Adopt xgboost 2.0.3 patch (#28)

* [backport][sklearn] Fix loading model attributes. (dmlc#9808) (dmlc#9880)

* [backport][py] Use the first found native library. (dmlc#9860) (dmlc#9879)

* [backport] [CI] Upload libxgboost4j.dylib (M1) to S3 bucket (dmlc#9887)

* [CI] Set up CI for Mac M1 (dmlc#9699)

* [CI] Improve CI for Mac M1 (dmlc#9748)

* [CI] Build libxgboost4j.dylib with CMAKE_OSX_DEPLOYMENT_TARGET (dmlc#9749)

* [CI] Upload libxgboost4j.dylib (M1) to S3 bucket (dmlc#9886)

* [jvm-packages] Fix POM for xgboost-jvm metapackage (dmlc#9893)

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

* Add script for updating the Scala version

* Bump version to 2.0.3 (dmlc#9895)

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

---------

Co-authored-by: Jiaming Yuan <[email protected]>
Co-authored-by: Philip Hyunsu Cho <[email protected]>

Author: 3 people

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
-Date: 2023-10-12
+Version: 2.0.3.1
+Date: 2023-12-14
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "[email protected]"),

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_STRING='xgboost 2.0.2'
+PACKAGE_VERSION='2.0.3'
+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 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
@@ -211,21 +211,29 @@ 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 "
         "to inspect the staged JAR files. Finally, press Release button to publish the "
         "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 @@
     "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",
 }
 
 
@@ -70,39 +69,35 @@ def normpath(path):
         return normalized
 
 
-if __name__ == "__main__":
-    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()
-
+def native_build(args):
     if sys.platform == "darwin":
         # Enable of your compiler supports OpenMP.
         CONFIG["USE_OPENMP"] = "OFF"
-        os.environ["JAVA_HOME"] = subprocess.check_output(
-            "/usr/libexec/java_home").strip().decode()
+        os.environ["JAVA_HOME"] = (
+            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":
                 maybe_parallel_build = " -- -j $(nproc)"
             else:
                 maybe_parallel_build = ""
 
-            if cli_args.log_capi_invocation == 'ON':
-                CONFIG['LOG_CAPI_INVOCATION'] = 'ON'
+            if cli_args.log_capi_invocation == "ON":
+                CONFIG["LOG_CAPI_INVOCATION"] = "ON"
 
-            if cli_args.use_cuda == 'ON':
-                CONFIG['USE_CUDA'] = 'ON'
-                CONFIG['USE_NCCL'] = 'ON'
+            if cli_args.use_cuda == "ON":
+                CONFIG["USE_CUDA"] = "ON"
+                CONFIG["USE_NCCL"] = "ON"
 
             args = ["-D{0}:BOOL={1}".format(k, v) for k, v in CONFIG.items()]
 
@@ -115,7 +110,7 @@ def normpath(path):
             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 @@ def normpath(path):
             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_spark = 'xgboost4j-spark-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j-spark'
+    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"
+    )
 
     print("copying native library")
     library_name, os_folder = {
@@ -141,14 +138,19 @@ def normpath(path):
         "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 @@ def normpath(path):
     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)