|
@@ -266,29 +266,29 @@ 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" "线上模型评估${predict_date_path: -8}的数据失败"
|
|
|
+ /opt/apps/SPARK3/spark-3.3.1-hadoop3.2-1.0.5/bin/spark-class org.apache.spark.deploy.SparkSubmit \
|
|
|
+ --class com.tzld.piaoquan.recommend.model.pred_01_xgb_ad_hdfsfile_20240813 \
|
|
|
+ --master yarn --driver-memory 1G --executor-memory 1G --executor-cores 1 --num-executors 30 \
|
|
|
+ --conf spark.yarn.executor.memoryoverhead=1024 \
|
|
|
+ --conf spark.shuffle.service.enabled=true \
|
|
|
+ --conf spark.shuffle.service.port=7337 \
|
|
|
+ --conf spark.shuffle.consolidateFiles=true \
|
|
|
+ --conf spark.shuffle.manager=sort \
|
|
|
+ --conf spark.storage.memoryFraction=0.4 \
|
|
|
+ --conf spark.shuffle.memoryFraction=0.5 \
|
|
|
+ --conf spark.default.parallelism=200 \
|
|
|
+ /root/zhangbo/recommend-model/recommend-model-produce/target/recommend-model-produce-jar-with-dependencies.jar \
|
|
|
+ featureFile:20240703_ad_feature_name.txt \
|
|
|
+ testPath:${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" "线上模型评估${predict_date_path: -8}的数据失败"
|
|
|
|
|
|
# 结果分析
|
|
|
- # local python_return_code=$(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 $step_start_time "分析线上模型评估${predict_date_path: -8}的数据" "分析线上模型评估${predict_date_path: -8}的数据失败"
|
|
|
+ local python_return_code=$(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 $step_start_time "分析线上模型评估${predict_date_path: -8}的数据" "分析线上模型评估${predict_date_path: -8}的数据失败"
|
|
|
|
|
|
calc_model_predict
|
|
|
|
|
@@ -343,15 +343,15 @@ model_upload_oss() {
|
|
|
main() {
|
|
|
init
|
|
|
|
|
|
- # check_ad_hive
|
|
|
+ check_ad_hive
|
|
|
|
|
|
- # origin_data
|
|
|
+ origin_data
|
|
|
|
|
|
- # bucket_feature
|
|
|
+ bucket_feature
|
|
|
|
|
|
if [ "${current_day_of_week}" -eq 2 ] || [ "${current_day_of_week}" -eq 5 ]; then
|
|
|
echo "当前是周二或周五,开始训练并更新模型"
|
|
|
- # xgb_train
|
|
|
+ xgb_train
|
|
|
|
|
|
model_predict
|
|
|
|