recommend-emr-dataprocess/ad/test_33.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)"
start_date="20250607"
end_date="20250629"


TRAIN_PATH=/dw/recommend/model/31_ad_sample_data_dev_20250623
BUCKET_FEATURE_PATH=/dw/recommend/model/dev_20250623/33_ad_train_data

make_bucket_feature() {

  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_33_bucketData_20250110 \
  --master yarn --driver-memory 2G --executor-memory 3G --executor-cores 1 --num-executors 16 \
  ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
  beginStr:${start_date} endStr:${end_date} repartition:64 \
  filterNames:_4h_,_5h_,adid_,targeting_conversion_ \
  bucketFileName:20250217_ad_bucket_707.txt \
  readPath:${TRAIN_PATH} \
  savePath:${BUCKET_FEATURE_PATH}

  local return_code=$?
  check_run_status ${return_code} ${step_start_time} "spark特征分桶任务"
}

make_bucket_feature