推荐模型自动化更新-handle rov

qiaojialiang/handle_rov.sh

@@ -38,10 +38,80 @@ FM_HOME=/root/sunmingze/alphaFM/bin
 HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop
 OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/
 
+# 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_qiao.makedata_13_originData_20240705 \
+--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:${begin_early_2_Str}${beginHhStr} endStr:${end_early_2_Str}${endHhStr} \
+savePath:${originDataPath} \
+table:${table}
+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
 
-# 0 对比AUC 前置对比2日模型数据 与 线上模型数据效果对比，如果2日模型优于线上，更新线上模型
-echo "$(date +%Y-%m-%d_%H-%M-%S)----------step0------------开始对比，新：${MODEL_PATH}/${model_name}_${today_early_3}.txt，与线上online模型数据auc效果"
+
+# 2 特征值拼接
+echo "$(date +%Y-%m-%d_%H-%M-%S)----------step2------------开始特征值拼接"
+/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
+--class com.aliyun.odps.spark.examples.makedata_qiao.makedata_14_valueData_20240705 \
+--master yarn --driver-memory 1G --executor-memory 3G --executor-cores 1 --num-executors 32 \
+../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+readPath:${originDataPath} \
+savePath:${valueDataPath} \
+beginStr:${begin_early_2_Str} endStr:${end_early_2_Str} repartition:1000
+if [ $? -ne 0 ]; then
+   echo "Spark特征值拼接处理任务执行失败"
+   exit 1
+else
+   echo "spark特征值拼接处理执行成功"
+fi
+
+# 3 特征分桶
+echo "$(date +%Y-%m-%d_%H-%M-%S)----------step3------------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_qiao.makedata_16_bucketData_20240705 \
+--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
+../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+readPath:${valueDataPath} \
+savePath:${bucketDataPath} \
+beginStr:${begin_early_2_Str} endStr:${end_early_2_Str} repartition:1000
+if [ $? -ne 0 ]; then
+   echo "Spark特征分桶处理任务执行失败"
+   exit 1
+else
+   echo "spark特征分桶处理执行成功"
+fi
+
+
+# 4 对比AUC 前置对比2日模型数据 与 线上模型数据效果对比，如果2日模型优于线上，更新线上模型
+echo "$(date +%Y-%m-%d_%H-%M-%S)----------step4------------开始对比，新：${MODEL_PATH}/${model_name}_${today_early_3}.txt，与线上online模型数据auc效果"
 $HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/fm_predict -m ${LAST_MODEL_HOME}/model_online.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_online.txt
 $HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/fm_predict -m ${MODEL_PATH}/${model_name}_${today_early_3}.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_new.txt
 
@@ -60,10 +130,10 @@ if [ $? -ne 0 ]; then
 fi
 
 
-# 1 对比auc数据判断是否更新线上模型
+# 4.1 对比auc数据判断是否更新线上模型
 if [ "$online_auc" \< "$new_auc" ]; then
     echo "新模型优于线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
-    # 1.1 模型格式转换
+    # 4.1.1 模型格式转换
     cat ${MODEL_PATH}/${model_name}_${today_early_3}.txt |
     awk -F " " '{
         if (NR == 1) {
@@ -83,7 +153,7 @@ if [ "$online_auc" \< "$new_auc" ]; then
 #       /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型文件格式转换失败"
        exit 1
     fi
-    # 1.2 模型文件上传OSS
+    # 4.1.2 模型文件上传OSS
     online_model_path=${OSS_PATH}/${model_name}.txt
     $HADOOP fs -test -e ${online_model_path}
     if [ $? -eq 0 ]; then
@@ -100,7 +170,7 @@ if [ "$online_auc" \< "$new_auc" ]; then
        echo "推荐模型文件至OSS失败"
        exit 1
     fi
-    # 1.3 本地保存最新的线上使用的模型，用于下一次的AUC验证
+    # 4.1.3 本地保存最新的线上使用的模型，用于下一次的AUC验证
     cp -f ${LAST_MODEL_HOME}/model_online.txt ${LAST_MODEL_HOME}/model_online_$(date +\%Y\%m\%d).txt
     cp -f ${MODEL_PATH}/${model_name}_${today_early_3}.txt ${LAST_MODEL_HOME}/model_online.txt
     if [ $? -ne 0 ]; then
@@ -116,78 +186,7 @@ fi
 
 
 
-# 2 判断上游表是否生产完成，最长等待到max_hour点
-# shellcheck disable=SC2154
-echo "$(date +%Y-%m-%d_%H-%M-%S)----------step1------------开始校验是否生产完数据，分区信息：beginStr:${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}-${current_minute}"
-    exit 1
-  fi
-done
-
-# 3 生产原始数据
-echo "$(date +%Y-%m-%d_%H-%M-%S)----------step2------------开始根据${table}生产原始数据"
-/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
---class com.aliyun.odps.spark.examples.makedata_qiao.makedata_13_originData_20240705 \
---master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
-../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-tablePart:64 repartition:32 \
-beginStr:${begin_early_2_Str}${beginHhStr} endStr:${end_early_2_Str}${endHhStr} \
-savePath:${originDataPath} \
-table:${table}
-if [ $? -ne 0 ]; then
-   echo "Spark原始样本生产任务执行失败"
-   exit 1
-else
-   echo "spark原始样本生产执行成功"
-fi
-
-
-# 4 特征值拼接
-echo "$(date +%Y-%m-%d_%H-%M-%S)----------step3------------开始特征值拼接"
-/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_qiao.makedata_14_valueData_20240705 \
---master yarn --driver-memory 1G --executor-memory 3G --executor-cores 1 --num-executors 32 \
-../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-readPath:${originDataPath} \
-savePath:${valueDataPath} \
-beginStr:${begin_early_2_Str} endStr:${end_early_2_Str} repartition:1000
-if [ $? -ne 0 ]; then
-   echo "Spark特征值拼接处理任务执行失败"
-   exit 1
-else
-   echo "spark特征值拼接处理执行成功"
-fi
-
-# 5 特征分桶
-echo "$(date +%Y-%m-%d_%H-%M-%S)----------step4------------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_qiao.makedata_16_bucketData_20240705 \
---master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
-../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-readPath:${valueDataPath} \
-savePath:${bucketDataPath} \
-beginStr:${begin_early_2_Str} endStr:${end_early_2_Str} repartition:1000
-if [ $? -ne 0 ]; then
-   echo "Spark特征分桶处理任务执行失败"
-   exit 1
-else
-   echo "spark特征分桶处理执行成功"
-fi
-
-# 6 模型训练
+# 5 模型训练
 echo "$(date +%Y-%m-%d_%H-%M-%S)----------step5------------开始模型训练"
 $HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/fm_train -m ${MODEL_PATH}/${model_name}_${begin_early_2_Str}.txt -dim 1,1,8 -im ${LAST_MODEL_HOME}/model_online.txt -core 8
 if [ $? -ne 0 ]; then