推荐模型自动化更新-check auc+模型数据处理

qiaojialiang/handle_rov.sh

@@ -31,51 +31,92 @@ 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=akaqjl8
+model_name=aka8
 # 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/
 
 
 
 # 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"
-#$HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/bin/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}/bin/fm_predict -m ${MODEL_PATH}/${model_name}_${today_early_3}.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_new.txt
-#
-#online_auc=`cat ${PREDICT_PATH}/${model_name}_${today}_online.txt | /root/sunmingze/AUC/AUC`
-#if [ $? -ne 0 ]; then
-#   echo "推荐线上模型AUC计算失败"
-##   /root/anaconda3/bin/python ad/ad_monitor_util.py "线上模型AUC计算失败"
-#   exit 1
-#fi
-#
-#new_auc=`${PREDICT_PATH}/${model_name}_${today}_new.txt | /root/sunmingze/AUC/AUC`
-#if [ $? -ne 0 ]; then
-#   echo "推荐新模型AUC计算失败"
-##   /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型AUC计算失败"
-#   exit 1
-#fi
-#
-#
-## 1 对比auc数据判断是否更新线上模型
-#if [ "$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}"
-#    # todo 模型格式转换
-#
-#    # todo 模型文件上传OSS
-#
-#    # todo 本地保存最新的线上使用的模型，用于下一次的AUC验证
-##    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型优于线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
-#else
-#    echo "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
-##    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
-#fi
-
-
-
-# 2 判断上游表是否生产完成，最长等待到12点
+echo "$(date +%Y-%m-%d_%H-%M-%S)----------step0------------开始对比，新：${MODEL_PATH}/${model_name}_${today_early_3}.txt，与线上online模型数据auc效果"
+$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
+
+online_auc=`cat ${PREDICT_PATH}/${model_name}_${today}_online.txt | /root/sunmingze/AUC/AUC`
+if [ $? -ne 0 ]; then
+   echo "推荐线上模型AUC计算失败"
+#   /root/anaconda3/bin/python ad/ad_monitor_util.py "线上模型AUC计算失败"
+   exit 1
+fi
+
+new_auc=`cat ${PREDICT_PATH}/${model_name}_${today}_new.txt | /root/sunmingze/AUC/AUC`
+if [ $? -ne 0 ]; then
+   echo "推荐新模型AUC计算失败"
+#   /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型AUC计算失败"
+   exit 1
+fi
+
+
+# 1 对比auc数据判断是否更新线上模型
+if [ "$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
+    cat ${MODEL_PATH}/${model_name}_${today_early_3}.txt |
+    awk -F " " '{
+        if (NR == 1) {
+            print $1"\t"$2
+        } else {
+            split($0, fields, " ");
+            OFS="\t";
+            line="" 1; i <= 10 && i <= length(fields); i++) {
+                line
+            for (i = = (line ? line "\t" : "") fields[i];
+            }
+            print line
+        }
+    }' > ${MODEL_PATH}/${model_name}_${today_early_3}_change.txt
+    if [ $? -ne 0 ]; then
+       echo "新模型文件格式转换失败"
+#       /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型文件格式转换失败"
+       exit 1
+    fi
+    # 1.2 模型文件上传OSS
+    online_model_path=${OSS_PATH}/${model_name}.txt
+    $HADOOP fs -test -e ${online_model_path}
+    if [ $? -eq 0 ]; then
+        echo "数据存在, 先删除。"
+        $HADOOP fs -rm -r -skipTrash ${online_model_path}
+    else
+        echo "数据不存在"
+    fi
+
+    $HADOOP fs -put ${MODEL_PATH}/${model_name}_${today_early_3}_change.txt ${online_model_path}
+    if [ $? -eq 0 ]; then
+       echo "推荐模型文件至OSS成功"
+    else
+       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
+    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
+       echo "模型备份失败"
+#       /root/anaconda3/bin/python ad/ad_monitor_util.py "模型备份失败 - 最新模型地址: ${MODEL_PATH}/${model_name}_${today_early_1}.txt"
+       exit 1
+    fi
+#    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型优于线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
+else
+    echo "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
+#    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
+fi
+
+
+
+# 2 判断上游表是否生产完成，最长等待到max_hour点
 # shellcheck disable=SC2154
 echo "$(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