add cut time

eda/esmm/Feature_pipline/data2ffm.py

@@ -149,38 +149,44 @@ 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,df.level2_ids,e.device_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,cut.time " \
           "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 diary_feat df on e.cid_id = df.diary_id " \
+          "left join cid_time_cut cut on e.cid_id = cut.cid " \
           "where e.stat_date >= '{}'".format(start)
     df = con_sql(db, sql)
-    print(df.shape)
+    # 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:"level2_ids",11:"device_id"})
+                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"level2_ids",
+                            11:"device_id",12:"time"})
     print("esmm data ok")
     # print(df.head(2)
     print("before")
     print(df.shape)
     print("after")
     df = df.drop_duplicates()
+    df = df.drop_duplicates(["ucity_id","clevel1_id", "ccity_name","device_type","manufacturer",
+                             "channel","top","level2_ids","time"])
     print(df.shape)
 
     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["time"] = df["time"].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("na")
     print(df.head(2))
     features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","level2_ids","top"]:
+    l = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","level2_ids","top","time"]
+    for i in l:
         features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
     # filter_list 中没有device_type，这个类别只有安卓、ios两种类型，转化前能完全覆盖到这两种类型
-    filter_list = ["ccity_name","ucity_id","manufacturer","channel","level2_ids","clevel1_id","top"]
+    filter_list = ["ccity_name","ucity_id","manufacturer","channel","level2_ids","clevel1_id","top","time"]
     column_map = dict()
     for i in filter_list:
         column_map[i] = list(set(df[i].values.tolist()))
@@ -219,14 +225,15 @@ def transform(a,validate_date):
 def get_predict_set(model,columns):
     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.label,e.ucity_id,e.clevel1_id,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,e.cid_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,e.cid_id,cut.time " \
           "from esmm_pre_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 diary_feat df on e.cid_id = df.diary_id"
+          "left join diary_feat df on e.cid_id = df.diary_id " \
+          "left join cid_time_cut cut on e.cid_id = cut.cid"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
                             6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "level2_ids",
-                            11:"device_id",12:"cid_id"})
+                            11:"device_id",12:"cid_id",13:"time"})
 
     print(df.shape)
     for i in columns.keys():
@@ -234,6 +241,7 @@ def get_predict_set(model,columns):
     df["cid_id"] = df["cid_id"].astype("str")
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["top"] = df["top"].astype("str")
+    df["time"] = df["time"].astype("str")
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
     df["label"] = df["label"].astype("str")