multi hot insert database

tensnsorflow/feature_engineering.py

@@ -26,17 +26,17 @@ 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,e.clevel1_id,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,cut.time " \
+          "u.device_type,u.manufacturer,u.channel,c.top,cl.l1,cl.l2,cl.l3,e.device_id,cut.time " \
           "from esmm_train_data 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 diary_feat df on e.cid_id = df.diary_id " \
+          "left join cid_level2 cl on e.cid_id = cl.cid " \
           "left join cid_time_cut cut on e.cid_id = cut.cid " \
           "where e.stat_date >= '{}'".format(start)
     df = con_sql(db, sql)
     # 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: "level2_ids",
-                            11: "device_id", 12: "time"})
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "l1",11: "l2",
+                            12: "l3",13: "device_id", 14: "time"})
     print("esmm data ok")
     # print(df.head(2)
     print("before")

tensnsorflow/multi_hot.py

@@ -59,7 +59,7 @@ def multi():
             temp = df.iloc[i:]
         else:
             temp = df.loc[i:i + n]
-        pd.io.sql.to_sql(temp, "cid_level2", yconnect, schema='jerry_test', if_exists='replace', index=False)
+        pd.io.sql.to_sql(temp, "cid_level2", yconnect, schema='jerry_test', if_exists='append', index=False)
         print("insert done")