|
|
@@ -1,7 +1,8 @@
|
|
|
package com.aliyun.odps.spark.examples.makedata_ad.v20240718
|
|
|
|
|
|
import com.alibaba.fastjson.{JSON, JSONObject}
|
|
|
-import com.aliyun.odps.spark.examples.makedata_ad.v20240718.makedata_ad_31_originData_20240718.func
|
|
|
+import com.aliyun.odps.TableSchema
|
|
|
+import com.aliyun.odps.data.Record
|
|
|
import com.aliyun.odps.spark.examples.myUtils.{MyDateUtils, ParamUtils, env}
|
|
|
import examples.extractor.{ExtractorUtils, RankExtractorFeature_20240530}
|
|
|
import examples.utils.{AdUtil, DateTimeUtil}
|
|
|
@@ -47,10 +48,11 @@ object makedata_ad_31_originData_hive_20240718 {
|
|
|
// 1 读取参数
|
|
|
val param = ParamUtils.parseArgs(args)
|
|
|
val tablePart = param.getOrElse("tablePart", "64").toInt
|
|
|
- val beginStr = param.getOrElse("beginStr", "2024062008")
|
|
|
- val endStr = param.getOrElse("endStr", "2024062023")
|
|
|
+ val beginStr = param.getOrElse("beginStr", "20250216")
|
|
|
+ val endStr = param.getOrElse("endStr", "20250216")
|
|
|
val project = param.getOrElse("project", "loghubods")
|
|
|
val inputTable = param.getOrElse("inputTable", "alg_recsys_ad_sample_all")
|
|
|
+ val outputTable = param.getOrElse("outputTable", "ad_easyrec_train_data_v1")
|
|
|
val filterHours = param.getOrElse("filterHours", "00,01,02,03,04,05,06,07").split(",").toSet
|
|
|
val idDefaultValue = param.getOrElse("idDefaultValue", "1.0").toDouble
|
|
|
val filterNames = param.getOrElse("filterNames", "").split(",").filter(_.nonEmpty).toSet
|
|
|
@@ -519,7 +521,7 @@ object makedata_ad_31_originData_hive_20240718 {
|
|
|
}
|
|
|
|
|
|
val partition = s"dt=$dt"
|
|
|
- odpsOps.saveToTable(project, table, partition, list, write, defaultCreate = true, overwrite = true)
|
|
|
+ odpsOps.saveToTable(project, outputTable, "dt=20250101", list, write, defaultCreate = true, overwrite = true)
|
|
|
}
|
|
|
}
|
|
|
|
xueyiming