模型bug修复

spark/featureEngSk.py

@@ -927,8 +927,8 @@ def get_service_feature_df():
 def addDays(n, format="%Y%m%d"):
     return (date.today() + timedelta(days=n)).strftime(format)
 
-def generatePartitionDates(trainDays):
-    return [addDays(-trainDay) for trainDay in range(trainDays)]
+def generatePartitionDates(partitionDates):
+    return [addDays(-trainDay) for trainDay in range(partitionDates)]
 
 #显示所有列
 pd.set_option('display.max_columns', None)
@@ -942,11 +942,12 @@ if __name__ == '__main__':
     start = time.time()
     #入参
     trainDays = int(sys.argv[1])
+    itemStatisticStartDays = int(sys.argv[2])
     print('trainDays:{}'.format(trainDays),flush=True)
 
     endDay = addDays(0)
     startDay = addDays(-int(trainDays))
-    itemStatisticStartDay = addDays(-int(trainDays + 31))
+    itemStatisticStartDay = addDays(-int(trainDays + itemStatisticStartDays))
 
     print("train_data start:{} end:{}".format(startDay,endDay))
 
@@ -968,7 +969,7 @@ if __name__ == '__main__':
     itemStatisticDF = spark.sql(itemStatisticSql)
     itemStatisticDF.show(100, False)
 
-    partitionDatas = generatePartitionDates(trainDays)
+    partitionDatas = generatePartitionDates(trainDays + itemStatisticStartDays)
     partitionDatasBC = spark.sparkContext.broadcast(partitionDatas)
 
     def splitPatitionDatasFlatMapFunc(row):
@@ -1064,7 +1065,7 @@ if __name__ == '__main__':
 
     # item统计特征处理
     itemStaticDF = addItemStaticFeatures(ratingDF,itemDF_spark,dataVocab)
-    sys.exit(1)
+    # sys.exit(1)
     # 统计数据处理
     # ratingSamplesWithLabel = addStaticsFeatures(ratingSamplesWithLabel,dataVocab)