liqian 3 years ago
parent
commit
ac2f86f23a
1 changed files with 4 additions and 0 deletions
  1. 4 0
      region_rule_rank_h.py

+ 4 - 0
region_rule_rank_h.py

@@ -170,6 +170,9 @@ def video_rank(df, now_date, now_h, rule_key, param, region):
     return_count = param.get('return_count', 1)
     score_value = param.get('score_rule', 0)
     h_recall_df = df[(df['lastonehour_return'] >= return_count) & (df['score'] >= score_value)]
+    # videoid重复时,保留分值高
+    h_recall_df = h_recall_df.sort_values(by=['score'], ascending=False)
+    h_recall_df = h_recall_df.drop_duplicates(subset=['videoid'], keep='first')
     h_recall_videos = h_recall_df['videoid'].to_list()
     log_.info(f'h_recall videos count = {len(h_recall_videos)}')
 
@@ -178,6 +181,7 @@ def video_rank(df, now_date, now_h, rule_key, param, region):
     h_recall_result = {}
     for video_id in h_recall_videos:
         score = h_recall_df[h_recall_df['videoid'] == video_id]['score']
+        # print(score)
         h_recall_result[int(video_id)] = float(score)
         h_video_ids.append(int(video_id))
     h_recall_key_name = \