Update classification.py

classification.py

@@ -178,17 +178,17 @@ def match_categories(df, category_df, treshold=0.45):
         if isinstance(ebd_content, torch.Tensor):
             cos_scores = util.cos_sim(ebd_content, torch.stack(list(category_df['Embeddings']), dim=0))[0]
             high_score_indices = [i for i, score in enumerate(cos_scores) if score > treshold]
-            categories_list.append([category_df.loc[index, 'description'] for index in high_score_indices])
-            experts_list.append([category_df.loc[index, 'experts'] for index in high_score_indices])
-            topic_list.append([category_df.loc[index, 'topic'] for index in high_score_indices])
-            scores_list.append([float(cos_scores[index]) for index in high_score_indices])
+            categories_list.append("@~@".join([category_df.loc[index, 'description'] for index in high_score_indices]))
+            experts_list.append("@~@".join([category_df.loc[index, 'experts'] for index in high_score_indices]))
+            topic_list.append("@~@".join([category_df.loc[index, 'topic'] for index in high_score_indices]))
+            scores_list.append("@~@".join([float(cos_scores[index]) for index in high_score_indices]))
             for j in high_score_indices:
                 df.loc[index, category_df.loc[j, 'topic']] = float(cos_scores[j])
         else:
             categories_list.append(np.nan)
             experts_list.append(np.nan)
             topic_list.append(np.nan)
-            scores_list.append('pas interessant')
+            scores_list.append(np.nan)
         df["Description"] = categories_list
         df["Expert"] = experts_list
         df["Topic"] = topic_list