模型调试

spark/featureEng.py

@@ -174,6 +174,7 @@ def addItemFeatures(itemDF,dataVocab,multi_col_vocab):
     itemDF = itemDF.drop(columns=onehot_col)
 
     for c in multi_col:
+        #TODO 这里多标签的应该拆开
         multi_col_vocab[c] = list(set(itemDF[c].tolist()))
 
         for i in range(1, 6):
@@ -884,15 +885,13 @@ if __name__ == '__main__':
 
     print("dataVocab:")
     for k, v in dataVocab.items():
-        print(k, len(v), v)
+        print(k, len(v))
 
 
     itemDF_spark = spark.createDataFrame(itemDF)
     itemDF_spark.printSchema()
     itemDF_spark.show(10, truncate=False)
 
-    sys.exit(1)
-
     # item统计特征处理
     itemStaticDF = addItemStaticFeatures(ratingSamplesWithLabel,itemDF_spark,dataVocab)