[jvm-packages] upgrade to Scala 2.12 (#4574)

* bump scala to 2.12 which requires java 8 and also newer flink and akka

* put scala version in artifactId

* fix appveyor

* fix for scaladoc issue that looks like https://github.com/scala/bug/issues/10509

* fix ci_build

* update versions in generate_pom.py

* fix generate_pom.py

* apache does not have a download for spark 2.4.3 distro using scala 2.12 yet, so for now i use a tgz i put on s3

* Upload spark-2.4.3-bin-scala2.12-hadoop2.7.tgz to our own S3

* Update Dockerfile.jvm_cross

* Update Dockerfile.jvm_cross
This commit is contained in:
koertkuipers
2019-07-16 11:43:34 -04:00
committed by Nan Zhu
parent 5544a730f1
commit 3c506b076e
12 changed files with 67 additions and 56 deletions

View File

@@ -15,14 +15,16 @@ RUN \
# Python
wget https://repo.continuum.io/miniconda/Miniconda3-4.5.12-Linux-x86_64.sh && \
bash Miniconda3-4.5.12-Linux-x86_64.sh -b -p /opt/python && \
/opt/python/bin/pip install awscli && \
# Maven
wget http://apache.osuosl.org/maven/maven-3/3.6.1/binaries/apache-maven-3.6.1-bin.tar.gz && \
tar xvf apache-maven-3.6.1-bin.tar.gz -C /opt && \
ln -s /opt/apache-maven-3.6.1/ /opt/maven && \
# Spark
wget https://archive.apache.org/dist/spark/spark-$SPARK_VERSION/spark-$SPARK_VERSION-bin-hadoop2.7.tgz && \
tar xvf spark-$SPARK_VERSION-bin-hadoop2.7.tgz -C /opt && \
ln -s /opt/spark-$SPARK_VERSION-bin-hadoop2.7 /opt/spark
# This should be: wget https://archive.apache.org/dist/spark/spark-$SPARK_VERSION/spark-$SPARK_VERSION-bin-scala2.12-hadoop2.7.tgz
/opt/python/bin/python -m awscli s3 cp s3://xgboost-ci-jenkins-artifacts/spark-$SPARK_VERSION-bin-scala2.12-hadoop2.7.tgz . && \
tar xvf spark-$SPARK_VERSION-bin-scala2.12-hadoop2.7.tgz -C /opt && \
ln -s /opt/spark-$SPARK_VERSION-bin-scala2.12-hadoop2.7 /opt/spark
ENV PATH=/opt/python/bin:/opt/spark/bin:/opt/maven/bin:$PATH

View File

@@ -16,10 +16,10 @@ scala_version=$(mvn help:evaluate -Dexpression=scala.version -q -DforceStdout)
scala_binary_version=$(mvn help:evaluate -Dexpression=scala.binary.version -q -DforceStdout)
# Install XGBoost4J JAR into local Maven repository
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j/target/xgboost4j-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j -Dversion=${xgboost4j_version} -Dpackaging=jar
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j/target/xgboost4j-${xgboost4j_version}-tests.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j -Dversion=${xgboost4j_version} -Dpackaging=test-jar -Dclassifier=tests
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j-spark/target/xgboost4j-spark-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j-spark -Dversion=${xgboost4j_version} -Dpackaging=jar
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j-example/target/xgboost4j-example-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j-example -Dversion=${xgboost4j_version} -Dpackaging=jar
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
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j/target/xgboost4j_${scala_binary_version}-${xgboost4j_version}-tests.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j_${scala_binary_version} -Dversion=${xgboost4j_version} -Dpackaging=test-jar -Dclassifier=tests
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j-spark/target/xgboost4j-spark_${scala_binary_version}-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j-spark_${scala_binary_version} -Dversion=${xgboost4j_version} -Dpackaging=jar
mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j-example/target/xgboost4j-example_${scala_binary_version}-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j-example_${scala_binary_version} -Dversion=${xgboost4j_version} -Dpackaging=jar
cd xgboost4j-tester
# Generate pom.xml for XGBoost4J-tester, a dummy project to run XGBoost4J tests
@@ -28,14 +28,14 @@ python3 ./generate_pom.py ${xgboost4j_version} ${maven_compiler_source} ${maven_
mvn --no-transfer-progress package
# Run integration tests with XGBoost4J
java -jar ./target/xgboost4j-tester-1.0-SNAPSHOT-jar-with-dependencies.jar
java -jar ./target/xgboost4j-tester_${scala_binary_version}-1.0-SNAPSHOT-jar-with-dependencies.jar
# Run integration tests with XGBoost4J-Spark
if [ ! -z "$RUN_INTEGRATION_TEST" ]
then
python3 get_iris.py
spark-submit --class ml.dmlc.xgboost4j.scala.example.spark.SparkTraining --master 'local[8]' ./target/xgboost4j-tester-1.0-SNAPSHOT-jar-with-dependencies.jar ${PWD}/iris.csv
spark-submit --class ml.dmlc.xgboost4j.scala.example.spark.SparkMLlibPipeline --master 'local[8]' ./target/xgboost4j-tester-1.0-SNAPSHOT-jar-with-dependencies.jar ${PWD}/iris.csv ${PWD}/native_model ${PWD}/pipeline_model
spark-submit --class ml.dmlc.xgboost4j.scala.example.spark.SparkTraining --master 'local[8]' ./target/xgboost4j-tester_${scala_binary_version}-1.0-SNAPSHOT-jar-with-dependencies.jar ${PWD}/iris.csv
spark-submit --class ml.dmlc.xgboost4j.scala.example.spark.SparkMLlibPipeline --master 'local[8]' ./target/xgboost4j-tester_${scala_binary_version}-1.0-SNAPSHOT-jar-with-dependencies.jar ${PWD}/iris.csv ${PWD}/native_model ${PWD}/pipeline_model
fi
set +x