update feature

spark/featureEng.py

@@ -822,24 +822,11 @@ if __name__ == '__main__':
     open(configUtils.VOCAB_PATH, mode='w', encoding='utf-8').write(dataVocabStr)
     # dataVocabToRedis(dataVocabStr)
 
-
-    """训练数据保存 ======================================"""
-    timestmp3 = int(round(time.time()))
-    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")))
-    splitAndSaveTrainingTestSamplesByTimeStamp(trainSamples, splitTimestamp, TRAIN_FILE_PATH)
-    print("write to hdfs success...")
-    timestmp4 = int(round(time.time()))
-    print("数据写入hdfs 耗时s:{}".format(timestmp4 - timestmp3))
-
-
     """特征数据存入redis======================================"""
     # user特征数据存入redis
     featuresToRedis(samplesWithUserFeatures, user_columns, "user", FEATURE_USER_KEY)
     timestmp5 = int(round(time.time()))
-    print("user feature to redis 耗时s:{}".format(timestmp5 - timestmp4))
+    print("user feature to redis 耗时s:{}".format(timestmp5 - timestmp3))
     # userDatas = collectFeaturesToDict(samplesWithUserFeatures, user_columns, "user")
     # featureToRedis(FEATURE_USER_KEY, userDatas)
     # itemDatas = collectFeaturesToDict(samplesWithUserFeatures, item_columns, "item")
@@ -851,6 +838,17 @@ if __name__ == '__main__':
     timestmp6 = int(round(time.time()))
     print("item feature to redis 耗时s:{}".format(timestmp6 - timestmp5))
 
-    print("总耗时m:{}".format((timestmp6 - start)/60))
+    """训练数据保存 ======================================"""
+    timestmp3 = int(round(time.time()))
+    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")))
+    splitAndSaveTrainingTestSamplesByTimeStamp(trainSamples, splitTimestamp, TRAIN_FILE_PATH)
+    print("write to hdfs success...")
+    timestmp4 = int(round(time.time()))
+    print("数据写入hdfs 耗时s:{}".format(timestmp4 - timestmp3))
+
+    print("总耗时m:{}".format((timestmp4 - start)/60))
 
     spark.stop()
\ No newline at end of file