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

rm 2018 to 201

tensnsorflow/ffm.py

@@ -156,14 +156,15 @@ def get_data():
     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))
+    # print(df.head(2)
 
     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(0.0)
+
+    df = df.drop(["z","stat_date","device_id","time"], axis=1).fillna("na")
     print(df.head(2))
     features = 0
     for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel"]:
@@ -210,7 +211,8 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     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,cid_time.time,e.device_id,e.cid_id " \
           "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 cid_time on e.cid_id = cid_time.cid_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.device_id = '358035085192742'"
     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: "time",
@@ -244,7 +246,7 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     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).fillna(0.0)
+    df = df.drop(["z","label","device_id","cid_id","time"], axis=1).fillna(0.0)
     print("before transform")
     print(df.shape)
     temp_series = model.transform(df,n=160000, processes=22)
@@ -289,7 +291,7 @@ if __name__ == "__main__":
     a = time.time()
     temp, validate_date, ucity_id,ccity_name,manufacturer,channel = get_data()
     model = transform(temp, validate_date)
-    # get_predict_set(ucity_id,model,ccity_name,manufacturer,channel)
+    get_predict_set(ucity_id,model,ccity_name,manufacturer,channel)
     b = time.time()
     print("cost(分钟)")
     print((b-a)/60)