recommend-emr-dataprocess/recommend/data_new_table.sh

#!/bin/sh
set -x

source /root/anaconda3/bin/activate py37

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

#  nohup sh handle_rov.sh > "$(date +%Y%m%d_%H%M%S)_handle_rov.log" 2>&1 &

# 原始数据table name
table='alg_recsys_sample_all_v2'
# 处理分区配置 推荐数据间隔一天生产，所以5日0点使用3日0-23点数据生产new模型数据
begin_early_2_Str=20240728
end_early_2_Str=20240728
beginHhStr=00
endHhStr=23
max_hour=05
max_minute=00
# 各节点产出hdfs文件绝对路径
# 源数据文件
originDataPath=/dw/recommend/model/41_recsys_sample_data_new_table/
# 特征分桶
bucketDataPath=/dw/recommend/model/43_recsys_train_data_new_table/


# hadoop
HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop

# 0 判断上游表是否生产完成，最长等待到max_hour点
# shellcheck disable=SC2154
# echo "$(date +%Y-%m-%d_%H-%M-%S)----------step0------------开始校验是否生产完数据，分区信息：beginStr:${begin_early_2_Str}${beginHhStr},endStr:${end_early_2_Str}${endHhStr}"
# while true; do
#   python_return_code=$(python /root/joe/recommend-emr-dataprocess/qiaojialiang/checkHiveDataUtil.py --table ${table} --beginStr ${begin_early_2_Str}${beginHhStr} --endStr ${end_early_2_Str}${endHhStr})
#   echo "python 返回值：${python_return_code}"
#   if [ $python_return_code -eq 0 ]; then
#     echo "Python程序返回0，校验存在数据，退出循环。"
#     break
#   fi
#   echo "Python程序返回非0值，不存在数据，等待五分钟后再次调用。"
#   sleep 300
#   current_hour=$(date +%H)
#   current_minute=$(date +%M)
#   # shellcheck disable=SC2039
#   if (( current_hour > max_hour || (current_hour == max_hour && current_minute >= max_minute) )); then
#     echo "最长等待时间已到，失败:${current_hour}-${current_minute}"
#     exit 1
#   fi
# done

# 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.makedata_recsys_41_originData_20240709 \
--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
tablePart:64 repartition:32 \
beginStr:${begin_early_2_Str}00 endStr:${end_early_2_Str}09 \
savePath:${originDataPath} \
table:${table} &

/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.makedata_recsys_41_originData_20240709 \
--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
tablePart:64 repartition:32 \
beginStr:${begin_early_2_Str}10 endStr:${end_early_2_Str}15 \
savePath:${originDataPath} \
table:${table} &

/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.makedata_recsys_41_originData_20240709 \
--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
tablePart:64 repartition:32 \
beginStr:${begin_early_2_Str}16 endStr:${end_early_2_Str}23 \
savePath:${originDataPath} \
table:${table} &

wait
if [ $? -ne 0 ]; then
   echo "Spark原始样本生产任务执行失败"
   exit 1
else
   echo "spark原始样本生产执行成功"
fi

# 2 特征分桶
echo "$(date +%Y-%m-%d_%H-%M-%S)----------step2------------根据特征分桶生产重打分特征数据"
/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
--class com.aliyun.odps.spark.examples.makedata_recsys.makedata_recsys_43_bucketData_20240709 \
--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
readPath:${originDataPath} \
savePath:${bucketDataPath} \
beginStr:${begin_early_2_Str} endStr:${end_early_2_Str} repartition:500 \
filterNames:XXXXXXXXX \
fileName:20240609_bucket_314.txt \
whatLabel:is_return whatApps:0,4,21,17
if [ $? -ne 0 ]; then
   echo "Spark特征分桶处理任务执行失败"
   exit 1
else
   echo "spark特征分桶处理执行成功"
fi
echo "$(date +%Y-%m-%d_%H-%M-%S)----------step5------------spark特征分桶处理执行成功:${begin_early_2_Str}"