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

tensnsorflow/ffm.py

@@ -146,14 +146,19 @@ def get_data():
     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')
+    # 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," \
+    #       "a.read,a.finance,a.fashion_clothes,a.muying,a.fresh,a.bijia,a.travel,a.airplane," \
+    #       "a.love,a.stock,a.car,a.child,a.homework,a.work,a.job " \
+    #       "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 " \
+    #       "left join app_list_sort a on e.device_id = a.device_id " \
+    #       "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," \
-          "a.competitor,a.dianshang,a.kuajing_dianshang,a.zhibo,a.youxizhibo,a.short_video,a.meitu,a.tiyu," \
-          "a.read,a.finance,a.fashion_clothes,a.muying,a.fresh,a.bijia,a.travel,a.airplane," \
-          "a.love,a.stock,a.car,a.child,a.homework,a.work,a.job " \
+          "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 " \
-          "left join app_list_sort a on e.device_id = a.device_id " \
           "where e.stat_date >= '{}'".format(start)
     df = con_sql(db, sql)
     print(df.shape)
@@ -164,16 +169,19 @@ def get_data():
 
     for i in range(12,35):
         df[i] = df[i].astype("str")
+        df[i] = df[i].fillna(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["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)
+    df = df.drop(["z","stat_date","device_id"], axis=1)
+    df = df.fillna(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())
+        df[i] = df[i].fillna(0)
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features+46))
     ccity_name = list(set(df["ccity_name"].values.tolist()))