HF test revert lang = qanastek

modules/utils.py

@@ -202,8 +202,8 @@ def process_data(uploaded_file, sens_level):
             df['SECTOR1'] = [item['SECTOR1'] for item in sectors_dict]
             df['SECTOR2'] = [item['SECTOR2'] for item in sectors_dict]
         elif model_name == 'LANG':
-            # df[model_name] = predict_category(df, model_name, progress_bar, repo='51-languages-classifier', profile='qanastek')
-            df[model_name] = predict_category(df, model_name, progress_bar, repo='xlm-roberta-base-language-detection', profile='papluca')
+            df[model_name] = predict_category(df, model_name, progress_bar, repo='51-languages-classifier', profile='qanastek')
+            # df[model_name] = predict_category(df, model_name, progress_bar, repo='xlm-roberta-base-language-detection', profile='papluca')
         
         logger.info(f"Completed: {model_name}")
         model_progress.empty()
@@ -265,7 +265,7 @@ def process_data(uploaded_file, sens_level):
     # labelling logic
     df['pred_action'] = df.apply(lambda x: 
         'INELIGIBLE' if (('concept_count' in df.columns and x['concept_count'] > 6) or 
-                        x['LANG'] != 'en' or 
+                        x['LANG'][0:2] != 'en' or 
                         x['ADAPMIT'] == 'Adaptation' or 
                         not any(sector in [x['SECTOR1'], x['SECTOR2']] for sector in sector_classes) or
                         x['word_length_check'] == True)