delete prints

diaryCandidateSet.py

@@ -23,7 +23,6 @@ def get_allCitiesDiaryTop3000():
     allCitiesTop3000 = allCitiesTop3000.rename(columns={0: "city_id", 1: "cid"})
     allCitiesTop3000 = filter_cid(allCitiesTop3000)
     allCitiesTop3000.to_csv(DIRECTORY_PATH + "diaryTestSet/allCitiesDiaryTop3000.csv",index=False)
-    print("成功获取全国日记点击量TOP3000")
     return allCitiesTop3000
 
 
@@ -33,7 +32,6 @@ def get_cityList():
     cityList = con_sql(sql)
     cityList.to_csv(DIRECTORY_PATH + "diaryTestSet/cityList.csv",index=False)
     cityList = cityList[0].values.tolist()
-    print("成功获取全国城市列表")
     return cityList
 
 
@@ -58,7 +56,7 @@ def get_eachCityDiaryTop3000():
 
         file_name = DIRECTORY_PATH + "diaryTestSet/{0}DiaryTop3000.csv".format(i)
         data.to_csv(file_name,index=False)
-        print("成功保存{}地区DiaryTop3000".format(i))
+
 
 def pool_method(city,sql,allCitiesTop3000):
     data = con_sql(sql)
@@ -72,7 +70,6 @@ def pool_method(city,sql,allCitiesTop3000):
 
     file_name = DIRECTORY_PATH + "diaryTestSet/{0}DiaryTop3000.csv".format(city)
     data.to_csv(file_name, index=False)
-    print("成功保存{}地区DiaryTop3000".format(city))
 
 
 # 多线程方法获取全国城市热门日记

diaryQueueUpdate.py

@@ -40,7 +40,7 @@ def feature_en(x_list, device_id):
     data["minute"] = data["minute"].astype("category")
     # 虽然预测y，但ffm转化需要y，并不影响预测结果
     data["y"] = 0
-    print("done 特征工程")
+    # print("done 特征工程")
 
     return data
 
@@ -52,7 +52,7 @@ def transform_ffm_format(df,queue_name,device_id):
         data = ffm_format_pandas.native_transform(df)
         predict_file_name = DIRECTORY_PATH + "result/{0}_{1}.csv".format(device_id, queue_name)
         data.to_csv(predict_file_name, index=False, header=None)
-        print("done ffm")
+        # print("done ffm")
         return predict_file_name
 
 
@@ -131,7 +131,7 @@ def update_dairy_queue(score_df,predict_score_df,total_video_id):
             new_queue.insert(i, j)
             i += 5
 
-        print("分数合并成功")
+        # print("分数合并成功")
         return new_queue
     # 如果没有视频日记
     else:
@@ -139,7 +139,7 @@ def update_dairy_queue(score_df,predict_score_df,total_video_id):
         predict_score_df = predict_score_df.set_index(["cid"])
         score_df["score"]=score_df["score"]+predict_score_df["score"]
         score_df = score_df.sort_values(by="score", ascending=False)
-        print("1分数合并成功")
+        # print("分数合并成功1")
         return score_df.index.tolist()
 
 
@@ -159,26 +159,6 @@ def update_sql_dairy_queue(queue_name, diary_id,device_id, city_id):
     print("成功写入diaryid")
 
 
-# 更新前获取最新的native_queue
-def get_megacity_queue(device_id, city_id):
-    db = pymysql.connect(host='rm-m5e842126ng59jrv6.mysql.rds.aliyuncs.com', port=3306, user='doris',
-                         passwd='o5gbA27hXHHm', db='doris_prod')
-    cursor = db.cursor()
-    sql = "select megacity_queue from device_diary_queue " \
-          "where device_id = '{}' and city_id = '{}';".format(device_id,city_id)
-    cursor.execute(sql)
-    result = cursor.fetchall()
-    df = pd.DataFrame(list(result))
-    if not df.empty:
-        megacity_queue = df.loc[0, 0].split(",")
-        megacity_queue = list(map(lambda x: "diary|" + str(x), megacity_queue))
-        db.close()
-        print("成功获取megacity_queue")
-        return megacity_queue
-    else:
-        return False
-
-
 def get_queue(device_id, city_id,queue_name):
     db = pymysql.connect(host='rm-m5e842126ng59jrv6.mysql.rds.aliyuncs.com', port=3306, user='doris',
                          passwd='o5gbA27hXHHm', db='doris_prod')
@@ -190,13 +170,13 @@ def get_queue(device_id, city_id,queue_name):
     df = pd.DataFrame(list(result))
 
     if df.empty:
-        print("该用户对应的日记为空")
+        # print("该用户对应的日记为空")
         return False
     else:
         queue_list = df.loc[0, 0].split(",")
         queue_list = list(map(lambda x: "diary|" + str(x), queue_list))
         db.close()
-        print("成功获取queue")
+        # print("成功获取queue")
         return queue_list
 
 
@@ -205,7 +185,7 @@ def pipe_line(queue_name, queue_arg, device_id,total_video_id):
     predict_score_df = save_result(queue_name, queue_arg, device_id)
     score_df = get_score(queue_arg)
     if score_df.empty:
-        print("获取的日记列表是空")
+        # print("获取的日记列表是空")
         return False
     else:
         score_df = score_df.rename(columns={0: "score", 1: "cid"})
@@ -224,7 +204,7 @@ def user_update(device_id, city_id, queue_name,data_set_cid,total_video_id):
             diary_queue = pipe_line(queue_name, queue_arg, device_id,total_video_id)
             if diary_queue:
                 update_sql_dairy_queue(queue_name, diary_queue, device_id, city_id)
-                print("更新结束")
+                # print("更新结束")
             else:
                 print("获取的日记列表是空，所以不更新日记队列")
         else:

processData.py

@@ -65,7 +65,6 @@ def feature_en(data_start_date, data_end_date, validation_date, test_date):
 
 
 def ffm_transform(data, test_number, validation_number):
-
     print("Start ffm transform")
     start = time.time()
     ffm_train = multiFFMFormatPandas()

train.py

@@ -23,7 +23,7 @@ if __name__ == "__main__":
     multi_get_eachCityDiaryTop3000()
     end = time.time()
     print("获取各城市热门日记耗时{}分".format((end - start) / 60))
-    print("end")
+