Bump R package version to 1.7.3. (#8649)

We can handle loading the pickle on a CPU-only machine if the XGBoost is built with CUDA
enabled (Linux and Windows PyPI package), but not if the distribution is CPU-only (macOS
PyPI package).

.github/workflows/main.yml

@@ -75,19 +75,18 @@ jobs:
     - 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
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
       with:
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        activate-environment: test
+        cache-downloads: true
+        cache-env: true
+        environment-name: cpp_test
+        environment-file: tests/ci_build/conda_env/cpp_test.yml
     - 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: |
@@ -109,6 +108,7 @@ jobs:
         cd ..
         rm -rf ./build
         popd
+
     - name: Build and install XGBoost shared library
       shell: bash -l {0}
       run: |

.github/workflows/python_tests.yml

@@ -41,12 +41,46 @@ jobs:
       run: |
         python tests/ci_build/lint_python.py --format=0 --type-check=0 --pylint=1
 
-  python-sdist-test:
+  python-sdist-test-on-Linux:
+    # Mismatched glibcxx version between system and conda forge.
     runs-on: ${{ matrix.os }}
     name: Test installing XGBoost Python source package on ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-11, windows-latest]
+        os: [ubuntu-latest]
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: false
+        environment-name: sdist_test
+        environment-file: tests/ci_build/conda_env/sdist_test.yml
+    - 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-sdist-test:
+    # Use system toolchain instead of conda toolchain for macos and windows.
+    # MacOS has linker error if clang++ from conda-forge is used
+    runs-on: ${{ matrix.os }}
+    name: Test installing XGBoost Python source package on ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-11, windows-latest]
         python-version: ["3.8"]
     steps:
     - uses: actions/checkout@v2
@@ -56,11 +90,7 @@ jobs:
       if: matrix.os == 'macos-11'
       run: |
         brew install ninja libomp
-    - name: Install Ubuntu system dependencies
-      if: matrix.os == 'ubuntu-latest'
-      run: |
-        sudo apt-get install -y --no-install-recommends ninja-build
-    - uses: conda-incubator/setup-miniconda@v2
+    - uses: conda-incubator/setup-miniconda@35d1405e78aa3f784fe3ce9a2eb378d5eeb62169 # v2.1.1
       with:
         auto-update-conda: true
         python-version: ${{ matrix.python-version }}
@@ -80,6 +110,58 @@ jobs:
         cd ..
         python -c 'import xgboost'
 
+  python-tests-on-macos:
+    name: Test XGBoost Python package on ${{ matrix.config.os }}
+    runs-on: ${{ matrix.config.os }}
+    timeout-minutes: 60
+    strategy:
+      matrix:
+        config:
+          - {os: macos-11}
+
+    steps:
+    - uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v2.5.0
+      with:
+        submodules: 'true'
+
+    - uses: mamba-org/provision-with-micromamba@f347426e5745fe3dfc13ec5baf20496990d0281f # v14
+      with:
+        cache-downloads: true
+        cache-env: false
+        environment-name: macos_test
+        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
+
+    - name: Display Conda env
+      shell: bash -l {0}
+      run: |
+        conda info
+        conda list
+
+    - name: Build XGBoost on macos
+      shell: bash -l {0}
+      run: |
+        brew install ninja
+
+        mkdir build
+        cd build
+        # Set prefix, to use OpenMP library from Conda env
+        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
+        # to learn why we don't use libomp from Homebrew.
+        cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
+        ninja
+
+    - name: Install Python package
+      shell: bash -l {0}
+      run: |
+        cd python-package
+        python --version
+        python setup.py install
+
+    - name: Test Python package
+      shell: bash -l {0}
+      run: |
+        pytest -s -v -rxXs --durations=0 ./tests/python
+
   python-tests-on-win:
     name: Test XGBoost Python package on ${{ matrix.config.os }}
     runs-on: ${{ matrix.config.os }}
@@ -125,56 +207,4 @@ jobs:
     - name: Test Python package
       shell: bash -l {0}
       run: |
-        pytest -s -v ./tests/python
-
-  python-tests-on-macos:
-    name: Test XGBoost Python package on ${{ matrix.config.os }}
-    runs-on: ${{ matrix.config.os }}
-    timeout-minutes: 90
-    strategy:
-      matrix:
-        config:
-          - {os: macos-11, python-version "3.8" }
-
-    steps:
-    - uses: actions/checkout@v2
-      with:
-        submodules: 'true'
-
-    - uses: conda-incubator/setup-miniconda@v2
-      with:
-        auto-update-conda: true
-        python-version: ${{ matrix.config.python-version }}
-        activate-environment: macos_test
-        environment-file: tests/ci_build/conda_env/macos_cpu_test.yml
-
-    - name: Display Conda env
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
-
-    - name: Build XGBoost on macos
-      shell: bash -l {0}
-      run: |
-        brew install ninja
-
-        mkdir build
-        cd build
-        # Set prefix, to use OpenMP library from Conda env
-        # See https://github.com/dmlc/xgboost/issues/7039#issuecomment-1025038228
-        # to learn why we don't use libomp from Homebrew.
-        cmake .. -GNinja -DGOOGLE_TEST=ON -DUSE_DMLC_GTEST=ON -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
-        ninja
-
-    - name: Install Python package
-      shell: bash -l {0}
-      run: |
-        cd python-package
-        python --version
-        python setup.py install
-
-    - name: Test Python package
-      shell: bash -l {0}
-      run: |
-        pytest -s -v ./tests/python
+        pytest -s -v -rxXs --durations=0 ./tests/python

.github/workflows/r_tests.yml

@@ -5,6 +5,7 @@ on: [push, pull_request]
 env:
   R_PACKAGES: c('XML', 'data.table', 'ggplot2', 'DiagrammeR', 'Ckmeans.1d.dp', 'vcd', 'testthat', 'lintr', 'knitr', 'rmarkdown', 'e1071', 'cplm', 'devtools', 'float', 'titanic')
   GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+  _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
 
 permissions:
   contents: read # to fetch code (actions/checkout)
@@ -68,6 +69,7 @@ jobs:
           - {os: windows-latest, r: 'release', compiler: 'mingw', build: 'cmake'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
+      _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
@@ -121,6 +123,10 @@ jobs:
         config:
           - {r: 'release'}
 
+    env:
+      _R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_: 2.5
+      MAKE: "make -j$(nproc)"
+
     steps:
     - uses: actions/checkout@v2
       with:

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.7.0)
+project(xgboost LANGUAGES CXX C VERSION 1.7.3)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

Makefile

@@ -126,7 +126,6 @@ Rpack: clean_all
 	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.in
 	cat R-package/src/Makevars.win|sed '2s/.*/PKGROOT=./' > xgboost/src/Makevars.win
 	rm -f xgboost/src/Makevars.win-e   # OSX sed create this extra file; remove it
-	rm -f xgboost/cleanup
 	bash R-package/remove_warning_suppression_pragma.sh
 	bash xgboost/remove_warning_suppression_pragma.sh
 	rm xgboost/remove_warning_suppression_pragma.sh

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.7.0.1
-Date: 2022-10-18
+Version: 1.7.3.1
+Date: 2023-01-06
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -66,5 +66,5 @@ Imports:
     methods,
     data.table (>= 1.9.6),
     jsonlite (>= 1.0),
-RoxygenNote: 7.1.1
+RoxygenNote: 7.2.2
 SystemRequirements: GNU make, C++14

R-package/R/callbacks.R

@@ -544,9 +544,11 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' @return
 #' Results are stored in the \code{coefs} element of the closure.
-#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
+#' The \code{\link{xgb.gblinear.history}} convenience function provides an easy
+#' way to access it.
 #' With \code{xgb.train}, it is either a dense of a sparse matrix.
-#' While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
+#' While with \code{xgb.cv}, it is a list (an element per each fold) of such
+#' matrices.
 #'
 #' @seealso
 #' \code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
@@ -558,7 +560,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' # without considering the 2nd order interactions:
 #' x <- model.matrix(Species ~ .^2, iris)[,-1]
 #' colnames(x)
-#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
+#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
 #' param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
 #'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For 'shotgun', which is a default linear updater, using high eta values may result in
@@ -583,14 +585,14 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' # For xgb.cv:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-#'              callbacks = list(cb.gblinear.history()))
+#'               callbacks = list(cb.gblinear.history()))
 #' # coefficients in the CV fold #3
 #' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 #'
 #'
 #' #### Multiclass classification:
 #' #
-#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
+#' dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 2)
 #' param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
 #'               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 #' # For the default linear updater 'shotgun' it sometimes is helpful

R-package/R/xgb.DMatrix.R

@@ -18,7 +18,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 #' dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 #' if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')
@@ -110,7 +110,7 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL, nth
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 #'
 #' stopifnot(nrow(dtrain) == nrow(train$data))
 #' stopifnot(ncol(dtrain) == ncol(train$data))
@@ -138,7 +138,7 @@ dim.xgb.DMatrix <- function(x) {
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' train <- agaricus.train
-#' dtrain <- xgb.DMatrix(train$data, label=train$label)
+#' dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 #' dimnames(dtrain)
 #' colnames(dtrain)
 #' colnames(dtrain) <- make.names(1:ncol(train$data))
@@ -193,7 +193,7 @@ dimnames.xgb.DMatrix <- function(x) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -249,7 +249,7 @@ getinfo.xgb.DMatrix <- function(object, name, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' labels <- getinfo(dtrain, 'label')
 #' setinfo(dtrain, 'label', 1-labels)
@@ -345,7 +345,7 @@ setinfo.xgb.DMatrix <- function(object, name, info, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' dsub <- slice(dtrain, 1:42)
 #' labels1 <- getinfo(dsub, 'label')
@@ -401,7 +401,7 @@ slice.xgb.DMatrix <- function(object, idxset, ...) {
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' dtrain
 #' print(dtrain, verbose=TRUE)

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

@@ -7,7 +7,7 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' 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/R/xgb.create.features.R

@@ -48,8 +48,8 @@
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 #'
 #' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 #' nrounds = 4
@@ -65,8 +65,12 @@
 #' 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$label)
+#' new.dtrain <- xgb.DMatrix(
+#'   data = new.features.train, label = agaricus.train$label, nthread = 2
+#' )
+#' new.dtest <- xgb.DMatrix(
+#'   data = new.features.test, label = agaricus.test$label, nthread = 2
+#' )
 #' watchlist <- list(train = new.dtrain)
 #' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 #'
@@ -79,7 +83,7 @@
 #'           accuracy.after, "!\n"))
 #'
 #' @export
-xgb.create.features <- function(model, data, ...){
+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)

R-package/R/xgb.cv.R

@@ -110,9 +110,9 @@
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-#'                   max_depth = 3, eta = 1, objective = "binary:logistic")
+#'              max_depth = 3, eta = 1, objective = "binary:logistic")
 #' print(cv)
 #' print(cv, verbose=TRUE)
 #'
@@ -192,7 +192,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 
   # create the booster-folds
   # train_folds
-  dall <- xgb.get.DMatrix(data, label, missing)
+  dall <- xgb.get.DMatrix(data, label, missing, nthread = params$nthread)
   bst_folds <- lapply(seq_along(folds), function(k) {
     dtest  <- slice(dall, folds[[k]])
     # code originally contributed by @RolandASc on stackoverflow

R-package/R/xgb.train.R

@@ -192,8 +192,8 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #'
-#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+#' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+#' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 #' watchlist <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for xgboost 1.7.0.
+# Generated by GNU Autoconf 2.69 for xgboost 1.7.3.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -576,8 +576,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='1.7.0'
-PACKAGE_STRING='xgboost 1.7.0'
+PACKAGE_VERSION='1.7.3'
+PACKAGE_STRING='xgboost 1.7.3'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1195,7 +1195,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures xgboost 1.7.0 to adapt to many kinds of systems.
+\`configure' configures xgboost 1.7.3 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1257,7 +1257,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 1.7.0:";;
+     short | recursive ) echo "Configuration of xgboost 1.7.3:";;
    esac
   cat <<\_ACEOF
 
@@ -1336,7 +1336,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 1.7.0
+xgboost configure 1.7.3
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1479,7 +1479,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by xgboost $as_me 1.7.0, which was
+It was created by xgboost $as_me 1.7.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -3294,7 +3294,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by xgboost $as_me 1.7.0, which was
+This file was extended by xgboost $as_me 1.7.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3347,7 +3347,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-xgboost config.status 1.7.0
+xgboost config.status 1.7.3
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[1.7.0],[],[xgboost],[])
+AC_INIT([xgboost],[1.7.3],[],[xgboost],[])
 
 # Use this line to set CC variable to a C compiler
 AC_PROG_CC

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

@@ -15,9 +15,11 @@ selected per iteration.}
 }
 \value{
 Results are stored in the \code{coefs} element of the closure.
-The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
+The \code{\link{xgb.gblinear.history}} convenience function provides an easy
+way to access it.
 With \code{xgb.train}, it is either a dense of a sparse matrix.
-While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
+While with \code{xgb.cv}, it is a list (an element per each fold) of such
+matrices.
 }
 \description{
 Callback closure for collecting the model coefficients history of a gblinear booster
@@ -38,7 +40,7 @@ Callback function expects the following values to be set in its calling frame:
 # without considering the 2nd order interactions:
 x <- model.matrix(Species ~ .^2, iris)[,-1]
 colnames(x)
-dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
+dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"), nthread = 2)
 param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For 'shotgun', which is a default linear updater, using high eta values may result in
@@ -63,14 +65,14 @@ matplot(xgb.gblinear.history(bst), type = 'l')
 
 # For xgb.cv:
 bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
-             callbacks = list(cb.gblinear.history()))
+              callbacks = list(cb.gblinear.history()))
 # coefficients in the CV fold #3
 matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
 
 
 #### Multiclass classification:
 #
-dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1, nthread = 2)
 param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
               lambda = 0.0003, alpha = 0.0003, nthread = 2)
 # For the default linear updater 'shotgun' it sometimes is helpful

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

@@ -19,7 +19,7 @@ be directly used with an \code{xgb.DMatrix} object.
 \examples{
 data(agaricus.train, package='xgboost')
 train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
+dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 
 stopifnot(nrow(dtrain) == nrow(train$data))
 stopifnot(ncol(dtrain) == ncol(train$data))

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

@@ -26,7 +26,7 @@ Since row names are irrelevant, it is recommended to use \code{colnames} directl
 \examples{
 data(agaricus.train, package='xgboost')
 train <- agaricus.train
-dtrain <- xgb.DMatrix(train$data, label=train$label)
+dtrain <- xgb.DMatrix(train$data, label=train$label, nthread = 2)
 dimnames(dtrain)
 colnames(dtrain)
 colnames(dtrain) <- make.names(1:ncol(train$data))

R-package/man/getinfo.Rd

@@ -34,7 +34,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

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

@@ -19,7 +19,7 @@ Currently it displays dimensions and presence of info-fields and colnames.
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 
 dtrain
 print(dtrain, verbose=TRUE)

R-package/man/setinfo.Rd

@@ -33,7 +33,7 @@ The \code{name} field can be one of the following:
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 
 labels <- getinfo(dtrain, 'label')
 setinfo(dtrain, 'label', 1-labels)

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

@@ -28,7 +28,7 @@ original xgb.DMatrix object
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 
 dsub <- slice(dtrain, 1:42)
 labels1 <- getinfo(dsub, 'label')

R-package/man/xgb.DMatrix.Rd

@@ -38,7 +38,7 @@ Supported input file formats are either a LIBSVM text file or a binary file that
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')

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

@@ -16,7 +16,7 @@ Save xgb.DMatrix object to binary file
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 xgb.DMatrix.save(dtrain, 'xgb.DMatrix.data')
 dtrain <- xgb.DMatrix('xgb.DMatrix.data')
 if (file.exists('xgb.DMatrix.data')) file.remove('xgb.DMatrix.data')

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

@@ -59,8 +59,8 @@ a rule on certain features."
 \examples{
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 nrounds = 4
@@ -76,8 +76,12 @@ 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)
+new.dtrain <- xgb.DMatrix(
+  data = new.features.train, label = agaricus.train$label, nthread = 2
+)
+new.dtest <- xgb.DMatrix(
+  data = new.features.test, label = agaricus.test$label, nthread = 2
+)
 watchlist <- list(train = new.dtrain)
 bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 

R-package/man/xgb.cv.Rd

@@ -158,9 +158,9 @@ Adapted from \url{https://en.wikipedia.org/wiki/Cross-validation_\%28statistics\
 }
 \examples{
 data(agaricus.train, package='xgboost')
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 cv <- xgb.cv(data = dtrain, nrounds = 3, nthread = 2, nfold = 5, metrics = list("rmse","auc"),
-                  max_depth = 3, eta = 1, objective = "binary:logistic")
+             max_depth = 3, eta = 1, objective = "binary:logistic")
 print(cv)
 print(cv, verbose=TRUE)
 

R-package/man/xgb.train.Rd

@@ -241,8 +241,8 @@ The following callbacks are automatically created when certain parameters are se
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
 
-dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label))
-dtest <- with(agaricus.test, xgb.DMatrix(data, label = label))
+dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
+dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 watchlist <- list(train = dtrain, eval = dtest)
 
 ## A simple xgb.train example:

doc/contrib/release.rst

@@ -4,7 +4,7 @@ XGBoost Release Policy
 =======================
 
 Versioning Policy
----------------------------
+-----------------
 
 Starting from XGBoost 1.0.0, each XGBoost release will be versioned as [MAJOR].[FEATURE].[MAINTENANCE]
 
@@ -34,6 +34,20 @@ Making a Release
 
    + The CRAN package is maintained by `Tong He <https://github.com/hetong007>`_ and `Jiaming Yuan <https://github.com/trivialfis>`__.
 
-     Before submitting a release, one should test the package on `R-hub <https://builder.r-hub.io/>`__ and `win-builder <https://win-builder.r-project.org/>`__ first.  Please note that the R-hub Windows instance doesn't have the exact same environment as the one hosted on win-builder.
-
    + The Maven package is maintained by `Nan Zhu <https://github.com/CodingCat>`_ and `Hyunsu Cho <https://github.com/hcho3>`_.
+
+
+R CRAN Package
+--------------
+Before submitting a release, one should test the package on `R-hub <https://builder.r-hub.io/>`__ and `win-builder <https://win-builder.r-project.org/>`__ first.  Please note that the R-hub Windows instance doesn't have the exact same environment as the one hosted on win-builder.
+
+According to the `CRAN policy <https://cran.r-project.org/web/packages/policies.html>`__:
+
+    If running a package uses multiple threads/cores it must never use more than two simultaneously: the check farm is a shared resource and will typically be running many checks simultaneously.
+
+We need to check the number of CPUs used in examples. Export ``_R_CHECK_EXAMPLE_TIMING_CPU_TO_ELAPSED_THRESHOLD_=2.5`` before running ``R CMD check --as-cran`` `[1] <#references>`__ and make sure the machine you are using has enough CPU cores to reveal any potential policy violation.
+
+References
+----------
+
+[1] https://stat.ethz.ch/pipermail/r-package-devel/2022q4/008610.html

doc/parameter.rst

@@ -44,8 +44,7 @@ General Parameters
 * ``validate_parameters`` [default to ``false``, except for Python, R and CLI interface]
 
   - When set to True, XGBoost will perform validation of input parameters to check whether
-    a parameter is used or not.  The feature is still experimental.  It's expected to have
-    some false positives.
+    a parameter is used or not.
 
 * ``nthread`` [default to maximum number of threads available if not set]
 
@@ -233,24 +232,21 @@ Parameters for Categorical Feature
 These parameters are only used for training with categorical data. See
 :doc:`/tutorials/categorical` for more information.
 
+.. note:: These parameters are experimental. ``exact`` tree method is not yet supported.
+
+
 * ``max_cat_to_onehot``
 
   .. versionadded:: 1.6.0
 
-  .. note:: This parameter is experimental. ``exact`` tree method is not yet supported.
-
   - A threshold for deciding whether XGBoost should use one-hot encoding based split for
     categorical data.  When number of categories is lesser than the threshold then one-hot
     encoding is chosen, otherwise the categories will be partitioned into children nodes.
-    Only relevant for regression and binary classification. Also, ``exact`` tree method is
-    not supported
 
 * ``max_cat_threshold``
 
   .. versionadded:: 1.7.0
 
-  .. note:: This parameter is experimental. ``exact`` tree method is not yet supported.
-
   - Maximum number of categories considered for each split. Used only by partition-based
     splits for preventing over-fitting.
 

doc/python/python_api.rst

@@ -25,9 +25,6 @@ Core Data Structure
 .. autoclass:: xgboost.QuantileDMatrix
     :show-inheritance:
 
-.. autoclass:: xgboost.DeviceQuantileDMatrix
-    :show-inheritance:
-
 .. autoclass:: xgboost.Booster
     :members:
     :show-inheritance:
@@ -115,7 +112,7 @@ Dask API
     :inherited-members:
     :show-inheritance:
 
-.. autoclass:: xgboost.dask.DaskDeviceQuantileDMatrix
+.. autoclass:: xgboost.dask.DaskQuantileDMatrix
     :members:
     :inherited-members:
     :show-inheritance:

doc/tutorials/categorical.rst

@@ -138,11 +138,11 @@ Miscellaneous
 
 By default, XGBoost assumes input categories are integers starting from 0 till the number
 of categories :math:`[0, n\_categories)`. However, user might provide inputs with invalid
-values due to mistakes or missing values. It can be negative value, integer values that
-can not be accurately represented by 32-bit floating point, or values that are larger than
-actual number of unique categories.  During training this is validated but for prediction
-it's treated as the same as missing value for performance reasons.  Lastly, missing values
-are treated as the same as numerical features (using the learned split direction).
+values due to mistakes or missing values in training dataset. It can be negative value,
+integer values that can not be accurately represented by 32-bit floating point, or values
+that are larger than actual number of unique categories.  During training this is
+validated but for prediction it's treated as the same as not-chosen category for
+performance reasons.
 
 
 **********

doc/tutorials/dask.rst

@@ -564,7 +564,7 @@ Here are some pratices on reducing memory usage with dask and xgboost.
   nice summary.
 
 - When using GPU input, like dataframe loaded by ``dask_cudf``, you can try
-  :py:class:`xgboost.dask.DaskDeviceQuantileDMatrix` as a drop in replacement for ``DaskDMatrix``
+  :py:class:`xgboost.dask.DaskQuantileDMatrix` as a drop in replacement for ``DaskDMatrix``
   to reduce overall memory usage.  See
   :ref:`sphx_glr_python_dask-examples_gpu_training.py` for an example.
 

include/xgboost/collective/socket.h

@@ -287,11 +287,22 @@ class TCPSocket {
 #elif defined(__APPLE__)
     return domain_;
 #elif defined(__unix__)
+#ifndef __PASE__
     std::int32_t domain;
     socklen_t len = sizeof(domain);
     xgboost_CHECK_SYS_CALL(
         getsockopt(handle_, SOL_SOCKET, SO_DOMAIN, reinterpret_cast<char *>(&domain), &len), 0);
     return ret_iafamily(domain);
+#else
+    struct sockaddr sa;
+    socklen_t sizeofsa = sizeof(sa);
+    xgboost_CHECK_SYS_CALL(
+      getsockname(handle_, &sa, &sizeofsa), 0);
+    if (sizeofsa < sizeof(uchar_t)*2) {
+      return ret_iafamily(AF_INET);
+    }
+    return ret_iafamily(sa.sa_family);
+#endif   // __PASE__
 #else
     LOG(FATAL) << "Unknown platform.";
     return ret_iafamily(AF_INET);

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 1
 #define XGBOOST_VER_MINOR 7
-#define XGBOOST_VER_PATCH 0
+#define XGBOOST_VER_PATCH 3
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.3</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>1.7.0</version>
+        <version>1.7.3</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.3</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.3</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.3</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>1.7.0</version>
+        <version>1.7.3</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.3</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.3</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>1.7.0</version>
+        <version>1.7.3</version>
     </parent>
     <artifactId>xgboost4j-gpu_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.3</version>
     <packaging>jar</packaging>
 
     <dependencies>

jvm-packages/xgboost4j-gpu/src/native/xgboost4j-gpu.cu

@@ -1,7 +1,7 @@
 #include <jni.h>
-#include <thrust/system/cuda/experimental/pinned_allocator.h>
 
 #include "../../../../src/common/device_helpers.cuh"
+#include "../../../../src/common/cuda_pinned_allocator.h"
 #include "../../../../src/data/array_interface.h"
 #include "jvm_utils.h"
 #include <xgboost/c_api.h>
@@ -131,7 +131,7 @@ class DataIteratorProxy {
   bool cache_on_host_{true}; // TODO(Bobby): Make this optional.
 
   template <typename T>
-  using Alloc = thrust::system::cuda::experimental::pinned_allocator<T>;
+  using Alloc = xgboost::common::cuda::pinned_allocator<T>;
   template <typename U>
   using HostVector = std::vector<U, Alloc<U>>;
 

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

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.3</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>1.7.0</version>
+            <version>1.7.3</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>1.7.0</version>
+        <version>1.7.3</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>1.7.0</version>
+            <version>1.7.3</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j-tester/get_iris.py

@@ -1,9 +1,9 @@
-from sklearn.datasets import load_iris
 import numpy as np
 import pandas
+from sklearn.datasets import load_iris
 
 X, y = load_iris(return_X_y=True)
-y = y.astype(np.int)
+y = y.astype(np.int32)
 df = pandas.DataFrame(data=X, columns=['sepal length', 'sepal width', 'petal length', 'petal width'])
 class_id_to_name = {0:'Iris-setosa', 1:'Iris-versicolor', 2:'Iris-virginica'}
 df['class'] = np.vectorize(class_id_to_name.get)(y)

jvm-packages/xgboost4j/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.3</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.3</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.7.0
+1.7.3

python-package/xgboost/__init__.py

@@ -4,7 +4,7 @@ Contributors: https://github.com/dmlc/xgboost/blob/master/CONTRIBUTORS.md
 """
 
 from . import tracker  # noqa
-from . import collective, dask
+from . import collective, dask, rabit
 from .core import (
     Booster,
     DataIter,

python-package/xgboost/compat.py

@@ -43,6 +43,7 @@ except ImportError:
     pandas_concat = None
     PANDAS_INSTALLED = False
 
+
 # sklearn
 try:
     from sklearn.base import BaseEstimator as XGBModelBase
@@ -72,6 +73,22 @@ except ImportError:
     XGBStratifiedKFold = None
 
 
+_logger = logging.getLogger(__name__)
+
+
+def is_cudf_available() -> bool:
+    """Check cuDF package available or not"""
+    if importlib.util.find_spec("cudf") is None:
+        return False
+    try:
+        import cudf
+
+        return True
+    except ImportError:
+        _logger.exception("Importing cuDF failed, use DMatrix instead of QDM")
+        return False
+
+
 class XGBoostLabelEncoder(LabelEncoder):
     """Label encoder with JSON serialization methods."""
 

python-package/xgboost/dask.py

@@ -853,7 +853,7 @@ async def _get_rabit_args(
         sched_addr = None
 
     # make sure all workers are online so that we can obtain reliable scheduler_info
-    client.wait_for_workers(n_workers)
+    await client.wait_for_workers(n_workers)  # type: ignore
     env = await client.run_on_scheduler(
         _start_tracker, n_workers, sched_addr, user_addr
     )

python-package/xgboost/rabit.py

@@ -0,0 +1,168 @@
+"""Compatibility shim for xgboost.rabit; to be removed in 2.0"""
+import logging
+import warnings
+from enum import IntEnum, unique
+from typing import Any, TypeVar, Callable, Optional, List
+
+import numpy as np
+
+from . import collective
+
+LOGGER = logging.getLogger("[xgboost.rabit]")
+
+
+def _deprecation_warning() -> str:
+    return (
+        "The xgboost.rabit submodule is marked as deprecated in 1.7 and will be removed "
+        "in 2.0. Please use xgboost.collective instead."
+    )
+
+
+def init(args: Optional[List[bytes]] = None) -> None:
+    """Initialize the rabit library with arguments"""
+    warnings.warn(_deprecation_warning(), FutureWarning)
+    parsed = {}
+    if args:
+        for arg in args:
+            kv = arg.decode().split('=')
+            if len(kv) == 2:
+                parsed[kv[0]] = kv[1]
+    collective.init(**parsed)
+
+
+def finalize() -> None:
+    """Finalize the process, notify tracker everything is done."""
+    collective.finalize()
+
+
+def get_rank() -> int:
+    """Get rank of current process.
+    Returns
+    -------
+    rank : int
+        Rank of current process.
+    """
+    return collective.get_rank()
+
+
+def get_world_size() -> int:
+    """Get total number workers.
+    Returns
+    -------
+    n : int
+        Total number of process.
+    """
+    return collective.get_world_size()
+
+
+def is_distributed() -> int:
+    """If rabit is distributed."""
+    return collective.is_distributed()
+
+
+def tracker_print(msg: Any) -> None:
+    """Print message to the tracker.
+    This function can be used to communicate the information of
+    the progress to the tracker
+    Parameters
+    ----------
+    msg : str
+        The message to be printed to tracker.
+    """
+    collective.communicator_print(msg)
+
+
+def get_processor_name() -> bytes:
+    """Get the processor name.
+    Returns
+    -------
+    name : str
+        the name of processor(host)
+    """
+    return collective.get_processor_name().encode()
+
+
+T = TypeVar("T")  # pylint:disable=invalid-name
+
+
+def broadcast(data: T, root: int) -> T:
+    """Broadcast object from one node to all other nodes.
+    Parameters
+    ----------
+    data : any type that can be pickled
+        Input data, if current rank does not equal root, this can be None
+    root : int
+        Rank of the node to broadcast data from.
+    Returns
+    -------
+    object : int
+        the result of broadcast.
+    """
+    return collective.broadcast(data, root)
+
+
+@unique
+class Op(IntEnum):
+    """Supported operations for rabit."""
+    MAX = 0
+    MIN = 1
+    SUM = 2
+    OR = 3
+
+
+def allreduce(  # pylint:disable=invalid-name
+        data: np.ndarray, op: Op, prepare_fun: Optional[Callable[[np.ndarray], None]] = None
+) -> np.ndarray:
+    """Perform allreduce, return the result.
+    Parameters
+    ----------
+    data :
+        Input data.
+    op :
+        Reduction operators, can be MIN, MAX, SUM, BITOR
+    prepare_fun :
+        Lazy preprocessing function, if it is not None, prepare_fun(data)
+        will be called by the function before performing allreduce, to initialize the data
+        If the result of Allreduce can be recovered directly,
+        then prepare_fun will NOT be called
+    Returns
+    -------
+    result :
+        The result of allreduce, have same shape as data
+    Notes
+    -----
+    This function is not thread-safe.
+    """
+    if prepare_fun is None:
+        return collective.allreduce(data, collective.Op(op))
+    raise Exception("preprocessing function is no longer supported")
+
+
+def version_number() -> int:
+    """Returns version number of current stored model.
+    This means how many calls to CheckPoint we made so far.
+    Returns
+    -------
+    version : int
+        Version number of currently stored model
+    """
+    return 0
+
+
+class RabitContext:
+    """A context controlling rabit initialization and finalization."""
+
+    def __init__(self, args: List[bytes] = None) -> None:
+        if args is None:
+            args = []
+        self.args = args
+
+    def __enter__(self) -> None:
+        init(self.args)
+        assert is_distributed()
+        LOGGER.warning(_deprecation_warning())
+        LOGGER.debug("-------------- rabit say hello ------------------")
+
+    def __exit__(self, *args: List) -> None:
+        finalize()
+        LOGGER.debug("--------------- rabit say bye ------------------")

python-package/xgboost/sklearn.py

@@ -674,7 +674,7 @@ class XGBModel(XGBModelBase):
                     self.kwargs = {}
                 self.kwargs[key] = value
 
-        if hasattr(self, "_Booster"):
+        if self.__sklearn_is_fitted__():
             parameters = self.get_xgb_params()
             self.get_booster().set_param(parameters)
 
@@ -701,39 +701,12 @@ class XGBModel(XGBModelBase):
                 np.iinfo(np.int32).max
             )
 
-        def parse_parameter(value: Any) -> Optional[Union[int, float, str]]:
-            for t in (int, float, str):
-                try:
-                    ret = t(value)
-                    return ret
-                except ValueError:
-                    continue
-            return None
-
-        # Get internal parameter values
-        try:
-            config = json.loads(self.get_booster().save_config())
-            stack = [config]
-            internal = {}
-            while stack:
-                obj = stack.pop()
-                for k, v in obj.items():
-                    if k.endswith("_param"):
-                        for p_k, p_v in v.items():
-                            internal[p_k] = p_v
-                    elif isinstance(v, dict):
-                        stack.append(v)
-
-            for k, v in internal.items():
-                if k in params and params[k] is None:
-                    params[k] = parse_parameter(v)
-        except ValueError:
-            pass
         return params
 
     def get_xgb_params(self) -> Dict[str, Any]:
         """Get xgboost specific parameters."""
-        params = self.get_params()
+        params: Dict[str, Any] = self.get_params()
+
         # Parameters that should not go into native learner.
         wrapper_specific = {
             "importance_type",
@@ -750,6 +723,7 @@ class XGBModel(XGBModelBase):
         for k, v in params.items():
             if k not in wrapper_specific and not callable(v):
                 filtered[k] = v
+
         return filtered
 
     def get_num_boosting_rounds(self) -> int:
@@ -1070,7 +1044,7 @@ class XGBModel(XGBModelBase):
         # error with incompatible data type.
         # Inplace predict doesn't handle as many data types as DMatrix, but it's
         # sufficient for dask interface where input is simpiler.
-        predictor = self.get_params().get("predictor", None)
+        predictor = self.get_xgb_params().get("predictor", None)
         if predictor in ("auto", None) and self.booster != "gblinear":
             return True
         return False
@@ -1336,7 +1310,7 @@ class XGBModel(XGBModelBase):
         -------
         coef_ : array of shape ``[n_features]`` or ``[n_classes, n_features]``
         """
-        if self.get_params()["booster"] != "gblinear":
+        if self.get_xgb_params()["booster"] != "gblinear":
             raise AttributeError(
                 f"Coefficients are not defined for Booster type {self.booster}"
             )
@@ -1366,7 +1340,7 @@ class XGBModel(XGBModelBase):
         -------
         intercept_ : array of shape ``(1,)`` or ``[n_classes]``
         """
-        if self.get_params()["booster"] != "gblinear":
+        if self.get_xgb_params()["booster"] != "gblinear":
             raise AttributeError(
                 f"Intercept (bias) is not defined for Booster type {self.booster}"
             )

python-package/xgboost/spark/core.py

@@ -1,7 +1,7 @@
 # type: ignore
 """Xgboost pyspark integration submodule for core code."""
 # pylint: disable=fixme, too-many-ancestors, protected-access, no-member, invalid-name
-# pylint: disable=too-few-public-methods, too-many-lines
+# pylint: disable=too-few-public-methods, too-many-lines, too-many-branches
 import json
 from typing import Iterator, Optional, Tuple
 
@@ -32,6 +32,7 @@ from pyspark.sql.types import (
     ShortType,
 )
 from scipy.special import expit, softmax  # pylint: disable=no-name-in-module
+from xgboost.compat import is_cudf_available
 from xgboost.core import Booster
 from xgboost.training import train as worker_train
 
@@ -728,6 +729,10 @@ class _SparkXGBEstimator(Estimator, _SparkXGBParams, MLReadable, MLWritable):
             else:
                 dataset = dataset.repartition(num_workers)
 
+        if self.isDefined(self.qid_col) and self.getOrDefault(self.qid_col):
+            # XGBoost requires qid to be sorted for each partition
+            dataset = dataset.sortWithinPartitions(alias.qid, ascending=True)
+
         train_params = self._get_distributed_train_params(dataset)
         booster_params, train_call_kwargs_params = self._get_xgb_train_call_args(
             train_params
@@ -755,7 +760,8 @@ class _SparkXGBEstimator(Estimator, _SparkXGBParams, MLReadable, MLWritable):
             k: v for k, v in train_call_kwargs_params.items() if v is not None
         }
         dmatrix_kwargs = {k: v for k, v in dmatrix_kwargs.items() if v is not None}
-        use_qdm = booster_params.get("tree_method", None) in ("hist", "gpu_hist")
+
+        use_hist = booster_params.get("tree_method", None) in ("hist", "gpu_hist")
 
         def _train_booster(pandas_df_iter):
             """Takes in an RDD partition and outputs a booster for that partition after
@@ -769,6 +775,15 @@ class _SparkXGBEstimator(Estimator, _SparkXGBParams, MLReadable, MLWritable):
 
             gpu_id = None
 
+            # If cuDF is not installed, then using DMatrix instead of QDM,
+            # because without cuDF, DMatrix performs better than QDM.
+            # Note: Checking `is_cudf_available` in spark worker side because
+            # spark worker might has different python environment with driver side.
+            if use_gpu:
+                use_qdm = use_hist and is_cudf_available()
+            else:
+                use_qdm = use_hist
+
             if use_qdm and (booster_params.get("max_bin", None) is not None):
                 dmatrix_kwargs["max_bin"] = booster_params["max_bin"]
 

src/common/categorical.h

@@ -48,20 +48,21 @@ inline XGBOOST_DEVICE bool InvalidCat(float cat) {
   return cat < 0 || cat >= kMaxCat;
 }
 
-/* \brief Whether should it traverse to left branch of a tree.
+/**
+ * \brief Whether should it traverse to left branch of a tree.
  *
- *  For one hot split, go to left if it's NOT the matching category.
+ *   Go to left if it's NOT the matching category, which matches one-hot encoding.
  */
-template <bool validate = true>
-inline XGBOOST_DEVICE bool Decision(common::Span<uint32_t const> cats, float cat, bool dft_left) {
+inline XGBOOST_DEVICE bool Decision(common::Span<uint32_t const> cats, float cat) {
   KCatBitField const s_cats(cats);
-  // FIXME: Size() is not accurate since it represents the size of bit set instead of
-  // actual number of categories.
-  if (XGBOOST_EXPECT(validate && (InvalidCat(cat) || cat >= s_cats.Size()), false)) {
-    return dft_left;
+  if (XGBOOST_EXPECT(InvalidCat(cat), false)) {
+    return true;
   }
 
   auto pos = KCatBitField::ToBitPos(cat);
+  // If the input category is larger than the size of the bit field, it implies that the
+  // category is not chosen. Otherwise the bit field would have the category instead of
+  // being smaller than the category value.
   if (pos.int_pos >= cats.size()) {
     return true;
   }

src/common/cuda_pinned_allocator.h

@@ -0,0 +1,91 @@
+/*!
+ * Copyright 2022 by XGBoost Contributors
+ * \file common.h
+ * \brief cuda pinned allocator for usage with thrust containers
+ */
+
+#pragma once
+
+#include <cstddef>
+#include <limits>
+
+#include "common.h"
+
+namespace xgboost {
+namespace common {
+namespace cuda {
+
+// \p pinned_allocator is a CUDA-specific host memory allocator
+//  that employs \c cudaMallocHost for allocation.
+//
+// This implementation is ported from the experimental/pinned_allocator
+// that Thrust used to provide.
+//
+//  \see https://en.cppreference.com/w/cpp/memory/allocator
+template <typename T>
+class pinned_allocator;
+
+template <>
+class pinned_allocator<void> {
+ public:
+  using value_type      = void;            // NOLINT: The type of the elements in the allocator
+  using pointer         = void*;           // NOLINT: The type returned by address() / allocate()
+  using const_pointer   = const void*;     // NOLINT: The type returned by address()
+  using size_type       = std::size_t;     // NOLINT: The type used for the size of the allocation
+  using difference_type = std::ptrdiff_t;  // NOLINT: The type of the distance between two pointers
+
+  template <typename U>
+  struct rebind {                       // NOLINT
+    using other = pinned_allocator<U>;  // NOLINT: The rebound type
+  };
+};
+
+
+template <typename T>
+class pinned_allocator {
+ public:
+  using value_type      = T;               // NOLINT: The type of the elements in the allocator
+  using pointer         = T*;              // NOLINT: The type returned by address() / allocate()
+  using const_pointer   = const T*;        // NOLINT: The type returned by address()
+  using reference       = T&;              // NOLINT: The parameter type for address()
+  using const_reference = const T&;        // NOLINT: The parameter type for address()
+  using size_type       = std::size_t;     // NOLINT: The type used for the size of the allocation
+  using difference_type = std::ptrdiff_t;  // NOLINT: The type of the distance between two pointers
+
+  template <typename U>
+  struct rebind {                       // NOLINT
+    using other = pinned_allocator<U>;  // NOLINT: The rebound type
+  };
+
+  XGBOOST_DEVICE inline pinned_allocator() {}; // NOLINT: host/device markup ignored on defaulted functions
+  XGBOOST_DEVICE inline ~pinned_allocator() {} // NOLINT: host/device markup ignored on defaulted functions
+  XGBOOST_DEVICE inline pinned_allocator(pinned_allocator const&) {} // NOLINT: host/device markup ignored on defaulted functions
+
+
+  template <typename U>
+  XGBOOST_DEVICE inline pinned_allocator(pinned_allocator<U> const&) {} // NOLINT
+
+  XGBOOST_DEVICE inline pointer address(reference r) { return &r; } // NOLINT
+  XGBOOST_DEVICE inline const_pointer address(const_reference r) { return &r; } // NOLINT
+
+  inline pointer allocate(size_type cnt, const_pointer = nullptr) { // NOLINT
+    if (cnt > this->max_size()) { throw std::bad_alloc(); }  // end if
+
+    pointer result(nullptr);
+    dh::safe_cuda(cudaMallocHost(reinterpret_cast<void**>(&result), cnt * sizeof(value_type)));
+    return result;
+  }
+
+  inline void deallocate(pointer p, size_type) { dh::safe_cuda(cudaFreeHost(p)); } // NOLINT
+
+  inline size_type max_size() const { return (std::numeric_limits<size_type>::max)() / sizeof(T); } // NOLINT
+
+  XGBOOST_DEVICE inline bool operator==(pinned_allocator const& x) const { return true; }
+
+  XGBOOST_DEVICE inline bool operator!=(pinned_allocator const& x) const {
+    return !operator==(x);
+  }
+};
+}  // namespace cuda
+}  // namespace common
+}  // namespace xgboost

src/common/linalg_op.h

@@ -62,7 +62,7 @@ void ElementWiseKernel(GenericParameter const* ctx, linalg::TensorView<T, D> t,
 #endif  // !defined(XGBOOST_USE_CUDA)
 
 template <typename T, std::int32_t kDim>
-auto cbegin(TensorView<T, kDim> v) {  // NOLINT
+auto cbegin(TensorView<T, kDim> const& v) {  // NOLINT
   auto it = common::MakeIndexTransformIter([&](size_t i) -> std::remove_cv_t<T> const& {
     return linalg::detail::Apply(v, linalg::UnravelIndex(i, v.Shape()));
   });
@@ -70,19 +70,19 @@ auto cbegin(TensorView<T, kDim> v) {  // NOLINT
 }
 
 template <typename T, std::int32_t kDim>
-auto cend(TensorView<T, kDim> v) {  // NOLINT
+auto cend(TensorView<T, kDim> const& v) {  // NOLINT
   return cbegin(v) + v.Size();
 }
 
 template <typename T, std::int32_t kDim>
-auto begin(TensorView<T, kDim> v) {  // NOLINT
+auto begin(TensorView<T, kDim>& v) {  // NOLINT
   auto it = common::MakeIndexTransformIter(
       [&](size_t i) -> T& { return linalg::detail::Apply(v, linalg::UnravelIndex(i, v.Shape())); });
   return it;
 }
 
 template <typename T, std::int32_t kDim>
-auto end(TensorView<T, kDim> v) {  // NOLINT
+auto end(TensorView<T, kDim>& v) {  // NOLINT
   return begin(v) + v.Size();
 }
 }  // namespace linalg

src/common/partition_builder.h

@@ -144,7 +144,7 @@ class PartitionBuilder {
         auto gidx = gidx_calc(ridx);
         bool go_left = default_left;
         if (gidx > -1) {
-          go_left = Decision(node_cats, cut_values[gidx], default_left);
+          go_left = Decision(node_cats, cut_values[gidx]);
         }
         return go_left;
       } else {
@@ -157,7 +157,7 @@ class PartitionBuilder {
       bool go_left = default_left;
       if (gidx > -1) {
         if (is_cat) {
-          go_left = Decision(node_cats, cut_values[gidx], default_left);
+          go_left = Decision(node_cats, cut_values[gidx]);
         } else {
           go_left = cut_values[gidx] <= nodes[node_in_set].split.split_value;
         }

src/data/array_interface.h

@@ -101,7 +101,7 @@ class ArrayInterfaceHandler {
   template <typename PtrType>
   static PtrType GetPtrFromArrayData(Object::Map const &obj) {
     auto data_it = obj.find("data");
-    if (data_it == obj.cend()) {
+    if (data_it == obj.cend() || IsA<Null>(data_it->second)) {
       LOG(FATAL) << "Empty data passed in.";
     }
     auto p_data = reinterpret_cast<PtrType>(
@@ -111,7 +111,7 @@ class ArrayInterfaceHandler {
 
   static void Validate(Object::Map const &array) {
     auto version_it = array.find("version");
-    if (version_it == array.cend()) {
+    if (version_it == array.cend() || IsA<Null>(version_it->second)) {
       LOG(FATAL) << "Missing `version' field for array interface";
     }
     if (get<Integer const>(version_it->second) > 3) {
@@ -119,17 +119,19 @@ class ArrayInterfaceHandler {
     }
 
     auto typestr_it = array.find("typestr");
-    if (typestr_it == array.cend()) {
+    if (typestr_it == array.cend() || IsA<Null>(typestr_it->second)) {
       LOG(FATAL) << "Missing `typestr' field for array interface";
     }
 
     auto typestr = get<String const>(typestr_it->second);
     CHECK(typestr.size() == 3 || typestr.size() == 4) << ArrayInterfaceErrors::TypestrFormat();
 
-    if (array.find("shape") == array.cend()) {
+    auto shape_it = array.find("shape");
+    if (shape_it == array.cend() || IsA<Null>(shape_it->second)) {
       LOG(FATAL) << "Missing `shape' field for array interface";
     }
-    if (array.find("data") == array.cend()) {
+    auto data_it = array.find("data");
+    if (data_it == array.cend() || IsA<Null>(data_it->second)) {
       LOG(FATAL) << "Missing `data' field for array interface";
     }
   }
@@ -139,8 +141,9 @@ class ArrayInterfaceHandler {
   static size_t ExtractMask(Object::Map const &column,
                             common::Span<RBitField8::value_type> *p_out) {
     auto &s_mask = *p_out;
-    if (column.find("mask") != column.cend()) {
-      auto const &j_mask = get<Object const>(column.at("mask"));
+    auto const &mask_it = column.find("mask");
+    if (mask_it != column.cend() && !IsA<Null>(mask_it->second)) {
+      auto const &j_mask = get<Object const>(mask_it->second);
       Validate(j_mask);
 
       auto p_mask = GetPtrFromArrayData<RBitField8::value_type *>(j_mask);
@@ -173,8 +176,9 @@ class ArrayInterfaceHandler {
       // assume 1 byte alignment.
       size_t const span_size = RBitField8::ComputeStorageSize(n_bits);
 
-      if (j_mask.find("strides") != j_mask.cend()) {
-        auto strides = get<Array const>(column.at("strides"));
+      auto strides_it = j_mask.find("strides");
+      if (strides_it != j_mask.cend() && !IsA<Null>(strides_it->second)) {
+        auto strides = get<Array const>(strides_it->second);
         CHECK_EQ(strides.size(), 1) << ArrayInterfaceErrors::Dimension(1);
         CHECK_EQ(get<Integer>(strides.at(0)), type_length) << ArrayInterfaceErrors::Contiguous();
       }
@@ -401,7 +405,9 @@ class ArrayInterface {
                             << "XGBoost doesn't support internal broadcasting.";
       }
     } else {
-      CHECK(array.find("mask") == array.cend()) << "Masked array is not yet supported.";
+      auto mask_it = array.find("mask");
+      CHECK(mask_it == array.cend() || IsA<Null>(mask_it->second))
+          << "Masked array is not yet supported.";
     }
 
     auto stream_it = array.find("stream");

src/gbm/gbtree.cc

@@ -28,6 +28,7 @@
 #include "xgboost/logging.h"
 #include "xgboost/objective.h"
 #include "xgboost/predictor.h"
+#include "xgboost/string_view.h"
 #include "xgboost/tree_updater.h"
 
 namespace xgboost {
@@ -395,23 +396,36 @@ void GBTree::LoadConfig(Json const& in) {
   tparam_.process_type = TreeProcessType::kDefault;
   int32_t const n_gpus = xgboost::common::AllVisibleGPUs();
   if (n_gpus == 0 && tparam_.predictor == PredictorType::kGPUPredictor) {
-    LOG(WARNING)
-        << "Loading from a raw memory buffer on CPU only machine.  "
-           "Changing predictor to auto.";
+    LOG(WARNING) << "Loading from a raw memory buffer on CPU only machine.  "
+                    "Changing predictor to auto.";
     tparam_.UpdateAllowUnknown(Args{{"predictor", "auto"}});
   }
+
+  auto msg = StringView{
+      R"(
+  Loading from a raw memory buffer (like pickle in Python, RDS in R) on a CPU-only
+  machine. Consider using `save_model/load_model` instead. See:
+
+    https://xgboost.readthedocs.io/en/latest/tutorials/saving_model.html
+
+  for more details about differences between saving model and serializing.)"};
+
   if (n_gpus == 0 && tparam_.tree_method == TreeMethod::kGPUHist) {
     tparam_.UpdateAllowUnknown(Args{{"tree_method", "hist"}});
-    LOG(WARNING)
-        << "Loading from a raw memory buffer on CPU only machine.  "
-           "Changing tree_method to hist.";
+    LOG(WARNING) << msg << "  Changing `tree_method` to `hist`.";
   }
 
   auto const& j_updaters = get<Object const>(in["updater"]);
   updaters_.clear();
+
   for (auto const& kv : j_updaters) {
-    std::unique_ptr<TreeUpdater> up(
-        TreeUpdater::Create(kv.first, ctx_, model_.learner_model_param->task));
+    auto name = kv.first;
+    if (n_gpus == 0 && name == "grow_gpu_hist") {
+      name = "grow_quantile_histmaker";
+      LOG(WARNING) << "Changing updater from `grow_gpu_hist` to `grow_quantile_histmaker`.";
+    }
+    std::unique_ptr<TreeUpdater> up{
+        TreeUpdater::Create(name, ctx_, model_.learner_model_param->task)};
     up->LoadConfig(kv.second);
     updaters_.push_back(std::move(up));
   }

src/predictor/predict_fn.h

@@ -18,9 +18,7 @@ inline XGBOOST_DEVICE bst_node_t GetNextNode(const RegTree::Node &node, const bs
     if (has_categorical && common::IsCat(cats.split_type, nid)) {
       auto node_categories =
           cats.categories.subspan(cats.node_ptr[nid].beg, cats.node_ptr[nid].size);
-      return common::Decision<true>(node_categories, fvalue, node.DefaultLeft())
-                 ? node.LeftChild()
-                 : node.RightChild();
+      return common::Decision(node_categories, fvalue) ? node.LeftChild() : node.RightChild();
     } else {
       return node.LeftChild() + !(fvalue < node.SplitCond());
     }

src/tree/gpu_hist/evaluate_splits.cuh

@@ -3,10 +3,10 @@
  */
 #ifndef EVALUATE_SPLITS_CUH_
 #define EVALUATE_SPLITS_CUH_
-#include <thrust/system/cuda/experimental/pinned_allocator.h>
 #include <xgboost/span.h>
 
 #include "../../common/categorical.h"
+#include "../../common/cuda_pinned_allocator.h"
 #include "../split_evaluator.h"
 #include "../updater_gpu_common.cuh"
 #include "expand_entry.cuh"
@@ -57,7 +57,7 @@ struct CatAccessor {
 class GPUHistEvaluator {
   using CatST = common::CatBitField::value_type;  // categorical storage type
   // use pinned memory to stage the categories, used for sort based splits.
-  using Alloc = thrust::system::cuda::experimental::pinned_allocator<CatST>;
+  using Alloc = xgboost::common::cuda::pinned_allocator<CatST>;
 
  private:
   TreeEvaluator tree_evaluator_;

src/tree/updater_gpu_hist.cu

@@ -403,8 +403,7 @@ struct GPUHistMakerDevice {
             go_left = data.split_node.DefaultLeft();
           } else {
             if (data.split_type == FeatureType::kCategorical) {
-              go_left = common::Decision<false>(data.node_cats.Bits(), cut_value,
-                                                data.split_node.DefaultLeft());
+              go_left = common::Decision(data.node_cats.Bits(), cut_value);
             } else {
               go_left = cut_value <= data.split_node.SplitCond();
             }
@@ -481,7 +480,7 @@ struct GPUHistMakerDevice {
           if (common::IsCat(d_feature_types, position)) {
             auto node_cats = categories.subspan(categories_segments[position].beg,
                                                 categories_segments[position].size);
-            go_left = common::Decision<false>(node_cats, element, node.DefaultLeft());
+            go_left = common::Decision(node_cats, element);
           } else {
             go_left = element <= node.SplitCond();
           }

tests/buildkite/test-cpp-gpu.sh

@@ -4,7 +4,7 @@ set -euo pipefail
 
 source tests/buildkite/conftest.sh
 
-echo "--- Run Google Tests with CUDA, using 4 GPUs"
+echo "--- Run Google Tests with CUDA, using a GPU"
 buildkite-agent artifact download "build/testxgboost" . --step build-cuda
 chmod +x build/testxgboost
 tests/ci_build/ci_build.sh gpu nvidia-docker \
@@ -12,11 +12,12 @@ tests/ci_build/ci_build.sh gpu nvidia-docker \
   --build-arg RAPIDS_VERSION_ARG=$RAPIDS_VERSION \
   build/testxgboost
 
-echo "--- Run Google Tests with CUDA, using 4 GPUs, RMM enabled"
-rm -rfv build/
-buildkite-agent artifact download "build/testxgboost" . --step build-cuda-with-rmm
-chmod +x build/testxgboost
-tests/ci_build/ci_build.sh rmm nvidia-docker \
-  --build-arg CUDA_VERSION_ARG=$CUDA_VERSION \
-  --build-arg RAPIDS_VERSION_ARG=$RAPIDS_VERSION bash -c \
-  "source activate gpu_test && build/testxgboost --use-rmm-pool"
+# Disabled until https://github.com/dmlc/xgboost/issues/8619 is resolved
+# echo "--- Run Google Tests with CUDA, using a GPU, RMM enabled"
+# rm -rfv build/
+# buildkite-agent artifact download "build/testxgboost" . --step build-cuda-with-rmm
+# chmod +x build/testxgboost
+# tests/ci_build/ci_build.sh rmm nvidia-docker \
+#   --build-arg CUDA_VERSION_ARG=$CUDA_VERSION \
+#   --build-arg RAPIDS_VERSION_ARG=$RAPIDS_VERSION bash -c \
+#   "source activate gpu_test && build/testxgboost --use-rmm-pool"

tests/ci_build/conda_env/cpp_test.yml

@@ -0,0 +1,11 @@
+# conda environment for CPP test on Linux distributions
+name: cpp_test
+channels:
+- defaults
+- conda-forge
+dependencies:
+- cmake
+- ninja
+- c-compiler
+- cxx-compiler
+- gtest

tests/ci_build/conda_env/sdist_test.yml

@@ -0,0 +1,13 @@
+# conda environment for source distribution test.
+name: sdist_test
+channels:
+- defaults
+- conda-forge
+dependencies:
+- python=3.8
+- pip
+- wheel
+- cmake
+- ninja
+- c-compiler
+- cxx-compiler

tests/cpp/common/test_categorical.cc

@@ -1,11 +1,14 @@
 /*!
- * Copyright 2021 by XGBoost Contributors
+ * Copyright 2021-2022 by XGBoost Contributors
  */
 #include <gtest/gtest.h>
+#include <xgboost/json.h>
+#include <xgboost/learner.h>
 
 #include <limits>
 
 #include "../../../src/common/categorical.h"
+#include "../helpers.h"
 
 namespace xgboost {
 namespace common {
@@ -15,29 +18,76 @@ TEST(Categorical, Decision) {
 
   ASSERT_TRUE(common::InvalidCat(a));
   std::vector<uint32_t> cats(256, 0);
-  ASSERT_TRUE(Decision(cats, a, true));
+  ASSERT_TRUE(Decision(cats, a));
 
   // larger than size
   a = 256;
-  ASSERT_TRUE(Decision(cats, a, true));
+  ASSERT_TRUE(Decision(cats, a));
 
   // negative
   a = -1;
-  ASSERT_TRUE(Decision(cats, a, true));
+  ASSERT_TRUE(Decision(cats, a));
 
   CatBitField bits{cats};
   bits.Set(0);
   a = -0.5;
-  ASSERT_TRUE(Decision(cats, a, true));
+  ASSERT_TRUE(Decision(cats, a));
 
   // round toward 0
   a = 0.5;
-  ASSERT_FALSE(Decision(cats, a, true));
+  ASSERT_FALSE(Decision(cats, a));
 
   // valid
   a = 13;
   bits.Set(a);
-  ASSERT_FALSE(Decision(bits.Bits(), a, true));
+  ASSERT_FALSE(Decision(bits.Bits(), a));
+}
+
+/**
+ * Test for running inference with input category greater than the one stored in tree.
+ */
+TEST(Categorical, MinimalSet) {
+  std::size_t constexpr kRows = 256, kCols = 1, kCat = 3;
+  std::vector<FeatureType> types{FeatureType::kCategorical};
+  auto Xy =
+      RandomDataGenerator{kRows, kCols, 0.0}.Type(types).MaxCategory(kCat).GenerateDMatrix(true);
+
+  std::unique_ptr<Learner> learner{Learner::Create({Xy})};
+  learner->SetParam("max_depth", "1");
+  learner->SetParam("tree_method", "hist");
+  learner->Configure();
+  learner->UpdateOneIter(0, Xy);
+
+  Json model{Object{}};
+  learner->SaveModel(&model);
+  auto tree = model["learner"]["gradient_booster"]["model"]["trees"][0];
+  ASSERT_GE(get<I32Array const>(tree["categories"]).size(), 1);
+  auto v = get<I32Array const>(tree["categories"])[0];
+
+  HostDeviceVector<float> predt;
+  {
+    std::vector<float> data{static_cast<float>(kCat),
+                            static_cast<float>(kCat + 1), 32.0f, 33.0f, 34.0f};
+    auto test = GetDMatrixFromData(data, data.size(), kCols);
+    learner->Predict(test, false, &predt, 0, 0, false, /*pred_leaf=*/true);
+    ASSERT_EQ(predt.Size(), data.size());
+    auto const& h_predt = predt.ConstHostSpan();
+    for (auto v : h_predt) {
+      ASSERT_EQ(v, 1);  // left child of root node
+    }
+  }
+
+  {
+    std::unique_ptr<Learner> learner{Learner::Create({Xy})};
+    learner->LoadModel(model);
+    std::vector<float> data = {static_cast<float>(v)};
+    auto test = GetDMatrixFromData(data, data.size(), kCols);
+    learner->Predict(test, false, &predt, 0, 0, false, /*pred_leaf=*/true);
+    auto const& h_predt = predt.ConstHostSpan();
+    for (auto v : h_predt) {
+      ASSERT_EQ(v, 2);  // right child of root node
+    }
+  }
 }
 }  // namespace common
 }  // namespace xgboost

tests/cpp/data/test_array_interface.cc

@@ -33,9 +33,8 @@ TEST(ArrayInterface, Error) {
   Json column { Object() };
   std::vector<Json> j_shape {Json(Integer(static_cast<Integer::Int>(kRows)))};
   column["shape"] = Array(j_shape);
-  std::vector<Json> j_data {
-    Json(Integer(reinterpret_cast<Integer::Int>(nullptr))),
-        Json(Boolean(false))};
+  std::vector<Json> j_data{Json(Integer(reinterpret_cast<Integer::Int>(nullptr))),
+                           Json(Boolean(false))};
 
   auto const& column_obj = get<Object>(column);
   std::string typestr{"<f4"};
@@ -45,6 +44,10 @@ TEST(ArrayInterface, Error) {
   EXPECT_THROW(ArrayInterfaceHandler::ExtractData(column_obj, n), dmlc::Error);
   column["version"] = 3;
   // missing data
+  EXPECT_THROW(ArrayInterfaceHandler::ExtractData(column_obj, n),
+               dmlc::Error);
+  // null data
+  column["data"] = Null{};
   EXPECT_THROW(ArrayInterfaceHandler::ExtractData(column_obj, n),
                dmlc::Error);
   column["data"] = j_data;
@@ -63,6 +66,11 @@ TEST(ArrayInterface, Error) {
       Json(Boolean(false))};
   column["data"] = j_data;
   EXPECT_NO_THROW(ArrayInterfaceHandler::ExtractData(column_obj, n));
+  // null data in mask
+  column["mask"] = Object{};
+  column["mask"]["data"] = Null{};
+  common::Span<RBitField8::value_type> s_mask;
+  EXPECT_THROW(ArrayInterfaceHandler::ExtractMask(column_obj, &s_mask), dmlc::Error);
 }
 
 TEST(ArrayInterface, GetElement) {

tests/python/test_collective.py

@@ -39,6 +39,37 @@ def test_rabit_communicator():
         assert worker.exitcode == 0
 
 
+# TODO(rongou): remove this once we remove the rabit api.
+def run_rabit_api_worker(rabit_env, world_size):
+    with xgb.rabit.RabitContext(rabit_env):
+        assert xgb.rabit.get_world_size() == world_size
+        assert xgb.rabit.is_distributed()
+        assert xgb.rabit.get_processor_name().decode() == socket.gethostname()
+        ret = xgb.rabit.broadcast('test1234', 0)
+        assert str(ret) == 'test1234'
+        ret = xgb.rabit.allreduce(np.asarray([1, 2, 3]), xgb.rabit.Op.SUM)
+        assert np.array_equal(ret, np.asarray([2, 4, 6]))
+
+
+# TODO(rongou): remove this once we remove the rabit api.
+def test_rabit_api():
+    world_size = 2
+    tracker = RabitTracker(host_ip='127.0.0.1', n_workers=world_size)
+    tracker.start(world_size)
+    rabit_env = []
+    for k, v in tracker.worker_envs().items():
+        rabit_env.append(f"{k}={v}".encode())
+    workers = []
+    for _ in range(world_size):
+        worker = multiprocessing.Process(target=run_rabit_api_worker,
+                                         args=(rabit_env, world_size))
+        workers.append(worker)
+        worker.start()
+    for worker in workers:
+        worker.join()
+        assert worker.exitcode == 0
+
+
 def run_federated_worker(port, world_size, rank):
     with xgb.collective.CommunicatorContext(xgboost_communicator='federated',
                                             federated_server_address=f'localhost:{port}',

tests/python/test_spark/test_spark_local.py

@@ -390,28 +390,6 @@ class XgboostLocalTest(SparkTestCase):
                 "expected_prediction_with_base_margin",
             ],
         )
-        self.ranker_df_train = self.session.createDataFrame(
-            [
-                (Vectors.dense(1.0, 2.0, 3.0), 0, 0),
-                (Vectors.dense(4.0, 5.0, 6.0), 1, 0),
-                (Vectors.dense(9.0, 4.0, 8.0), 2, 0),
-                (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 0, 1),
-                (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, 1),
-                (Vectors.sparse(3, {1: 8.0, 2: 9.5}), 2, 1),
-            ],
-            ["features", "label", "qid"],
-        )
-        self.ranker_df_test = self.session.createDataFrame(
-            [
-                (Vectors.dense(1.5, 2.0, 3.0), 0, -1.87988),
-                (Vectors.dense(4.5, 5.0, 6.0), 0, 0.29556),
-                (Vectors.dense(9.0, 4.5, 8.0), 0, 2.36570),
-                (Vectors.sparse(3, {1: 1.0, 2: 6.0}), 1, -1.87988),
-                (Vectors.sparse(3, {1: 6.0, 2: 7.0}), 1, -0.30612),
-                (Vectors.sparse(3, {1: 8.0, 2: 10.5}), 1, 2.44826),
-            ],
-            ["features", "qid", "expected_prediction"],
-        )
 
         self.reg_df_sparse_train = self.session.createDataFrame(
             [
@@ -1039,15 +1017,6 @@ class XgboostLocalTest(SparkTestCase):
         for row1, row2 in zip(pred_result, pred_result2):
             self.assertTrue(np.allclose(row1.probability, row2.probability, rtol=1e-3))
 
-    def test_ranker(self):
-        ranker = SparkXGBRanker(qid_col="qid")
-        assert ranker.getOrDefault(ranker.objective) == "rank:pairwise"
-        model = ranker.fit(self.ranker_df_train)
-        pred_result = model.transform(self.ranker_df_test).collect()
-
-        for row in pred_result:
-            assert np.isclose(row.prediction, row.expected_prediction, rtol=1e-3)
-
     def test_empty_validation_data(self) -> None:
         for tree_method in [
             "hist",
@@ -1130,3 +1099,63 @@ class XgboostLocalTest(SparkTestCase):
     def test_unsupported_params(self):
         with pytest.raises(ValueError, match="evals_result"):
             SparkXGBClassifier(evals_result={})
+
+
+class XgboostRankerLocalTest(SparkTestCase):
+    def setUp(self):
+        self.session.conf.set("spark.sql.execution.arrow.maxRecordsPerBatch", "8")
+        self.ranker_df_train = self.session.createDataFrame(
+            [
+                (Vectors.dense(1.0, 2.0, 3.0), 0, 0),
+                (Vectors.dense(4.0, 5.0, 6.0), 1, 0),
+                (Vectors.dense(9.0, 4.0, 8.0), 2, 0),
+                (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 0, 1),
+                (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, 1),
+                (Vectors.sparse(3, {1: 8.0, 2: 9.5}), 2, 1),
+            ],
+            ["features", "label", "qid"],
+        )
+        self.ranker_df_test = self.session.createDataFrame(
+            [
+                (Vectors.dense(1.5, 2.0, 3.0), 0, -1.87988),
+                (Vectors.dense(4.5, 5.0, 6.0), 0, 0.29556),
+                (Vectors.dense(9.0, 4.5, 8.0), 0, 2.36570),
+                (Vectors.sparse(3, {1: 1.0, 2: 6.0}), 1, -1.87988),
+                (Vectors.sparse(3, {1: 6.0, 2: 7.0}), 1, -0.30612),
+                (Vectors.sparse(3, {1: 8.0, 2: 10.5}), 1, 2.44826),
+            ],
+            ["features", "qid", "expected_prediction"],
+        )
+        self.ranker_df_train_1 = self.session.createDataFrame(
+            [
+                (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 0, 9),
+                (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, 9),
+                (Vectors.sparse(3, {1: 8.0, 2: 9.5}), 2, 9),
+                (Vectors.dense(1.0, 2.0, 3.0), 0, 8),
+                (Vectors.dense(4.0, 5.0, 6.0), 1, 8),
+                (Vectors.dense(9.0, 4.0, 8.0), 2, 8),
+                (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 0, 7),
+                (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, 7),
+                (Vectors.sparse(3, {1: 8.0, 2: 9.5}), 2, 7),
+                (Vectors.dense(1.0, 2.0, 3.0), 0, 6),
+                (Vectors.dense(4.0, 5.0, 6.0), 1, 6),
+                (Vectors.dense(9.0, 4.0, 8.0), 2, 6),
+            ]
+            * 4,
+            ["features", "label", "qid"],
+        )
+
+    def test_ranker(self):
+        ranker = SparkXGBRanker(qid_col="qid")
+        assert ranker.getOrDefault(ranker.objective) == "rank:pairwise"
+        model = ranker.fit(self.ranker_df_train)
+        pred_result = model.transform(self.ranker_df_test).collect()
+
+        for row in pred_result:
+            assert np.isclose(row.prediction, row.expected_prediction, rtol=1e-3)
+
+    def test_ranker_qid_sorted(self):
+        ranker = SparkXGBRanker(qid_col="qid", num_workers=4)
+        assert ranker.getOrDefault(ranker.objective) == "rank:pairwise"
+        model = ranker.fit(self.ranker_df_train_1)
+        model.transform(self.ranker_df_test).collect()

tests/python/test_with_pandas.py

@@ -112,7 +112,6 @@ class TestPandas:
 
         # test Index as columns
         df = pd.DataFrame([[1, 1.1], [2, 2.2]], columns=pd.Index([1, 2]))
-        print(df.columns, isinstance(df.columns, pd.Index))
         Xy = xgb.DMatrix(df)
         np.testing.assert_equal(np.array(Xy.feature_names), np.array(["1", "2"]))
 

tests/python/test_with_shap.py

@@ -4,7 +4,7 @@ import pytest
 
 try:
     import shap
-except ImportError:
+except Exception:
     shap = None
     pass
 

tests/python/test_with_sklearn.py

@@ -2,6 +2,7 @@ import collections
 import importlib.util
 import json
 import os
+import pickle
 import random
 import tempfile
 from typing import Callable, Optional
@@ -636,26 +637,74 @@ def test_sklearn_n_jobs():
 
 def test_parameters_access():
     from sklearn import datasets
-    params = {'updater': 'grow_gpu_hist', 'subsample': .5, 'n_jobs': -1}
+
+    params = {"updater": "grow_gpu_hist", "subsample": 0.5, "n_jobs": -1}
     clf = xgb.XGBClassifier(n_estimators=1000, **params)
-    assert clf.get_params()['updater'] == 'grow_gpu_hist'
-    assert clf.get_params()['subsample'] == .5
-    assert clf.get_params()['n_estimators'] == 1000
+    assert clf.get_params()["updater"] == "grow_gpu_hist"
+    assert clf.get_params()["subsample"] == 0.5
+    assert clf.get_params()["n_estimators"] == 1000
 
     clf = xgb.XGBClassifier(n_estimators=1, nthread=4)
     X, y = datasets.load_iris(return_X_y=True)
     clf.fit(X, y)
 
     config = json.loads(clf.get_booster().save_config())
-    assert int(config['learner']['generic_param']['nthread']) == 4
+    assert int(config["learner"]["generic_param"]["nthread"]) == 4
 
     clf.set_params(nthread=16)
     config = json.loads(clf.get_booster().save_config())
-    assert int(config['learner']['generic_param']['nthread']) == 16
+    assert int(config["learner"]["generic_param"]["nthread"]) == 16
 
     clf.predict(X)
     config = json.loads(clf.get_booster().save_config())
-    assert int(config['learner']['generic_param']['nthread']) == 16
+    assert int(config["learner"]["generic_param"]["nthread"]) == 16
+
+    clf = xgb.XGBClassifier(n_estimators=2)
+    assert clf.tree_method is None
+    assert clf.get_params()["tree_method"] is None
+    clf.fit(X, y)
+    assert clf.get_params()["tree_method"] is None
+
+    def save_load(clf: xgb.XGBClassifier) -> xgb.XGBClassifier:
+        with tempfile.TemporaryDirectory() as tmpdir:
+            path = os.path.join(tmpdir, "model.json")
+            clf.save_model(path)
+            clf = xgb.XGBClassifier()
+            clf.load_model(path)
+        return clf
+
+    def get_tm(clf: xgb.XGBClassifier) -> str:
+        tm = json.loads(clf.get_booster().save_config())["learner"]["gradient_booster"][
+            "gbtree_train_param"
+        ]["tree_method"]
+        return tm
+
+    assert get_tm(clf) == "exact"
+
+    clf = pickle.loads(pickle.dumps(clf))
+
+    assert clf.tree_method is None
+    assert clf.n_estimators == 2
+    assert clf.get_params()["tree_method"] is None
+    assert clf.get_params()["n_estimators"] == 2
+    assert get_tm(clf) == "exact"  # preserved for pickle
+
+    clf = save_load(clf)
+
+    assert clf.tree_method is None
+    assert clf.n_estimators == 2
+    assert clf.get_params()["tree_method"] is None
+    assert clf.get_params()["n_estimators"] == 2
+    assert get_tm(clf) == "auto"  # discarded for save/load_model
+
+    clf.set_params(tree_method="hist")
+    assert clf.get_params()["tree_method"] == "hist"
+    clf = pickle.loads(pickle.dumps(clf))
+    assert clf.get_params()["tree_method"] == "hist"
+    clf = save_load(clf)
+    # FIXME(jiamingy): We should remove this behavior once we remove parameters
+    # serialization for skl save/load_model.
+    assert clf.get_params()["tree_method"] == "hist"
 
 
 def test_kwargs_error():
@@ -695,13 +744,19 @@ def test_sklearn_clone():
 
 def test_sklearn_get_default_params():
     from sklearn.datasets import load_digits
+
     digits_2class = load_digits(n_class=2)
-    X = digits_2class['data']
-    y = digits_2class['target']
+    X = digits_2class["data"]
+    y = digits_2class["target"]
     cls = xgb.XGBClassifier()
-    assert cls.get_params()['base_score'] is None
+    assert cls.get_params()["base_score"] is None
     cls.fit(X[:4, ...], y[:4, ...])
-    assert cls.get_params()['base_score'] is not None
+    base_score = float(
+        json.loads(cls.get_booster().save_config())["learner"]["learner_model_param"][
+            "base_score"
+        ]
+    )
+    np.testing.assert_equal(base_score, 0.5)
 
 
 def run_validation_weights(model):
@@ -1029,9 +1084,9 @@ def test_pandas_input():
 
     clf_isotonic = CalibratedClassifierCV(model, cv="prefit", method="isotonic")
     clf_isotonic.fit(train, target)
-    assert isinstance(
-        clf_isotonic.calibrated_classifiers_[0].base_estimator, xgb.XGBClassifier
-    )
+    clf = clf_isotonic.calibrated_classifiers_[0]
+    est = clf.estimator if hasattr(clf, "estimator") else clf.base_estimator
+    assert isinstance(est, xgb.XGBClassifier)
     np.testing.assert_allclose(np.array(clf_isotonic.classes_), np.array([0, 1]))