debug

generic_ner.py

@@ -245,7 +245,10 @@ def postprocess_entities(entities):
         num_dots = entity["entity"].count(".")
 
         # If the entity text is new, or this entity has more dots, update the map
-        if entity_text not in entity_map or entity_map[entity_text]["entity"].count(".") < num_dots:
+        if (
+            entity_text not in entity_map
+            or entity_map[entity_text]["entity"].count(".") < num_dots
+        ):
             entity_map[entity_text] = entity
 
     # Collect the filtered entities from the map
@@ -257,7 +260,6 @@ def postprocess_entities(entities):
     return filtered_entities
 
 
-
 def remove_included_entities(entities):
     # Loop through entities and remove those whose text is included in another with the same label
     final_entities = []
@@ -386,11 +388,11 @@ class MultitaskTokenClassificationPipeline(Pipeline):
         # pprint(all_entities)
 
         all_entities = remove_trailing_stopwords(all_entities)
-        # print("After remove_trailing_stopwords:")
-        # pprint(all_entities)
+        print("After remove_trailing_stopwords:")
+        pprint(all_entities)
         # Attach "comp.function" entities to the closest non-"comp.function" entity
         all_entities = attach_comp_to_closest(all_entities)
-        # print("After attach_comp_to_closest:")
-        # pprint(all_entities)
+        print("After attach_comp_to_closest:")
+        pprint(all_entities)
         # print("\n")
         return all_entities