recommend-emr-dataprocess/rec_scripts/rov/sample/scripts/v1/rov_sample_v1.sh

#!/bin/sh
set -x

start_date=""
end_date=""
feature_file=""
if(($#==3))
then
  start_date=$1
  end_date=$2
  feature_file=$3
else
  exit -1
fi

# env
export SPARK_HOME=/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8
export PATH=$SPARK_HOME/bin:$PATH
export HADOOP_CONF_DIR=/etc/taihao-apps/hadoop-conf
export JAVA_HOME=/usr/lib/jvm/java-1.8.0

# param
sampleRate=2
readPath=/dw/recommend/model/83_origin_data/
savePath=/dw/recommend/model/831_recsys_rov_train_data/

echo `date` "rov sample"
/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
--class com.aliyun.odps.spark.examples.makedata_recsys_r_rate.makedata_recsys_86_fm_sample_20250627 \
--master yarn --driver-memory 2G --executor-memory 6G --executor-cores 1 --num-executors 24 \
--files ${feature_file} \
/mnt/disk1/jch/recommend-emr-dataprocess/target/spark-examples-1.0.0-SNAPSHOT-jar-with-dependencies.jar \
readPath:${readPath} \
beginStr:${start_date} endStr:${end_date} \
whatApps:0,4,32,31,21,29,27,26,28,34,3,36,6,17,35 \
whatPages:"详情后沉浸页,回流后沉浸页&内页feed,首页feed,详情页" \
whatLabel:is_return_noself \
fuSampleRate:${sampleRate} \
notUseBucket:1 \
featureName:${feature_file} \
featureBucket:20241209_recsys_rov_bucket.txt \
repartition:64 \
savePath:${savePath} \