merge master

.ci/test.sh

@@ -8,6 +8,11 @@ elif [[ $OS_NAME == "linux" ]] && [[ $COMPILER == "clang" ]]; then
     export CC=clang
 fi
 
+if [[ $IN_UBUNTU_BASE_CONTAINER == "true" ]]; then
+    export LANG="en_US.UTF-8"
+    export LC_ALL="en_US.UTF-8"
+fi
+
 if [[ "${TASK}" == "r-package" ]] || [[ "${TASK}" == "r-rchk" ]]; then
     bash ${BUILD_DIRECTORY}/.ci/test_r_package.sh || exit -1
     exit 0

.github/workflows/linkchecker.yml

@@ -17,7 +17,7 @@ env:
 jobs:
   check-links:
     timeout-minutes: 60
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3

.github/workflows/optional_checks.yml

@@ -7,9 +7,9 @@ on:
       - release/*
 
 jobs:
-  all-successful:
+  all-optional-checks-successful:
     timeout-minutes: 120
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3

.github/workflows/r_package.yml

@@ -223,76 +223,78 @@ jobs:
           $env:GITHUB_ACTIONS = "true"
           $env:TASK = "${{ matrix.task }}"
           & "$env:GITHUB_WORKSPACE/.ci/test_windows.ps1"
-  # test-r-sanitizers:
-  #   name: r-sanitizers (ubuntu-latest, R-devel, ${{ matrix.compiler }} ASAN/UBSAN)
-  #   timeout-minutes: 60
-  #   runs-on: ubuntu-latest
-  #   container: wch1/r-debug
-  #   strategy:
-  #     fail-fast: false
-  #     matrix:
-  #       include:
-  #         - r_customization: san
-  #           compiler: gcc
-  #         - r_customization: csan
-  #           compiler: clang
-  #   steps:
-  #     - name: Trust git cloning LightGBM
-  #       run: |
-  #         git config --global --add safe.directory "${GITHUB_WORKSPACE}"
-  #     - name: Checkout repository
-  #       uses: actions/checkout@v3
-  #       with:
-  #         fetch-depth: 5
-  #         submodules: true
-  #     - name: Install packages
-  #       shell: bash
-  #       run: |
-  #         RDscript${{ matrix.r_customization }} -e "install.packages(c('R6', 'data.table', 'jsonlite', 'knitr', 'Matrix', 'RhpcBLASctl', 'rmarkdown', 'testthat'), repos = 'https://cran.rstudio.com', Ncpus = parallel::detectCores())"
-  #         sh build-cran-package.sh --r-executable=RD${{ matrix.r_customization }}
-  #         RD${{ matrix.r_customization }} CMD INSTALL lightgbm_*.tar.gz || exit -1
-  #     - name: Run tests with sanitizers
-  #       shell: bash
-  #       run: |
-  #         cd R-package/tests
-  #         exit_code=0
-  #         RDscript${{ matrix.r_customization }} testthat.R >> tests.log 2>&1 || exit_code=-1
-  #         cat ./tests.log
-  #         exit ${exit_code}
-  # test-r-debian-clang:
-  #   name: r-package (debian, R-devel, clang)
-  #   timeout-minutes: 60
-  #   runs-on: ubuntu-latest
-  #   container: rhub/debian-clang-devel
-  #   steps:
-  #     - name: Install Git before checkout
-  #       shell: bash
-  #       run: |
-  #         apt-get update --allow-releaseinfo-change
-  #         apt-get install --no-install-recommends -y git
-  #     - name: Trust git cloning LightGBM
-  #       run: |
-  #         git config --global --add safe.directory "${GITHUB_WORKSPACE}"
-  #     - name: Checkout repository
-  #       uses: actions/checkout@v3
-  #       with:
-  #         fetch-depth: 5
-  #         submodules: true
-  #     - name: Install packages and run tests
-  #       shell: bash
-  #       run: |
-  #         export PATH=/opt/R-devel/bin/:${PATH}
-  #         Rscript -e "install.packages(c('R6', 'data.table', 'jsonlite', 'knitr', 'Matrix', 'RhpcBLASctl', 'rmarkdown', 'testthat'), repos = 'https://cran.rstudio.com', Ncpus = parallel::detectCores())"
-  #         sh build-cran-package.sh
-  #         R CMD check --as-cran --run-donttest lightgbm_*.tar.gz || exit -1
-  #         if grep -q -E "NOTE|WARNING|ERROR" lightgbm.Rcheck/00check.log; then
-  #             echo "NOTEs, WARNINGs, or ERRORs have been found by R CMD check"
-  #             exit -1
-  #         fi
-  all-successful:
-    # https://github.community/t/is-it-possible-to-require-all-github-actions-tasks-to-pass-without-enumerating-them/117957/4?u=graingert
+#  test-r-sanitizers:
+#    name: r-sanitizers (ubuntu-latest, R-devel, ${{ matrix.compiler }} ASAN/UBSAN)
+#    timeout-minutes: 60
+#    runs-on: ubuntu-latest
+#    container: wch1/r-debug
+#    strategy:
+#      fail-fast: false
+#      matrix:
+#        include:
+#          - r_customization: san
+#            compiler: gcc
+#          - r_customization: csan
+#            compiler: clang
+#    steps:
+#      - name: Trust git cloning LightGBM
+#        run: |
+#          git config --global --add safe.directory "${GITHUB_WORKSPACE}"
+#      - name: Checkout repository
+#        uses: actions/checkout@v3
+#        with:
+#          fetch-depth: 5
+#          submodules: true
+#      - name: Install packages
+#        shell: bash
+#        run: |
+#          RDscript${{ matrix.r_customization }} -e "install.packages(c('R6', 'data.table', 'jsonlite', 'knitr', 'Matrix', 'RhpcBLASctl', 'rmarkdown', 'testthat'), repos = 'https://cran.rstudio.com', Ncpus = parallel::detectCores())"
+#          sh build-cran-package.sh --r-executable=RD${{ matrix.r_customization }}
+#          RD${{ matrix.r_customization }} CMD INSTALL lightgbm_*.tar.gz || exit -1
+#      - name: Run tests with sanitizers
+#        shell: bash
+#        run: |
+#          cd R-package/tests
+#          exit_code=0
+#          RDscript${{ matrix.r_customization }} testthat.R >> tests.log 2>&1 || exit_code=-1
+#          cat ./tests.log
+#          exit ${exit_code}
+#  test-r-debian-clang:
+#    name: r-package (debian, R-devel, clang)
+#    timeout-minutes: 60
+#    runs-on: ubuntu-latest
+#    container: rhub/debian-clang-devel
+#    steps:
+#      - name: Install Git before checkout
+#        shell: bash
+#        run: |
+#          apt-get update --allow-releaseinfo-change
+#          apt-get install --no-install-recommends -y git
+#      - name: Trust git cloning LightGBM
+#        run: |
+#          git config --global --add safe.directory "${GITHUB_WORKSPACE}"
+#      - name: Checkout repository
+#        uses: actions/checkout@v3
+#        with:
+#          fetch-depth: 5
+#          submodules: true
+#      - name: Install packages and run tests
+#        shell: bash
+#        run: |
+#          export PATH=/opt/R-devel/bin/:${PATH}
+#          Rscript -e "install.packages(c('R6', 'data.table', 'jsonlite', 'knitr', 'Matrix', 'RhpcBLASctl', 'rmarkdown', 'testthat'), repos = 'https://cran.rstudio.com', Ncpus = parallel::detectCores())"
+#          sh build-cran-package.sh
+#          R CMD check --as-cran --run-donttest lightgbm_*.tar.gz || exit -1
+#          if grep -q -E "NOTE|WARNING|ERROR" lightgbm.Rcheck/00check.log; then
+#              echo "NOTEs, WARNINGs, or ERRORs have been found by R CMD check"
+#              exit -1
+#          fi
+  all-r-package-jobs-successful:
+    if: always()
     runs-on: ubuntu-latest
     needs: [test]
     steps:
     - name: Note that all tests succeeded
-      run: echo "🎉"
+      uses: re-actors/[email protected]
+      with:
+        jobs: ${{ toJSON(needs) }}

.github/workflows/static_analysis.yml

@@ -47,7 +47,7 @@ jobs:
   r-check-docs:
     name: r-package-check-docs
     timeout-minutes: 60
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     container: rocker/verse
     steps:
       - name: Trust git cloning LightGBM
@@ -80,10 +80,12 @@ jobs:
               echo ""
               exit -1
           fi
-  all-successful:
-    # https://github.community/t/is-it-possible-to-require-all-github-actions-tasks-to-pass-without-enumerating-them/117957/4?u=graingert
-    runs-on: ubuntu-22.04
+  all-static-analysis-jobs-successful:
+    if: always()
+    runs-on: ubuntu-latest
     needs: [test, r-check-docs]
     steps:
     - name: Note that all tests succeeded
-      run: echo "🎉"
+      uses: re-actors/[email protected]
+      with:
+        jobs: ${{ toJSON(needs) }}

R-package/cran-comments.md

@@ -1,9 +1,31 @@
 # CRAN Submission History
 
+## v3.3.4 - Submission 1 - (December 15, 2022)
+
+### CRAN response
+
+Accepted to CRAN
+
+### Maintainer Notes
+
+Submitted with the following comment:
+
+> This submission contains {lightgbm} 3.3.3.
+
+> Per CRAN's policies, I am submitting it on behalf of the project's maintainer (Yu Shi), with his permission.
+
+> This submission includes patches to address the following warnings observed on the fedora and debian CRAN checks.
+>
+> Compiled code should not call entry points which might terminate R nor write to stdout/stderr instead of to the console, nor use Fortran I/O nor system RNGs nor [v]sprintf.
+
+> Thank you very much for your time and consideration.
+
 ## v3.3.3 - Submission 1 - (October 10, 2022)
 
 ### CRAN response
 
+Accepted to CRAN
+
 ### Maintainer Notes
 
 Submitted with the following comment:

R-package/src/Makevars.in

@@ -26,6 +26,7 @@ OBJECTS = \
     boosting/gbdt_model_text.o \
     boosting/gbdt_prediction.o \
     boosting/prediction_early_stop.o \
+    boosting/sample_strategy.o \
     io/bin.o \
     io/config.o \
     io/config_auto.o \

R-package/src/Makevars.win.in

@@ -27,6 +27,7 @@ OBJECTS = \
     boosting/gbdt_model_text.o \
     boosting/gbdt_prediction.o \
     boosting/prediction_early_stop.o \
+    boosting/sample_strategy.o \
     io/bin.o \
     io/config.o \
     io/config_auto.o \

README.md

@@ -121,6 +121,8 @@ MLflow (experiment tracking, model monitoring framework): https://github.com/mlf
 
 lightgbm-transform (feature transformation binding): https://github.com/microsoft/lightgbm-transform
 
+`postgresml` (LightGBM training and prediction in SQL, via a Postgres extension): https://github.com/postgresml/postgresml
+
 Support
 -------
 

docs/Development-Guide.rst

@@ -19,7 +19,7 @@ Important Classes
 +-------------------------+----------------------------------------------------------------------------------------+
 | ``Bin``                 | Data structure used for storing feature discrete values (converted from float values)  |
 +-------------------------+----------------------------------------------------------------------------------------+
-| ``Boosting``            | Boosting interface (GBDT, DART, GOSS, etc.)                                            |
+| ``Boosting``            | Boosting interface (GBDT, DART, etc.)                                                  |
 +-------------------------+----------------------------------------------------------------------------------------+
 | ``Config``              | Stores parameters and configurations                                                   |
 +-------------------------+----------------------------------------------------------------------------------------+

docs/Parameters.rst

@@ -127,18 +127,24 @@ Core Parameters
 
       -  label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
 
--  ``boosting`` :raw-html:`<a id="boosting" title="Permalink to this parameter" href="#boosting">&#x1F517;&#xFE0E;</a>`, default = ``gbdt``, type = enum, options: ``gbdt``, ``rf``, ``dart``, ``goss``, aliases: ``boosting_type``, ``boost``
+-  ``boosting`` :raw-html:`<a id="boosting" title="Permalink to this parameter" href="#boosting">&#x1F517;&#xFE0E;</a>`, default = ``gbdt``, type = enum, options: ``gbdt``, ``rf``, ``dart``, aliases: ``boosting_type``, ``boost``
 
    -  ``gbdt``, traditional Gradient Boosting Decision Tree, aliases: ``gbrt``
 
    -  ``rf``, Random Forest, aliases: ``random_forest``
 
    -  ``dart``, `Dropouts meet Multiple Additive Regression Trees <https://arxiv.org/abs/1505.01866>`__
 
-   -  ``goss``, Gradient-based One-Side Sampling
-
       -  **Note**: internally, LightGBM uses ``gbdt`` mode for the first ``1 / learning_rate`` iterations
 
+-  ``data_sample_strategy`` :raw-html:`<a id="data_sample_strategy" title="Permalink to this parameter" href="#data_sample_strategy">&#x1F517;&#xFE0E;</a>`, default = ``bagging``, type = enum, options: ``bagging``, ``goss``
+
+   -  ``bagging``, Randomly Bagging Sampling
+
+      -  **Note**: ``bagging`` is only effective when ``bagging_freq > 0`` and ``bagging_fraction < 1.0``
+
+   -  ``goss``, Gradient-based One-Side Sampling
+
 -  ``data`` :raw-html:`<a id="data" title="Permalink to this parameter" href="#data">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``train``, ``train_data``, ``train_data_file``, ``data_filename``
 
    -  path of training data, LightGBM will train from this data
@@ -268,7 +274,7 @@ Learning Control Parameters
 
       -  ``num_threads`` is relatively small, e.g. ``<= 16``
 
-      -  you want to use small ``bagging_fraction`` or ``goss`` boosting to speed up
+      -  you want to use small ``bagging_fraction`` or ``goss`` sample strategy to speed up
 
    -  **Note**: setting this to ``true`` will double the memory cost for Dataset object. If you have not enough memory, you can try setting ``force_col_wise=true``
 

include/LightGBM/config.h

@@ -153,14 +153,21 @@ struct Config {
   // [doc-only]
   // type = enum
   // alias = boosting_type, boost
-  // options = gbdt, rf, dart, goss
+  // options = gbdt, rf, dart
   // desc = ``gbdt``, traditional Gradient Boosting Decision Tree, aliases: ``gbrt``
   // desc = ``rf``, Random Forest, aliases: ``random_forest``
   // desc = ``dart``, `Dropouts meet Multiple Additive Regression Trees <https://arxiv.org/abs/1505.01866>`__
-  // desc = ``goss``, Gradient-based One-Side Sampling
   // descl2 = **Note**: internally, LightGBM uses ``gbdt`` mode for the first ``1 / learning_rate`` iterations
   std::string boosting = "gbdt";
 
+  // [doc-only]
+  // type = enum
+  // options = bagging, goss
+  // desc = ``bagging``, Randomly Bagging Sampling
+  // descl2 = **Note**: ``bagging`` is only effective when ``bagging_freq > 0`` and ``bagging_fraction < 1.0``
+  // desc = ``goss``, Gradient-based One-Side Sampling
+  std::string data_sample_strategy = "bagging";
+
   // alias = train, train_data, train_data_file, data_filename
   // desc = path of training data, LightGBM will train from this data
   // desc = **Note**: can be used only in CLI version
@@ -263,7 +270,7 @@ struct Config {
   // desc = enabling this is recommended when:
   // descl2 = the number of data points is large, and the total number of bins is relatively small
   // descl2 = ``num_threads`` is relatively small, e.g. ``<= 16``
-  // descl2 = you want to use small ``bagging_fraction`` or ``goss`` boosting to speed up
+  // descl2 = you want to use small ``bagging_fraction`` or ``goss`` sample strategy to speed up
   // desc = **Note**: setting this to ``true`` will double the memory cost for Dataset object. If you have not enough memory, you can try setting ``force_col_wise=true``
   // desc = **Note**: when both ``force_col_wise`` and ``force_row_wise`` are ``false``, LightGBM will firstly try them both, and then use the faster one. To remove the overhead of testing set the faster one to ``true`` manually
   // desc = **Note**: this parameter cannot be used at the same time with ``force_col_wise``, choose only one of them

include/LightGBM/cuda/cuda_tree.hpp

@@ -77,6 +77,8 @@ class CUDATree : public Tree {
                             const data_size_t* used_data_indices,
                             data_size_t num_data, double* score) const override;
 
+  inline void AsConstantTree(double val) override;
+
   const int* cuda_leaf_parent() const { return cuda_leaf_parent_; }
 
   const int* cuda_left_child() const { return cuda_left_child_; }

include/LightGBM/cuda/cuda_utils.h

@@ -10,10 +10,10 @@
 #include <cuda.h>
 #include <cuda_runtime.h>
 #include <stdio.h>
+#include <LightGBM/utils/log.h>
 #endif  // USE_CUDA || USE_CUDA_EXP
 
 #ifdef USE_CUDA_EXP
-#include <LightGBM/utils/log.h>
 #include <vector>
 #endif  // USE_CUDA_EXP
 
@@ -119,8 +119,12 @@ class CUDAVector {
   }
 
   void Resize(size_t size) {
+    if (size == size_) {
+      return;
+    }
     if (size == 0) {
       Clear();
+      return;
     }
     T* new_data = nullptr;
     AllocateCUDAMemory<T>(&new_data, size, __FILE__, __LINE__);

include/LightGBM/objective_function.h

@@ -101,9 +101,12 @@ class ObjectiveFunction {
   /*!
   * \brief Convert output for CUDA version
   */
-  const double* ConvertOutputCUDA(data_size_t /*num_data*/, const double* input, double* /*output*/) const {
+  virtual const double* ConvertOutputCUDA(data_size_t /*num_data*/, const double* input, double* /*output*/) const {
     return input;
   }
+
+  virtual bool NeedConvertOutputCUDA () const { return false; }
+
   #endif  // USE_CUDA_EXP
 };