add level2

tensnsorflow/ffm.py

@@ -147,14 +147,15 @@ 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,cid_time.time,e.device_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id " \
           "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 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 diary_feat df on e.cid_id = df.diary_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:"level2_ids",11:"device_id"})
     print("esmm data ok")
     # print(df.head(2)
 
@@ -164,10 +165,10 @@ def get_data():
     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","time"], axis=1).fillna("na")
+    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"]:
+    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","level2_ids","top"]:
         features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
@@ -201,8 +202,8 @@ def transform(a,validate_date):
     print("train shape")
     print(train.shape)
 
-    # train.to_csv(path + "tr.csv", sep="\t", index=False)
-    # test.to_csv(path + "va.csv", sep="\t", index=False)
+    train.to_csv(path + "tr.csv", sep="\t", index=False)
+    test.to_csv(path + "va.csv", sep="\t", index=False)
 
     return model
 
@@ -210,13 +211,14 @@ def transform(a,validate_date):
 def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     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,cid_time.time,e.device_id,e.cid_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,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 diary_feat df on e.cid_id = df.diary_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",
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "level2_ids",
                             11:"device_id",12:"cid_id"})
 
     print("before filter:")
@@ -247,7 +249,7 @@ 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","time"], axis=1).fillna(0.0)
+    df = df.drop(["z","label","device_id","cid_id"], axis=1).fillna(0.0)
     print("before transform")
     print(df.shape)
     temp_series = model.transform(df,n=160000, processes=22)
@@ -273,8 +275,8 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     print(native_pre.shape)
     print(native_pre.loc[native_pre["device_id"] == "358035085192742"].shape)
     native_pre.to_csv(path+"native.csv",sep="\t",index=False)
-    # print("native_pre shape")
-    # print(native_pre.shape)
+    print("native_pre shape")
+    print(native_pre.shape)
 
     nearby_pre = df[df["label"] == "1"]
     nearby_pre = nearby_pre.drop("label", axis=1)
@@ -282,8 +284,8 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     print(nearby_pre.shape)
     print(nearby_pre.loc[nearby_pre["device_id"] == "358035085192742"].shape)
     nearby_pre.to_csv(path + "nearby.csv", sep="\t", index=False)
-    # print("nearby_pre shape")
-    # print(nearby_pre.shape)
+    print("nearby_pre shape")
+    print(nearby_pre.shape)
 
 
 
@@ -292,7 +294,7 @@ 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)