va data add y,z,uid

eda/esmm/Feature_pipline/data2ffm.py

@@ -146,14 +146,14 @@ 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,cid_time.time " \
+          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,e.device_id " \
           "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 cid_time on e.cid_id = cid_time.cid_id " \
           "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:"time"})
+                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",11:"device_id"})
     print("esmm data ok")
     print(df.head(2))
 
@@ -161,8 +161,8 @@ def get_data():
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
     df["top"] = df["top"].astype("str")
-    df["y"] = df["stat_date"].str.cat([df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
-    df = df.drop(["z","stat_date"], axis=1).fillna(0.0)
+    df["y"] = df["stat_date"].str.cat([df["device_id"].values.tolist(),df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
+    df = df.drop(["z","stat_date","device_id"], axis=1).fillna(0.0)
     print(df.head(2))
     features = 0
     for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel"]:
@@ -179,10 +179,13 @@ def transform(a,validate_date):
     df = model.fit_transform(a, y="y", n=160000, processes=22)
     df = pd.DataFrame(df)
     df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
+    df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
+    df["y"] = df[0].apply(lambda x: x.split(",")[2])
+    df["z"] = df[0].apply(lambda x: x.split(",")[3])
     df["number"] = np.random.randint(1, 2147483647, df.shape[0])
     df["seq"] = list(range(df.shape[0]))
     df["seq"] = df["seq"].astype("str")
-    df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[1:]))
+    df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[2:]))
     df["data"] = df["seq"].str.cat(df["data"], sep=",")
     df = df.drop([0,"seq"], axis=1)
     print(df.head(2))