feat:修改定时任务脚本

ad/01_ad_model_update_everyday.sh

@@ -13,7 +13,7 @@ MODEL_PATH=/root/zhaohp/recommend-emr-dataprocess/model
 PREDICT_PATH=/root/zhaohp/recommend-emr-dataprocess/predict
 HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop
 FM_HOME=/root/sunmingze/alphaFM
-OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/
+OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/ad_model/
 max_hour=17
 max_minute=00
 OSS_ONLINE_MODEL_PATH=${OSS_PATH}/${model_name}.txt
@@ -24,63 +24,63 @@ export HADOOP_CONF_DIR=/etc/taihao-apps/hadoop-conf
 export JAVA_HOME=/usr/lib/jvm/java-1.8.0
 
 ## 1 判断依赖的数据表是否生产完成
-#source /root/anaconda3/bin/activate py37
-#while true; do
-#  python_return_code=$(python ad/ad_utils.py --excute_program check_ad_origin_hive --partition ${today} --hh 10)
-#  if [ $python_return_code -eq 0 ]; then
-#    echo "Python程序返回0，退出循环。"
-#    break
-#  fi
-#  echo "Python程序返回非0值，等待五分钟后再次调用。"
-#  sleep 300
-#  current_hour=$(date +%H)
-#  current_minute=$(date +%M)
-#  if (( current_hour > max_hour || (current_hour == max_hour && current_minute >= max_minute) )); then
-#    echo "最长等待时间已到，失败:${current_hour}-${current_minute}"
-#    msg="广告特征数据校验失败，大数据分区没有数据: ${today}10"
-#    /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
-#    exit 1
-#  fi
-#done
-#
-#
-## 2 原始特征生成
-#/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
-#--class com.aliyun.odps.spark.zhp.makedata_ad.makedata_ad_31_originData_20240620 \
-#--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
-#./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-#tablePart:64 repartition:16 \
-#beginStr:${today_early_1}00 endStr:${today}10 \
-#savePath:${originDataSavePath} \
-#table:alg_recsys_ad_sample_all filterHours:00,01,02,03,04,05,06,07 \
-#idDefaultValue:0.01
-#if [ $? -ne 0 ]; then
-#   echo "Spark原始样本生产任务执行失败"
-#   msg="广告特征数据生成失败，Spark原始样本生产任务执行失败"
-#   /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
-#   exit 1
-#else
-#    echo "spark原始样本生产执行成功"
-#fi
-#
-#
-## 3 特征分桶
-#/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
-#--class com.aliyun.odps.spark.zhp.makedata_ad.makedata_ad_33_bucketData_20240622 \
-#--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
-#./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-#beginStr:${today_early_1} endStr:${today} repartition:100 \
-#filterNames:adid_,targeting_conversion_ \
-#readPath:${originDataSavePath} \
-#savePath:${bucketFeatureSavePath}
-#if [ $? -ne 0 ]; then
-#   echo "Spark特征分桶处理任务执行失败"
-#   msg="广告特征分桶失败，Spark特征分桶处理任务执行失败"
-#   /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
-#   exit 1
-#else
-#   echo "spark特征分桶处理执行成功"
-#fi
+source /root/anaconda3/bin/activate py37
+while true; do
+  python_return_code=$(python ad/ad_utils.py --excute_program check_ad_origin_hive --partition ${today} --hh 10)
+  if [ $python_return_code -eq 0 ]; then
+    echo "Python程序返回0，退出循环。"
+    break
+  fi
+  echo "Python程序返回非0值，等待五分钟后再次调用。"
+  sleep 300
+  current_hour=$(date +%H)
+  current_minute=$(date +%M)
+  if (( current_hour > max_hour || (current_hour == max_hour && current_minute >= max_minute) )); then
+    echo "最长等待时间已到，失败:${current_hour}-${current_minute}"
+    msg="广告特征数据校验失败，大数据分区没有数据: ${today}10"
+    /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
+    exit 1
+  fi
+done
+
+
+# 2 原始特征生成
+/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
+--class com.aliyun.odps.spark.zhp.makedata_ad.makedata_ad_31_originData_20240620 \
+--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
+./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+tablePart:64 repartition:16 \
+beginStr:${today_early_1}00 endStr:${today}10 \
+savePath:${originDataSavePath} \
+table:alg_recsys_ad_sample_all filterHours:00,01,02,03,04,05,06,07 \
+idDefaultValue:0.01
+if [ $? -ne 0 ]; then
+   echo "Spark原始样本生产任务执行失败"
+   msg="广告特征数据生成失败，Spark原始样本生产任务执行失败"
+   /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
+   exit 1
+else
+    echo "spark原始样本生产执行成功"
+fi
+
+
+# 3 特征分桶
+/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
+--class com.aliyun.odps.spark.zhp.makedata_ad.makedata_ad_33_bucketData_20240622 \
+--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
+./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+beginStr:${today_early_1} endStr:${today} repartition:100 \
+filterNames:adid_,targeting_conversion_ \
+readPath:${originDataSavePath} \
+savePath:${bucketFeatureSavePath}
+if [ $? -ne 0 ]; then
+   echo "Spark特征分桶处理任务执行失败"
+   msg="广告特征分桶失败，Spark特征分桶处理任务执行失败"
+   /root/anaconda3/bin/python ad/ad_monitor_util.py ${msg}
+   exit 1
+else
+   echo "spark特征分桶处理执行成功"
+fi
 
 
 # 4 模型训练