修改str cat函数

tensnsorflow/ffm.py

@@ -44,32 +44,33 @@ def get_data():
     df["cid_id"] = df["cid_id"].astype("str")
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
-    df["y"] = df["device_id"].str.cat([df["ucity_id"].values.tolist(), df["cid_id"].values.tolist(),
+    df["y"] = df["device_id"].str.cat([df["stat_date"].values.tolist(),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())
-    train = df[df["stat_date"] != "2018-11-25"]
-    transform(train,"crvtrain.csv")
-    test = df[df["stat_date"] == "2018-11-25"]
-    transform(test, "crvtest.csv")
+    transform(df)
 
 
-def transform(df,table):
+def transform(df):
     model = multiFFMFormatPandas()
     df = model.fit_transform(df, y="y", n=80000, processes=20)
     df = pd.DataFrame(df)
-    df["device_id"] = df[0].apply(lambda x: x.split(",")[0])
-    df["city_id"] = df[0].apply(lambda x: x.split(",")[1])
-    df["diary_id"] = df[0].apply(lambda x: x.split(",")[2])
+    df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
+    df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
+    df["city_id"] = df[0].apply(lambda x: x.split(",")[2])
+    df["diary_id"] = df[0].apply(lambda x: x.split(",")[3])
     df["seq"] = list(range(df.shape[0]))
     df["seq"] = df["seq"].astype("str")
-    df["ffm"] = df[0].apply(lambda x: ",".join(x.split(",")[3:]))
+    df["ffm"] = df[0].apply(lambda x: ",".join(x.split(",")[4:]))
     df["ffm"] = df["seq"].str.cat(df["ffm"], sep=",")
     df["random"] = np.random.randint(1, 2147483647, df.shape[0])
     df = df.drop(0, axis=1).drop("seq",axis=1)
     print("size")
     print(df.shape)
-    df.to_csv(path+table,index=None)
+    train = df[df["stat_date"] != "2018-11-25"].drop("stat_date",axis=1)
+    test = df[df["stat_date"] == "2018-11-25"].drop("stat_date",axis=1)
+    train.to_csv(path+"train.csv",index=None)
+    test.to_csv(path + "test.csv", index=None)
     # yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
     # n = 100000
     # for i in range(0,df.shape[0],n):