瀏覽代碼

Update run_category_model_v1: remove abnormal read_rate samples

StrayWarrior 3 月之前
父節點
當前提交
baa2d60ca1
共有 1 個文件被更改,包括 2 次插入2 次删除
  1. 2 2
      run_category_model_v1.py

+ 2 - 2
run_category_model_v1.py

@@ -34,7 +34,7 @@ def prepare_raw_data(dt_begin, dt_end):
     sql = f"""
         SELECT {fields_str} FROM datastat_score WHERE dt BETWEEN {dt_begin} AND {dt_end}
             AND similarity > 0 AND category IS NOT NULL AND read_avg > 500
-            AND read_avg_rate BETWEEN 0 AND 3 AND view_count_rate > 0
+            AND read_avg_rate BETWEEN 0.3 AND 3 AND view_count_rate > 0
             AND `index` in (1, 2)
             AND (FROM_UNIXTIME(coalesce(publish_timestamp, 0), '%H') < '15'
                 OR gh_id in {night_accounts_condition})
@@ -54,7 +54,7 @@ def clear_old_version(db_manager, dt):
         WHERE dt < {dt} and status = 1
     """
     rows = db_manager.execute(sql)
-    print(f"updated rows: {rows}")
+    print(f"updated rows for clear: {rows}")
 
 def get_last_version(db_manager, dt):
     sql = f"""