Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[jvm-packages][breaking]Rework xgboost4j jvm packages for spark #10617

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

[jvm-packages][breaking]Rework xgboost4j jvm packages for spark #10617

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions dev/change_scala_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,17 @@ def main(args):
)
if nsubs > 0:
replaced_scala_binver = True
# Replace the final name of shaded jar
if "<finalName>" in line:
for artifact in [
"xgboost-spark",
"xgboost-spark-gpu",
]:
line = re.sub(
f"<finalName>{artifact}_[0-9\\.]*",
f"<finalName>{artifact}_{scala_ver}",
line,
)
f.write(line)


Expand Down
2 changes: 2 additions & 0 deletions include/xgboost/c_api.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,13 +402,15 @@ XGB_EXTERN_C typedef int XGBCallbackDataIterNext( // NOLINT(*)
* \param data_handle The handle to the data.
* \param callback The callback to get the data.
* \param cache_info Additional information about cache file, can be null.
* \param missing Which value to represent missing value.
* \param out The created DMatrix
* \return 0 when success, -1 when failure happens.
*/
XGB_DLL int XGDMatrixCreateFromDataIter(
DataIterHandle data_handle,
XGBCallbackDataIterNext* callback,
const char* cache_info,
float missing,
DMatrixHandle *out);

/**
Expand Down
3 changes: 2 additions & 1 deletion jvm-packages/.gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
tracker.py
build.sh
xgboost4j-tester/pom.xml
xgboost4j-tester/iris.csv
dependency-reduced-pom.xml
surefire-reports
4 changes: 2 additions & 2 deletions jvm-packages/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,11 @@ find_package(JNI REQUIRED)

list(APPEND JVM_SOURCES
${PROJECT_SOURCE_DIR}/jvm-packages/xgboost4j/src/native/xgboost4j.cpp
${PROJECT_SOURCE_DIR}/jvm-packages/xgboost4j-gpu/src/native/xgboost4j-gpu.cpp)
${PROJECT_SOURCE_DIR}/jvm-packages/xgboost4j/src/native/xgboost4j-gpu.cpp)

if(USE_CUDA)
list(APPEND JVM_SOURCES
${PROJECT_SOURCE_DIR}/jvm-packages/xgboost4j-gpu/src/native/xgboost4j-gpu.cu)
${PROJECT_SOURCE_DIR}/jvm-packages/xgboost4j/src/native/xgboost4j-gpu.cu)
endif()

add_library(xgboost4j SHARED ${JVM_SOURCES} ${XGBOOST_OBJ_SOURCES})
Expand Down
67 changes: 67 additions & 0 deletions jvm-packages/aggregator-gpu/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost-jvm_2.12</artifactId>
<version>2.2.0-SNAPSHOT</version>
</parent>

<name>xgboost-spark-gpu</name>
<artifactId>xgboost-spark-gpu_2.12</artifactId>

<dependencies>
<dependency>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost4j_2.12</artifactId>
<version>${project.version}</version>
<scope>compile</scope>
</dependency>

<dependency>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost4j-spark_2.12</artifactId>
<version>${project.version}</version>
<scope>compile</scope>
</dependency>

<dependency>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost4j-spark-gpu_2.12</artifactId>
<version>${project.version}</version>
<scope>compile</scope>
</dependency>
</dependencies>

<build>
<finalName>xgboost-spark-gpu_2.12-${project.version}</finalName>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<configuration>
<shadedArtifactAttached>false</shadedArtifactAttached>
<createDependencyReducedPom>true</createDependencyReducedPom>
<artifactSet>
<includes>
<include>ml.dmlc:xgboost4j_2.12</include>
<include>ml.dmlc:xgboost4j-spark_2.12</include>
<include>ml.dmlc:xgboost4j-spark-gpu_2.12</include>
</includes>
</artifactSet>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>

</project>
59 changes: 59 additions & 0 deletions jvm-packages/aggregator/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost-jvm_2.12</artifactId>
<version>2.2.0-SNAPSHOT</version>
</parent>

<name>xgboost-spark</name>
<artifactId>xgboost-spark_2.12</artifactId>

<dependencies>
<dependency>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost4j_2.12</artifactId>
<version>${project.version}</version>
<scope>compile</scope>
</dependency>

<dependency>
<groupId>ml.dmlc</groupId>
<artifactId>xgboost4j-spark_2.12</artifactId>
<version>${project.version}</version>
<scope>compile</scope>
</dependency>
</dependencies>

<build>
<finalName>xgboost-spark_2.12-${project.version}</finalName>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<configuration>
<shadedArtifactAttached>false</shadedArtifactAttached>
<createDependencyReducedPom>true</createDependencyReducedPom>
<artifactSet>
<includes>
<include>ml.dmlc:xgboost4j_2.12</include>
<include>ml.dmlc:xgboost4j-spark_2.12</include>
</includes>
</artifactSet>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>

</project>
2 changes: 1 addition & 1 deletion jvm-packages/checkstyle.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@
<property name="braceAdjustment" value="0"/>
<property name="caseIndent" value="2"/>
<property name="throwsIndent" value="4"/>
<property name="lineWrappingIndentation" value="4"/>
<property name="lineWrappingIndentation" value="2"/>
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's make this change in another PR

<property name="arrayInitIndent" value="2"/>
</module>
<module name="ImportOrder">
Expand Down
34 changes: 17 additions & 17 deletions jvm-packages/create_jni.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,14 +131,6 @@ def native_build(args):
run("cmake .. " + " ".join(args))
run("cmake --build . --config Release" + maybe_parallel_build)

with cd("demo/CLI/regression"):
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"
)

print("copying native library")
library_name, os_folder = {
Expand All @@ -155,26 +147,34 @@ def native_build(args):
"arm64": "aarch64", # on macOS & Windows ARM 64-bit
"aarch64": "aarch64",
}[platform.machine().lower()]
output_folder = "{}/src/main/resources/lib/{}/{}".format(
xgboost4j, os_folder, arch_folder
output_folder = "xgboost4j/src/main/resources/lib/{}/{}".format(
os_folder, arch_folder
)
maybe_makedirs(output_folder)
cp("../lib/" + library_name, output_folder)

print("copying train/test files")
maybe_makedirs("{}/src/test/resources".format(xgboost4j_spark))

# for xgboost4j
maybe_makedirs("xgboost4j/src/test/resources")
for file in glob.glob("../demo/data/agaricus.*"):
cp(file, "xgboost4j/src/test/resources")

# for xgboost4j-spark
maybe_makedirs("xgboost4j-spark/src/test/resources")
with cd("../demo/CLI/regression"):
run(f'"{sys.executable}" mapfeat.py')
run(f'"{sys.executable}" mknfold.py machine.txt 1')

for file in glob.glob("../demo/CLI/regression/machine.txt.t*"):
cp(file, "{}/src/test/resources".format(xgboost4j_spark))
cp(file, "xgboost4j-spark/src/test/resources")
for file in glob.glob("../demo/data/agaricus.*"):
cp(file, "{}/src/test/resources".format(xgboost4j_spark))
cp(file, "xgboost4j-spark/src/test/resources")

maybe_makedirs("{}/src/test/resources".format(xgboost4j))
for file in glob.glob("../demo/data/agaricus.*"):
cp(file, "{}/src/test/resources".format(xgboost4j))
# for xgboost4j-spark-gpu
if cli_args.use_cuda == "ON":
maybe_makedirs("xgboost4j-spark-gpu/src/test/resources")
for file in glob.glob("../demo/data/veterans_lung_cancer.csv"):
cp(file, "xgboost4j-spark-gpu/src/test/resources")


if __name__ == "__main__":
Expand Down
Loading
Loading