删除获取热门日记集合

diaryCandidateSet.py

@@ -17,7 +17,7 @@ def filter_cid(df):
 def get_allCitiesDiaryTop3000():
     # 获取全国点击量TOP3000日记
 
-    sql = "select city_id,cid from data_feed_click " \
+    sql = "select city_id,cid from data_feed_click2 " \
           "where cid_type = 'diary' group by cid order by max(click_count_choice) desc limit 3000"
     allCitiesTop3000 = con_sql(sql)
     allCitiesTop3000 = allCitiesTop3000.rename(columns={0: "city_id", 1: "cid"})
@@ -28,7 +28,7 @@ def get_allCitiesDiaryTop3000():
 
 def get_cityList():
     # 获取全国城市列表
-    sql = "select distinct city_id from data_feed_click"
+    sql = "select distinct city_id from data_feed_click2"
     cityList = con_sql(sql)
     cityList.to_csv(DIRECTORY_PATH + "diaryTestSet/cityList.csv",index=False)
     cityList = cityList[0].values.tolist()
@@ -40,7 +40,7 @@ def get_eachCityDiaryTop3000():
     cityList = get_cityList()
     allCitiesTop3000 = get_allCitiesDiaryTop3000()
     for i in cityList:
-        sql = "select city_id,cid from data_feed_click " \
+        sql = "select city_id,cid from data_feed_click2 " \
               "where cid_type = 'diary' and city_id = '{0}' group by cid " \
               "order by max(click_count_choice) desc limit 3000".format(i)
         data = con_sql(sql)
@@ -78,7 +78,7 @@ def multi_get_eachCityDiaryTop3000(processes=8):
     allCitiesTop3000 = get_allCitiesDiaryTop3000()
     pool = Pool(processes)
     for city in city_list:
-        sql = "select city_id,cid from data_feed_click " \
+        sql = "select city_id,cid from data_feed_click2 " \
           "where cid_type = 'diary' and city_id = '{0}' group by cid " \
           "order by max(click_count_choice) desc limit 3000".format(city)
 

train.py

@@ -18,11 +18,6 @@ if __name__ == "__main__":
     train()
     end_train = time.time()
     print("训练模型耗时{}分".format((end_train-start_train)/60))
-    print('---------------prepare candidates--------------')
-    start = time.time()
-    multi_get_eachCityDiaryTop3000()
-    end = time.time()
-    print("获取各城市热门日记耗时{}分".format((end - start) / 60))