update feature

spark/featureEng.py

@@ -819,7 +819,7 @@ if __name__ == '__main__':
 
     """训练数据保存 ======================================"""
     timestmp3 = int(round(time.time()))
-    train_columns = model_columns + ["label", "timestamp", "page_stay"]
+    train_columns = model_columns + ["label", "timestamp", "rating"]
     trainSamples = samplesWithUserFeatures.select(*train_columns)
     print("write to hdfs start...")
     splitTimestamp = int(time.mktime(time.strptime(addDays(0), "%Y%m%d")))

train/train_service.py

@@ -92,8 +92,8 @@ def getWeight(x):
 def getDataSet(df,shuffleSize = 10000,batchSize=128):
     # print(df.dtypes)
     labels = df.pop('label')
-    # df["page_stay"] = df["page_stay"].map(getWeight)
-    # weights = df.pop('page_stay')
+    # df["rating"] = df["rating"].map(getWeight)
+    # weights = df.pop('rating')
     dataSet = tf.data.Dataset.from_tensor_slices((dict(df), labels)).shuffle(shuffleSize).batch(batchSize)
     return dataSet