Explorar el Código

feat:添加新的训练样本生成脚本

zhaohaipeng hace 1 semana
padre
commit
4a6f6f8ddf

+ 9 - 11
src/main/scala/com/aliyun/odps/spark/examples/makedata_recsys/v20250411/makedata_recsys_41_str_train_data_sample_20250411.scala

@@ -231,6 +231,15 @@ object makedata_recsys_41_str_train_data_sample_20250411 {
           小时 星期 apptype city province pagesource 机器型号
            */
 
+          val logs = new JSONObject
+          for (logKey <- List("apptype", "pagesource", "mid", "vid", "subsessionid", "page", "abcode", "recomtraceid", "headvideoid", "hotsencetype", "ts", "extend_alg")) {
+            if (!record.isNull(logKey)) {
+              logs.put(logKey, record.getString(logKey))
+            }
+          }
+
+          logs.put("hour", ExtractorUtils.getHourByTimestamp(ts))
+          logs.put("day_of_week", ExtractorUtils.getDayOfWeekByTimestamp(ts))
 
           //4 处理label信息。
           val labels = new JSONObject
@@ -243,17 +252,6 @@ object makedata_recsys_41_str_train_data_sample_20250411 {
             }
           }
 
-
-          val logs = new JSONObject
-          for (logKey <- List("apptype", "pagesource", "mid", "vid", "subsessionid", "page", "abcode", "recomtraceid", "headvideoid", "hotsencetype", "ts")) {
-            if (!record.isNull(logKey)) {
-              logs.put(logKey, record.getString(logKey))
-            }
-          }
-
-          logs.put("hour", ExtractorUtils.getHourByTimestamp(ts))
-          logs.put("day_of_week", ExtractorUtils.getDayOfWeekByTimestamp(ts))
-
           //5 处理log key表头。
           val logKey = logs.toString()
           val labelKey = labels.toString()