add device_id

tensnsorflow/ffm.py

-#! -*- coding: utf8 -*-
+#coding=utf-8
 
 import pymysql
 import pandas as pd
@@ -137,45 +137,36 @@ class multiFFMFormatPandas:
 
 
 def get_data():
-    # db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    # sql = "select max(stat_date) from jerry_test.esmm_train_data"
-    # validate_date = con_sql(db, sql)[0].values.tolist()[0]
-    validate_date = "2018-12-19"
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select max(stat_date) from esmm_train_data"
+    validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
-    # temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    # start = (temp - datetime.timedelta(days=30)).strftime("%Y-%m-%d")
-    start = "2018-11-19"
+    temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=30)).strftime("%Y-%m-%d")
     print(start)
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
+    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,s.hospital_id,s.doctor_id,f.level2_ids " \
-          "from jerry_test.esmm_train_data e left join jerry_test.user_feature u on e.device_id = u.device_id " \
-          "left join jerry_test.cid_type_top c on e.device_id = c.device_id left join jerry_test.cid_time on e.cid_id = cid_time.cid_id " \
-          "left join jerry_test.service_hospital s on e.diary_service_id = s.id left join jerry_prod.diary_feat f on e.cid_id = f.diary_id " \
+          "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",
-                            11:"hospital_id",12:"doctor_id",13:"level2_ids"})
+                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",11:"device_id"})
     print("esmm data ok")
-
     print(df.head(2))
-    features = 0
-    category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","doctor_id",
-                "hospital_id","level2_ids"]
-    for i in category:
-        df[i] = df[i].fillna("na")
-        features = features + len(df[i].unique())
-    df["time"] = df["time"].fillna(0.0)
+
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     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)
+    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"]:
+        features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
     ccity_name = list(set(df["ccity_name"].values.tolist()))
@@ -188,10 +179,11 @@ 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["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))
@@ -226,10 +218,6 @@ def get_predict_set(ucity_id,model,ccity_name):
     df = df[df["ccity_name"].isin(ccity_name)]
     print("after ccity_name filter:")
     print(df.shape)
-    category = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer", "channel", "top"]
-    for i in category:
-        df[i] = df[i].fillna("na")
-    df["time"] = df["time"].fillna(0.0)
     df["cid_id"] = df["cid_id"].astype("str")
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["top"] = df["top"].astype("str")
@@ -239,7 +227,7 @@ def get_predict_set(ucity_id,model,ccity_name):
     df["y"] = df["label"].str.cat(
         [df["device_id"].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","label","device_id","cid_id"], axis=1)
+    df = df.drop(["z","label","device_id","cid_id"], axis=1).fillna(0.0)
     print(df.head(2))
     df = model.transform(df,n=160000, processes=22)
     df = pd.DataFrame(df)
@@ -270,13 +258,11 @@ def get_predict_set(ucity_id,model,ccity_name):
 
 
 if __name__ == "__main__":
-    path = "/home/gmuser/ffm/"
+    path = "/home/gmuser/data/"
     a = time.time()
     df, validate_date, ucity_id,ccity_name = get_data()
     model = transform(df, validate_date)
-    # get_predict_set(ucity_id,model,ccity_name)
-
+    get_predict_set(ucity_id,model,ccity_name)
     b = time.time()
     print("cost(分钟)")
     print((b-a)/60)
-