按照用户去重应用列表样本

tensnsorflow/ffm.py

@@ -146,27 +146,30 @@ 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 " \
+          "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:"device_id"})
+    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"})
+
     print("esmm data ok")
     print(df.head(2))
 
-    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")
@@ -178,10 +181,9 @@ def get_data():
         features = features + len(df[i].unique())
         df[i] = df[i].fillna(0)
     df["time"] = df["time"].fillna(df["time"].mode()[0])
-    print(df.count())
     print(df.head(2))
     print("fields:{}".format(df.shape[1]-1))
-    print("features:{}".format(features+46))
+    print("features:{}".format(features))
     ccity_name = list(set(df["ccity_name"].values.tolist()))
     ucity_id = list(set(df["ucity_id"].values.tolist()))
     manufacturer = list(set(df["manufacturer"].values.tolist()))