增加新的模型样本和模型更新

ad/02_ad_model_dnn_v11_update.sh

@@ -224,7 +224,7 @@ run_pai_flow() {
   python ad/pai_flow_operator.py &
   pid1=$!
 
-  python ad/pai_flow_operator_v2.py &
+  python ad/pai_flow_operator_v3.py &
   pid2=$!
 
   # 等待两个进程完成并获取返回码

ad/25_xgb_make_data_origin_bucket.sh

@@ -163,13 +163,36 @@ make_bucket_feature_from_origin_to_hive() {
   flag:1
   local task2=$!
 
+  /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_ad.v20240718.makedata_ad_33_bucketDataFromOriginToHive_20260703 \
+    --master yarn --driver-memory 2G --executor-memory 3G --executor-cores 1 --num-executors 30 \
+    --conf spark.dynamicAllocation.enabled=true \
+    --conf spark.shuffle.service.enabled=true \
+    --conf spark.dynamicAllocation.maxExecutors=100 \
+    ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+    beginStr:${today_early_1} endStr:${today_early_1} \
+    filterHours:${FILTER_HOURS:-00,01,02,03,04,05} \
+    filterAdverIds:${FILTER_ADVER_IDS} \
+    filterNames:_4h_,_5h_,adid_,targeting_conversion_ \
+    outputTable:ad_easyrec_train_realtime_data_new_v1_sampled \
+    inputTable:alg_recsys_ad_sample_all_tmp \
+    negSampleRate:${neg_sample_rate} \
+    maskFeatureRate:${mask_feature_rate} \
+    bucketFile:20260410_ad_bucket_920.txt \
+    flag:1
+    local task3=$!
+
   wait ${task1}
   local task1_return_code=$?
 
   wait ${task2}
   local task2_return_code=$?
 
+  wait ${task3}
+  local task3_return_code=$?
+
   check_run_status ${task1_return_code} ${step_start_time} "离线数据spark特征分桶任务"
   check_run_status ${task2_return_code} ${step_start_time} "在线日志spark特征分桶任务"
+  check_run_status ${task3_return_code} ${step_start_time} "新特征表spark特征分桶任务"
 
 }