修改str.cat

tensnsorflow/ffm.py

@@ -31,7 +31,7 @@ def get_data():
     temp = temp.rename(columns={0: "device_id"})
     print("click data ok")
     print(temp.head())
-    df = pd.merge(esmm,temp,on = "device_id")
+    df = pd.merge(esmm,temp,on = "device_id").dropna()
 
     print(df.head())
 
@@ -44,6 +44,7 @@ def get_data():
     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)
+    print(df.head())
     df = df[df["stat_date"] != "2018-11-25"]
     transform(df,"train")
     df = df[df["stat_date"] == "2018-11-25"]
@@ -61,7 +62,7 @@ def transform(df,table):
     df["ffm"] = df[0].apply(lambda x: x.split(",")[4])
     df["seq"] = list(range(df.shape[0]))
     df["seq"] = df["seq"].astype("str")
-    df["ffm"] = df["seq"].str.cat(df[["y", "ffm"]], sep=",")
+    df["ffm"] = df["seq"].str.cat([df["y"].values.tolist(), df["ffm"].values.tolist()], sep=",")
     df["number"] = np.random.randint(1, 2147483647, df.shape[0])
     df = df.drop(0, axis=1)
     yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')