update

whole_movies_update.py

@@ -60,14 +60,12 @@ def get_feature_data(now_date, project, table):
     return feature_df
 
 
-def video_rank(app_type, df, now_date, now_h, return_count):
+def video_rank(app_type, df, now_date):
     """
     对视频进行排序
     :param app_type:
     :param df:
     :param now_date:
-    :param now_h:
-    :param return_count: 小时级数据回流限制数
     :return:
     """
     df = df.fillna(0)
@@ -90,44 +88,30 @@ def video_rank(app_type, df, now_date, now_h, return_count):
     filtered_df_1 = filtered_df_1.sort_values(by=['站外播放量'], ascending=False)
     log_.info(f'filtered_df_1 count = {len(filtered_df_1)}')
 
-    # 排序合并
-
-
-
-
-    # 获取符合进入召回源条件的视频，进入条件：小时级回流>=20 && score>=0.005
-    h_recall_df = df[(df['lastonehour_return'] >= return_count) & (df['score'] >= 0.005)]
-    h_recall_videos = h_recall_df['videoid'].to_list()
-    log_.info(f'h_recall videos count = {len(h_recall_videos)}')
-    # 不符合进入召回源条件的视频
-    df = df.append(h_recall_df)
-    h_else_df = df.drop_duplicates(['videoid'], keep=False)
-    h_else_df = h_else_df.sort_values(by=['score'], ascending=False)
-    h_else_videos = h_else_df['videoid'].to_list()
-    # 合并，给定分数
-    final_videos = h_recall_videos + h_else_videos
+    # 排序合并,给定分数
+    merge_df = filtered_df_1.append(filtered_df_6)
+    merge_df = merge_df.drop_duplicates(['videoid'], keep=False)
+    merge_videos = merge_df['videoid'].to_list()
     final_result = {}
-    step = round(100/len(final_videos), 3)
-    for i, video_id in enumerate(final_videos):
+    step = round(100 / len(merge_videos), 3)
+    for i, video_id in enumerate(merge_videos):
         score = 100 - i * step
         final_result[int(video_id)] = score
     # 写入对应的redis
-    key_name = \
-        f"{config_.RECALL_KEY_NAME_PREFIX_APP_TYPE}{app_type}.{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}"
-    if len(final_result) > 0:
-        redis_helper = RedisHelper()
-        redis_helper.add_data_with_zset(key_name=key_name, data=final_result, expire_time=23 * 3600)
+    # key_name = \
+    #     f"{}{app_type}.{datetime.datetime.strftime(now_date, '%Y%m%d')}"
+    # if len(final_result) > 0:
+    #     redis_helper = RedisHelper()
+    #     redis_helper.add_data_with_zset(key_name=key_name, data=final_result, expire_time=23 * 3600)
 
 
 def rank_by_h(app_type, now_date, now_h, return_count_list, project, table):
     # 获取特征数据
     feature_df = get_feature_data(now_date=now_date, project=project, table=table)
-    # 计算score
-    score_df = cal_score(df=feature_df)
     # rank
     for cnt in return_count_list:
         log_.info(f"return_count = {cnt}")
-        video_rank(app_type=app_type, df=score_df, now_date=now_date, now_h=now_h, return_count=cnt)
+        video_rank(app_type=app_type, df=feature_df, now_date=now_date)
     # to-csv
-    score_filename = f"score_{app_type}_{datetime.datetime.strftime(now_date, '%Y%m%d%H')}.csv"
-    score_df.to_csv(f'./data/{score_filename}')
+    # score_filename = f"score_{app_type}_{datetime.datetime.strftime(now_date, '%Y%m%d%H')}.csv"
+    # score_df.to_csv(f'./data/{score_filename}')