广告通过print数据验证一致性

src/main/scala/com/aliyun/odps/spark/examples/makedata/makedata_17_bucketDataPrint_20240617.scala

@@ -235,7 +235,7 @@ object makedata_17_bucketDataPrint_20240617 {
           (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap, flag)
         }).filter{
           case (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap, flag) =>
-            apptype.equals("0") && pagesource.endsWith("recommend") &&
+            apptype.equals("3") && pagesource.endsWith("recommend") &&
 //            Set("ab0", "ab1", "ab2", "ab3").contains(abcode) &&
               level.equals("0") && !flag
         }.mapPartitions(row => {

src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本-广告

@@ -32,7 +32,6 @@ beginStr:20240623 endStr:20240623 repartition:400 \
 filterNames:XXXXXXX \
 > p33_data.log 2>&1 &
 
-
 filterNames:cid_,adid_,adverid_,targeting_conversion_ \
 savePath:/dw/recommend/model/33_ad_train_data_nosparse/ \
 

src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本 → src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本-推荐

@@ -156,6 +156,8 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --class com.aliyun.odps.spark.examples.makedata.makedata_17_bucketDataPrint_20240617 \
 --master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-beginStr:2024062700 endStr:2024062700 \
-readDate:20240618 \
-> p17_data_check.log 2>&1 &
+beginStr:2024062700 endStr:2024062723 \
+readDate:20240627 \
+> p17_data_check.log 2>&1 &
+
+/dw/recommend/model/17_for_check/