修改str.cat

tensnsorflow/ffm.py

@@ -21,7 +21,7 @@ def get_data():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
     sql = "select * from esmm_data where stat_date >= '2018-11-20'"
     esmm = con_sql(db,sql)
-    esmm = esmm.rename(columns={0:"stat_date",1: "device_id",2:"ucity_id",3:"cid_id",4:"diary_service_id",5:"y_old",
+    esmm = esmm.rename(columns={0:"stat_date",1: "device_id",2:"ucity_id",3:"cid_id",4:"diary_service_id",5:"y",
                                 6:"z",7:"clevel1_id",8:"slevel1_id"})
     print("esmm data ok")
     print(esmm.head())
@@ -39,9 +39,10 @@ def get_data():
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["slevel1_id"] = df["slevel1_id"].astype("str")
     df["cid_id"] = df["cid_id"].astype("str")
-    df["y_old"] = df["y_old"].astype("str")
+    df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
-    df["y"] = df["device_id"].str.cat(df[["ucity_id", "cid_id", "y_old", "z"]], sep=",")
+    df["y"] = df["device_id"].str.cat([df["ucity_id"].values.tolist(), df["cid_id"].values.tolist(),
+                                       df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
     df = df.drop("z", axis=1)
     df = df[df["stat_date"] != "2018-11-25"]
     transform(df,"train")