增加新的特征表制作

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/v20240718/makedata_ad_33_bucketDataFromOriginToHive_20260808.scala

@@ -173,7 +173,8 @@ object makedata_ad_33_bucketDataFromOriginToHive_20260808 {
               !filterAdverIds.contains(adverId)
             })
             .filter(record => {
-              val label = record.getString(whatLabel).toInt
+              val labelJson = getJsonObject(record, "label_json")
+              val label = labelJson.getIntValue(whatLabel)
               label > 0 || Random.nextDouble() < negSampleRate
             })
             .map(record => {
@@ -754,12 +755,15 @@ object makedata_ad_33_bucketDataFromOriginToHive_20260808 {
              */
 
 
-              //4 处理label信息。
+              //4 处理label信息（从 label_json 读取）。
               val labels = new JSONObject
-              for (labelKey <- List("ad_is_click", "ad_is_conversion")) {
-                if (!record.isNull(labelKey)) {
-                  labels.put(labelKey, record.getString(labelKey))
-                }
+              val labelJson = getJsonObject(record, "label_json")
+              if (!labelJson.isEmpty) {
+                labels.put("ad_is_click", labelJson.getIntValue("ad_is_click"))
+                labels.put("ad_is_conversion", labelJson.getIntValue("ad_is_conversion"))
+              } else {
+                labels.put("ad_is_click", 0)
+                labels.put("ad_is_conversion", 0)
               }
               //5 处理log key表头。
               val headvideoid = record.getString("headvideoid")