feat:添加评估结果分析脚本

ad/01_ad_model_update.sh

@@ -22,17 +22,22 @@ feature_file=20240703_ad_feature_name.txt
 model_local_home=/root/zhaohp/XGB/
 
 # 模型HDFS保存路径，测试时修改为其他路径，避免影响线上
-MODEL_PATH=/dw/recommend/model/35_ad_model_test
+MODEL_PATH=/dw/recommend/model/35_ad_model
 # 预测结果保存路径，测试时修改为其他路径，避免影响线上
-PREDICT_RESULT_SAVE_PATH=/dw/recommend/model/34_ad_predict_data_test
+PREDICT_RESULT_SAVE_PATH=/dw/recommend/model/34_ad_predict_data
 # 模型OSS保存路径，测试时修改为其他路径，避免影响线上
-MODEL_OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/model/
+MODEL_OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/
 # 线上模型名，测试时修改为其他模型名，避免影响线上
-model_name=model_xgb_351_1000_v2_test
+model_name=model_xgb_351_1000_v2
 # 本地保存HDFS模型路径文件，测试时修改为其他模型名，避免影响线上
-model_path_file=${model_local_home}/online_model_path_test.txt
+model_path_file=${model_local_home}/online_model_path.txt
 
+# 任务开始时间
+start_time=$(date +%s)
+# 前一天
 today_early_1="$(date -d '1 days ago' +%Y%m%d)"
+# 线上模型在HDFS中的路径
+online_model_path=`cat ${model_path_file}`
 # 训练用的数据路径
 train_data_path=""
 # 评估用的数据路径
@@ -41,11 +46,6 @@ predict_date_path=""
 new_model_predict_result_path=""
 # 模型保存路径
 model_save_path=""
-
-# 任务开始时间
-start_time=$(date +%s)
-# 线上模型在HDFS中的路径
-online_model_path=`cat ${model_path_file}`
 # 评测结果保存路径，后续需要根据此文件评估是否要更新模型
 predict_analyse_file_path=""
 # 保存模型评估的分析结果
@@ -225,13 +225,11 @@ calc_model_predict() {
   check_run_status $return_code $step_start_time "计算Top10差异"
 
   old_incr_rate_avg=$( echo "scale=6; ${old_total_diff} / ${count}" | bc -l )
-  return_code=$?
-  check_run_status $return_code $step_start_time "计算老模型Top10差异"
+  check_run_status $? $step_start_time "计算老模型Top10差异"
 
 
   new_incr_rate_avg=$( echo "scale=6; ${new_total_diff} / ${count}" | bc -l )
-  return_code=$?
-  check_run_status $return_code $step_start_time "计算新模型Top10差异"
+  check_run_status $? $step_start_time "计算新模型Top10差异"
 
   echo "老模型Top10差异平均值: ${old_incr_rate_avg}"
   echo "老模型Top10差异列表: ${old_incr_rate_list}"
@@ -243,29 +241,29 @@ model_predict() {
 
   # 线上模型评估最新的数据
   local step_start_time=$(date +%s)
-  # /opt/apps/SPARK3/spark-3.3.1-hadoop3.2-1.0.5/bin/spark-class org.apache.spark.deploy.SparkSubmit \
-  # --class com.tzld.piaoquan.recommend.model.pred_01_xgb_ad_hdfsfile_20240813 \
-  # --master yarn --driver-memory 1G --executor-memory 1G --executor-cores 1 --num-executors 30 \
-  # --conf spark.yarn.executor.memoryoverhead=1024 \
-  # --conf spark.shuffle.service.enabled=true \
-  # --conf spark.shuffle.service.port=7337 \
-  # --conf spark.shuffle.consolidateFiles=true \
-  # --conf spark.shuffle.manager=sort \
-  # --conf spark.storage.memoryFraction=0.4 \
-  # --conf spark.shuffle.memoryFraction=0.5 \
-  # --conf spark.default.parallelism=200 \
-  # /root/zhangbo/recommend-model/recommend-model-produce/target/recommend-model-produce-jar-with-dependencies.jar \
-  # featureFile:20240703_ad_feature_name.txt \
-  # testPath:${predict_date_path} \
-  # savePath:${online_model_predict_result_path} \
-  # modelPath:${online_model_path}
-
-  # local return_code=$?
-  # check_run_status $return_code $step_start_time "线上模型评估${predict_date_path: -8}的数据"
+  /opt/apps/SPARK3/spark-3.3.1-hadoop3.2-1.0.5/bin/spark-class org.apache.spark.deploy.SparkSubmit \
+  --class com.tzld.piaoquan.recommend.model.pred_01_xgb_ad_hdfsfile_20240813 \
+  --master yarn --driver-memory 1G --executor-memory 1G --executor-cores 1 --num-executors 30 \
+  --conf spark.yarn.executor.memoryoverhead=1024 \
+  --conf spark.shuffle.service.enabled=true \
+  --conf spark.shuffle.service.port=7337 \
+  --conf spark.shuffle.consolidateFiles=true \
+  --conf spark.shuffle.manager=sort \
+  --conf spark.storage.memoryFraction=0.4 \
+  --conf spark.shuffle.memoryFraction=0.5 \
+  --conf spark.default.parallelism=200 \
+  /root/zhangbo/recommend-model/recommend-model-produce/target/recommend-model-produce-jar-with-dependencies.jar \
+  featureFile:20240703_ad_feature_name.txt \
+  testPath:${predict_date_path} \
+  savePath:${online_model_predict_result_path} \
+  modelPath:${online_model_path}
+
+  local return_code=$?
+  check_run_status $return_code $step_start_time "线上模型评估${predict_date_path: -8}的数据"
 
   # 结果分析
-  # local python_return_code=$(python ${sh_path}/model_predict_analyse.py -p ${online_model_predict_result_path} ${new_model_predict_result_path} -f ${predict_analyse_file_path})
-  # check_run_status $python_return_code $step_start_time "线上模型评估${predict_date_path: -8}的数据"
+  local python_return_code=$(python ${sh_path}/model_predict_analyse.py -p ${online_model_predict_result_path} ${new_model_predict_result_path} -f ${predict_analyse_file_path})
+  check_run_status $python_return_code $step_start_time "线上模型评估${predict_date_path: -8}的数据"
 
   calc_model_predict
 
@@ -321,13 +319,13 @@ model_upload_oss() {
 main() {
   init
 
-  # check_ad_hive
+  check_ad_hive
 
-  # origin_data
+  origin_data
 
-  # bucket_feature
+  bucket_feature
 
-  # xgb_train
+  xgb_train
 
   model_predict