Update news_category_similar_news_prediction.py

news_category_similar_news_prediction.py

@@ -137,6 +137,8 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
             final_df['similar_news'] = sim_news
             final_df.reset_index(drop=True, inplace=True)
             final_df.loc[final_df['pred_proba']<CLASSIFIER_THRESHOLD, 'category'] = 'OTHERS'
+            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')
         else:
             logger.warning('Prior predictions found in old news')
             if not cols_check([*new_news.columns], [*old_news.columns][:-3]):
@@ -155,6 +157,8 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
                 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'] = 'OTHERS'
+                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')
             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