service model 优化

spark/featureEng2.py

@@ -95,7 +95,7 @@ def addItemStaticFeatures(samples,itemDF,dataVocab):
 
     staticFeatures.show(20, truncate=False)
 
-    staticFeatures = itemDF.join(itemStaticDF, on=["item_id"], how='left')
+    staticFeatures = itemDF.join(staticFeatures, on=["item_id"], how='left')
 
     # 连续特征分桶
     bucket_vocab = [str(i) for i in range(101)]

train/train_service2.py

@@ -10,16 +10,6 @@ from datetime import date, timedelta
 sys.path.append(os.path.dirname(os.path.abspath(os.path.dirname(__file__))))
 import utils.configUtils as configUtils
 
-ITEM_NUMBER_COLUMNS = ["item_"+c for c in ["smart_rank2"]]
-embedding_columns = ["itemid","userid"] + ["item_"+c for c in ["doctor_id","hospital_id","merchant_id"]]
-multi_columns = ["tags_v3","first_demands","second_demands","first_solutions","second_solutions","first_positions","second_positions"]
-one_hot_columns = ["user_os"] + ["item_"+c for c in ["service_type","doctor_type","doctor_famous","hospital_city_tag_id","hospital_type","hospital_is_high_quality"]]
-# history_columns = ["userRatedHistory"]
-
-# 数据加载
-# data_path_train = "/Users/zhigangzheng/Desktop/work/guoyu/service_sort/train/part-00000-a61205d1-ad4e-4fa7-895d-ad8db41189e6-c000.csv"
-# data_path_test = "/Users/zhigangzheng/Desktop/work/guoyu/service_sort/train/part-00000-a61205d1-ad4e-4fa7-895d-ad8db41189e6-c000.csv"
-
 VERSION = configUtils.SERVICE_VERSION
 trainDay = time.strftime("%Y%m%d%H", time.localtime())
 data_path_train = "/data/files/service_feature_{}_train.csv".format(VERSION)