recommend-emr-dataprocess/qiaojialiang/handle_0724.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'
today="$(date +%Y%m%d)"
today_early_3="$(date -d '3 days ago' +%Y%m%d)"
#table='alg_recsys_sample_all_test'
# 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="$(date -d '2 days ago' +%Y%m%d)"
end_early_2_Str="$(date -d '2 days ago' +%Y%m%d)"
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/
# 特征值
valueDataPath=/dw/recommend/model/14_feature_data/
# 特征分桶
bucketDataPath=/dw/recommend/model/43_recsys_train_data/
# 模型数据路径
MODEL_PATH=/root/joe/recommend-emr-dataprocess/model
# 预测路径
PREDICT_PATH=/root/joe/recommend-emr-dataprocess/predict
# 历史线上正在使用的模型数据路径
LAST_MODEL_HOME=/root/joe/model_online
# 模型数据文件前缀
model_name=model_nba8
# fm模型
FM_HOME=/root/sunmingze/alphaFM/bin
# hadoop
HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop
OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/


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:20240716 endStr:20240722 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"
   /root/anaconda3/bin/python monitor_util.py --level error --msg "荐模型数据更新 \n【任务名称】:step3训练数据产出\n【是否成功】:error\n【信息】: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