Update news_category_similar_news_prediction.py

news_category_similar_news_prediction.py

@@ -170,12 +170,6 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
             final_df['category'] = label
             final_df['pred_proba'] = prob
             final_df['similar_news'] = sim_news
-            # final_df.reset_index(drop=True, inplace=True)
-            # final_df.loc[final_df['pred_proba']<CLASSIFIER_THRESHOLD, 'category'] = 'NATION'
-            # final_df.loc[(final_df['title'].str.contains('Pakistan')) & (final_df['category'] == 'NATION'), 'category'] = 'WORLD'
-            # logger.warning('Updated category of articles having Pakistan in title and category=NATION to WORLD')
-            # final_df.loc[(final_df['title'].str.contains('Zodiac Sign', case=False)) | (final_df['title'].str.contains('Horoscope', case=False)), 'category'] = 'SCIENCE'
-            # logger.warning('Updated category of articles having Zodiac Sign in title to SCIENCE')
 
             final_df = process_prediction_df(final_df, df_type="production & prediction")
             prediction_df = final_df.copy()
@@ -208,13 +202,6 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
                 prediction_df = new_news.copy()
                 prediction_df = add_flags_to_prediction_df(prediction_df)
                 
-                # final_df.drop_duplicates(subset='url', keep='first', inplace=True)
-                # final_df.reset_index(drop=True, inplace=True)
-                # final_df.loc[final_df['pred_proba']<CLASSIFIER_THRESHOLD, 'category'] = 'NATION'
-                # final_df.loc[(final_df['title'].str.contains('Pakistan')) & (final_df['category'] == 'NATION'), 'category'] = 'WORLD'
-                # logger.warning('Updated category of articles having Pakistan in title and category=NATION to WORLD')
-                # final_df.loc[(final_df['title'].str.contains('Zodiac Sign', case=False)) | (final_df['title'].str.contains('Horoscope', case=False)), 'category'] = 'SCIENCE'
-                # logger.warning('Updated category of articles having Zodiac Sign in title to SCIENCE')
             else:
                 logger.warning('INFO: Old & New Articles are the same. There is no requirement of updating them in the database. Database is not updated.')
                 db_updation_required = 0