delete print

local/precitDiaryLocal.py

@@ -41,7 +41,7 @@ def test_con_sql(device_id):
 # 将device_id、city_id拼接到对应的城市热门日记表。注意：下面预测集特征顺序要与训练集保持一致
 def feature_en(x_list, device_id):
     data = pd.DataFrame(x_list)
-    data = data.rename(columns={0: "diary_id"})
+    data = data.rename(columns={0: "cid"})
     data["device_id"] = device_id
     now = datetime.now()
     data["hour"] = now.hour
@@ -87,7 +87,7 @@ def predict(queue_name, x_list, device_id):
 def save_result(queue_name, x_list):
     score_df = pd.read_csv("/Users/mac/utils/result/{0}_output.txt".format(queue_name), header=None)
     score_df = score_df.rename(columns={0: "score"})
-    score_df["diary_id"] = x_list
+    score_df["cid"] = x_list
     merge_score(x_list, score_df)
 
 
@@ -111,19 +111,19 @@ def merge_score(x_list, score_df):
 
 
 def update_dairy_queue(score_df):
-    diary_id = score_df["diary_id"].values.tolist()
+    diary_id = score_df["cid"].values.tolist()
     video_id = []
     x = 1
     while x <= len(diary_id):
         video_id.append(diary_id[x])
         x += 5
     not_video_id = list(set(diary_id) - set(video_id))
-    not_video_id_df = score_df.loc[score_df["diary_id"].isin(not_video_id)]
+    not_video_id_df = score_df.loc[score_df["cid"].isin(not_video_id)]
     not_video_id_df = not_video_id_df.sort_values(by="score", ascending=False)
-    video_id_df = score_df.loc[score_df["diary_id"].isin(video_id)]
+    video_id_df = score_df.loc[score_df["cid"].isin(video_id)]
     video_id_df = video_id_df.sort_values(by="score", ascending=False)
-    not_video_id = not_video_id_df["diary_id"].values.tolist()
-    video_id = video_id_df["diary_id"].values.tolist()
+    not_video_id = not_video_id_df["cid"].values.tolist()
+    video_id = video_id_df["cid"].values.tolist()
     diary_id = not_video_id
     i = 1
     for j in video_id:

predictDiary.py

@@ -23,7 +23,6 @@ def feature_en(user_profile):
     # 虽然预测y，但ffm转化需要y，并不影响预测结果
     data["y"] = 0
     data = data.drop("city_id", axis=1)
-    print(data.head(10))
     return data
 
 
@@ -103,20 +102,20 @@ def multi_predict(predict_list,processes=12):
 
 if __name__ == "__main__":
     # TODO 如果耗时小于一分钟，下一次取到的device_id和上一次相同。还有一种情况，一个用户持续活跃，会被重复预测
-    # while True:
-    #     empty,device_id_list = get_active_users()
-    #     if empty:
-    #         for eachFile in os.listdir("/tmp"):
-    #             if "xlearn" in eachFile:
-    #                 os.remove("/tmp" + "/" + eachFile)
-    #         time.sleep(58)
-    #     else:
-    #         old_device_id_list = pd.read_csv(DIRECTORY_PATH + "data_set_device_id.csv")["device_id"].values.tolist()
-    #         # 求活跃用户和老用户的交集，也就是只预测老用户
-    #         predict_list = list(set(device_id_list) & set(old_device_id_list))
-    #         multi_predict(predict_list)
-
-    router("358035085192742")
+    while True:
+        empty,device_id_list = get_active_users()
+        if empty:
+            for eachFile in os.listdir("/tmp"):
+                if "xlearn" in eachFile:
+                    os.remove("/tmp" + "/" + eachFile)
+            time.sleep(58)
+        else:
+            old_device_id_list = pd.read_csv(DIRECTORY_PATH + "data_set_device_id.csv")["device_id"].values.tolist()
+            # 求活跃用户和老用户的交集，也就是只预测老用户
+            predict_list = list(set(device_id_list) & set(old_device_id_list))
+            multi_predict(predict_list)
+
+
             #TODO 上线前把预测流程中的计时器、打印代码删掉或者注释，因为预测对性能要求高，能少一条代码语句就少一条
 
 

userProfile.py

@@ -31,5 +31,4 @@ def fetch_user_profile(device_id):
             user_profile_dict = {}
             for i in user_profile.columns:
                 user_profile_dict[i] = user_profile.loc[0, i]
-            print(user_profile_dict)
             return user_profile_dict, False