Merge branch 'master' of http://git.wanmeizhensuo.com/ML/ffm-baseline

tensnsorflow/ffm.py

@@ -145,7 +145,7 @@ def get_data():
     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='jerry_test')
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
     # 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,e.device_id," \
     #       "a.competitor,a.dianshang,a.kuajing_dianshang,a.zhibo,a.youxizhibo,a.short_video,a.meitu,a.tiyu," \
@@ -158,17 +158,22 @@ def get_data():
     #       "where e.stat_date >= '{}'".format(start)
 
     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,e.device_id " \
-          "from esmm_train_data e left join user_feature_clean 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 " \
+          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,e.device_id,feat.max_level1_id " \
+          "from jerry_test.esmm_train_data e " \
+          "left join jerry_test.user_feature_clean 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_prod.device_feat feat on e.device_id = feat.device_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: "device_id"})
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "time",
+                            11: "device_id",12:"max_level1_id"})
 
     print("esmm data ok")
     print(df.head(2))
+    print(df.count())
 
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["y"] = df["y"].astype("str")
@@ -177,10 +182,10 @@ def get_data():
     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)
     features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top"]:
+    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","max_level1_id"]:
         features = features + len(df[i].unique())
-        df[i] = df[i].fillna(0)
-    df["time"] = df["time"].fillna(df["time"].mode()[0])
+        df[i] = df[i].fillna("a")
+    df["time"] = df["time"].fillna(df["time"].mean())
     print(df.head(2))
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))