Update news_category_similar_news_prediction.py

news_category_similar_news_prediction.py

@@ -87,7 +87,7 @@ def process_prediction_df(df, df_type: str="production"):
     df.drop_duplicates(subset='url', keep='first', inplace=True)
     df.reset_index(drop=True, inplace=True)
 
-    # df.loc[df['pred_proba']<CLASSIFIER_THRESHOLD, 'category'] = 'NATION'
+    df.loc[df['pred_proba']<CLASSIFIER_THRESHOLD, 'category'] = 'NATION'
     df.loc[(df['title'].str.contains('Pakistan')) & (df['category'] == 'NATION'), 'category'] = 'WORLD'
     logger.warning('Updated category of articles having Pakistan in title and category=NATION to WORLD')
     df.loc[(df['title'].str.contains('Zodiac Sign', case=False)) | (df['title'].str.contains('Horoscope', case=False)), 'category'] = 'ASTROLOGY'