add level id 1

tensnsorflow/ffm.py

@@ -147,8 +147,8 @@ def get_data():
     start = "2018-11-19"
     print(start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
-    sql = "select e.y,e.z,e.stat_date,e.ucity_id,f.level2_ids,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,s.hospital_id,s.doctor_id " \
+    sql = "select e.y,e.z,e.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,s.hospital_id,s.doctor_id,f.level2_ids " \
           "from jerry_test.esmm_train_data e left join jerry_test.user_feature u on e.device_id = u.device_id " \
           "left join jerry_test.cid_type_top c on e.device_id = c.device_id left join jerry_test.cid_time on e.cid_id = cid_time.cid_id " \
           "left join jerry_test.service_hospital s on e.diary_service_id = s.id left join jerry_prod.diary_feat f on e.cid_id = f.diary_id " \
@@ -158,13 +158,13 @@ def get_data():
     print(df.shape)
     df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id",4: "clevel1_id", 5: "ccity_name",
                             6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",
-                            11:"hospital_id",12:"doctor_id"})
+                            11:"hospital_id",12:"doctor_id",13:"level2_ids"})
     print("esmm data ok")
 
     print(df.head(2))
     features = 0
     category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","doctor_id",
-                "hospital_id"]
+                "hospital_id","level2_ids"]
     for i in category:
         df[i] = df[i].fillna("na")
         features = features + len(df[i].unique())