Update classification.py

classification.py

@@ -171,6 +171,7 @@ def process_categories(categories, model):
 
 
 def match_categories(df, category_df, treshold=0.45):
+    categories_list, experts_list, topic_list, scores_list = [], [], []
     for topic in category_df['topic']:
         df[topic] = 0
     for index, ebd_content in enumerate(df['Embeddings']):
@@ -183,9 +184,18 @@ def match_categories(df, category_df, treshold=0.45):
             scores_list.append([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')
+        df["Description"] = categories_list
+        df["Expert"] = experts_list
+        df["Topic"] = topic_list
+        df["Score"] = scores_list
     return df
 
+
 def save_data(df, filename):
     df = df.drop(columns=['Embeddings'])
     new_filename = filename.replace(".", "_classified.")