recommend-emr-dataprocess/profile_scripts/make_data.sh

#!/bin/bash

year=""
table=""
if(($#==2))
then
    year=$1
    table=$2
else
    year=2025
    table=alg_recsys_feature_behavior_profile
fi

set -x
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
suffix="y,8,4,0,e,a,c,k,o,w,g,s,u,q,i,m"
savePath=/dw/recommend/model/user_profile/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"

/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_profile_20251114 \
--master yarn --driver-memory 4G --executor-memory 6G --executor-cores 1 --num-executors 16 \
--conf spark.yarn.executor.memoryoverhead=2048 \
/mnt/disk1/jch/recommend-emr-dataprocess/target/spark-examples-1.0.0-SNAPSHOT-jar-with-dependencies.jar \
table:${table} tablePart:48 \
year:${year} \
suffix:${suffix} \
repartition:32 \
savePath:${savePath} \