Bump release version to 1.5.2. (#7567)

* Add new classifiers.
* Typehint.

.github/workflows/python_tests.yml

@@ -45,13 +45,59 @@ jobs:
         cd ..
         python -c 'import xgboost'
 
-  python-tests:
+  python-tests-on-win:
     name: Test XGBoost Python package on ${{ matrix.config.os }}
     runs-on: ${{ matrix.config.os }}
     strategy:
       matrix:
         config:
           - {os: windows-2016, python-version: '3.8'}
+
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        submodules: 'true'
+
+    - uses: conda-incubator/setup-miniconda@v2
+      with:
+        auto-update-conda: true
+        python-version: ${{ matrix.config.python-version }}
+        activate-environment: win64_env
+        environment-file: tests/ci_build/conda_env/win64_cpu_test.yml
+
+    - name: Display Conda env
+      shell: bash -l {0}
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on Windows
+      shell: bash -l {0}
+      run: |
+        mkdir build_msvc
+        cd build_msvc
+        cmake .. -G"Visual Studio 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
+
+  python-tests-on-macos:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    strategy:
+      matrix:
+        config:
           - {os: macos-10.15, python-version "3.8" }
 
     steps:
@@ -63,8 +109,8 @@ jobs:
       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
+        activate-environment: macos_test
+        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
 
     - name: Display Conda env
       shell: bash -l {0}
@@ -72,17 +118,7 @@ jobs:
         conda info
         conda list
 
-    - name: Build XGBoost on Windows
-      shell: bash -l {0}
-      if: matrix.config.os == 'windows-2016'
-      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: Build XGBoost on macos
-      if: matrix.config.os == 'macos-10.15'
       run: |
         wget https://raw.githubusercontent.com/Homebrew/homebrew-core/679923b4eb48a8dc7ecc1f05d06063cd79b3fc00/Formula/libomp.rb -O $(find $(brew --repository) -name libomp.rb)
         brew install ninja libomp
@@ -108,16 +144,19 @@ jobs:
 
     - name: Rename Python wheel
       shell: bash -l {0}
-      if: matrix.config.os == 'macos-10.15'
       run: |
         TAG=macosx_10_15_x86_64.macosx_11_0_x86_64.macosx_12_0_x86_64
         python tests/ci_build/rename_whl.py python-package/dist/*.whl ${{ github.sha }} ${TAG}
 
+    - name: Extract branch name
+      shell: bash
+      run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+      id: extract_branch
+      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
+
     - name: Upload Python wheel
       shell: bash -l {0}
-      if: |
-        (github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')) &&
-        matrix.os == 'macos-latest'
+      if: github.ref == 'refs/heads/master' || contains(github.ref, 'refs/heads/release_')
       run: |
         python -m awscli s3 cp python-package/dist/*.whl s3://xgboost-nightly-builds/${{ steps.extract_branch.outputs.branch }}/ --acl public-read
       env:

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.5.1)
+project(xgboost LANGUAGES CXX C VERSION 1.5.2)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.5.1.1
-Date: 2021-10-13
+Version: 1.5.2.1
+Date: 2022-1-17
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),

R-package/R/xgb.Booster.R

@@ -435,7 +435,8 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       lapply(seq_len(n_groups), function(g) arr[g, , ])
     } else {
       ## remove the first axis (group)
-      as.matrix(arr[1, , ])
+      dn <- dimnames(arr)
+      matrix(arr[1, , ], nrow = dim(arr)[2], ncol = dim(arr)[3], dimnames = c(dn[2], dn[3]))
     }
   } else if (predinteraction) {
     ## Predict interaction
@@ -447,7 +448,8 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
       lapply(seq_len(n_groups), function(g) arr[g, , , ])
     } else {
       ## remove the first axis (group)
-      arr[1, , , ]
+      arr <- arr[1, , , , drop = FALSE]
+      array(arr, dim = dim(arr)[2:4], dimnames(arr)[2:4])
     }
   } else {
     ## Normal prediction

R-package/tests/testthat/test_glm.R

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

R-package/tests/testthat/test_interactions.R

@@ -157,3 +157,28 @@ test_that("multiclass feature interactions work", {
   # sums WRT columns must be close to feature contributions
   expect_lt(max(abs(apply(intr, c(1, 2, 3), sum) - aperm(cont, c(3, 1, 2)))), 0.00001)
 })
+
+
+test_that("SHAP single sample works", {
+  train <- agaricus.train
+  test <- agaricus.test
+  booster <- xgboost(
+    data = train$data,
+    label = train$label,
+    max_depth = 2,
+    nrounds = 4,
+    objective = "binary:logistic",
+  )
+
+  predt <- predict(
+    booster,
+    newdata = train$data[1, , drop = FALSE], predcontrib = TRUE
+  )
+  expect_equal(dim(predt), c(1, dim(train$data)[2] + 1))
+
+  predt <- predict(
+    booster,
+    newdata = train$data[1, , drop = FALSE], predinteraction = TRUE
+  )
+  expect_equal(dim(predt), c(1, dim(train$data)[2] + 1, dim(train$data)[2] + 1))
+})

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 1
 #define XGBOOST_VER_MINOR 5
-#define XGBOOST_VER_PATCH 0
+#define XGBOOST_VER_PATCH 2
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.5.1</version>
+    <version>1.5.2</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>

jvm-packages/xgboost4j-example/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.5.1</version>
+    <version>1.5.2</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.5.1</version>
+            <version>1.5.2</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.5.1</version>
+            <version>1.5.2</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-flink/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.5.1</version>
+    <version>1.5.2</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.5.1</version>
+            <version>1.5.2</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-gpu/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j-gpu_2.12</artifactId>
-    <version>1.5.1</version>
+    <version>1.5.2</version>
     <packaging>jar</packaging>
 
     <properties>

jvm-packages/xgboost4j-spark-gpu/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j-spark-gpu_2.12</artifactId>
     <build>
@@ -24,7 +24,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>
-            <version>1.5.1</version>
+            <version>1.5.2</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j-spark/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j-spark_2.12</artifactId>
     <build>
@@ -24,7 +24,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.5.1</version>
+            <version>1.5.2</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.5.1</version>
+        <version>1.5.2</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.5.1</version>
+    <version>1.5.2</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/setup.py

@@ -4,6 +4,7 @@ import shutil
 import subprocess
 import logging
 import distutils
+from typing import Optional, List
 import sys
 from platform import system
 from setuptools import setup, find_packages, Extension
@@ -36,7 +37,7 @@ NEED_CLEAN_FILE = set()
 BUILD_TEMP_DIR = None
 
 
-def lib_name():
+def lib_name() -> str:
     '''Return platform dependent shared object name.'''
     if system() == 'Linux' or system().upper().endswith('BSD'):
         name = 'libxgboost.so'
@@ -47,13 +48,13 @@ def lib_name():
     return name
 
 
-def copy_tree(src_dir, target_dir):
+def copy_tree(src_dir: str, target_dir: str) -> None:
     '''Copy source tree into build directory.'''
-    def clean_copy_tree(src, dst):
+    def clean_copy_tree(src: str, dst: str) -> None:
         distutils.dir_util.copy_tree(src, dst)
         NEED_CLEAN_TREE.add(os.path.abspath(dst))
 
-    def clean_copy_file(src, dst):
+    def clean_copy_file(src: str, dst: str) -> None:
         distutils.file_util.copy_file(src, dst)
         NEED_CLEAN_FILE.add(os.path.abspath(dst))
 
@@ -77,7 +78,7 @@ def copy_tree(src_dir, target_dir):
     clean_copy_file(lic, os.path.join(target_dir, 'LICENSE'))
 
 
-def clean_up():
+def clean_up() -> None:
     '''Removed copied files.'''
     for path in NEED_CLEAN_TREE:
         shutil.rmtree(path)
@@ -87,7 +88,7 @@ def clean_up():
 
 class CMakeExtension(Extension):  # pylint: disable=too-few-public-methods
     '''Wrapper for extension'''
-    def __init__(self, name):
+    def __init__(self, name: str) -> None:
         super().__init__(name=name, sources=[])
 
 
@@ -97,7 +98,14 @@ class BuildExt(build_ext.build_ext):  # pylint: disable=too-many-ancestors
     logger = logging.getLogger('XGBoost build_ext')
 
     # pylint: disable=too-many-arguments,no-self-use
-    def build(self, src_dir, build_dir, generator, build_tool=None, use_omp=1):
+    def build(
+        self,
+        src_dir: str,
+        build_dir: str,
+        generator: str,
+        build_tool: Optional[str] = None,
+        use_omp: int = 1,
+    ) -> None:
         '''Build the core library with CMake.'''
         cmake_cmd = ['cmake', src_dir, generator]
 
@@ -116,13 +124,14 @@ class BuildExt(build_ext.build_ext):  # pylint: disable=too-many-ancestors
 
         if system() != 'Windows':
             nproc = os.cpu_count()
+            assert build_tool is not None
             subprocess.check_call([build_tool, '-j' + str(nproc)],
                                   cwd=build_dir)
         else:
             subprocess.check_call(['cmake', '--build', '.',
                                    '--config', 'Release'], cwd=build_dir)
 
-    def build_cmake_extension(self):
+    def build_cmake_extension(self) -> None:
         '''Configure and build using CMake'''
         if USER_OPTIONS['use-system-libxgboost'][2]:
             self.logger.info('Using system libxgboost.')
@@ -174,14 +183,14 @@ class BuildExt(build_ext.build_ext):  # pylint: disable=too-many-ancestors
                 self.logger.warning('Disabling OpenMP support.')
                 self.build(src_dir, build_dir, gen, build_tool, use_omp=0)
 
-    def build_extension(self, ext):
+    def build_extension(self, ext: Extension) -> None:
         '''Override the method for dispatching.'''
         if isinstance(ext, CMakeExtension):
             self.build_cmake_extension()
         else:
             super().build_extension(ext)
 
-    def copy_extensions_to_source(self):
+    def copy_extensions_to_source(self) -> None:
         '''Dummy override.  Invoked during editable installation.  Our binary
         should available in `lib`.
 
@@ -196,7 +205,7 @@ class Sdist(sdist.sdist):       # pylint: disable=too-many-ancestors
     '''Copy c++ source into Python directory.'''
     logger = logging.getLogger('xgboost sdist')
 
-    def run(self):
+    def run(self) -> None:
         copy_tree(os.path.join(CURRENT_DIR, os.path.pardir),
                   os.path.join(CURRENT_DIR, 'xgboost'))
         libxgboost = os.path.join(
@@ -213,7 +222,7 @@ class InstallLib(install_lib.install_lib):
     '''Copy shared object into installation directory.'''
     logger = logging.getLogger('xgboost install_lib')
 
-    def install(self):
+    def install(self) -> List[str]:
         outfiles = super().install()
 
         if USER_OPTIONS['use-system-libxgboost'][2] != 0:
@@ -255,7 +264,7 @@ class Install(install.install):  # pylint: disable=too-many-instance-attributes
     user_options = install.install.user_options + list(
         (k, v[0], v[1]) for k, v in USER_OPTIONS.items())
 
-    def initialize_options(self):
+    def initialize_options(self) -> None:
         super().initialize_options()
         self.use_openmp = 1
         self.use_cuda = 0
@@ -271,7 +280,7 @@ class Install(install.install):  # pylint: disable=too-many-instance-attributes
 
         self.use_system_libxgboost = 0
 
-    def run(self):
+    def run(self) -> None:
         # setuptools will configure the options according to user supplied command line
         # arguments, then here we propagate them into `USER_OPTIONS` for visibility to
         # other sub-commands like `build_ext`.
@@ -341,7 +350,9 @@ if __name__ == '__main__':
                        'Programming Language :: Python :: 3',
                        'Programming Language :: Python :: 3.6',
                        'Programming Language :: Python :: 3.7',
-                       'Programming Language :: Python :: 3.8'],
+                       'Programming Language :: Python :: 3.8',
+                       'Programming Language :: Python :: 3.9',
+                       'Programming Language :: Python :: 3.10'],
           python_requires='>=3.6',
           url='https://github.com/dmlc/xgboost')
 

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.5.1
+1.5.2

python-package/xgboost/core.py

@@ -229,7 +229,7 @@ def _numpy2ctypes_type(dtype):
     }
     if np.intc is not np.int32:  # Windows
         _NUMPY_TO_CTYPES_MAPPING[np.intc] = _NUMPY_TO_CTYPES_MAPPING[np.int32]
-    if dtype not in _NUMPY_TO_CTYPES_MAPPING.keys():
+    if dtype not in _NUMPY_TO_CTYPES_MAPPING:
         raise TypeError(
             f"Supported types: {_NUMPY_TO_CTYPES_MAPPING.keys()}, got: {dtype}"
         )
@@ -266,7 +266,7 @@ def ctypes2cupy(cptr, length, dtype):
     from cupy.cuda.memory import UnownedMemory
 
     CUPY_TO_CTYPES_MAPPING = {cupy.float32: ctypes.c_float, cupy.uint32: ctypes.c_uint}
-    if dtype not in CUPY_TO_CTYPES_MAPPING.keys():
+    if dtype not in CUPY_TO_CTYPES_MAPPING:
         raise RuntimeError(f"Supported types: {CUPY_TO_CTYPES_MAPPING.keys()}")
     addr = ctypes.cast(cptr, ctypes.c_void_p).value
     # pylint: disable=c-extension-no-member,no-member

python-package/xgboost/dask.py

@@ -1606,8 +1606,9 @@ class DaskScikitLearnBase(XGBModel):
         should use `worker_client' instead of default client.
 
         """
-        asynchronous = getattr(self, "_asynchronous", False)
+
         if self._client is None:
+            asynchronous = getattr(self, "_asynchronous", False)
             try:
                 distributed.get_worker()
                 in_worker = True
@@ -1620,7 +1621,7 @@ class DaskScikitLearnBase(XGBModel):
                         return ret
                     return ret
 
-        return self.client.sync(func, **kwargs, asynchronous=asynchronous)
+        return self.client.sync(func, **kwargs, asynchronous=self.client.asynchronous)
 
 
 @xgboost_model_doc(
@@ -1833,7 +1834,7 @@ class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
         vstack = update_wrapper(
             partial(da.vstack, allow_unknown_chunksizes=True), da.vstack
         )
-        return _cls_predict_proba(getattr(self, "n_classes_", None), predts, vstack)
+        return _cls_predict_proba(getattr(self, "n_classes_", 0), predts, vstack)
 
     # pylint: disable=missing-function-docstring
     def predict_proba(

python-package/xgboost/data.py

@@ -814,7 +814,7 @@ def dispatch_data_backend(
 
 def _to_data_type(dtype: str, name: str):
     dtype_map = {'float32': 1, 'float64': 2, 'uint32': 3, 'uint64': 4}
-    if dtype not in dtype_map.keys():
+    if dtype not in dtype_map:
         raise TypeError(
             f'Expecting float32, float64, uint32, uint64, got {dtype} ' +
             f'for {name}.')

python-package/xgboost/sklearn.py

@@ -1354,9 +1354,7 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
             iteration_range=iteration_range
         )
         # If model is loaded from a raw booster there's no `n_classes_`
-        return _cls_predict_proba(
-            getattr(self, "n_classes_", None), class_probs, np.vstack
-        )
+        return _cls_predict_proba(getattr(self, "n_classes_", 0), class_probs, np.vstack)
 
     def evals_result(self) -> TrainingCallback.EvalsLog:
         """Return the evaluation results.

src/common/bitfield.h

@@ -58,14 +58,15 @@ __forceinline__ __device__ BitFieldAtomicType AtomicAnd(BitFieldAtomicType* addr
 template <typename VT, typename Direction, bool IsConst = false>
 struct BitFieldContainer {
   using value_type = std::conditional_t<IsConst, VT const, VT>;  // NOLINT
-  using pointer = value_type*;  // NOLINT
+  using index_type = size_t;                                     // NOLINT
+  using pointer = value_type*;                                   // NOLINT
 
-  static value_type constexpr kValueSize = sizeof(value_type) * 8;
-  static value_type constexpr kOne = 1;  // force correct type.
+  static index_type constexpr kValueSize = sizeof(value_type) * 8;
+  static index_type constexpr kOne = 1;  // force correct type.
 
   struct Pos {
-    std::remove_const_t<value_type> int_pos {0};
-    std::remove_const_t<value_type> bit_pos {0};
+    index_type int_pos{0};
+    index_type bit_pos{0};
   };
 
  private:
@@ -73,13 +74,13 @@ struct BitFieldContainer {
   static_assert(!std::is_signed<VT>::value, "Must use unsiged type as underlying storage.");
 
  public:
-  XGBOOST_DEVICE static Pos ToBitPos(value_type pos) {
+  XGBOOST_DEVICE static Pos ToBitPos(index_type pos) {
     Pos pos_v;
     if (pos == 0) {
       return pos_v;
     }
-    pos_v.int_pos =  pos / kValueSize;
-    pos_v.bit_pos =  pos % kValueSize;
+    pos_v.int_pos = pos / kValueSize;
+    pos_v.bit_pos = pos % kValueSize;
     return pos_v;
   }
 
@@ -96,7 +97,7 @@ struct BitFieldContainer {
   /*\brief Compute the size of needed memory allocation.  The returned value is in terms
    *       of number of elements with `BitFieldContainer::value_type'.
    */
-  XGBOOST_DEVICE static size_t ComputeStorageSize(size_t size) {
+  XGBOOST_DEVICE static size_t ComputeStorageSize(index_type size) {
     return common::DivRoundUp(size, kValueSize);
   }
 #if defined(__CUDA_ARCH__)
@@ -138,14 +139,14 @@ struct BitFieldContainer {
 #endif  // defined(__CUDA_ARCH__)
 
 #if defined(__CUDA_ARCH__)
-  __device__ auto Set(value_type pos) {
+  __device__ auto Set(index_type pos) {
     Pos pos_v = Direction::Shift(ToBitPos(pos));
     value_type& value = bits_[pos_v.int_pos];
     value_type set_bit = kOne << pos_v.bit_pos;
     using Type = typename dh::detail::AtomicDispatcher<sizeof(value_type)>::Type;
     atomicOr(reinterpret_cast<Type *>(&value), set_bit);
   }
-  __device__ void Clear(value_type pos) {
+  __device__ void Clear(index_type pos) {
     Pos pos_v = Direction::Shift(ToBitPos(pos));
     value_type& value = bits_[pos_v.int_pos];
     value_type clear_bit = ~(kOne << pos_v.bit_pos);
@@ -153,13 +154,13 @@ struct BitFieldContainer {
     atomicAnd(reinterpret_cast<Type *>(&value), clear_bit);
   }
 #else
-  void Set(value_type pos) {
+  void Set(index_type pos) {
     Pos pos_v = Direction::Shift(ToBitPos(pos));
     value_type& value = bits_[pos_v.int_pos];
     value_type set_bit = kOne << pos_v.bit_pos;
     value |= set_bit;
   }
-  void Clear(value_type pos) {
+  void Clear(index_type pos) {
     Pos pos_v = Direction::Shift(ToBitPos(pos));
     value_type& value = bits_[pos_v.int_pos];
     value_type clear_bit = ~(kOne << pos_v.bit_pos);
@@ -175,7 +176,7 @@ struct BitFieldContainer {
     value_type result = test_bit & value;
     return static_cast<bool>(result);
   }
-  XGBOOST_DEVICE bool Check(value_type pos) const {
+  XGBOOST_DEVICE bool Check(index_type pos) const {
     Pos pos_v = ToBitPos(pos);
     return Check(pos_v);
   }

src/gbm/gblinear.cc

@@ -62,9 +62,8 @@ struct GBLinearTrainParam : public XGBoostParameter<GBLinearTrainParam> {
   }
 };
 
-void LinearCheckLayer(unsigned layer_begin, unsigned layer_end) {
+void LinearCheckLayer(unsigned layer_begin) {
   CHECK_EQ(layer_begin, 0) << "Linear booster does not support prediction range.";
-  CHECK_EQ(layer_end, 0)   << "Linear booster does not support prediction range.";
 }
 
 /*!
@@ -152,7 +151,7 @@ class GBLinear : public GradientBooster {
   void PredictBatch(DMatrix *p_fmat, PredictionCacheEntry *predts,
                     bool training, unsigned layer_begin, unsigned layer_end) override {
     monitor_.Start("PredictBatch");
-    LinearCheckLayer(layer_begin, layer_end);
+    LinearCheckLayer(layer_begin);
     auto* out_preds = &predts->predictions;
     this->PredictBatchInternal(p_fmat, &out_preds->HostVector());
     monitor_.Stop("PredictBatch");
@@ -161,7 +160,7 @@ class GBLinear : public GradientBooster {
   void PredictInstance(const SparsePage::Inst &inst,
                        std::vector<bst_float> *out_preds,
                        unsigned layer_begin, unsigned layer_end) override {
-    LinearCheckLayer(layer_begin, layer_end);
+    LinearCheckLayer(layer_begin);
     const int ngroup = model_.learner_model_param->num_output_group;
     for (int gid = 0; gid < ngroup; ++gid) {
       this->Pred(inst, dmlc::BeginPtr(*out_preds), gid,
@@ -177,8 +176,8 @@ class GBLinear : public GradientBooster {
                            HostDeviceVector<bst_float>* out_contribs,
                            unsigned layer_begin, unsigned layer_end, bool, int, unsigned) override {
     model_.LazyInitModel();
-    LinearCheckLayer(layer_begin, layer_end);
-    const auto& base_margin = p_fmat->Info().base_margin_.ConstHostVector();
+    LinearCheckLayer(layer_begin);
+    const auto &base_margin = p_fmat->Info().base_margin_.ConstHostVector();
     const int ngroup = model_.learner_model_param->num_output_group;
     const size_t ncolumns = model_.learner_model_param->num_feature + 1;
     // allocate space for (#features + bias) times #groups times #rows
@@ -214,7 +213,7 @@ class GBLinear : public GradientBooster {
   void PredictInteractionContributions(DMatrix* p_fmat,
                                        HostDeviceVector<bst_float>* out_contribs,
                                        unsigned layer_begin, unsigned layer_end, bool) override {
-    LinearCheckLayer(layer_begin, layer_end);
+    LinearCheckLayer(layer_begin);
     std::vector<bst_float>& contribs = out_contribs->HostVector();
 
     // linear models have no interaction effects

src/gbm/gblinear_model.cc

@@ -18,6 +18,7 @@ void GBLinearModel::SaveModel(Json* p_out) const {
     j_weights[i] = weight[i];
   }
   out["weights"] = std::move(j_weights);
+  out["boosted_rounds"] = Json{this->num_boosted_rounds};
 }
 
 void GBLinearModel::LoadModel(Json const& in) {
@@ -27,6 +28,13 @@ void GBLinearModel::LoadModel(Json const& in) {
   for (size_t i = 0; i < n_weights; ++i) {
     weight[i] = get<Number const>(j_weights[i]);
   }
+  auto const& obj = get<Object const>(in);
+  auto boosted_rounds = obj.find("boosted_rounds");
+  if (boosted_rounds != obj.cend()) {
+    this->num_boosted_rounds = get<Integer const>(boosted_rounds->second);
+  } else {
+    this->num_boosted_rounds = 0;
+  }
 }
 
 DMLC_REGISTER_PARAMETER(DeprecatedGBLinearModelParam);

tests/ci_build/conda_env/macos_cpu_test.yml

@@ -1,4 +1,4 @@
-name: cpu_test
+name: macos_test
 channels:
 - conda-forge
 dependencies:

tests/cpp/common/test_bitfield.cc

@@ -38,6 +38,14 @@ TEST(BitField, Check) {
       ASSERT_FALSE(bits.Check(i));
     }
   }
+
+  {
+    // regression test for correct index type.
+    std::vector<RBitField8::value_type> storage(33, 0);
+    storage[32] = static_cast<uint8_t>(1);
+    auto bits = RBitField8({storage.data(), storage.size()});
+    ASSERT_TRUE(bits.Check(256));
+  }
 }
 
 template <typename BitFieldT, typename VT = typename BitFieldT::value_type>

tests/python-gpu/test_gpu_linear.py

@@ -1,7 +1,6 @@
 import sys
-from hypothesis import strategies, given, settings, assume
+from hypothesis import strategies, given, settings, assume, note
 import pytest
-import numpy
 import xgboost as xgb
 sys.path.append("tests/python")
 import testing as tm
@@ -17,10 +16,14 @@ parameter_strategy = strategies.fixed_dictionaries({
     'top_k': strategies.integers(1, 10),
 })
 
+
 def train_result(param, dmat, num_rounds):
     result = {}
-    xgb.train(param, dmat, num_rounds, [(dmat, 'train')], verbose_eval=False,
-              evals_result=result)
+    booster = xgb.train(
+        param, dmat, num_rounds, [(dmat, 'train')], verbose_eval=False,
+        evals_result=result
+    )
+    assert booster.num_boosted_rounds() == num_rounds
     return result
 
 
@@ -33,6 +36,7 @@ class TestGPULinear:
         param['updater'] = 'gpu_coord_descent'
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         assert tm.non_increasing(result)
 
     # Loss is not guaranteed to always decrease because of regularisation parameters
@@ -49,6 +53,7 @@ class TestGPULinear:
         param['lambda'] = lambd
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         assert tm.non_increasing([result[0], result[-1]])
 
     @pytest.mark.skipif(**tm.no_cupy())

tests/python/test_linear.py

@@ -32,6 +32,7 @@ class TestLinear:
         param.update(coord_param)
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         assert tm.non_increasing(result, 5e-4)
 
     # Loss is not guaranteed to always decrease because of regularisation parameters
@@ -48,6 +49,7 @@ class TestLinear:
         param.update(coord_param)
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         assert tm.non_increasing([result[0], result[-1]])
 
     @given(parameter_strategy, strategies.integers(10, 50),
@@ -57,6 +59,7 @@ class TestLinear:
         param['updater'] = 'shotgun'
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         # shotgun is non-deterministic, so we relax the test by only using first and last
         # iteration.
         if len(result) > 2:
@@ -75,4 +78,5 @@ class TestLinear:
         param['lambda'] = lambd
         param = dataset.set_params(param)
         result = train_result(param, dataset.get_dmat(), num_rounds)['train'][dataset.metric]
+        note(result)
         assert tm.non_increasing([result[0], result[-1]])

tests/python/test_with_dask.py

@@ -705,8 +705,7 @@ async def run_from_dask_array_asyncio(scheduler_address: str) -> xgb.dask.TrainR
 async def run_dask_regressor_asyncio(scheduler_address: str) -> None:
     async with Client(scheduler_address, asynchronous=True) as client:
         X, y, _ = generate_array()
-        regressor = await xgb.dask.DaskXGBRegressor(verbosity=1,
-                                                    n_estimators=2)
+        regressor = await xgb.dask.DaskXGBRegressor(verbosity=1, n_estimators=2)
         regressor.set_params(tree_method='hist')
         regressor.client = client
         await regressor.fit(X, y, eval_set=[(X, y)])