Update classification.py

classification.py

@@ -179,9 +179,9 @@ def match_categories(df, category_df, treshold=0.45):
             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("@~@".join([category_df.loc[index, 'description'] for index in high_score_indices]))
-            experts_list.append("@~@".join([", ".join(category_df.loc[index, 'experts']) for index in high_score_indices]))
+            experts_list.append("@~@".join(["@~@".join(list(set(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(", ".join([float(cos_scores[index])) 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: