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

[ML-101] [Release] Add version update scripts and improve scripts for examples #102

Merged
merged 4 commits into from
Jul 27, 2021
Merged

[ML-101] [Release] Add version update scripts and improve scripts for examples #102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e5b1a66
add set version script and update example versions
xwu99 Jul 26, 2021
27c7dc4
merge master
xwu99 Jul 27, 2021
df7a2c1
improve example test scripts
xwu99 Jul 27, 2021
26271f5
update
xwu99 Jul 27, 2021
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
19 changes: 19 additions & 0 deletions dev/set-examples-version.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
#!/usr/bin/env bash

SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"

SPARK_VERSION=3.1.1
OAP_VERSION=1.2.0
OAP_EXAMPLE_VERSION=$OAP_VERSION

exampleDirs=(kmeans pca als naive-bayes linear-regression)

cd $SCRIPT_DIR/../examples

for dir in ${exampleDirs[*]}
do
cd $dir
mvn versions:set -DnewVersion=$OAP_EXAMPLE_VERSION
mvn versions:set-property -Dproperty=spark.version -DnewVersion=$SPARK_VERSION
cd ..
done
7 changes: 7 additions & 0 deletions dev/set-pom-version.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
#!/usr/bin/env bash

SPARK_VERSION=3.1.1
OAP_VERSION=1.2.0

mvn versions:set -DnewVersion=$OAP_VERSION
mvn versions:set-property -Dproperty=spark.version -DnewVersion=$SPARK_VERSION
5 changes: 3 additions & 2 deletions examples/als-pyspark/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,15 @@ source ../../conf/env.sh

# Data file is converted from oneDAL examples ($DAALROOT/examples/daal/data/batch/implicit_als_csr.csv)
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/onedal_als_csr_ratings.txt
DATA_FILE=$HDFS_ROOT/data/onedal_als_csr_ratings.txt

APP_PY=als-pyspark.py

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 2 additions & 2 deletions examples/als/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

<groupId>com.intel.oap</groupId>
<artifactId>oap-mllib-examples</artifactId>
<version>${oap.version}-with-spark-${spark.version}</version>
<version>1.2.0</version>
<packaging>jar</packaging>

<name>ALSExample</name>
Expand All @@ -15,7 +15,7 @@
<oap.version>1.2.0</oap.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<spark.version>3.0.0</spark.version>
<spark.version>3.1.1</spark.version>
</properties>

<dependencies>
Expand Down
7 changes: 4 additions & 3 deletions examples/als/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,15 +4,16 @@ source ../../conf/env.sh

# Data file is converted from oneDAL examples ($DAALROOT/examples/daal/data/batch/implicit_als_csr.csv)
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/onedal_als_csr_ratings.txt
DATA_FILE=$HDFS_ROOT/data/onedal_als_csr_ratings.txt

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION-with-spark-3.0.0.jar
APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.ALSExample

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 3 additions & 1 deletion examples/build-all.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
#!/usr/bin/env bash

for dir in kmeans pca als naive-bayes linear-regression
exampleDirs=(kmeans pca als naive-bayes linear-regression)

for dir in ${exampleDirs[*]}
do
cd $dir
./build.sh
Expand Down
5 changes: 3 additions & 2 deletions examples/kmeans-pyspark/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,15 @@ source ../../conf/env.sh

# Data file is from Spark Examples (data/mllib/sample_kmeans_data.txt) and put in examples/data
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/sample_kmeans_data.txt
DATA_FILE=$HDFS_ROOT/data/sample_kmeans_data.txt

APP_PY=kmeans-pyspark.py

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 2 additions & 2 deletions examples/kmeans/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

<groupId>com.intel.oap</groupId>
<artifactId>oap-mllib-examples</artifactId>
<version>${oap.version}-with-spark-${spark.version}</version>
<version>1.2.0</version>
<packaging>jar</packaging>

<name>KMeansExample</name>
Expand All @@ -15,7 +15,7 @@
<oap.version>1.2.0</oap.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<spark.version>3.0.0</spark.version>
<spark.version>3.1.1</spark.version>
</properties>

<dependencies>
Expand Down
23 changes: 15 additions & 8 deletions examples/kmeans/run-gpu-standalone.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,27 +4,34 @@ source ../../conf/env.sh

# Data file is from Spark Examples (data/mllib/sample_kmeans_data.txt) and put in examples/data
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/sample_kmeans_data.txt
DATA_FILE=$HDFS_ROOT/data/sample_kmeans_data.txt

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.KMeansExample

RESOURCE_FILE=$PWD/IntelGpuResourceFile.json
WORKER_GPU_AMOUNT=4
EXECUTOR_GPU_AMOUNT=1
TASK_GPU_AMOUNT=1
USE_GPU=true

# Should run in standalone mode
time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--total-executor-cores $SPARK_TOTAL_CORES \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
--conf "spark.sql.shuffle.partitions=$SPARK_DEFAULT_PARALLELISM" \
--conf "spark.driver.extraClassPath=$SPARK_DRIVER_CLASSPATH" \
--conf "spark.executor.extraClassPath=$SPARK_EXECUTOR_CLASSPATH" \
--conf "spark.worker.resource.gpu.amount=4" \
--conf "spark.worker.resourcesFile=$PWD/IntelGpuResourceFile.json" \
--conf "spark.oap.mllib.useGPU=true" \
--conf "spark.executor.resource.gpu.amount=1" \
--conf "spark.task.resource.gpu.amount=1" \
--conf "spark.oap.mllib.useGPU=$USE_GPU" \
--conf "spark.worker.resourcesFile=$RESOURCE_FILE" \
--conf "spark.worker.resource.gpu.amount=$WORKER_GPU_AMOUNT" \
--conf "spark.executor.resource.gpu.amount=$EXECUTOR_GPU_AMOUNT" \
--conf "spark.task.resource.gpu.amount=$TASK_GPU_AMOUNT" \
--conf "spark.shuffle.reduceLocality.enabled=false" \
--conf "spark.network.timeout=1200s" \
--conf "spark.task.maxFailures=1" \
Expand Down
6 changes: 3 additions & 3 deletions examples/kmeans/run-cpu.sh → examples/kmeans/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,16 +4,16 @@ source ../../conf/env.sh

# Data file is from Spark Examples (data/mllib/sample_kmeans_data.txt) and put in examples/data
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/sample_kmeans_data.txt
DATA_FILE=$HDFS_ROOT/data/sample_kmeans_data.txt

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.KMeansExample

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--total-executor-cores $SPARK_TOTAL_CORES \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 2 additions & 2 deletions examples/linear-regression/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

<groupId>com.intel.oap</groupId>
<artifactId>oap-mllib-examples</artifactId>
<version>${oap.version}-with-spark-${spark.version}</version>
<version>1.2.0</version>
<packaging>jar</packaging>

<name>LinearRegressionExample</name>
Expand All @@ -15,7 +15,7 @@
<oap.version>1.2.0</oap.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<spark.version>3.0.0</spark.version>
<spark.version>3.1.1</spark.version>
</properties>

<dependencies>
Expand Down
13 changes: 7 additions & 6 deletions examples/linear-regression/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,18 +2,19 @@

source ../../conf/env.sh

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION-with-spark-3.0.0.jar
APP_CLASS=org.apache.spark.examples.ml.LinearRegressionExample
DATA_FILE=data/sample_linear_regression_data.txt
# Data file is from Spark Examples (data/mllib/sample_linear_regression_data.txt) and put in examples/data
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=$HDFS_ROOT/data/sample_linear_regression_data.txt

OAP_MLLIB_ENABLED=true
APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.LinearRegressionExample

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.oap.mllib.enabled=$OAP_MLLIB_ENABLED" \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
--conf "spark.sql.shuffle.partitions=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 2 additions & 2 deletions examples/naive-bayes/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

<groupId>com.intel.oap</groupId>
<artifactId>oap-mllib-examples</artifactId>
<version>${oap.version}-with-spark-${spark.version}</version>
<version>1.2.0</version>
<packaging>jar</packaging>

<name>NaiveBayesExample</name>
Expand All @@ -15,7 +15,7 @@
<oap.version>1.2.0</oap.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<spark.version>3.0.0</spark.version>
<spark.version>3.1.1</spark.version>
</properties>

<dependencies>
Expand Down
13 changes: 8 additions & 5 deletions examples/naive-bayes/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,16 +2,19 @@

source ../../conf/env.sh

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION-with-spark-3.0.0.jar
# Data file is from Spark Examples (data/mllib/sample_libsvm_data.txt) and put in examples/data
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=$HDFS_ROOT/data/sample_libsvm_data.txt

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.NaiveBayesExample
DATA_FILE=data/sample_libsvm_data.txt

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.oap.mllib.enabled=true" \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
--conf "spark.sql.shuffle.partitions=$SPARK_DEFAULT_PARALLELISM" \
Expand All @@ -22,5 +25,5 @@ time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--conf "spark.task.maxFailures=1" \
--jars $OAP_MLLIB_JAR \
--class $APP_CLASS \
$APP_JAR $DATA_FILE $K \
$APP_JAR $DATA_FILE \
2>&1 | tee NaiveBayes-$(date +%m%d_%H_%M_%S).log
56 changes: 0 additions & 56 deletions examples/pca-pyspark/run-vanilla.sh
View file
Open in desktop

This file was deleted.

5 changes: 3 additions & 2 deletions examples/pca-pyspark/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,15 +4,16 @@ source ../../conf/env.sh

# CSV data is the same as in Spark example "ml/pca_example.py"
# The data file should be copied to $HDFS_ROOT before running examples
DATA_FILE=data/pca_data.csv
DATA_FILE=$HDFS_ROOT/data/pca_data.csv

APP_PY=pca-pyspark.py
K=3

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
4 changes: 2 additions & 2 deletions examples/pca/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

<groupId>com.intel.oap</groupId>
<artifactId>oap-mllib-examples</artifactId>
<version>${oap.version}-with-spark-${spark.version}</version>
<version>1.2.0</version>
<packaging>jar</packaging>

<name>PCAExample</name>
Expand All @@ -15,7 +15,7 @@
<oap.version>1.2.0</oap.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<spark.version>3.0.0</spark.version>
<spark.version>3.1.1</spark.version>
</properties>

<dependencies>
Expand Down
7 changes: 5 additions & 2 deletions examples/pca/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,16 @@

source ../../conf/env.sh

APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION-with-spark-3.0.0.jar
APP_JAR=target/oap-mllib-examples-$OAP_MLLIB_VERSION.jar
APP_CLASS=org.apache.spark.examples.ml.PCAExample

# Dataset is created in the code, so no need to pass in as parameter

time $SPARK_HOME/bin/spark-submit --master $SPARK_MASTER -v \
--num-executors $SPARK_NUM_EXECUTORS \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-cores $SPARK_EXECUTOR_CORES \
--total-executor-cores $SPARK_TOTAL_CORES \
--driver-memory $SPARK_DRIVER_MEMORY \
--executor-memory $SPARK_EXECUTOR_MEMORY \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf "spark.default.parallelism=$SPARK_DEFAULT_PARALLELISM" \
Expand Down
Loading