排序模型优化

spark/featureEng.py

@@ -315,7 +315,7 @@ def addUserFeatures(samples,dataVocab,multiVocab):
     return samples
 
 def addSampleLabel(ratingSamples):
-    ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 5, 1).otherwise(0))
+    ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 1, 1).otherwise(0))
     ratingSamples.show(5, truncate=False)
     ratingSamples.printSchema()
     return ratingSamples
@@ -852,8 +852,8 @@ if __name__ == '__main__':
     df = ratingSamplesWithLabel.toPandas()
     df = pd.DataFrame(df)
 
-    posCount = df.loc[df["label"]==0]["label"].count()
-    negCount = df.loc[df["label"]==1]["label"].count()
+    posCount = df.loc[df["label"]==1]["label"].count()
+    negCount = df.loc[df["label"]==0]["label"].count()
     print("pos size:"+str(posCount),"neg size:"+str(negCount))
 
     itemDF = get_service_feature_df()