model')
 #' bst <- xgb.load('xgb.model')

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

@@ -0,0 +1,14 @@
+#' Load serialised xgboost model from R's raw vector
+#'
+#' User can generate raw memory buffer by calling xgb.save.raw
+#'
+#' @param buffer the buffer returned by xgb.save.raw
+#'
+#' @export
+xgb.load.raw <- function(buffer) {
+  cachelist <- list()
+  handle <- .Call(XGBoosterCreate_R, cachelist)
+  .Call(XGBoosterLoadModelFromRaw_R, handle, buffer)
+  class(handle) <- "xgb.Booster.handle"
+  return (handle)
+}

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

@@ -1,12 +1,12 @@
 #' Parse a boosted tree model text dump
-#' 
+#'
 #' Parse a boosted tree model text dump into a \code{data.table} structure.
-#' 
+#'
 #' @param feature_names character vector of feature names. If the model already
 #'          contains feature names, those would be used when \code{feature_names=NULL} (default value).
 #'          Non-null \code{feature_names} could be provided to override those in the model.
 #' @param model object of class \code{xgb.Booster}
-#' @param text \code{character} vector previously generated by the \code{xgb.dump} 
+#' @param text \code{character} vector previously generated by the \code{xgb.dump}
 #'          function  (where parameter \code{with_stats = TRUE} should have been set).
 #'          \code{text} takes precedence over \code{model}.
 #' @param trees an integer vector of tree indices that should be parsed.
@@ -18,11 +18,11 @@
 #'          represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).
 #' @param ... currently not used.
 #'
-#' @return 
+#' @return
 #' A \code{data.table} with detailed information about model trees' nodes.
 #'
 #' The columns of the \code{data.table} are:
-#' 
+#'
 #' \itemize{
 #'  \item \code{Tree}: integer ID of a tree in a model (zero-based index)
 #'  \item \code{Node}: integer ID of a node in a tree (zero-based index)
@@ -36,109 +36,111 @@
 #'  \item \code{Quality}: either the split gain (change in loss) or the leaf value
 #'  \item \code{Cover}: metric related to the number of observation either seen by a split
 #'                      or collected by a leaf during training.
-#' } 
-#' 
+#' }
+#'
 #' When \code{use_int_id=FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
-#' in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from 
+#' in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from
 #' the corresponding trees in the "Node" column.
-#' 
+#'
 #' @examples
 #' # Basic use:
-#' 
+#'
 #' data(agaricus.train, package='xgboost')
-#' 
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+#'
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
-#' 
+#'
 #' (dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
-#' 
-#' # This bst model already has feature_names stored with it, so those would be used when 
+#'
+#' # This bst model already has feature_names stored with it, so those would be used when
 #' # feature_names is not set:
 #' (dt <- xgb.model.dt.tree(model = bst))
-#' 
+#'
 #' # How to match feature names of splits that are following a current 'Yes' branch:
-#' 
+#'
 #' merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
-#'  
+#'
 #' @export
 xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
                               trees = NULL, use_int_id = FALSE, ...){
   check.deprecation(...)
-  
+
   if (!inherits(model, "xgb.Booster") && !is.character(text)) {
     stop("Either 'model' must be an object of class xgb.Booster\n",
          "  or 'text' must be a character vector with the result of xgb.dump\n",
          "  (or NULL if 'model' was provided).")
   }
-  
+
   if (is.null(feature_names) && !is.null(model) && !is.null(model$feature_names))
     feature_names <- model$feature_names
-  
+
   if (!(is.null(feature_names) || is.character(feature_names))) {
     stop("feature_names: must be a character vector")
   }
-  
+
   if (!(is.null(trees) || is.numeric(trees))) {
     stop("trees: must be a vector of integers.")
   }
-  
+
   if (is.null(text)){
     text <- xgb.dump(model = model, with_stats = TRUE)
   }
-  
+
   if (length(text) < 2 ||
-      sum(stri_detect_regex(text, 'yes=(\\d+),no=(\\d+)')) < 1) {
+      sum(grepl('yes=(\\d+),no=(\\d+)', text)) < 1) {
     stop("Non-tree model detected! This function can only be used with tree models.")
   }
-  
-  position <- which(!is.na(stri_match_first_regex(text, "booster")))
-  
+
+  position <- which(grepl("booster", text, fixed = TRUE))
+
   add.tree.id <- function(node, tree) if (use_int_id) node else paste(tree, node, sep = "-")
-  
+
   anynumber_regex <- "[-+]?[0-9]*\\.?[0-9]+([eE][-+]?[0-9]+)?"
-  
+
   td <- data.table(t = text)
   td[position, Tree := 1L]
   td[, Tree := cumsum(ifelse(is.na(Tree), 0L, Tree)) - 1L]
-  
+
   if (is.null(trees)) {
     trees <- 0:max(td$Tree)
   } else {
     trees <- trees[trees >= 0 & trees <= max(td$Tree)]
   }
   td <- td[Tree %in% trees & !grepl('^booster', t)]
-  
-  td[, Node := stri_match_first_regex(t, "(\\d+):")[,2] %>% as.integer ]
+
+  td[, Node := as.integer(sub("^([0-9]+):.*", "\\1", t))]
   if (!use_int_id) td[, ID := add.tree.id(Node, Tree)]
-  td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
+  td[, isLeaf := grepl("leaf", t, fixed = TRUE)]
 
   # parse branch lines
   branch_rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
                       "gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   branch_cols <- c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
-  td[isLeaf == FALSE, 
+  td[isLeaf == FALSE,
      (branch_cols) := {
-      # skip some indices with spurious capture groups from anynumber_regex
-      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)
-      lapply(seq_len(ncol(xtr)), function(i) xtr[,i])
+       matches <- regmatches(t, regexec(branch_rx, t))
+       # skip some indices with spurious capture groups from anynumber_regex
+       xtr <- do.call(rbind, matches)[, c(2, 3, 5, 6, 7, 8, 10), drop = FALSE]
+       xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
+       as.data.table(xtr)
     }]
   # assign feature_names when available
   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] ]
+    td[isLeaf == FALSE, Feature := feature_names[as.numeric(Feature) + 1]]
   }
-  
+
   # parse leaf lines
   leaf_rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
   leaf_cols <- c("Feature", "Quality", "Cover")
   td[isLeaf == TRUE,
      (leaf_cols) := {
-      xtr <- stri_match_first_regex(t, leaf_rx)[, c(2,4)]
-      c("Leaf", lapply(seq_len(ncol(xtr)), function(i) xtr[,i]))
+       matches <- regmatches(t, regexec(leaf_rx, t))
+       xtr <- do.call(rbind, matches)[, c(2, 4)]
+       c("Leaf", as.data.table(xtr))
     }]
-  
+
   # convert some columns to numeric
   numeric_cols <- c("Split", "Quality", "Cover")
   td[, (numeric_cols) := lapply(.SD, as.numeric), .SDcols = numeric_cols]
@@ -146,14 +148,14 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
     int_cols <- c("Yes", "No", "Missing")
     td[, (int_cols) := lapply(.SD, as.integer), .SDcols = int_cols]
   }
-  
+
   td[, t := NULL]
   td[, isLeaf := NULL]
-  
+
   td[order(Tree, Node)]
 }
 
 # Avoid error messages during CRAN check.
 # The reason is that these variables are never declared
 # They are mainly column names inferred by Data.table...
-globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf",".SD", ".SDcols"))
+globalVariables(c("Tree", "Node", "ID", "Feature", "t", "isLeaf", ".SD", ".SDcols"))

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

@@ -2,48 +2,48 @@
 #'
 #' Visualizes distributions related to depth of tree leafs.
 #' \code{xgb.plot.deepness} uses base R graphics, while \code{xgb.ggplot.deepness} uses the ggplot backend.
-#' 
+#'
 #' @param model either an \code{xgb.Booster} model generated by the \code{xgb.train} function
 #'        or a data.table result of the \code{xgb.model.dt.tree} function.
-#' @param plot (base R barplot) whether a barplot should be produced. 
+#' @param plot (base R barplot) whether a barplot should be produced.
 #'        If FALSE, only a data.table is returned.
 #' @param which which distribution to plot (see details).
 #' @param ... other parameters passed to \code{barplot} or \code{plot}.
-#' 
+#'
 #' @details
-#' 
+#'
 #' When \code{which="2x1"}, two distributions with respect to the leaf depth
 #' are plotted on top of each other:
 #' \itemize{
 #'  \item the distribution of the number of leafs in a tree model at a certain depth;
-#'  \item the distribution of average weighted number of observations ("cover") 
+#'  \item the distribution of average weighted number of observations ("cover")
 #'        ending up in leafs at certain depth.
 #' }
-#' Those could be helpful in determining sensible ranges of the \code{max_depth} 
+#' Those could be helpful in determining sensible ranges of the \code{max_depth}
 #' and \code{min_child_weight} parameters.
-#' 
+#'
 #' When \code{which="max.depth"} or \code{which="med.depth"}, plots of either maximum or median depth
 #' per tree with respect to tree number are created. And \code{which="med.weight"} allows to see how
 #' a tree's median absolute leaf weight changes through the iterations.
 #'
 #' This function was inspired by the blog post
 #' \url{https://github.com/aysent/random-forest-leaf-visualization}.
-#' 
+#'
 #' @return
-#' 
+#'
 #' Other than producing plots (when \code{plot=TRUE}), the \code{xgb.plot.deepness} function
 #' silently returns a processed data.table where each row corresponds to a terminal leaf in a tree model,
 #' and contains information about leaf's depth, cover, and weight (which is used in calculating predictions).
-#' 
+#'
 #' The \code{xgb.ggplot.deepness} silently returns either a list of two ggplot graphs when \code{which="2x1"}
 #' or a single ggplot graph for the other \code{which} options.
 #'
-#' @seealso 
-#' 
+#' @seealso
+#'
 #' \code{\link{xgb.train}}, \code{\link{xgb.model.dt.tree}}.
-#' 
+#'
 #' @examples
-#' 
+#'
 #' data(agaricus.train, package='xgboost')
 #'
 #' # Change max_depth to a higher number to get a more significant result
@@ -53,16 +53,16 @@
 #'
 #' xgb.plot.deepness(bst)
 #' xgb.ggplot.deepness(bst)
-#' 
+#'
 #' xgb.plot.deepness(bst, which='max.depth', pch=16, col=rgb(0,0,1,0.3), cex=2)
-#' 
+#'
 #' xgb.plot.deepness(bst, which='med.weight', pch=16, col=rgb(0,0,1,0.3), cex=2)
 #'
 #' @rdname xgb.plot.deepness
 #' @export
 xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.depth", "med.weight"),
                               plot = TRUE, ...) {
-  
+
   if (!(inherits(model, "xgb.Booster") || is.data.table(model)))
     stop("model: Has to be either an xgb.Booster model generaged by the xgb.train function\n",
          "or a data.table result of the xgb.importance function")
@@ -71,32 +71,32 @@ xgb.plot.deepness <- function(model = NULL, which = c("2x1", "max.depth", "med.d
     stop("igraph package is required for plotting the graph deepness.", call. = FALSE)
 
   which <- match.arg(which)
-  
+
   dt_tree <- model
   if (inherits(model, "xgb.Booster"))
     dt_tree <- xgb.model.dt.tree(model = model)
-  
+
   if (!all(c("Feature", "Tree", "ID", "Yes", "No", "Cover") %in% colnames(dt_tree)))
     stop("Model tree columns are not as expected!\n",
          "  Note that this function works only for tree models.")
-  
+
   dt_depths <- merge(get.leaf.depth(dt_tree), dt_tree[, .(ID, Cover, Weight = Quality)], by = "ID")
   setkeyv(dt_depths, c("Tree", "ID"))
   # count by depth levels, and also calculate average cover at a depth
   dt_summaries <- dt_depths[, .(.N, Cover = mean(Cover)), Depth]
   setkey(dt_summaries, "Depth")
-  
+
   if (plot) {
     if (which == "2x1") {
       op <- par(no.readonly = TRUE)
-      par(mfrow = c(2,1),
-          oma = c(3,1,3,1) + 0.1,
-          mar = c(1,4,1,0) + 0.1)
+      par(mfrow = c(2, 1),
+          oma = c(3, 1, 3, 1) + 0.1,
+          mar = c(1, 4, 1, 0) + 0.1)
 
       dt_summaries[, barplot(N, border = NA, ylab = 'Number of leafs', ...)]
 
       dt_summaries[, barplot(Cover, border = NA, ylab = "Weighted cover", names.arg = Depth, ...)]
-    
+
       title("Model complexity", xlab = "Leaf depth", outer = TRUE, line = 1)
       par(op)
     } else if (which == "max.depth") {
@@ -123,14 +123,14 @@ get.leaf.depth <- function(dt_tree) {
       dt_tree[Feature != "Leaf", .(ID, To = No, Tree)]
     ))
   # whether "To" is a leaf:
-  dt_edges <- 
+  dt_edges <-
     merge(dt_edges,
           dt_tree[Feature == "Leaf", .(ID, Leaf = TRUE)],
           all.x = TRUE, by.x = "To", by.y = "ID")
   dt_edges[is.na(Leaf), Leaf := FALSE]
 
   dt_edges[, {
-    graph <- igraph::graph_from_data_frame(.SD[,.(ID, To)])
+    graph <- igraph::graph_from_data_frame(.SD[, .(ID, To)])
     # min(ID) in a tree is a root node
     paths_tmp <- igraph::shortest_paths(graph, from = min(ID), to = To[Leaf == TRUE])
     # list of paths to each leaf in a tree

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

@@ -92,28 +92,27 @@ xgb.plot.importance <- function(importance_matrix = NULL, top_n = NULL, measure
     importance_matrix <- head(importance_matrix, top_n)
   }
   if (rel_to_first) {
-    importance_matrix[, Importance := Importance/max(abs(Importance))]
+    importance_matrix[, Importance := Importance / max(abs(Importance))]
   }
   if (is.null(cex)) {
-    cex <- 2.5/log2(1 + nrow(importance_matrix))
+    cex <- 2.5 / log2(1 + nrow(importance_matrix))
   }
 
   if (plot) {
-    op <- par(no.readonly = TRUE)
-    mar <- op$mar
+    original_mar <- par()$mar
+
+    # reset margins so this function doesn't have side effects
+    on.exit({par(mar = original_mar)})
+
+    mar <- original_mar
     if (!is.null(left_margin))
       mar[2] <- left_margin
     par(mar = mar)
 
     # reverse the order of rows to have the highest ranked at the top
-    importance_matrix[nrow(importance_matrix):1,
+    importance_matrix[rev(seq_len(nrow(importance_matrix))),
                       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

@@ -9,7 +9,7 @@
 #' @param plot_height height in pixels of the graph to produce
 #' @param render a logical flag for whether the graph should be rendered (see Value).
 #' @param ... currently not used
-#' 
+#'
 #' @details
 #'
 #' This function tries to capture the complexity of a gradient boosted tree model
@@ -67,77 +67,87 @@ 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[stri_detect_regex(ID, "\\d+-0"), ID]
+  root.nodes <- tree.matrix[Node == 0, ID]
   tree.matrix[ID %in% root.nodes, abs.node.position := root.nodes]
 
   precedent.nodes <- root.nodes
 
-  while(tree.matrix[,sum(is.na(abs.node.position))] > 0) {
+  while (tree.matrix[, sum(is.na(abs.node.position))] > 0) {
     yes.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(Yes)]
     no.row.nodes <- tree.matrix[abs.node.position %in% precedent.nodes & !is.na(No)]
-    yes.nodes.abs.pos <- yes.row.nodes[, abs.node.position] %>% paste0("_0")
-    no.nodes.abs.pos <- no.row.nodes[, abs.node.position] %>% paste0("_1")
-    
+    yes.nodes.abs.pos <- paste0(yes.row.nodes[, abs.node.position], "_0")
+    no.nodes.abs.pos <- paste0(no.row.nodes[, abs.node.position], "_1")
+
     tree.matrix[ID %in% yes.row.nodes[, Yes], abs.node.position := yes.nodes.abs.pos]
     tree.matrix[ID %in% no.row.nodes[, No], abs.node.position := no.nodes.abs.pos]
     precedent.nodes <- c(yes.nodes.abs.pos, no.nodes.abs.pos)
   }
-  
+
   tree.matrix[!is.na(Yes), Yes := paste0(abs.node.position, "_0")]
   tree.matrix[!is.na(No), No := paste0(abs.node.position, "_1")]
-  
-  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))]
-  
+
+  for (nm in c("abs.node.position", "Yes", "No"))
+    data.table::set(tree.matrix, j = nm, value = sub("^\\d+-", "", tree.matrix[[nm]]))
+
   nodes.dt <- tree.matrix[
         , .(Quality = sum(Quality))
         , by = .(abs.node.position, Feature)
-      ][, .(Text = paste0(Feature[1:min(length(Feature), features_keep)],
-                          " (",
-                          format(Quality[1:min(length(Quality), features_keep)], digits=5),
-                          ")") %>%
-                   paste0(collapse = "\n"))
-        , by = abs.node.position]
-  
-  edges.dt <- tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)] %>%
-    list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>%
-    rbindlist() %>%
-    setnames(c("From", "To")) %>%
-    .[, .N, .(From, To)] %>%
-    .[, N:=NULL]
-  
+      ][, .(Text = paste0(
+              paste0(
+                Feature[1:min(length(Feature), features_keep)],
+                " (",
+                format(Quality[1:min(length(Quality), features_keep)], digits = 5),
+                ")"
+              ),
+              collapse = "\n"
+            )
+          )
+        , by = abs.node.position
+      ]
+
+  edges.dt <- data.table::rbindlist(
+    l = list(
+      tree.matrix[Feature != "Leaf", .(abs.node.position, Yes)],
+      tree.matrix[Feature != "Leaf", .(abs.node.position, No)]
+    )
+  )
+  data.table::setnames(edges.dt, c("From", "To"))
+  edges.dt <- edges.dt[, .N, .(From, To)]
+  edges.dt[, N := NULL]
+
   nodes <- DiagrammeR::create_node_df(
     n = nrow(nodes.dt),
-    label = nodes.dt[,Text]
+    label = nodes.dt[, Text]
   )
-  
+
   edges <- DiagrammeR::create_edge_df(
-    from = match(edges.dt[,From], nodes.dt[,abs.node.position]),
-    to = match(edges.dt[,To], nodes.dt[,abs.node.position]),
+    from = match(edges.dt[, From], nodes.dt[, abs.node.position]),
+    to = match(edges.dt[, To], nodes.dt[, abs.node.position]),
     rel = "leading_to")
-  
+
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "node",
       attr  = c("color", "fillcolor", "style", "shape", "fontname"),
       value = c("DimGray", "beige", "filled", "rectangle", "Helvetica")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
+      value = c("DimGray", "1.5", "vee", "Helvetica")
+  )
 
   if (!render) return(invisible(graph))
 

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

@@ -33,7 +33,7 @@
 #' @param col_loess a color to use for the loess curves.
 #' @param span_loess the \code{span} parameter in \code{\link[stats]{loess}}'s call.
 #' @param which whether to do univariate or bivariate plotting. NOTE: only 1D is implemented so far.
-#' @param plot whether a plot should be drawn. If FALSE, only a lits of matrices is returned.
+#' @param plot whether a plot should be drawn. If FALSE, only a list of matrices is returned.
 #' @param ... other parameters passed to \code{plot}.
 #'
 #' @details
@@ -81,6 +81,7 @@
 #' 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
@@ -99,6 +100,7 @@
 #'               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
@@ -109,69 +111,33 @@ 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, ...) {
-
-  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,]
-  }
+  data_list <- xgb.shap.data(
+    data = data,
+    shap_contrib = shap_contrib,
+    features = features,
+    top_n = top_n,
+    model = model,
+    trees = trees,
+    target_class = target_class,
+    approxcontrib = approxcontrib,
+    subsample = subsample,
+    max_observations = 100000
+  )
+  data <- data_list[["data"]]
+  shap_contrib <- data_list[["shap_contrib"]]
+  features <- colnames(data)
 
   which <- match.arg(which)
   if (which == "2d")
     stop("2D plots are not implemented yet")
 
-  if (is.null(features)) {
-    imp <- xgb.importance(model = model, trees = trees)
-    top_n <- as.integer(top_n[1])
-    if (top_n < 1 && top_n > 100)
-      stop("top_n: must be an integer within [1, 100]")
-    features <- imp$Feature[1:min(top_n, NROW(imp))]
-  }
-
-  if (is.character(features)) {
-    if (is.null(colnames(data)))
-      stop("Either provide `data` with column names or provide `features` as column indices")
-    features <- match(features, colnames(data))
-  }
-
   if (n_col > length(features)) n_col <- length(features)
-
-  if (is.list(shap_contrib)) { # multiclass: either choose a class or merge
-    shap_contrib <- if (!is.null(target_class)) shap_contrib[[target_class + 1]]
-                    else Reduce("+", lapply(shap_contrib, abs))
-  }
-
-  shap_contrib <- shap_contrib[, features, drop = FALSE]
-  data <- data[, features, drop = FALSE]
-  cols <- colnames(data)
-  if (is.null(cols)) cols <- colnames(shap_contrib)
-  if (is.null(cols)) cols <- paste0('X', 1:ncol(data))
-  colnames(data) <- cols
-  colnames(shap_contrib) <- cols
-
   if (plot && which == "1d") {
     op <- par(mfrow = c(ceiling(length(features) / n_col), n_col),
-              oma = c(0,0,0,0) + 0.2,
-              mar = c(3.5,3.5,0,0) + 0.1,
+              oma = c(0, 0, 0, 0) + 0.2,
+              mar = c(3.5, 3.5, 0, 0) + 0.1,
               mgp = c(1.7, 0.6, 0))
-    for (f in cols) {
+    for (f in features) {
       ord <- order(data[, f])
       x <- data[, f][ord]
       y <- shap_contrib[, f][ord]
@@ -191,8 +157,8 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
       plot(x2plot, y, pch = pch, xlab = f, col = col, xlim = x_lim, ylim = y_lim, ylab = ylab, ...)
       grid()
       if (plot_loess) {
-        # compress x to 3 digits, and mean-aggredate y
-        zz <- data.table(x = signif(x, 3), y)[, .(.N, y=mean(y)), x]
+        # compress x to 3 digits, and mean-aggregate y
+        zz <- data.table(x = signif(x, 3), y)[, .(.N, y = mean(y)), x]
         if (nrow(zz) <= 5) {
           lines(zz$x, zz$y, col = col_loess)
         } else {
@@ -216,3 +182,108 @@ 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

@@ -1,7 +1,7 @@
 #' Plot a boosted tree model
-#' 
-#' Read a tree model text dump and plot the model. 
-#' 
+#'
+#' Read a tree model text dump and plot the model.
+#'
 #' @param feature_names names of each feature as a \code{character} vector.
 #' @param model produced by the \code{xgb.train} function.
 #' @param trees an integer vector of tree indices that should be visualized.
@@ -14,10 +14,10 @@
 #' @param show_node_id a logical flag for whether to show node id's in the graph.
 #' @param ... currently not used.
 #'
-#' @details 
-#' 
+#' @details
+#'
 #' The content of each node is organised that way:
-#' 
+#'
 #' \itemize{
 #'  \item Feature name.
 #'  \item \code{Cover}: The sum of second order gradient of training data classified to the leaf.
@@ -27,21 +27,21 @@
 #'  \item \code{Gain} (for split nodes): the information gain metric of a split
 #'        (corresponds to the importance of the node in the model).
 #'  \item \code{Value} (for leafs): the margin value that the leaf may contribute to prediction.
-#' } 
+#' }
 #' The tree root nodes also indicate the Tree index (0-based).
-#' 
+#'
 #' The "Yes" branches are marked by the "< split_value" label.
 #' The branches that also used for missing values are marked as bold
 #' (as in "carrying extra capacity").
-#' 
+#'
 #' This function uses \href{http://www.graphviz.org/}{GraphViz} as a backend of DiagrammeR.
-#'  
+#'
 #' @return
-#' 
+#'
 #' When \code{render = TRUE}:
 #' returns a rendered graph object which is an \code{htmlwidget} of class \code{grViz}.
 #' Similar to ggplot objects, it needs to be printed to see it when not running from command line.
-#' 
+#'
 #' When \code{render = FALSE}:
 #' silently returns a graph object which is of DiagrammeR's class \code{dgr_graph}.
 #' This could be useful if one wants to modify some of the graph attributes
@@ -49,23 +49,23 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' 
+#'
 #' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 3,
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' # plot all the trees
 #' xgb.plot.tree(model = bst)
 #' # plot only the first tree and display the node ID:
 #' xgb.plot.tree(model = bst, trees = 0, show_node_id = TRUE)
-#' 
+#'
 #' \dontrun{
-#' # Below is an example of how to save this plot to a file. 
+#' # Below is an example of how to save this plot to a file.
 #' # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
 #' library(DiagrammeR)
 #' gr <- xgb.plot.tree(model=bst, trees=0:1, render=FALSE)
 #' export_graph(gr, 'tree.pdf', width=1500, height=1900)
 #' export_graph(gr, 'tree.png', width=1500, height=1900)
 #' }
-#' 
+#'
 #' @export
 xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot_width = NULL, plot_height = NULL,
                           render = TRUE, show_node_id = FALSE, ...){
@@ -77,18 +77,18 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
   if (!requireNamespace("DiagrammeR", quietly = TRUE)) {
     stop("DiagrammeR package is required for xgb.plot.tree", call. = FALSE)
   }
-  
+
   dt <- xgb.model.dt.tree(feature_names = feature_names, model = model, trees = trees)
 
-  dt[, label:= paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
+  dt[, label := paste0(Feature, "\nCover: ", Cover, ifelse(Feature == "Leaf", "\nValue: ", "\nGain: "), Quality)]
   if (show_node_id)
     dt[, label := paste0(ID, ": ", label)]
   dt[Node == 0, label := paste0("Tree ", Tree, "\n", label)]
-  dt[, shape:= "rectangle"][Feature == "Leaf", shape:= "oval"]
-  dt[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"]
+  dt[, shape := "rectangle"][Feature == "Leaf", shape := "oval"]
+  dt[, filledcolor := "Beige"][Feature == "Leaf", filledcolor := "Khaki"]
   # in order to draw the first tree on top:
   dt <- dt[order(-Tree)]
-  
+
   nodes <- DiagrammeR::create_node_df(
     n         = nrow(dt),
     ID        = dt$ID,
@@ -97,38 +97,46 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, trees = NULL, plot
     shape     = dt$shape,
     data      = dt$Feature,
     fontcolor = "black")
-  
+
   edges <- DiagrammeR::create_edge_df(
-    from  = match(dt[Feature != "Leaf", c(ID)] %>% rep(2), dt$ID),
+    from  = match(rep(dt[Feature != "Leaf", c(ID)], 2), dt$ID),
     to    = match(dt[Feature != "Leaf", c(Yes, No)], dt$ID),
-    label = dt[Feature != "Leaf", paste("<", Split)] %>%
-            c(rep("", nrow(dt[Feature != "Leaf"]))),
-    style = dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")] %>%
-            c(dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]),
+    label = c(
+      dt[Feature != "Leaf", paste("<", Split)],
+      rep("", nrow(dt[Feature != "Leaf"]))
+    ),
+    style = c(
+      dt[Feature != "Leaf", ifelse(Missing == Yes, "bold", "solid")],
+      dt[Feature != "Leaf", ifelse(Missing == No, "bold", "solid")]
+    ),
     rel   = "leading_to")
 
   graph <- DiagrammeR::create_graph(
       nodes_df = nodes,
       edges_df = edges,
       attr_theme = NULL
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "graph",
       attr  = c("layout", "rankdir"),
       value = c("dot", "LR")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "node",
       attr  = c("color", "style", "fontname"),
       value = c("DimGray", "filled", "Helvetica")
-      ) %>%
-    DiagrammeR::add_global_graph_attrs(
+  )
+  graph <- DiagrammeR::add_global_graph_attrs(
+      graph = graph,
       attr_type = "edge",
       attr  = c("color", "arrowsize", "arrowhead", "fontname"),
-      value = c("DimGray", "1.5", "vee", "Helvetica"))
-  
+      value = c("DimGray", "1.5", "vee", "Helvetica")
+  )
+
   if (!render) return(invisible(graph))
-  
+
   DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
 }
 

R-package/R/xgb.save.R

@@ -1,29 +1,33 @@
 #' Save xgboost model to binary file
-#' 
+#'
 #' Save xgboost model to a file in binary format.
-#' 
+#'
 #' @param model model object of \code{xgb.Booster} class.
 #' @param fname name of the file to write.
-#' 
-#' @details 
-#' This methods allows to save a model in an xgboost-internal binary format which is universal 
+#'
+#' @details
+#' This methods allows to save a model in an xgboost-internal binary format which is universal
 #' among the various xgboost interfaces. In R, the saved model file could be read-in later
-#' using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter 
+#' using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter
 #' of \code{\link{xgb.train}}.
-#' 
-#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
-#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
-#' corresponding R-methods would need to be used to load it.
-#' 
-#' @seealso 
-#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}. 
-#' 
+#'
+#' Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}}
+#' or \code{\link[base]{save}}). However, it would then only be compatible with R, and
+#' corresponding R-methods would need to be used to load it. Moreover, persisting the model with
+#' \code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
+#' future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
+#' how to persist models in a future-proof way, i.e. to make the model accessible in future
+#' releases of XGBoost.
+#'
+#' @seealso
+#' \code{\link{xgb.load}}, \code{\link{xgb.Booster.complete}}.
+#'
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' xgb.save(bst, 'xgb.model')
 #' bst <- xgb.load('xgb.model')
@@ -38,6 +42,7 @@ 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

@@ -1,23 +1,23 @@
 #' Save xgboost model to R's raw vector,
-#' user can call xgb.load to load the model back from raw vector
-#' 
+#' user can call xgb.load.raw to load the model back from raw vector
+#'
 #' Save xgboost model from xgboost or xgb.train
-#' 
+#'
 #' @param model the model object.
-#' 
+#'
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 #'                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 #' raw <- xgb.save.raw(bst)
-#' bst <- xgb.load(raw)
+#' bst <- xgb.load.raw(raw)
 #' pred <- predict(bst, test$data)
 #'
 #' @export
 xgb.save.raw <- function(model) {
-  model <- xgb.get.handle(model)
-  .Call(XGBoosterModelToRaw_R, model)
+  handle <- xgb.get.handle(model)
+  .Call(XGBoosterModelToRaw_R, handle)
 }

R-package/R/xgb.serialize.R

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

R-package/R/xgb.train.R

@@ -3,9 +3,9 @@
 #' \code{xgb.train} is an advanced interface for training an xgboost model.
 #' The \code{xgboost} function is a simpler wrapper for \code{xgb.train}.
 #'
-#' @param params the list of parameters.
-#'        The complete list of parameters is available at \url{http://xgboost.readthedocs.io/en/latest/parameter.html}.
-#'        Below is a shorter summary:
+#' @param params the list of parameters. The complete list of parameters is
+#'   available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
+#'   is a shorter summary:
 #'
 #' 1. General Parameters
 #'
@@ -15,7 +15,7 @@
 #'
 #' 2. Booster Parameters
 #'
-#' 2.1. Parameter for Tree Booster
+#' 2.1. Parameters for Tree Booster
 #'
 #' \itemize{
 #'   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
@@ -24,12 +24,14 @@
 #'   \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{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
+#'   \item \code{lambda} L2 regularization term on weights. Default: 1
+#'   \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
+#'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through XGBoost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
 #'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
 #'   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 #' }
 #'
-#' 2.2. Parameter for Linear Booster
+#' 2.2. Parameters for Linear Booster
 #'
 #' \itemize{
 #'   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -43,13 +45,23 @@
 #' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
 #'   \itemize{
 #'     \item \code{reg:squarederror} Regression with squared loss (Default).
+#'     \item \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
 #'     \item \code{reg:logistic} logistic regression.
+#'     \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
 #'     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
 #'     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
-#'     \item \code{num_class} set the number of classes. To use only with multiclass objectives.
+#'     \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
+#'     \item \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+#'     \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
+#'     \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
+#'     \item \code{aft_loss_distribution}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
 #'     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
 #'     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
 #'     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
+#'     \item \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
+#'     \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
+#'     \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
+#'     \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
 #'   }
 #'   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
 #'   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
@@ -114,22 +126,24 @@
 #' 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{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{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
+#'      \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
+#'      \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
 #'      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
 #'            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
 #'            Different threshold (e.g., 0.) could be specified as "error@0."
 #'      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-#'      \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+#'      \item \code{mae} Mean absolute error
+#'      \item \code{mape} Mean absolute percentage error
+#'      \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
 #'      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
+#'      \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
 #'   }
 #'
 #' The following callbacks are automatically created when certain parameters are set:
@@ -157,9 +171,6 @@
 #'         explicitly passed.
 #'   \item \code{best_iteration} iteration number with the best evaluation metric value
 #'         (only available with early stopping).
-#'   \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-#'         which could further be used in \code{predict} method
-#'         (only available with early stopping).
 #'   \item \code{best_score} the best evaluation metric value during early stopping.
 #'         (only available with early stopping).
 #'   \item \code{feature_names} names of the training dataset features
@@ -181,8 +192,8 @@
 #' 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)
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 #' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:
@@ -267,8 +278,8 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   }
 
   # evaluation printing callback
-  params <- c(params, list(silent = ifelse(verbose > 1, 0, 1)))
-  print_every_n <- max( as.integer(print_every_n), 1L)
+  params <- c(params)
+  print_every_n <- max(as.integer(print_every_n), 1L)
   if (!has.callbacks(callbacks, 'cb.print.evaluation') &&
       verbose) {
     callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n))
@@ -291,8 +302,10 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
                                                  maximize = maximize, verbose = verbose))
   }
+
   # Sort the callbacks into categories
   cb <- categorize.callbacks(callbacks)
+  params['validate_parameters'] <- TRUE
   if (!is.null(params[['seed']])) {
     warning("xgb.train: `seed` is ignored in R package.  Use `set.seed()` instead.")
   }
@@ -316,12 +329,9 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
       niter_init <- xgb.ntree(bst) %/% (num_parallel_tree * num_class)
     }
   }
-  if(is_update && nrounds > niter_init)
+  if (is_update && nrounds > niter_init)
     stop("nrounds cannot be larger than ", niter_init, " (nrounds of xgb_model)")
 
-  # TODO: distributed code
-  rank <- 0
-
   niter_skip <- ifelse(is_update, 0, niter_init)
   begin_iteration <- niter_skip + 1
   end_iteration <- niter_skip + nrounds
@@ -333,7 +343,6 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
 
     xgb.iter.update(bst$handle, dtrain, iteration - 1, obj)
 
-    bst_evaluation <- numeric(0)
     if (length(watchlist) > 0)
       bst_evaluation <- xgb.iter.eval(bst$handle, watchlist, iteration - 1, feval)
 
@@ -348,7 +357,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   bst <- xgb.Booster.complete(bst, saveraw = TRUE)
 
   # store the total number of boosting iterations
-  bst$niter = end_iteration
+  bst$niter <- end_iteration
 
   # store the evaluation results
   if (length(evaluation_log) > 0 &&

R-package/R/xgb.unserialize.R

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

R-package/R/xgboost.R

@@ -10,7 +10,7 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
                     save_period = NULL, save_name = "xgboost.model",
                     xgb_model = NULL, callbacks = list(), ...) {
 
-  dtrain <- xgb.get.DMatrix(data, label, missing, weight)
+  dtrain <- xgb.get.DMatrix(data, label, missing, weight, nthread = params$nthread)
 
   watchlist <- list(train = dtrain)
 
@@ -90,12 +90,8 @@ NULL
 #' @importFrom data.table setkey
 #' @importFrom data.table setkeyv
 #' @importFrom data.table setnames
-#' @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 jsonlite fromJSON
+#' @importFrom jsonlite toJSON
 #' @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/contribute.html#r-package) of the contributors guide.
+* See the [R Package section](https://xgboost.readthedocs.io/en/latest/contrib/coding_guide.html#r-coding-guideline) of the contributors guide.

R-package/cleanup

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

R-package/configure

@@ -613,6 +613,7 @@ infodir
 docdir
 oldincludedir
 includedir
+runstatedir
 localstatedir
 sharedstatedir
 sysconfdir
@@ -682,6 +683,7 @@ datadir='${datarootdir}'
 sysconfdir='${prefix}/etc'
 sharedstatedir='${prefix}/com'
 localstatedir='${prefix}/var'
+runstatedir='${localstatedir}/run'
 includedir='${prefix}/include'
 oldincludedir='/usr/include'
 docdir='${datarootdir}/doc/${PACKAGE_TARNAME}'
@@ -934,6 +936,15 @@ do
   | -silent | --silent | --silen | --sile | --sil)
     silent=yes ;;
 
+  -runstatedir | --runstatedir | --runstatedi | --runstated \
+  | --runstate | --runstat | --runsta | --runst | --runs \
+  | --run | --ru | --r)
+    ac_prev=runstatedir ;;
+  -runstatedir=* | --runstatedir=* | --runstatedi=* | --runstated=* \
+  | --runstate=* | --runstat=* | --runsta=* | --runst=* | --runs=* \
+  | --run=* | --ru=* | --r=*)
+    runstatedir=$ac_optarg ;;
+
   -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb)
     ac_prev=sbindir ;;
   -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \
@@ -1071,7 +1082,7 @@ fi
 for ac_var in	exec_prefix prefix bindir sbindir libexecdir datarootdir \
 		datadir sysconfdir sharedstatedir localstatedir includedir \
 		oldincludedir docdir infodir htmldir dvidir pdfdir psdir \
-		libdir localedir mandir
+		libdir localedir mandir runstatedir
 do
   eval ac_val=\$$ac_var
   # Remove trailing slashes.
@@ -1224,6 +1235,7 @@ Fine tuning of the installation directories:
   --sysconfdir=DIR        read-only single-machine data [PREFIX/etc]
   --sharedstatedir=DIR    modifiable architecture-independent data [PREFIX/com]
   --localstatedir=DIR     modifiable single-machine data [PREFIX/var]
+  --runstatedir=DIR       modifiable per-process data [LOCALSTATEDIR/run]
   --libdir=DIR            object code libraries [EPREFIX/lib]
   --includedir=DIR        C header files [PREFIX/include]
   --oldincludedir=DIR     C header files for non-gcc [/usr/include]
@@ -2698,7 +2710,7 @@ fi
 if test `uname -s` = "Darwin"
 then
   OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='/usr/local/lib/libomp.dylib'
+  OPENMP_LIB='-lomp'
   ac_pkg_openmp=no
   { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether OpenMP will work in a package" >&5
 $as_echo_n "checking whether OpenMP will work in a package... " >&6; }
@@ -2713,14 +2725,14 @@ main ()
   return 0;
 }
 _ACEOF
-  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 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 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
+    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
     echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
     echo '             brew install libomp'
     echo '*****************************************************************************************'

R-package/configure.ac

@@ -1,6 +1,6 @@
 ### configure.ac					-*- Autoconf -*-
 
-AC_PREREQ(2.62)
+AC_PREREQ(2.69)
 
 AC_INIT([xgboost],[0.6-3],[],[xgboost],[])
 
@@ -29,17 +29,17 @@ fi
 if test `uname -s` = "Darwin"
 then
   OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='/usr/local/lib/libomp.dylib'
+  OPENMP_LIB='-lomp'
   ac_pkg_openmp=no
   AC_MSG_CHECKING([whether OpenMP will work in a package])
   AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
-  ${CC} -o conftest conftest.c /usr/local/lib/libomp.dylib -Xclang -fopenmp 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 'WARNING: OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
+    echo '         OpenMP is unavailable on this Mac OSX system. Training speed may be suboptimal.'
     echo '         To use all CPU cores for training jobs, you should install OpenMP by running\n'
     echo '             brew install libomp'
     echo '*****************************************************************************************'
@@ -52,4 +52,3 @@ 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                Cutomize loss function, and evaluation metric
+custom_objective                Customize loss function, and evaluation metric
 boost_from_prediction           Boosting from existing prediction
 predict_first_ntree             Predicting using first n trees
 generalized_linear_model        Generalized Linear Model
@@ -8,8 +8,8 @@ cross_validation                Cross validation
 create_sparse_matrix            Create Sparse Matrix
 predict_leaf_indices            Predicting the corresponding leaves
 early_stopping                  Early Stop in training
-poisson_regression              Poisson Regression on count data
-tweedie_regression              Tweddie Regression
+poisson_regression              Poisson regression on count data
+tweedie_regression              Tweedie regression
 gpu_accelerated                 GPU-accelerated tree building algorithms
 interaction_constraints         Interaction constraints among features
 

R-package/demo/README.md

@@ -2,7 +2,7 @@ XGBoost R Feature Walkthrough
 ====
 * [Basic walkthrough of wrappers](basic_walkthrough.R)
 * [Train a xgboost model from caret library](caret_wrapper.R)
-* [Cutomize loss function, and evaluation metric](custom_objective.R)
+* [Customize loss function, and evaluation metric](custom_objective.R)
 * [Boosting from existing prediction](boost_from_prediction.R)
 * [Predicting using first n trees](predict_first_ntree.R)
 * [Generalized Linear Model](generalized_linear_model.R)
@@ -17,4 +17,4 @@ Benchmarks
 Notes
 ====
 * Contribution of examples, benchmarks is more than welcomed!
-* If you like to share how you use xgboost to solve your problem, send a pull request:)
+* If you like to share how you use xgboost to solve your problem, send a pull request :)

R-package/demo/basic_walkthrough.R

@@ -3,8 +3,8 @@ require(methods)
 
 # we load in the agaricus dataset
 # In this example, we are aiming to predict whether a mushroom is edible
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 train <- agaricus.train
 test <- agaricus.test
 # the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
@@ -26,7 +26,7 @@ bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2,
 # you can also put in xgb.DMatrix object, which stores label, data and other meta datas needed for advanced features
 print("Training xgboost with xgb.DMatrix")
 dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2, 
+bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2,
                objective = "binary:logistic")
 
 # Verbose = 0,1,2
@@ -40,13 +40,13 @@ print("Train xgboost with verbose 2, also print information about tree")
 bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
                nthread = 2, objective = "binary:logistic", verbose = 2)
 
-# you can also specify data as file path to a LibSVM format input
+# you can also specify data as file path to a LIBSVM format input
 # since we do not have this file with us, the following line is just for illustration
 # bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nrounds = 2,objective = "binary:logistic")
 
 #--------------------basic prediction using xgboost--------------
 # you can do prediction using the following line
-# you can put in Matrix, sparseMatrix, or xgb.DMatrix 
+# you can put in Matrix, sparseMatrix, or xgb.DMatrix
 pred <- predict(bst, test$data)
 err <- mean(as.numeric(pred > 0.5) != test$label)
 print(paste("test-error=", err))
@@ -58,31 +58,31 @@ xgb.save(bst, "xgboost.model")
 bst2 <- xgb.load("xgboost.model")
 pred2 <- predict(bst2, test$data)
 # pred2 should be identical to pred
-print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
+print(paste("sum(abs(pred2-pred))=", sum(abs(pred2 - pred))))
 
 # save model to R's raw vector
-raw = xgb.save.raw(bst)
+raw <- xgb.save.raw(bst)
 # load binary model to R
 bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
 # pred3 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
+print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix
-dtrain <- xgb.DMatrix(data = train$data, label=train$label)
-dtest <- xgb.DMatrix(data = test$data, label=test$label)
+dtrain <- xgb.DMatrix(data = train$data, label = train$label)
+dtest <- xgb.DMatrix(data = test$data, label = test$label)
 #---------------Using watchlist----------------
 # watchlist is a list of xgb.DMatrix, each of them is tagged with name
-watchlist <- list(train=dtrain, test=dtest)
+watchlist <- list(train = dtrain, test = dtest)
 # to train with watchlist, use xgb.train, which contains more advanced features
-# watchlist allows us to monitor the evaluation result on all data in the list 
+# watchlist allows us to monitor the evaluation result on all data in the list
 print("Train xgboost using xgb.train with watchlist")
-bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
+bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
                  nthread = 2, objective = "binary:logistic")
 # we can change evaluation metrics, or use multiple evaluation metrics
 print("train xgboost using xgb.train with watchlist, watch logloss and error")
-bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
+bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
                  eval_metric = "error", eval_metric = "logloss",
                  nthread = 2, objective = "binary:logistic")
 
@@ -90,17 +90,17 @@ bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist
 xgb.DMatrix.save(dtrain, "dtrain.buffer")
 # to load it in, simply call xgb.DMatrix
 dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data=dtrain2, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
+bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
                  nthread = 2, objective = "binary:logistic")
 # information can be extracted from xgb.DMatrix using getinfo
-label = getinfo(dtest, "label")
+label <- getinfo(dtest, "label")
 pred <- predict(bst, dtest)
-err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
+err <- as.numeric(sum(as.integer(pred > 0.5) != label)) / length(label)
 print(paste("test-error=", err))
 
 # You can dump the tree you learned using xgb.dump into a text file
-dump_path = file.path(tempdir(), 'dump.raw.txt')
-xgb.dump(bst, dump_path, with_stats = T)
+dump_path <- file.path(tempdir(), 'dump.raw.txt')
+xgb.dump(bst, dump_path, with_stats = TRUE)
 
 # Finally, you can check which features are the most important.
 print("Most important features (look at column Gain):")

R-package/demo/boost_from_prediction.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
@@ -11,12 +11,12 @@ watchlist <- list(eval = dtest, train = dtrain)
 #
 print('start running example to start from a initial prediction')
 # train xgboost for 1 round
-param <- list(max_depth=2, eta=1, nthread = 2, silent=1, objective='binary:logistic')
+param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
 bst <- xgb.train(param, dtrain, 1, watchlist)
 # Note: we need the margin value instead of transformed prediction in set_base_margin
 # do predict with output_margin=TRUE, will always give you margin values before logistic transformation
-ptrain <- predict(bst, dtrain, outputmargin=TRUE)
-ptest  <- predict(bst, dtest, outputmargin=TRUE)
+ptrain <- predict(bst, dtrain, outputmargin = TRUE)
+ptest  <- predict(bst, dtest, outputmargin = TRUE)
 # set the base_margin property of dtrain and dtest
 # base margin is the base prediction we will boost from
 setinfo(dtrain, "base_margin", ptrain)

R-package/demo/caret_wrapper.R

@@ -1,5 +1,5 @@
 # install development version of caret library that contains xgboost models
-devtools::install_github("topepo/caret/pkg/caret") 
+devtools::install_github("topepo/caret/pkg/caret")
 require(caret)
 require(xgboost)
 require(data.table)
@@ -9,17 +9,17 @@ require(e1071)
 # Load Arthritis dataset in memory.
 data(Arthritis)
 # Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = F)
+df <- data.table(Arthritis, keep.rownames = FALSE)
 
 # Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 # For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[,AgeDiscret:= as.factor(round(Age/10,0))]
+df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
 # Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[,ID:=NULL]
+df[, ID := NULL]
 
 #-------------Basic Training using XGBoost in caret Library-----------------
 # Set up control parameters for caret::train

R-package/demo/create_sparse_matrix.R

@@ -2,47 +2,47 @@ require(xgboost)
 require(Matrix)
 require(data.table)
 if (!require(vcd)) {
-  install.packages('vcd') #Available in Cran. Used for its dataset with categorical values.
+  install.packages('vcd') #Available in CRAN. Used for its dataset with categorical values.
   require(vcd)
 }
-# According to its documentation, Xgboost works only on numbers.
-# Sometimes the dataset we have to work on have categorical data. 
+# According to its documentation, XGBoost works only on numbers.
+# Sometimes the dataset we have to work on have categorical data.
 # A categorical variable is one which have a fixed number of values. By example, if for each observation a variable called "Colour" can have only "red", "blue" or "green" as value, it is a categorical variable.
 #
-# In R, categorical variable is called Factor. 
+# In R, categorical variable is called Factor.
 # Type ?factor in console for more information.
 #
-# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in Xgboost.
+# In this demo we will see how to transform a dense dataframe with categorical variables to a sparse matrix before analyzing it in XGBoost.
 # The method we are going to see is usually called "one hot encoding".
 
 #load Arthritis dataset in memory.
 data(Arthritis)
 
 # create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = F)
+df <- data.table(Arthritis, keep.rownames = FALSE)
 
 # Let's have a look to the data.table
 cat("Print the dataset\n")
 print(df)
 
-# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values wich can be ordered, here: None > Some > Marked).
+# 2 columns have factor type, one has ordinal type (ordinal variable is a categorical variable with values which can be ordered, here: None > Some > Marked).
 cat("Structure of the dataset\n")
 str(df)
 
 # Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
 
-# 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))]
+# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independent values.
+df[, AgeDiscret := as.factor(round(Age / 10, 0))]
 
 # Here is an even stronger simplification of the real age with an arbitrary split at 30 years old. I choose this value based on nothing. We will see later if simplifying the information based on arbitrary values is a good strategy (I am sure you already have an idea of how well it will work!).
-df[,AgeCat:= as.factor(ifelse(Age > 30, "Old", "Young"))]
+df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
 
 # We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[,ID:=NULL]
+df[, ID := NULL]
 
 # List the different values for the column Treatment: Placebo, Treated.
 cat("Values of the categorical feature Treatment\n")
-print(levels(df[,Treatment]))
+print(levels(df[, Treatment]))
 
 # Next step, we will transform the categorical data to dummy variables.
 # This method is also called one hot encoding.
@@ -52,16 +52,16 @@ print(levels(df[,Treatment]))
 #
 # Formulae Improved~.-1 used below means transform all categorical features but column Improved to binary values.
 # Column Improved is excluded because it will be our output column, the one we want to predict.
-sparse_matrix = sparse.model.matrix(Improved~.-1, data = df)
+sparse_matrix <- sparse.model.matrix(Improved ~ . - 1, data = df)
 
 cat("Encoding of the sparse Matrix\n")
 print(sparse_matrix)
 
 # Create the output vector (not sparse)
-# 1. Set, for all rows, field in Y column to 0; 
-# 2. set Y to 1 when Improved == Marked; 
+# 1. Set, for all rows, field in Y column to 0;
+# 2. set Y to 1 when Improved == Marked;
 # 3. Return Y column
-output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
+output_vector <- df[, Y := 0][Improved == "Marked", Y := 1][, Y]
 
 # Following is the same process as other demo
 cat("Learning...\n")

R-package/demo/cross_validation.R

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

R-package/demo/custom_objective.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
@@ -12,10 +12,10 @@ watchlist <- list(eval = dtest, train = dtrain)
 num_round <- 2
 
 # user define objective function, given prediction, return gradient and second order gradient
-# this is loglikelihood loss
+# this is log likelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
+  preds <- 1 / (1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
@@ -23,42 +23,42 @@ logregobj <- function(preds, dtrain) {
 
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
+# this may make builtin evaluation metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
+# the builtin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
+  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
-              objective=logregobj, eval_metric=evalerror)
+param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
+              objective = logregobj, eval_metric = evalerror)
 print ('start training with user customized objective')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
 bst <- xgb.train(param, dtrain, num_round, watchlist)
 
 #
-# there can be cases where you want additional information 
+# there can be cases where you want additional information
 # being considered besides the property of DMatrix you can get by getinfo
 # you can set additional information as attributes if DMatrix
 
-# set label attribute of dtrain to be label, we use label as an example, it can be anything 
+# set label attribute of dtrain to be label, we use label as an example, it can be anything
 attr(dtrain, 'label') <- getinfo(dtrain, 'label')
 # this is new customized objective, where you can access things you set
 # same thing applies to customized evaluation function
 logregobjattr <- function(preds, dtrain) {
   # now you can access the attribute in customized function
   labels <- attr(dtrain, 'label')
-  preds <- 1/(1 + exp(-preds))
+  preds <- 1 / (1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
-param <- list(max_depth=2, eta=1, nthread = 2, verbosity=0, 
-              objective=logregobjattr, eval_metric=evalerror)
+param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
+              objective = logregobjattr, eval_metric = evalerror)
 print ('start training with user customized objective, with additional attributes in DMatrix')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train

R-package/demo/early_stopping.R

@@ -1,33 +1,33 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-param <- list(max_depth=2, eta=1, nthread=2, verbosity=0)
+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 loglikelihood loss
+# this is log likelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
+  preds <- 1 / (1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
 # user defined evaluation function, return a pair metric_name, result
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
+# this may make builtin evaluation metric not function properly
 # for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
+# the builtin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
+  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
   return(list(metric = "error", value = err))
 }
 print ('start training with early Stopping setting')

R-package/demo/generalized_linear_model.R

@@ -1,7 +1,7 @@
 require(xgboost)
 # load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
@@ -11,14 +11,14 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 ##
 
 # change booster to gblinear, so that we are fitting a linear model
-# alpha is the L1 regularizer 
+# alpha is the L1 regularizer
 # lambda is the L2 regularizer
 # you can also set lambda_bias which is L2 regularizer on the bias term
 param <- list(objective = "binary:logistic", booster = "gblinear",
               nthread = 2, alpha = 0.0001, lambda = 1)
 
 # normally, you do not need to set eta (step_size)
-# XGBoost uses a parallel coordinate descent algorithm (shotgun), 
+# XGBoost uses a parallel coordinate descent algorithm (shotgun),
 # there could be affection on convergence with parallelization on certain cases
 # setting eta to be smaller value, e.g 0.5 can make the optimization more stable
 
@@ -30,5 +30,4 @@ num_round <- 2
 bst <- xgb.train(param, dtrain, num_round, watchlist)
 ypred <- predict(bst, dtest)
 labels <- getinfo(dtest, 'label')
-cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
-
+cat('error of preds=', mean(as.numeric(ypred > 0.5) != labels), '\n')

R-package/demo/gpu_accelerated.R

@@ -1,9 +1,9 @@
 # An example of using GPU-accelerated tree building algorithms
-# 
-# NOTE: it can only run if you have a CUDA-enable GPU and the package was 
+#
+# NOTE: it can only run if you have a CUDA-enable GPU and the package was
 #       specially compiled with GPU support.
 #
-# For the current functionality, see 
+# For the current functionality, see
 # https://xgboost.readthedocs.io/en/latest/gpu/index.html
 #
 
@@ -21,8 +21,8 @@ m <- X[, sel] %*% betas - 1 + rnorm(N)
 y <- rbinom(N, 1, plogis(m))
 
 tr <- sample.int(N, N * 0.75)
-dtrain <- xgb.DMatrix(X[tr,], label = y[tr])
-dtest <- xgb.DMatrix(X[-tr,], label = y[-tr])
+dtrain <- xgb.DMatrix(X[tr, ], label = y[tr])
+dtest <- xgb.DMatrix(X[-tr, ], label = y[-tr])
 wl <- list(train = dtrain, test = dtest)
 
 # An example of running 'gpu_hist' algorithm

R-package/demo/interaction_constraints.R

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

R-package/demo/poisson_regression.R

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

R-package/demo/predict_first_ntree.R

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

R-package/demo/predict_leaf_indices.R

@@ -5,34 +5,34 @@ require(Matrix)
 set.seed(1982)
 
 # load in the agaricus dataset
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
+data(agaricus.train, package = 'xgboost')
+data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 
-param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-nrounds = 4
+param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic')
+nrounds <- 4
 
 # training the model for two rounds
-bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
+bst <- xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy without new features
-accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
+accuracy.before <- (sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label)
+                    / length(agaricus.test$label))
 
 # by default, we predict using all the trees
-
-pred_with_leaf = predict(bst, dtest, predleaf = TRUE)
+pred_with_leaf <- predict(bst, dtest, predleaf = TRUE)
 head(pred_with_leaf)
 
 create.new.tree.features <- function(model, original.features){
   pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
   cols <- list()
-  for(i in 1:model$niter){
+  for (i in 1:model$niter) {
     # max is not the real max but it s not important for the purpose of adding features
-    leaf.id <- sort(unique(pred_with_leaf[,i]))
-    cols[[i]] <- factor(x = pred_with_leaf[,i], level = leaf.id)
+    leaf.id <- sort(unique(pred_with_leaf[, i]))
+    cols[[i]] <- factor(x = pred_with_leaf[, i], level = leaf.id)
   }
-  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
+  cbind(original.features, sparse.model.matrix(~ . - 1, as.data.frame(cols)))
 }
 
 # Convert previous features to one hot encoding
@@ -47,7 +47,9 @@ watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy with new features
-accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
+accuracy.after <- (sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label)
+                   / length(agaricus.test$label))
 
 # Here the accuracy was already good and is now perfect.
-cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now", accuracy.after, "!\n"))
+cat(paste("The accuracy was", accuracy.before, "before adding leaf features and it is now",
+          accuracy.after, "!\n"))

R-package/demo/runall.R

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

R-package/demo/tweedie_regression.R

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

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

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

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

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

R-package/man/agaricus.test.Rd

@@ -4,8 +4,10 @@
 \name{agaricus.test}
 \alias{agaricus.test}
 \title{Test part from Mushroom Data Set}
-\format{A list containing a label vector, and a dgCMatrix object with 1611 
-rows and 126 variables}
+\format{
+A list containing a label vector, and a dgCMatrix object with 1611
+rows and 126 variables
+}
 \usage{
 data(agaricus.test)
 }
@@ -24,8 +26,8 @@ This data set includes the following fields:
 \references{
 https://archive.ics.uci.edu/ml/datasets/Mushroom
 
-Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
+Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
+[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 School of Information and Computer Science.
 }
 \keyword{datasets}

R-package/man/agaricus.train.Rd

@@ -4,8 +4,10 @@
 \name{agaricus.train}
 \alias{agaricus.train}
 \title{Training part from Mushroom Data Set}
-\format{A list containing a label vector, and a dgCMatrix object with 6513 
-rows and 127 variables}
+\format{
+A list containing a label vector, and a dgCMatrix object with 6513
+rows and 127 variables
+}
 \usage{
 data(agaricus.train)
 }
@@ -24,8 +26,8 @@ This data set includes the following fields:
 \references{
 https://archive.ics.uci.edu/ml/datasets/Mushroom
 
-Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository 
-[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, 
+Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
+[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
 School of Information and Computer Science.
 }
 \keyword{datasets}

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

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

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

@@ -8,7 +8,7 @@ during its training.}
 cb.gblinear.history(sparse = FALSE)
 }
 \arguments{
-\item{sparse}{when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
+\item{sparse}{when set to FALSE/TRUE, a dense/sparse matrix is used to store the result.
 Sparse format is useful when one expects only a subset of coefficients to be non-zero,
 when using the "thrifty" feature selector with fairly small number of top features
 selected per iteration.}
@@ -36,7 +36,6 @@ 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"))
@@ -57,7 +56,7 @@ matplot(coef_path, type = 'l')
 bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
                  updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
                  callbacks = list(cb.gblinear.history()))
-xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst), type = 'l')
 #  Componentwise boosting is known to have similar effect to Lasso regularization.
 # Try experimenting with various values of top_k, eta, nrounds,
 # as well as different feature_selectors.
@@ -66,7 +65,7 @@ xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
              callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
-xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
+matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 
 
 #### Multiclass classification:
@@ -79,15 +78,15 @@ 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:
-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')
+matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
+matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
 
 # CV:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
               callbacks = list(cb.gblinear.history(FALSE)))
-# 1st forld of 1st class
-xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
+# 1st fold of 1st class
+matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], 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}.
 
 }
@@ -34,8 +34,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

R-package/man/normalize.Rd

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

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

@@ -17,6 +17,8 @@
   predinteraction = FALSE,
   reshape = FALSE,
   training = FALSE,
+  iterationrange = NULL,
+  strict_shape = FALSE,
   ...
 )
 
@@ -34,8 +36,7 @@ missing values in data (e.g., sometimes 0 or some other extreme value is used).}
 sum of predictions from boosting iterations' results. E.g., setting \code{outputmargin=TRUE} for
 logistic regression would result in predictions for log-odds instead of probabilities.}
 
-\item{ntreelimit}{limit the number of model's trees or boosting iterations used in prediction (see Details).
-It will use all the trees by default (\code{NULL} value).}
+\item{ntreelimit}{Deprecated, use \code{iterationrange} instead.}
 
 \item{predleaf}{whether predict leaf index.}
 
@@ -49,10 +50,23 @@ It will use all the trees by default (\code{NULL} value).}
 prediction outputs per case. This option has no effect when either of predleaf, predcontrib,
 or predinteraction flags is TRUE.}
 
+\item{training}{whether is the prediction result used for training.  For dart booster,
+training predicting will perform dropout.}
+
+\item{iterationrange}{Specifies which layer of trees are used in prediction.  For
+example, if a random forest is trained with 100 rounds.  Specifying
+`iteration_range=(1, 21)`, then only the forests built during [1, 21) (half open set)
+rounds are used in this prediction.  It's 1-based index just like R vector.  When set
+to \code{c(1, 1)} XGBoost will use all trees.}
+
+\item{strict_shape}{Default is \code{FALSE}. When it's set to \code{TRUE}, output
+type and shape of prediction are invariant to model type.}
+
 \item{...}{Parameters passed to \code{predict.xgb.Booster}}
 }
 \value{
-For regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
+The return type is different depending whether \code{strict_shape} is set to \code{TRUE}.  By default,
+for regression or binary classification, it returns a vector of length \code{nrows(newdata)}.
 For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
 a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
 the \code{reshape} value.
@@ -73,18 +87,19 @@ two dimensions. The "+ 1" columns corresponds to bias. Summing this array along
 produce practically the same result as predict with \code{predcontrib = TRUE}.
 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
 such an array.
+
+When \code{strict_shape} is set to \code{TRUE}, the output is always an array.  For
+normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
+
+For \code{predcontrib = TRUE}, output is \code{(ncol(newdata) + 1, num_class, nrow(newdata))}
+For \code{predinteraction = TRUE}, output is \code{(ncol(newdata) + 1, ncol(newdata) + 1, num_class, nrow(newdata))}
+For \code{predleaf = TRUE}, output is \code{(n_trees_in_forest, num_class, n_iterations, nrow(newdata))}
 }
 \description{
 Predicted values based on either xgboost model or model handle object.
 }
 \details{
-Note that \code{ntreelimit} is not necessarily equal to the number of boosting iterations
-and it is not necessarily equal to the number of trees in a model.
-E.g., in a random forest-like model, \code{ntreelimit} would limit the number of trees.
-But for multiclass classification, while there are multiple trees per iteration,
-\code{ntreelimit} limits the number of boosting iterations.
-
-Also note that \code{ntreelimit} would currently do nothing for predictions from gblinear,
+Note that \code{iterationrange} would currently do nothing for predictions from gblinear,
 since gblinear doesn't keep its boosting history.
 
 One possible practical applications of the \code{predleaf} option is to use the model
@@ -117,7 +132,7 @@ bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
 # use all trees by default
 pred <- predict(bst, test$data)
 # use only the 1st tree
-pred1 <- predict(bst, test$data, ntreelimit = 1)
+pred1 <- predict(bst, test$data, iterationrange = c(1, 2))
 
 # Predicting tree leafs:
 # the result is an nsamples X ntrees matrix
@@ -169,25 +184,9 @@ str(pred)
 all.equal(pred, pred_labels)
 # prediction from using only 5 iterations should result
 # in the same error as seen in iteration 5:
-pred5 <- predict(bst, as.matrix(iris[, -5]), ntreelimit=5)
+pred5 <- predict(bst, as.matrix(iris[, -5]), iterationrange=c(1, 6))
 sum(pred5 != lb)/length(lb)
 
-
-## random forest-like model of 25 trees for binary classification:
-
-set.seed(11)
-bst <- xgboost(data = train$data, label = train$label, max_depth = 5,
-               nthread = 2, nrounds = 1, objective = "binary:logistic",
-               num_parallel_tree = 25, subsample = 0.6, colsample_bytree = 0.1)
-# Inspect the prediction error vs number of trees:
-lb <- test$label
-dtest <- xgb.DMatrix(test$data, label=lb)
-err <- sapply(1:25, function(n) {
-  pred <- predict(bst, dtest, ntreelimit=n)
-  sum((pred > 0.5) != lb)/length(lb)
-})
-plot(err, type='l', ylim=c(0,0.1), xlab='#trees')
-
 }
 \references{
 Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017, \url{https://arxiv.org/abs/1705.07874}

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

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

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

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

R-package/man/setinfo.Rd

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

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

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

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

@@ -38,6 +38,8 @@ bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_dep
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 saveRDS(bst, "xgb.model.rds")
 
+# Warning: The resulting RDS file is only compatible with the current XGBoost version.
+# Refer to the section titled "a-compatibility-note-for-saveRDS-save".
 bst1 <- readRDS("xgb.model.rds")
 if (file.exists("xgb.model.rds")) file.remove("xgb.model.rds")
 # the handle is invalid:

R-package/man/xgb.DMatrix.Rd

@@ -22,13 +22,12 @@ It is useful when a 0 or some other extreme value represents missing values in d
 }
 \description{
 Construct xgb.DMatrix object from either a dense matrix, a sparse matrix, or a local file.
-Supported input file formats are either a libsvm text file or a binary file that was created previously by
+Supported input file formats are either a LIBSVM text file or a binary file that was created previously by
 \code{\link{xgb.DMatrix.save}}).
 }
 \examples{
 data(agaricus.train, package='xgboost')
-train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')

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

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

R-package/man/xgb.attr.Rd

@@ -55,7 +55,7 @@ than for \code{xgb.Booster}, since only just a handle (pointer) would need to be
 That would only matter if attributes need to be set many times.
 Note, however, that when feeding a handle of an \code{xgb.Booster} object to the attribute setters,
 the raw model cache of an \code{xgb.Booster} object would not be automatically updated,
-and it would be user's responsibility to call \code{xgb.save.raw} to update it.
+and it would be user's responsibility to call \code{xgb.serialize} to update it.
 
 The \code{xgb.attributes<-} setter either updates the existing or adds one or several attributes,
 but it doesn't delete the other existing attributes.

R-package/man/xgb.config.Rd

@@ -0,0 +1,28 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.Booster.R
+\name{xgb.config}
+\alias{xgb.config}
+\alias{xgb.config<-}
+\title{Accessors for model parameters as JSON string.}
+\usage{
+xgb.config(object)
+
+xgb.config(object) <- value
+}
+\arguments{
+\item{object}{Object of class \code{xgb.Booster}}
+
+\item{value}{A JSON string.}
+}
+\description{
+Accessors for model parameters as JSON string.
+}
+\examples{
+data(agaricus.train, package='xgboost')
+train <- agaricus.train
+
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+               eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+config <- xgb.config(bst)
+
+}

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

@@ -24,9 +24,9 @@ This is the function inspired from the paragraph 3.1 of the paper:
 
 \strong{Practical Lessons from Predicting Clicks on Ads at Facebook}
 
-\emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, 
+\emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers,
 Joaquin Quinonero Candela)}
- 
+
 International Workshop on Data Mining for Online Advertising (ADKDD) - August 24, 2014
 
 \url{https://research.fb.com/publications/practical-lessons-from-predicting-clicks-on-ads-at-facebook/}.
@@ -37,10 +37,10 @@ Extract explaining the method:
 convenient way to implement non-linear and tuple transformations
 of the kind we just described. We treat each individual
 tree as a categorical feature that takes as value the
-index of the leaf an instance ends up falling in. We use 
-1-of-K coding of this type of features. 
+index of the leaf an instance ends up falling in. We use
+1-of-K coding of this type of features.
 
-For example, consider the boosted tree model in Figure 1 with 2 subtrees, 
+For example, consider the boosted tree model in Figure 1 with 2 subtrees,
 where the first subtree has 3 leafs and the second 2 leafs. If an
 instance ends up in leaf 2 in the first subtree and leaf 1 in
 second subtree, the overall input to the linear classifier will
@@ -59,8 +59,8 @@ a rule on certain features."
 \examples{
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
-dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 nrounds = 4

R-package/man/xgb.cv.Rd

@@ -28,12 +28,15 @@ xgb.cv(
 )
 }
 \arguments{
-\item{params}{the list of parameters. Commonly used ones are:
+\item{params}{the list of parameters. The complete list of parameters is
+  available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
+  is a shorter summary:
 \itemize{
   \item \code{objective} objective function, common ones are
   \itemize{
-    \item \code{reg:squarederror} Regression with squared loss
-    \item \code{binary:logistic} logistic regression for classification
+    \item \code{reg:squarederror} Regression with squared loss.
+    \item \code{binary:logistic} logistic regression for classification.
+    \item See \code{\link[=xgb.train]{xgb.train}()} for complete list of objectives.
   }
   \item \code{eta} step size of each boosting step
   \item \code{max_depth} maximum depth of the tree
@@ -67,6 +70,8 @@ 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
@@ -130,12 +135,10 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
         parameter or randomly generated.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
-  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-        which could further be used in \code{predict} method
-        (only available with early stopping).
+  \item \code{best_ntreelimit} and the \code{ntreelimit} Deprecated attributes, use \code{best_iteration} instead.
   \item \code{pred} CV prediction values available when \code{prediction} is set.
         It is either vector or matrix (see \code{\link{cb.cv.predict}}).
-  \item \code{models} a liost of the CV folds' models. It is only available with the explicit
+  \item \code{models} a list of the CV folds' models. It is only available with the explicit
         setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
 }
 }
@@ -151,11 +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{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
+Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29}
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
 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

@@ -16,14 +16,14 @@ xgb.dump(
 \arguments{
 \item{model}{the model object.}
 
-\item{fname}{the name of the text file where to save the model text dump. 
+\item{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.}
 
 \item{fmap}{feature map file representing feature types.
-Detailed description could be found at 
+Detailed description could be found at
 \url{https://github.com/dmlc/xgboost/wiki/Binary-Classification#dump-model}.
 See demo/ for walkthrough example in R, and
-\url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt} 
+\url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
 for example Format.}
 
 \item{with_stats}{whether to dump some additional statistics about the splits.
@@ -47,7 +47,7 @@ data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 # save the model in file 'xgb.model.dump'
 dump_path = file.path(tempdir(), 'model.dump')

R-package/man/xgb.importance.Rd

@@ -22,7 +22,7 @@ Non-null \code{feature_names} could be provided to override those in the model.}
 
 \item{trees}{(only for the gbtree booster) an integer vector of tree indices that should be included
 into the importance calculation. If set to \code{NULL}, all trees of the model are parsed.
-It could be useful, e.g., in multiclass classification to get feature importances 
+It could be useful, e.g., in multiclass classification to get feature importances
 for each class separately. IMPORTANT: the tree index in xgboost models
 is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).}
 
@@ -37,7 +37,7 @@ For a tree model, a \code{data.table} with the following columns:
 \itemize{
   \item \code{Features} names of the features used in the model;
   \item \code{Gain} represents fractional contribution of each feature to the model based on
-       the total gain of this feature's splits. Higher percentage means a more important 
+       the total gain of this feature's splits. Higher percentage means a more important
        predictive feature.
   \item \code{Cover} metric of the number of observation related to this feature;
   \item \code{Frequency} percentage representing the relative number of times
@@ -51,7 +51,7 @@ A linear model's importance \code{data.table} has the following columns:
   \item \code{Class} (only for multiclass models) class label.
 }
 
-If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names}, 
+If \code{feature_names} is not provided and \code{model} doesn't have \code{feature_names},
 index of the features will be used instead. Because the index is extracted from the model dump
 (based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
 }
@@ -61,21 +61,21 @@ Creates a \code{data.table} of feature importances in a model.
 \details{
 This function works for both linear and tree models.
 
-For linear models, the importance is the absolute magnitude of linear coefficients. 
-For that reason, in order to obtain a meaningful ranking by importance for a linear model, 
-the features need to be on the same scale (which you also would want to do when using either 
+For linear models, the importance is the absolute magnitude of linear coefficients.
+For that reason, in order to obtain a meaningful ranking by importance for a linear model,
+the features need to be on the same scale (which you also would want to do when using either
 L1 or L2 regularization).
 }
 \examples{
 
 # binomial classification using gbtree:
 data(agaricus.train, package='xgboost')
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 xgb.importance(model = bst)
 
 # binomial classification using gblinear:
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear", 
+bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear",
                eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
 xgb.importance(model = bst)
 

R-package/man/xgb.load.Rd

@@ -17,8 +17,8 @@ Load xgboost model from the binary model file.
 }
 \details{
 The input file is expected to contain a model saved in an xgboost-internal binary format
-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 
+using either \code{\link{xgb.save}} or \code{\link{cb.save.model}} in R, or using some
+appropriate methods from other xgboost interfaces. E.g., a model trained in Python and
 saved from there in xgboost format, could be loaded from R.
 
 Note: a model saved as an R-object, has to be loaded using corresponding R-methods,
@@ -29,7 +29,7 @@ data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 xgb.save(bst, 'xgb.model')
 bst <- xgb.load('xgb.model')

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

@@ -0,0 +1,14 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.load.raw.R
+\name{xgb.load.raw}
+\alias{xgb.load.raw}
+\title{Load serialised xgboost model from R's raw vector}
+\usage{
+xgb.load.raw(buffer)
+}
+\arguments{
+\item{buffer}{the buffer returned by xgb.save.raw}
+}
+\description{
+User can generate raw memory buffer by calling xgb.save.raw
+}

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

@@ -20,7 +20,7 @@ Non-null \code{feature_names} could be provided to override those in the model.}
 
 \item{model}{object of class \code{xgb.Booster}}
 
-\item{text}{\code{character} vector previously generated by the \code{xgb.dump} 
+\item{text}{\code{character} vector previously generated by the \code{xgb.dump}
 function  (where parameter \code{with_stats = TRUE} should have been set).
 \code{text} takes precedence over \code{model}.}
 
@@ -53,10 +53,10 @@ The columns of the \code{data.table} are:
  \item \code{Quality}: either the split gain (change in loss) or the leaf value
  \item \code{Cover}: metric related to the number of observation either seen by a split
                      or collected by a leaf during training.
-} 
+}
 
 When \code{use_int_id=FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
-in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from 
+in the "ID" column. When \code{use_int_id=TRUE}, those columns point to node identifiers from
 the corresponding trees in the "Node" column.
 }
 \description{
@@ -67,17 +67,17 @@ Parse a boosted tree model text dump into a \code{data.table} structure.
 
 data(agaricus.train, package='xgboost')
 
-bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2, 
+bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 
 (dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
 
-# This bst model already has feature_names stored with it, so those would be used when 
+# This bst model already has feature_names stored with it, so those would be used when
 # feature_names is not set:
 (dt <- xgb.model.dt.tree(model = bst))
 
 # How to match feature names of splits that are following a current 'Yes' branch:
 
 merge(dt, dt[, .(ID, Y.Feature=Feature)], by.x='Yes', by.y='ID', all.x=TRUE)[order(Tree,Node)]
- 
+
 }

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

@@ -23,7 +23,7 @@ or a data.table result of the \code{xgb.model.dt.tree} function.}
 
 \item{which}{which distribution to plot (see details).}
 
-\item{plot}{(base R barplot) whether a barplot should be produced. 
+\item{plot}{(base R barplot) whether a barplot should be produced.
 If FALSE, only a data.table is returned.}
 
 \item{...}{other parameters passed to \code{barplot} or \code{plot}.}
@@ -45,10 +45,10 @@ When \code{which="2x1"}, two distributions with respect to the leaf depth
 are plotted on top of each other:
 \itemize{
  \item the distribution of the number of leafs in a tree model at a certain depth;
- \item the distribution of average weighted number of observations ("cover") 
+ \item the distribution of average weighted number of observations ("cover")
        ending up in leafs at certain depth.
 }
-Those could be helpful in determining sensible ranges of the \code{max_depth} 
+Those could be helpful in determining sensible ranges of the \code{max_depth}
 and \code{min_child_weight} parameters.
 
 When \code{which="max.depth"} or \code{which="med.depth"}, plots of either maximum or median depth

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

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

@@ -0,0 +1,78 @@
+% 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.plot.tree.Rd

@@ -60,7 +60,7 @@ The content of each node is organised that way:
  \item \code{Gain} (for split nodes): the information gain metric of a split
        (corresponds to the importance of the node in the model).
  \item \code{Value} (for leafs): the margin value that the leaf may contribute to prediction.
-} 
+}
 The tree root nodes also indicate the Tree index (0-based).
 
 The "Yes" branches are marked by the "< split_value" label.
@@ -80,7 +80,7 @@ xgb.plot.tree(model = bst)
 xgb.plot.tree(model = bst, trees = 0, show_node_id = TRUE)
 
 \dontrun{
-# Below is an example of how to save this plot to a file. 
+# Below is an example of how to save this plot to a file.
 # Note that for `export_graph` to work, the DiagrammeRsvg and rsvg packages must also be installed.
 library(DiagrammeR)
 gr <- xgb.plot.tree(model=bst, trees=0:1, render=FALSE)

R-package/man/xgb.save.Rd

@@ -15,21 +15,25 @@ xgb.save(model, fname)
 Save xgboost model to a file in binary format.
 }
 \details{
-This methods allows to save a model in an xgboost-internal binary format which is universal 
+This methods allows to save a model in an xgboost-internal binary format which is universal
 among the various xgboost interfaces. In R, the saved model file could be read-in later
-using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter 
+using either the \code{\link{xgb.load}} function or the \code{xgb_model} parameter
 of \code{\link{xgb.train}}.
 
-Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}} 
-or \code{\link[base]{save}}). However, it would then only be compatible with R, and 
-corresponding R-methods would need to be used to load it.
+Note: a model can also be saved as an R-object (e.g., by using \code{\link[base]{readRDS}}
+or \code{\link[base]{save}}). However, it would then only be compatible with R, and
+corresponding R-methods would need to be used to load it. Moreover, persisting the model with
+\code{\link[base]{readRDS}} or \code{\link[base]{save}}) will cause compatibility problems in
+future versions of XGBoost. Consult \code{\link{a-compatibility-note-for-saveRDS-save}} to learn
+how to persist models in a future-proof way, i.e. to make the model accessible in future
+releases of XGBoost.
 }
 \examples{
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 xgb.save(bst, 'xgb.model')
 bst <- xgb.load('xgb.model')

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

@@ -3,7 +3,7 @@
 \name{xgb.save.raw}
 \alias{xgb.save.raw}
 \title{Save xgboost model to R's raw vector,
-user can call xgb.load to load the model back from raw vector}
+user can call xgb.load.raw to load the model back from raw vector}
 \usage{
 xgb.save.raw(model)
 }
@@ -18,10 +18,10 @@ data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 train <- agaricus.train
 test <- agaricus.test
-bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
                eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
 raw <- xgb.save.raw(bst)
-bst <- xgb.load(raw)
+bst <- xgb.load.raw(raw)
 pred <- predict(bst, test$data)
 
 }

R-package/man/xgb.serialize.Rd

@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.serialize.R
+\name{xgb.serialize}
+\alias{xgb.serialize}
+\title{Serialize the booster instance into R's raw vector.  The serialization method differs
+from \code{\link{xgb.save.raw}} as the latter one saves only the model but not
+parameters.  This serialization format is not stable across different xgboost versions.}
+\usage{
+xgb.serialize(booster)
+}
+\arguments{
+\item{booster}{the booster instance}
+}
+\description{
+Serialize the booster instance into R's raw vector.  The serialization method differs
+from \code{\link{xgb.save.raw}} as the latter one saves only the model but not
+parameters.  This serialization format is not stable across different xgboost versions.
+}
+\examples{
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
+train <- agaricus.train
+test <- agaricus.test
+bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
+               eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
+raw <- xgb.serialize(bst)
+bst <- xgb.unserialize(raw)
+
+}

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

@@ -0,0 +1,55 @@
+% 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

@@ -42,9 +42,9 @@ xgboost(
 )
 }
 \arguments{
-\item{params}{the list of parameters.
-       The complete list of parameters is available at \url{http://xgboost.readthedocs.io/en/latest/parameter.html}.
-       Below is a shorter summary:
+\item{params}{the list of parameters. The complete list of parameters is
+  available in the \href{http://xgboost.readthedocs.io/en/latest/parameter.html}{online documentation}. Below
+  is a shorter summary:
 
 1. General Parameters
 
@@ -54,7 +54,7 @@ xgboost(
 
 2. Booster Parameters
 
-2.1. Parameter for Tree Booster
+2.1. Parameters for Tree Booster
 
 \itemize{
   \item \code{eta} control the learning rate: scale the contribution of each tree by a factor of \code{0 < eta < 1} when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for \code{eta} implies larger value for \code{nrounds}: low \code{eta} value means model more robust to overfitting but slower to compute. Default: 0.3
@@ -63,12 +63,14 @@ 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{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
+  \item \code{lambda} L2 regularization term on weights. Default: 1
+  \item \code{alpha} L1 regularization term on weights. (there is no L1 reg on bias because it is not important). Default: 0
+  \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through XGBoost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.
   \item \code{interaction_constraints} A list of vectors specifying feature indices of permitted interactions. Each item of the list represents one permitted interaction where specified features are allowed to interact with each other. Feature index values should start from \code{0} (\code{0} references the first column).  Leave argument unspecified for no interaction constraints.
 }
 
-2.2. Parameter for Linear Booster
+2.2. Parameters for Linear Booster
 
 \itemize{
   \item \code{lambda} L2 regularization term on weights. Default: 0
@@ -82,13 +84,23 @@ xgboost(
 \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
   \itemize{
     \item \code{reg:squarederror} Regression with squared loss (Default).
+    \item \code{reg:squaredlogerror}: regression with squared log loss \eqn{1/2 * (log(pred + 1) - log(label + 1))^2}. All inputs are required to be greater than -1. Also, see metric rmsle for possible issue with this objective.
     \item \code{reg:logistic} logistic regression.
+    \item \code{reg:pseudohubererror}: regression with Pseudo Huber loss, a twice differentiable alternative to absolute loss.
     \item \code{binary:logistic} logistic regression for binary classification. Output probability.
     \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
-    \item \code{num_class} set the number of classes. To use only with multiclass objectives.
+    \item \code{binary:hinge}: hinge loss for binary classification. This makes predictions of 0 or 1, rather than producing probabilities.
+    \item \code{count:poisson}: Poisson regression for count data, output mean of Poisson distribution. \code{max_delta_step} is set to 0.7 by default in poisson regression (used to safeguard optimization).
+    \item \code{survival:cox}: Cox regression for right censored survival time data (negative values are considered right censored). Note that predictions are returned on the hazard ratio scale (i.e., as HR = exp(marginal_prediction) in the proportional hazard function \code{h(t) = h0(t) * HR)}.
+    \item \code{survival:aft}: Accelerated failure time model for censored survival time data. See \href{https://xgboost.readthedocs.io/en/latest/tutorials/aft_survival_analysis.html}{Survival Analysis with Accelerated Failure Time} for details.
+    \item \code{aft_loss_distribution}: Probability Density Function used by \code{survival:aft} and \code{aft-nloglik} metric.
     \item \code{multi:softmax} set xgboost to do multiclass classification using the softmax objective. Class is represented by a number and should be from 0 to \code{num_class - 1}.
     \item \code{multi:softprob} same as softmax, but prediction outputs a vector of ndata * nclass elements, which can be further reshaped to ndata, nclass matrix. The result contains predicted probabilities of each data point belonging to each class.
     \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
+    \item \code{rank:ndcg}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Discounted_cumulative_gain}{Normalized Discounted Cumulative Gain (NDCG)} is maximized.
+    \item \code{rank:map}: Use LambdaMART to perform list-wise ranking where \href{https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Mean_average_precision}{Mean Average Precision (MAP)} is maximized.
+    \item \code{reg:gamma}: gamma regression with log-link. Output is a mean of gamma distribution. It might be useful, e.g., for modeling insurance claims severity, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Gamma_distribution#Applications}{gamma-distributed}.
+    \item \code{reg:tweedie}: Tweedie regression with log-link. It might be useful, e.g., for modeling total loss in insurance, or for any outcome that might be \href{https://en.wikipedia.org/wiki/Tweedie_distribution#Applications}{Tweedie-distributed}.
   }
   \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
   \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
@@ -175,9 +187,6 @@ An object of class \code{xgb.Booster} with the following elements:
         explicitly passed.
   \item \code{best_iteration} iteration number with the best evaluation metric value
         (only available with early stopping).
-  \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
-        which could further be used in \code{predict} method
-        (only available with early stopping).
   \item \code{best_score} the best evaluation metric value during early stopping.
         (only available with early stopping).
   \item \code{feature_names} names of the training dataset features
@@ -199,22 +208,24 @@ 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{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{rmse} root mean square error. \url{https://en.wikipedia.org/wiki/Root_mean_square_error}
+     \item \code{logloss} negative log-likelihood. \url{https://en.wikipedia.org/wiki/Log-likelihood}
+     \item \code{mlogloss} multiclass logloss. \url{https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html}
      \item \code{error} Binary classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
            By default, it uses the 0.5 threshold for predicted values to define negative and positive instances.
            Different threshold (e.g., 0.) could be specified as "error@0."
      \item \code{merror} Multiclass classification error rate. It is calculated as \code{(# wrong cases) / (# all cases)}.
-     \item \code{auc} Area under the curve. \url{http://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
+     \item \code{mae} Mean absolute error
+     \item \code{mape} Mean absolute percentage error
+     \item \code{auc} Area under the curve. \url{https://en.wikipedia.org/wiki/Receiver_operating_characteristic#'Area_under_curve} for ranking evaluation.
      \item \code{aucpr} Area under the PR curve. \url{https://en.wikipedia.org/wiki/Precision_and_recall} for ranking evaluation.
-     \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{http://en.wikipedia.org/wiki/NDCG}
+     \item \code{ndcg} Normalized Discounted Cumulative Gain (for ranking task). \url{https://en.wikipedia.org/wiki/NDCG}
   }
 
 The following callbacks are automatically created when certain parameters are set:
@@ -230,8 +241,8 @@ The following callbacks are automatically created when certain parameters are se
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 
-dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
-dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:

R-package/man/xgb.unserialize.Rd

@@ -0,0 +1,21 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/xgb.unserialize.R
+\name{xgb.unserialize}
+\alias{xgb.unserialize}
+\title{Load the instance back from \code{\link{xgb.serialize}}}
+\usage{
+xgb.unserialize(buffer, handle = NULL)
+}
+\arguments{
+\item{buffer}{the buffer containing booster instance saved by \code{\link{xgb.serialize}}}
+
+\item{handle}{An \code{xgb.Booster.handle} object which will be overwritten with
+the new deserialized object. Must be a null handle (e.g. when loading the model through
+`readRDS`). If not provided, a new handle will be created.}
+}
+\value{
+An \code{xgb.Booster.handle} object.
+}
+\description{
+Load the instance back from \code{\link{xgb.serialize}}
+}