recommend-emr-dataprocess/ad/test_32.sh

#!/bin/sh
set -x

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
export SPARK_HOME=/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8


sh_path=$(dirname $0)
source ${sh_path}/00_common.sh

source /root/anaconda3/bin/activate py37

today_early_1="$(date -d '1 days ago' +%Y%m%d)"
TRAIN_PATH=/dw/recommend/model/31_ad_sample_data_dev_20250623
TABLE=alg_recsys_ad_sample_all


make_32() {
  local step_start_time=$(date +%s)

  /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_ad.v20240718.makedata_ad_31_originData_20250623 \
    --master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
    ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \

    readPath:/dw/recommend/model/31_ad_sample_data_dev_20250623 \
    savePath:/dw/recommend/model/32_bucket_data_dev_20250623 \
    fileName:ad_bucket_688.txt
    local task1=$!
    wait ${task1}
    local task1_return_code=$?


}

end_date="20250628"
date_offset=21        # 修改为需要向前推的天数

# 循环计算并输出日期
for ((i=0; i<=date_offset; i++)); do
    # 计算当前偏移日期（结束日期 - i天）
    today_early_1=$(date -d "$end_date - $i days" +%Y%m%d)
    echo $today_early_1
  make_origin_data
done