update feature

spark/featureEng.py

@@ -166,7 +166,7 @@ def addUserFeatures(samples,dataVocab,multiVocab):
         .withColumn("userPositiveHistory", arrayReverseUdf(F.col("userPositiveHistory")))
     for i in range(1,11):
         samples = samples.withColumn("userRatedHistory"+str(i), F.when(F.col("userPositiveHistory")[i-1].isNotNull(),F.col("userPositiveHistory")[i-1]).otherwise("-1"))
-        # dataVocab["userRatedHistory"+str(i)] = dataVocab["itemid"]
+        dataVocab["userRatedHistory"+str(i)] = dataVocab["itemid"]
     samples = samples.drop("userPositiveHistory")
 
     # user历史点击分值统计
@@ -216,7 +216,7 @@ def addUserFeatures(samples,dataVocab,multiVocab):
 
 
 def addSampleLabel(ratingSamples):
-    ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 8, 1).otherwise(0))
+    ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 5, 1).otherwise(0))
     ratingSamples.show(5, truncate=False)
     ratingSamples.printSchema()
     return ratingSamples