latest_news_backend_with_cat_pred_similar_news

Running

App Files Files Community

lalithadevi commited on Apr 5

Commit

c1b9bc4

•

1 Parent(s): 203e844

Update news_category_similar_news_prediction.py

Browse files

Files changed (1) hide show

news_category_similar_news_prediction.py +2 -2

news_category_similar_news_prediction.py CHANGED Viewed

@@ -143,7 +143,7 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
             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'] = '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')
             final_df.loc[(final_df['title'].str.contains('Zodiac Sign', case=False)) | (final_df['title'].str.contains('Horoscope', case=False)), 'category'] = 'SCIENCE'
@@ -172,7 +172,7 @@ def predict_news_category_similar_news(old_news: pd.DataFrame, new_news: pd.Data
                 final_df = pd.concat([old_news, new_news], axis=0, ignore_index=True)
                 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')
                 final_df.loc[(final_df['title'].str.contains('Zodiac Sign', case=False)) | (final_df['title'].str.contains('Horoscope', case=False)), 'category'] = 'SCIENCE'

             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'
                 final_df = pd.concat([old_news, new_news], axis=0, ignore_index=True)
                 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'