调整ros-训练方式

recommend-model-produce/src/main/scala/com/tzld/piaoquan/recommend/model/train_recsys_61_xgb_nor_20241209.scala

@@ -27,14 +27,13 @@ object train_recsys_61_xgb_nor_20241209 {
     val testPath = param.getOrElse("testPath", "")
     val savePath = param.getOrElse("savePath", "/dw/recommend/model/61_recsys_nor_predict_data/")
     val featureFilter = param.getOrElse("featureFilter", "XXXXXX").split(",")
-    val maxLabel = param.getOrElse("maxLabel", "30").toDouble
     val eta = param.getOrElse("eta", "0.01").toDouble
     val gamma = param.getOrElse("gamma", "0.0").toDouble
     val max_depth = param.getOrElse("max_depth", "5").toInt
     val num_round = param.getOrElse("num_round", "100").toInt
     val num_worker = param.getOrElse("num_worker", "20").toInt
-    val func_object = param.getOrElse("func_object", "reg:squarederror")
-    val func_metric = param.getOrElse("func_metric", "rmse")
+    val func_object = param.getOrElse("func_object", "reg:squaredlogerror")
+    val func_metric = param.getOrElse("func_metric", "rmsle")
     val repartition = param.getOrElse("repartition", "20").toInt
     val modelPath = param.getOrElse("modelPath", "/dw/recommend/model/61_recsys_nor_model/model_xgb")
     val modelFile = param.getOrElse("modelFile", "model_xgb_for_recsys_nor.tar.gz")
@@ -58,8 +57,7 @@ object train_recsys_61_xgb_nor_20241209 {
 
     val trainData = createData(
       sc.textFile(trainPath),
-      features,
-      maxLabel
+      features
     )
     println("recsys nor:train data size：" + trainData.count())
 
@@ -130,7 +128,7 @@ object train_recsys_61_xgb_nor_20241209 {
     }
   }
 
-  def createData(data: RDD[String], features: Array[String], maxLabel: Double = 30): RDD[Row] = {
+  def createData(data: RDD[String], features: Array[String]): RDD[Row] = {
     data
       .filter(r => {
         val line: Array[String] = StringUtils.split(r, '\t')
@@ -148,7 +146,7 @@ object train_recsys_61_xgb_nor_20241209 {
         }
 
         val v: Array[Any] = new Array[Any](features.length + 1)
-        v(0) = clipLabel(label, maxLabel)
+        v(0) = label
         for (i <- 0 until features.length) {
           v(i + 1) = map.getOrDefault(features(i), 0.0d)
         }