recommend-emr-dataprocess/ad_display/make_data.sh

#!/bin/bash

start_date=""
end_date=""
table=""
if(($#==3))
then
    start_date=$1
    end_date=$2
    table=$3
else
    start_date=20251216
    end_date=20251216
    table=alg_ad_display_fission_rate_20251218
fi

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

# params
savePath=/dw/recommend/model/ad_display/data

# 1 生产原始数据
echo "$(date +%Y-%m-%d_%H-%M-%S)----------step1------------开始根据${table}生产原始数据"
set -x
/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_display_ad_20251218 \
--master yarn --driver-memory 4G --executor-memory 6G --executor-cores 1 --num-executors 8 \
--conf spark.yarn.executor.memoryoverhead=2048 \
/mnt/disk1/jch/recommend-emr-dataprocess/target/spark-examples-1.0.0-SNAPSHOT-jar-with-dependencies.jar \
table:${table} \
tablePart:64 \
beginStr:${start_date} \
endStr:${end_date} \
repartition:32 \
savePath:${savePath} \