Update change_scala_version.py to also change scala.version property (#9897)

* [jvm-packages] Fix POM for xgboost-jvm metapackage

* Add script for updating the Scala version

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.18 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 2.0.2)
+project(xgboost LANGUAGES CXX C VERSION 2.0.3)
 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: 2.0.2.1
+Version: 2.0.3.1
-Date: 2023-10-12
+Date: 2023-12-14
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for xgboost 2.0.2.
+# Generated by GNU Autoconf 2.71 for xgboost 2.0.3.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -607,8 +607,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='2.0.2'
+PACKAGE_VERSION='2.0.3'
-PACKAGE_STRING='xgboost 2.0.2'
+PACKAGE_STRING='xgboost 2.0.3'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1225,7 +1225,7 @@ 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 2.0.2 to adapt to many kinds of systems.
+\`configure' configures xgboost 2.0.3 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1287,7 +1287,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 2.0.2:";;
+     short | recursive ) echo "Configuration of xgboost 2.0.3:";;
    esac
   cat <<\_ACEOF
 
@@ -1367,7 +1367,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 2.0.2
+xgboost configure 2.0.3
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1533,7 +1533,7 @@ 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 2.0.2, which was
+It was created by xgboost $as_me 2.0.3, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3412,7 +3412,7 @@ 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 2.0.2, which was
+This file was extended by xgboost $as_me 2.0.3, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3467,7 +3467,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-xgboost config.status 2.0.2
+xgboost config.status 2.0.3
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[2.0.2],[],[xgboost],[])
+AC_INIT([xgboost],[2.0.3],[],[xgboost],[])
 
 : ${R_HOME=`R RHOME`}
 if test -z "${R_HOME}"; then

dev/change_scala_version.py

@@ -0,0 +1,79 @@
+import argparse
+import pathlib
+import re
+import shutil
+
+
+def main(args):
+    if args.scala_version == "2.12":
+        scala_ver = "2.12"
+        scala_patchver = "2.12.18"
+    elif args.scala_version == "2.13":
+        scala_ver = "2.13"
+        scala_patchver = "2.13.11"
+    else:
+        raise ValueError(f"Unsupported Scala version: {args.scala_version}")
+
+    # Clean artifacts
+    if args.purge_artifacts:
+        for target in pathlib.Path("jvm-packages/").glob("**/target"):
+            if target.is_dir():
+                print(f"Removing {target}...")
+                shutil.rmtree(target)
+
+    # Update pom.xml
+    for pom in pathlib.Path("jvm-packages/").glob("**/pom.xml"):
+        print(f"Updating {pom}...")
+        with open(pom, "r", encoding="utf-8") as f:
+            lines = f.readlines()
+        with open(pom, "w", encoding="utf-8") as f:
+            replaced_scalaver = False
+            replaced_scala_binver = False
+            for line in lines:
+                for artifact in [
+                    "xgboost-jvm",
+                    "xgboost4j",
+                    "xgboost4j-gpu",
+                    "xgboost4j-spark",
+                    "xgboost4j-spark-gpu",
+                    "xgboost4j-flink",
+                    "xgboost4j-example",
+                ]:
+                    line = re.sub(
+                        f"<artifactId>{artifact}_[0-9\\.]*",
+                        f"<artifactId>{artifact}_{scala_ver}",
+                        line,
+                    )
+                # Only replace the first occurrence of scala.version
+                if not replaced_scalaver:
+                    line, nsubs = re.subn(
+                        r"<scala.version>[0-9\.]*",
+                        f"<scala.version>{scala_patchver}",
+                        line,
+                    )
+                    if nsubs > 0:
+                        replaced_scalaver = True
+                # Only replace the first occurrence of scala.binary.version
+                if not replaced_scala_binver:
+                    line, nsubs = re.subn(
+                        r"<scala.binary.version>[0-9\.]*",
+                        f"<scala.binary.version>{scala_ver}",
+                        line,
+                    )
+                    if nsubs > 0:
+                        replaced_scala_binver = True
+                f.write(line)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--purge-artifacts", action="store_true")
+    parser.add_argument(
+        "--scala-version",
+        type=str,
+        required=True,
+        help="Version of Scala to use in the JVM packages",
+        choices=["2.12", "2.13"],
+    )
+    parsed_args = parser.parse_args()
+    main(parsed_args)

dev/prepare_jvm_release.py

@@ -2,7 +2,6 @@ import argparse
 import errno
 import glob
 import os
-import platform
 import re
 import shutil
 import subprocess
@@ -88,10 +87,6 @@ def main():
         help="Version of the release being prepared",
     )
     args = parser.parse_args()
-
-    if sys.platform != "darwin" or platform.machine() != "arm64":
-        raise NotImplementedError("Please run this script using an M1 Mac")
-
     version = args.release_version
     expected_git_tag = "v" + version
     current_git_tag = get_current_git_tag()
@@ -141,6 +136,7 @@ def main():
             ("linux", "x86_64"),
             ("windows", "x86_64"),
             ("macos", "x86_64"),
+            ("macos", "aarch64"),
         ]:
             output_dir = f"xgboost4j/src/main/resources/lib/{os_ident}/{arch}"
             maybe_makedirs(output_dir)
@@ -164,6 +160,10 @@ def main():
             url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_{commit_hash}.dylib",
             filename="xgboost4j/src/main/resources/lib/macos/x86_64/libxgboost4j.dylib",
         )
+        retrieve(
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_m1_{commit_hash}.dylib",
+            filename="xgboost4j/src/main/resources/lib/macos/aarch64/libxgboost4j.dylib",
+        )
 
         with tempfile.TemporaryDirectory() as tempdir:
             # libxgboost4j.so for Linux x86_64, CPU only
@@ -211,9 +211,14 @@ def main():
         "https://central.sonatype.org/publish/publish-maven/"
     )
     print(
-        "3. Now on a M1 Mac machine, run the following to build Scala 2.12 artifacts:"
+        "3. Now on a Linux machine, run the following to build Scala 2.12 artifacts. "
+        "Make sure to use an Internet connection with fast upload speed:"
+    )
+    print(
+        "   # Skip native build, since we have all needed native binaries from CI\n"
+        "   export MAVEN_SKIP_NATIVE_BUILD=1\n"
+        "   GPG_TTY=$(tty) mvn deploy -Prelease -DskipTests"
     )
-    print("   GPG_TTY=$(tty) mvn deploy -Prelease -DskipTests")
     print(
         "4. Log into https://oss.sonatype.org/. On the left menu panel, click Staging "
         "Repositories. Visit the URL https://oss.sonatype.org/content/repositories/mldmlc-xxxx "
@@ -221,11 +226,14 @@ def main():
         "artifacts to the Maven Central repository. The top-level metapackage should be "
         "named xgboost-jvm_2.12."
     )
-    print("5. Remove the Scala 2.12 artifacts and build Scala 2.13 artifacts:")
-    print("   rm -rf targets/")
-    print("   GPG_TTY=$(tty) mvn deploy -Prelease-cpu-only,scala-2.13 -DskipTests")
     print(
-        "6. Go to https://oss.sonatype.org/ to release the Scala 2.13 artifacts."
+        "5. Remove the Scala 2.12 artifacts and build Scala 2.13 artifacts:\n"
+        "   export MAVEN_SKIP_NATIVE_BUILD=1\n"
+        "   python dev/change_scala_version.py --scala-version 2.13 --purge-artifacts\n"
+        "   GPG_TTY=$(tty) mvn deploy -Prelease-cpu-only,scala-2.13 -DskipTests"
+    )
+    print(
+        "6. Go to https://oss.sonatype.org/ to release the Scala 2.13 artifacts. "
         "The top-level metapackage should be named xgboost-jvm_2.13."
     )
 

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 2  /* NOLINT */
 #define XGBOOST_VER_MINOR 0  /* NOLINT */
-#define XGBOOST_VER_PATCH 2  /* NOLINT */
+#define XGBOOST_VER_PATCH 3  /* NOLINT */
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/create_jni.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
-import errno
 import argparse
+import errno
 import glob
 import os
 import platform
@@ -19,11 +19,10 @@ CONFIG = {
     "USE_HDFS": "OFF",
     "USE_AZURE": "OFF",
     "USE_S3": "OFF",
-
     "USE_CUDA": "OFF",
     "USE_NCCL": "OFF",
     "JVM_BINDINGS": "ON",
-    "LOG_CAPI_INVOCATION": "OFF"
+    "LOG_CAPI_INVOCATION": "OFF",
 }
 
 
@@ -70,26 +69,22 @@ def normpath(path):
         return normalized
 
 
-if __name__ == "__main__":
+def native_build(args):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--log-capi-invocation', type=str, choices=['ON', 'OFF'], default='OFF')
-    parser.add_argument('--use-cuda', type=str, choices=['ON', 'OFF'], default='OFF')
-    cli_args = parser.parse_args()
-
     if sys.platform == "darwin":
         # Enable of your compiler supports OpenMP.
         CONFIG["USE_OPENMP"] = "OFF"
-        os.environ["JAVA_HOME"] = subprocess.check_output(
+        os.environ["JAVA_HOME"] = (
-            "/usr/libexec/java_home").strip().decode()
+            subprocess.check_output("/usr/libexec/java_home").strip().decode()
+        )
 
     print("building Java wrapper")
     with cd(".."):
-        build_dir = 'build-gpu' if cli_args.use_cuda == 'ON' else 'build'
+        build_dir = "build-gpu" if cli_args.use_cuda == "ON" else "build"
         maybe_makedirs(build_dir)
         with cd(build_dir):
             if sys.platform == "win32":
                 # Force x64 build on Windows.
-                maybe_generator = ' -A x64'
+                maybe_generator = " -A x64"
             else:
                 maybe_generator = ""
             if sys.platform == "linux":
@@ -97,12 +92,12 @@ if __name__ == "__main__":
             else:
                 maybe_parallel_build = ""
 
-            if cli_args.log_capi_invocation == 'ON':
+            if cli_args.log_capi_invocation == "ON":
-                CONFIG['LOG_CAPI_INVOCATION'] = 'ON'
+                CONFIG["LOG_CAPI_INVOCATION"] = "ON"
 
-            if cli_args.use_cuda == 'ON':
+            if cli_args.use_cuda == "ON":
-                CONFIG['USE_CUDA'] = 'ON'
+                CONFIG["USE_CUDA"] = "ON"
-                CONFIG['USE_NCCL'] = 'ON'
+                CONFIG["USE_NCCL"] = "ON"
 
             args = ["-D{0}:BOOL={1}".format(k, v) for k, v in CONFIG.items()]
 
@@ -115,7 +110,7 @@ if __name__ == "__main__":
             if gpu_arch_flag is not None:
                 args.append("%s" % gpu_arch_flag)
 
-            lib_dir = os.path.join(os.pardir, 'lib')
+            lib_dir = os.path.join(os.pardir, "lib")
             if os.path.exists(lib_dir):
                 shutil.rmtree(lib_dir)
             run("cmake .. " + " ".join(args) + maybe_generator)
@@ -125,8 +120,10 @@ if __name__ == "__main__":
             run(f'"{sys.executable}" mapfeat.py')
             run(f'"{sys.executable}" mknfold.py machine.txt 1')
 
-    xgboost4j = 'xgboost4j-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j'
+    xgboost4j = "xgboost4j-gpu" if cli_args.use_cuda == "ON" else "xgboost4j"
-    xgboost4j_spark = 'xgboost4j-spark-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j-spark'
+    xgboost4j_spark = (
+        "xgboost4j-spark-gpu" if cli_args.use_cuda == "ON" else "xgboost4j-spark"
+    )
 
     print("copying native library")
     library_name, os_folder = {
@@ -141,14 +138,19 @@ if __name__ == "__main__":
         "i86pc": "x86_64",  # on Solaris x86_64
         "sun4v": "sparc",  # on Solaris sparc
         "arm64": "aarch64",  # on macOS & Windows ARM 64-bit
-        "aarch64": "aarch64"
+        "aarch64": "aarch64",
     }[platform.machine().lower()]
-    output_folder = "{}/src/main/resources/lib/{}/{}".format(xgboost4j, os_folder, arch_folder)
+    output_folder = "{}/src/main/resources/lib/{}/{}".format(
+        xgboost4j, os_folder, arch_folder
+    )
     maybe_makedirs(output_folder)
     cp("../lib/" + library_name, output_folder)
 
     print("copying pure-Python tracker")
-    cp("../python-package/xgboost/tracker.py", "{}/src/main/resources".format(xgboost4j))
+    cp(
+        "../python-package/xgboost/tracker.py",
+        "{}/src/main/resources".format(xgboost4j),
+    )
 
     print("copying train/test files")
     maybe_makedirs("{}/src/test/resources".format(xgboost4j_spark))
@@ -164,3 +166,18 @@ if __name__ == "__main__":
     maybe_makedirs("{}/src/test/resources".format(xgboost4j))
     for file in glob.glob("../demo/data/agaricus.*"):
         cp(file, "{}/src/test/resources".format(xgboost4j))
+
+
+if __name__ == "__main__":
+    if "MAVEN_SKIP_NATIVE_BUILD" in os.environ:
+        print("MAVEN_SKIP_NATIVE_BUILD is set. Skipping native build...")
+    else:
+        parser = argparse.ArgumentParser()
+        parser.add_argument(
+            "--log-capi-invocation", type=str, choices=["ON", "OFF"], default="OFF"
+        )
+        parser.add_argument(
+            "--use-cuda", type=str, choices=["ON", "OFF"], default="OFF"
+        )
+        cli_args = parser.parse_args()
+        native_build(cli_args)

jvm-packages/pom.xml

@@ -5,8 +5,8 @@
     <modelVersion>4.0.0</modelVersion>
 
     <groupId>ml.dmlc</groupId>
-    <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+    <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>2.0.2</version>
+    <version>2.0.3</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>

jvm-packages/xgboost4j-example/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
     <name>xgboost4j-example</name>
-    <artifactId>xgboost4j-example_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>2.0.2</version>
+    <version>2.0.3</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
     <dependencies>
         <dependency>
             <groupId>ml.dmlc</groupId>
-            <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
+            <artifactId>xgboost4j-spark_2.12</artifactId>
             <version>${project.version}</version>
         </dependency>
         <dependency>
@@ -37,7 +37,7 @@
         </dependency>
         <dependency>
             <groupId>ml.dmlc</groupId>
-            <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
+            <artifactId>xgboost4j-flink_2.12</artifactId>
             <version>${project.version}</version>
         </dependency>
     </dependencies>

jvm-packages/xgboost4j-flink/pom.xml

@@ -5,13 +5,13 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
 
     <name>xgboost4j-flink</name>
-    <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>2.0.2</version>
+    <version>2.0.3</version>
     <properties>
       <flink-ml.version>2.2.0</flink-ml.version>
     </properties>
@@ -30,7 +30,7 @@
     <dependencies>
         <dependency>
             <groupId>ml.dmlc</groupId>
-            <artifactId>xgboost4j_${scala.binary.version}</artifactId>
+            <artifactId>xgboost4j_2.12</artifactId>
             <version>${project.version}</version>
         </dependency>
         <dependency>

jvm-packages/xgboost4j-gpu/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
-    <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j-gpu_2.12</artifactId>
     <name>xgboost4j-gpu</name>
-    <version>2.0.2</version>
+    <version>2.0.3</version>
     <packaging>jar</packaging>
 
     <dependencies>

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

@@ -5,11 +5,11 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
     <name>xgboost4j-spark-gpu</name>
-    <artifactId>xgboost4j-spark-gpu_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j-spark-gpu_2.12</artifactId>
     <build>
         <plugins>
             <plugin>
@@ -24,7 +24,7 @@
     <dependencies>
         <dependency>
             <groupId>ml.dmlc</groupId>
-            <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>
+            <artifactId>xgboost4j-gpu_2.12</artifactId>
             <version>${project.version}</version>
         </dependency>
         <dependency>

jvm-packages/xgboost4j-spark/pom.xml

@@ -5,11 +5,11 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
     <name>xgboost4j-spark</name>
-    <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j-spark_2.12</artifactId>
     <build>
         <plugins>
             <plugin>
@@ -24,7 +24,7 @@
     <dependencies>
         <dependency>
             <groupId>ml.dmlc</groupId>
-            <artifactId>xgboost4j_${scala.binary.version}</artifactId>
+            <artifactId>xgboost4j_2.12</artifactId>
             <version>${project.version}</version>
         </dependency>
         <dependency>

jvm-packages/xgboost4j/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>2.0.2</version>
+        <version>2.0.3</version>
     </parent>
     <name>xgboost4j</name>
-    <artifactId>xgboost4j_${scala.binary.version}</artifactId>
+    <artifactId>xgboost4j_2.12</artifactId>
-    <version>2.0.2</version>
+    <version>2.0.3</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "packager.pep517"
 
 [project]
 name = "xgboost"
-version = "2.0.2"
+version = "2.0.3"
 authors = [
     { name = "Hyunsu Cho", email = "chohyu01@cs.washington.edu" },
     { name = "Jiaming Yuan", email = "jm.yuan@outlook.com" }

python-package/xgboost/VERSION

@@ -1 +1 @@
-2.0.2
+2.0.3

python-package/xgboost/core.py

@@ -206,6 +206,7 @@ def _load_lib() -> ctypes.CDLL:
             lib = ctypes.cdll.LoadLibrary(lib_path)
             setattr(lib, "path", os.path.normpath(lib_path))
             lib_success = True
+            break
         except OSError as e:
             os_error_list.append(str(e))
             continue

python-package/xgboost/dask.py

@@ -78,7 +78,6 @@ from .data import _is_cudf_ser, _is_cupy_array
 from .sklearn import (
     XGBClassifier,
     XGBClassifierBase,
-    XGBClassifierMixIn,
     XGBModel,
     XGBRanker,
     XGBRankerMixIn,
@@ -1854,7 +1853,7 @@ class DaskXGBRegressor(DaskScikitLearnBase, XGBRegressorBase):
     "Implementation of the scikit-learn API for XGBoost classification.",
     ["estimators", "model"],
 )
-class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierMixIn, XGBClassifierBase):
+class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
     # pylint: disable=missing-class-docstring
     async def _fit_async(
         self,
@@ -2036,10 +2035,6 @@ class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierMixIn, XGBClassifierBa
             preds = da.map_blocks(_argmax, pred_probs, drop_axis=1)
         return preds
 
-    def load_model(self, fname: ModelIn) -> None:
-        super().load_model(fname)
-        self._load_model_attributes(self.get_booster())
-
 
 @xgboost_model_doc(
     """Implementation of the Scikit-Learn API for XGBoost Ranking.

python-package/xgboost/sklearn.py

@@ -43,19 +43,6 @@ from .data import _is_cudf_df, _is_cudf_ser, _is_cupy_array, _is_pandas_df
 from .training import train
 
 
-class XGBClassifierMixIn:  # pylint: disable=too-few-public-methods
-    """MixIn for classification."""
-
-    def __init__(self, *args: Any, **kwargs: Any) -> None:
-        super().__init__(*args, **kwargs)
-
-    def _load_model_attributes(self, booster: Booster) -> None:
-        config = json.loads(booster.save_config())
-        self.n_classes_ = int(config["learner"]["learner_model_param"]["num_class"])
-        # binary classification is treated as regression in XGBoost.
-        self.n_classes_ = 2 if self.n_classes_ < 2 else self.n_classes_
-
-
 class XGBRankerMixIn:  # pylint: disable=too-few-public-methods
     """MixIn for ranking, defines the _estimator_type usually defined in scikit-learn
     base classes.
@@ -845,21 +832,38 @@ class XGBModel(XGBModelBase):
         self.get_booster().load_model(fname)
 
         meta_str = self.get_booster().attr("scikit_learn")
-        if meta_str is None:
+        if meta_str is not None:
-            return
+            meta = json.loads(meta_str)
+            t = meta.get("_estimator_type", None)
+            if t is not None and t != self._get_type():
+                raise TypeError(
+                    "Loading an estimator with different type. Expecting: "
+                    f"{self._get_type()}, got: {t}"
+                )
 
-        meta = json.loads(meta_str)
-        t = meta.get("_estimator_type", None)
-        if t is not None and t != self._get_type():
-            raise TypeError(
-                "Loading an estimator with different type. Expecting: "
-                f"{self._get_type()}, got: {t}"
-            )
         self.feature_types = self.get_booster().feature_types
         self.get_booster().set_attr(scikit_learn=None)
+        config = json.loads(self.get_booster().save_config())
+        self._load_model_attributes(config)
 
     load_model.__doc__ = f"""{Booster.load_model.__doc__}"""
 
+    def _load_model_attributes(self, config: dict) -> None:
+        """Load model attributes without hyper-parameters."""
+        from sklearn.base import is_classifier
+
+        booster = self.get_booster()
+
+        self.objective = config["learner"]["objective"]["name"]
+        self.booster = config["learner"]["gradient_booster"]["name"]
+        self.base_score = config["learner"]["learner_model_param"]["base_score"]
+        self.feature_types = booster.feature_types
+
+        if is_classifier(self):
+            self.n_classes_ = int(config["learner"]["learner_model_param"]["num_class"])
+            # binary classification is treated as regression in XGBoost.
+            self.n_classes_ = 2 if self.n_classes_ < 2 else self.n_classes_
+
     # pylint: disable=too-many-branches
     def _configure_fit(
         self,
@@ -1409,7 +1413,7 @@ def _cls_predict_proba(n_classes: int, prediction: PredtT, vstack: Callable) ->
         Number of boosting rounds.
 """,
 )
-class XGBClassifier(XGBModel, XGBClassifierMixIn, XGBClassifierBase):
+class XGBClassifier(XGBModel, XGBClassifierBase):
     # pylint: disable=missing-docstring,invalid-name,too-many-instance-attributes
     @_deprecate_positional_args
     def __init__(
@@ -1637,10 +1641,6 @@ class XGBClassifier(XGBModel, XGBClassifierMixIn, XGBClassifierBase):
     def classes_(self) -> np.ndarray:
         return np.arange(self.n_classes_)
 
-    def load_model(self, fname: ModelIn) -> None:
-        super().load_model(fname)
-        self._load_model_attributes(self.get_booster())
-
 
 @xgboost_model_doc(
     "scikit-learn API for XGBoost random forest classification.",

tests/buildkite/build-jvm-packages.sh

@@ -8,13 +8,18 @@ echo "--- Build XGBoost JVM packages scala 2.12"
 tests/ci_build/ci_build.sh jvm docker tests/ci_build/build_jvm_packages.sh \
   ${SPARK_VERSION}
 
+echo "--- Stash XGBoost4J JARs (Scala 2.12)"
+buildkite-agent artifact upload "jvm-packages/xgboost4j/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-spark/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-flink/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-example/target/*.jar"
 
 echo "--- Build XGBoost JVM packages scala 2.13"
 
 tests/ci_build/ci_build.sh jvm docker tests/ci_build/build_jvm_packages.sh \
   ${SPARK_VERSION} "" "" "true"
 
-echo "--- Stash XGBoost4J JARs"
+echo "--- Stash XGBoost4J JARs (Scala 2.13)"
 buildkite-agent artifact upload "jvm-packages/xgboost4j/target/*.jar"
 buildkite-agent artifact upload "jvm-packages/xgboost4j-spark/target/*.jar"
 buildkite-agent artifact upload "jvm-packages/xgboost4j-flink/target/*.jar"

tests/buildkite/pipeline-mac-m1.yml

@@ -0,0 +1,8 @@
+steps:
+  - block: ":rocket: Run this test job"
+    if: build.pull_request.id != null || build.branch =~ /^dependabot\//
+  - label: ":macos: Build and Test XGBoost for MacOS M1 with Clang 11"
+    command: "tests/buildkite/test-macos-m1-clang11.sh"
+    key: mac-m1-appleclang11
+    agents:
+      queue: mac-mini-m1

tests/buildkite/test-macos-m1-clang11.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source tests/buildkite/conftest.sh
+
+# Display system info
+echo "--- Display system information"
+set -x
+system_profiler SPSoftwareDataType
+sysctl -n machdep.cpu.brand_string
+uname -m
+set +x
+
+# Build XGBoost4J binary
+echo "--- Build libxgboost4j.dylib"
+set -x
+mkdir build
+pushd build
+export JAVA_HOME=$(/usr/libexec/java_home)
+cmake .. -GNinja -DJVM_BINDINGS=ON -DUSE_OPENMP=OFF -DCMAKE_OSX_DEPLOYMENT_TARGET=10.15
+ninja -v
+popd
+rm -rf build
+set +x
+
+echo "--- Upload Python wheel"
+set -x
+pushd lib
+mv -v libxgboost4j.dylib libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
+buildkite-agent artifact upload libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
+if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+then
+  aws s3 cp libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib \
+    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
+    --acl public-read --no-progress
+fi
+popd
+set +x
+
+# Ensure that XGBoost can be built with Clang 11
+echo "--- Build and Test XGBoost with MacOS M1, Clang 11"
+set -x
+LLVM11_PATH=$(brew --prefix llvm\@11)
+mkdir build
+pushd build
+cmake .. -GNinja -DCMAKE_C_COMPILER=${LLVM11_PATH}/bin/clang \
+  -DCMAKE_CXX_COMPILER=${LLVM11_PATH}/bin/clang++ -DGOOGLE_TEST=ON \
+  -DUSE_DMLC_GTEST=ON
+ninja -v

tests/ci_build/build_jvm_packages.sh

@@ -27,6 +27,9 @@ fi
 mvn_profile_string=""
 if [ "x$use_scala213" != "x" ]; then
   export mvn_profile_string="-Pdefault,scala-2.13"
+  cd ..
+  python dev/change_scala_version.py --scala-version 2.13 --purge-artifacts
+  cd jvm-packages
 fi
 
 mvn --no-transfer-progress package $mvn_profile_string -Dspark.version=${spark_version} $gpu_options

tests/ci_build/conda_env/macos_cpu_test.yml

@@ -32,11 +32,10 @@ dependencies:
 - jsonschema
 - boto3
 - awscli
-- py-ubjson
 - cffi
 - pyarrow
 - pyspark>=3.4.0
 - cloudpickle
 - pip:
   - sphinx_rtd_theme
-  - datatable
+  - py-ubjson

tests/ci_build/deploy_jvm_packages.sh

@@ -27,6 +27,9 @@ rm -rf ../build/
 # Deploy to S3 bucket xgboost-maven-repo
 mvn --no-transfer-progress package deploy -P default,gpu,release-to-s3 -Dspark.version=${spark_version} -DskipTests
 # Deploy scala 2.13 to S3 bucket xgboost-maven-repo
+cd ..
+python dev/change_scala_version.py --scala-version 2.13 --purge-artifacts
+cd jvm-packages/
 mvn --no-transfer-progress package deploy -P release-to-s3,default,scala-2.13 -Dspark.version=${spark_version} -DskipTests
 
 

tests/ci_build/test_jvm_cross.sh

@@ -21,9 +21,18 @@ if [ ! -z "$RUN_INTEGRATION_TEST" ]; then
 fi
 
 # including maven profiles for different scala versions: 2.12 is the default at the moment.
-for _maven_profile_string in "" "-Pdefault,scala-2.13"; do
+for scala_binary_version in "2.12" "2.13"; do
+  cd ..
+  python dev/change_scala_version.py --scala-version ${scala_binary_version}
+  cd jvm-packages
   scala_version=$(mvn help:evaluate $_maven_profile_string -Dexpression=scala.version -q -DforceStdout)
-  scala_binary_version=$(mvn help:evaluate $_maven_profile_string -Dexpression=scala.binary.version -q -DforceStdout)
+  if [[ "$scala_binary_version" == "2.12" ]]; then
+    _maven_profile_string=""
+  elif [[ "$scala_binary_version" == "2.13" ]]; then
+    _maven_profile_string="-Pdefault,scala-2.13"
+  else
+    echo "Unexpected scala version: $scala_version ($scala_binary_version)."
+  fi
 
   # Install XGBoost4J JAR into local Maven repository
   mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j/target/xgboost4j_${scala_binary_version}-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j_${scala_binary_version} -Dversion=${xgboost4j_version} -Dpackaging=jar

tests/python/test_with_sklearn.py

@@ -940,6 +940,7 @@ def save_load_model(model_path):
     predt_0 = clf.predict(X)
     clf.save_model(model_path)
     clf.load_model(model_path)
+    assert clf.booster == "gblinear"
     predt_1 = clf.predict(X)
     np.testing.assert_allclose(predt_0, predt_1)
     assert clf.best_iteration == best_iteration
@@ -955,25 +956,26 @@ def save_load_model(model_path):
 
 def test_save_load_model():
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model')
+        model_path = os.path.join(tempdir, "digits.model")
         save_load_model(model_path)
 
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model.json')
+        model_path = os.path.join(tempdir, "digits.model.json")
         save_load_model(model_path)
 
     from sklearn.datasets import load_digits
     from sklearn.model_selection import train_test_split
 
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model.ubj')
+        model_path = os.path.join(tempdir, "digits.model.ubj")
         digits = load_digits(n_class=2)
-        y = digits['target']
+        y = digits["target"]
-        X = digits['data']
+        X = digits["data"]
-        booster = xgb.train({'tree_method': 'hist',
+        booster = xgb.train(
-                             'objective': 'binary:logistic'},
+            {"tree_method": "hist", "objective": "binary:logistic"},
-                            dtrain=xgb.DMatrix(X, y),
+            dtrain=xgb.DMatrix(X, y),
-                            num_boost_round=4)
+            num_boost_round=4,
+        )
         predt_0 = booster.predict(xgb.DMatrix(X))
         booster.save_model(model_path)
         cls = xgb.XGBClassifier()
@@ -1007,6 +1009,8 @@ def test_save_load_model():
         clf = xgb.XGBClassifier()
         clf.load_model(model_path)
         assert clf.classes_.size == 10
+        assert clf.objective == "multi:softprob"
+
         np.testing.assert_equal(clf.classes_, np.arange(10))
         assert clf.n_classes_ == 10
 

tests/test_distributed/test_with_dask/test_with_dask.py

@@ -1932,6 +1932,7 @@ class TestWithDask:
         cls.client = client
         cls.fit(X, y)
         predt_0 = cls.predict(X)
+        proba_0 = cls.predict_proba(X)
 
         with tempfile.TemporaryDirectory() as tmpdir:
             path = os.path.join(tmpdir, "model.pkl")
@@ -1941,7 +1942,9 @@ class TestWithDask:
             with open(path, "rb") as fd:
                 cls = pickle.load(fd)
             predt_1 = cls.predict(X)
+            proba_1 = cls.predict_proba(X)
             np.testing.assert_allclose(predt_0.compute(), predt_1.compute())
+            np.testing.assert_allclose(proba_0.compute(), proba_1.compute())
 
             path = os.path.join(tmpdir, "cls.json")
             cls.save_model(path)
@@ -1950,16 +1953,20 @@ class TestWithDask:
             cls.load_model(path)
             assert cls.n_classes_ == 10
             predt_2 = cls.predict(X)
+            proba_2 = cls.predict_proba(X)
 
             np.testing.assert_allclose(predt_0.compute(), predt_2.compute())
+            np.testing.assert_allclose(proba_0.compute(), proba_2.compute())
 
             # Use single node to load
             cls = xgb.XGBClassifier()
             cls.load_model(path)
             assert cls.n_classes_ == 10
             predt_3 = cls.predict(X_)
+            proba_3 = cls.predict_proba(X_)
 
             np.testing.assert_allclose(predt_0.compute(), predt_3)
+            np.testing.assert_allclose(proba_0.compute(), proba_3)
 
 
 def test_dask_unsupported_features(client: "Client") -> None: