esmm 测试项目增加知识图谱特征

tensnsorflow/es/feature.py

@@ -41,12 +41,13 @@ def get_data():
     print(start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
-          "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids " \
+          "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,k.level2_name " \
           "from {} e left join user_feature u on e.device_id = u.device_id " \
           "left join cid_type_top c on e.device_id = c.device_id " \
           "left join cid_time_cut cut on e.cid_id = cut.cid " \
           "left join device_app_list dl on e.device_id = dl.device_id " \
           "left join diary_feat feat on e.cid_id = feat.diary_id " \
+          "left join train_Knowledge_network_data k on substring_index(feat.level2_ids,",",1) = k.level2_id " \
           "where e.stat_date >= '{}'".format(train_data_set,start)
     df = con_sql(db, sql)
     # print(df.shape)
@@ -57,7 +58,7 @@ def get_data():
     print("esmm data ok")
 
     # print(df["method","min","max","treatment_time","maintain_time","recover_time"].head(6))
-    print(df.count(axis = 1))
+    print(df.count())
 
     service_id = tuple(df["service_id"].unique())
     db = pymysql.connect(host='rdsfewzdmf0jfjp9un8xj.mysql.rds.aliyuncs.com', port=3306, user='work',