def create_cats_overview(
gold_data_container: GoldDataContainer, root_coding_node: CodingNode,
article_annotated_list: List[ArticleAnnotated]) -> GoldDataContainer:
# TODO : remove this once sure it's not needed anymore
def save_cats_hierarchy_into_dict(current_coding_node: CodingNode):
cats_dict = {}
for c in current_coding_node.children:
cats_dict.update(save_cats_hierarchy_into_dict(c))
return {current_coding_node.coding_value: cats_dict}
# TODO : remove this once sure it's not needed anymore
def save_cats_dict_into_list(cat_dict):
current_leafs_list = []
for k, v in cat_dict.items():
if v != {}:
current_leafs_list.extend(save_cats_dict_into_list(v))
else:
current_leafs_list.append(k)
return current_leafs_list
def filter_out_unused_cats(
root_coding_node: CodingNode,
article_annotated_list: List[ArticleAnnotated],
) -> List[str]:
len_all_aa_list = len(article_annotated_list)
all_cats_used_list = []
for cn in root_coding_node.get_all_subnodes():
len_aa_set = len(cn.article_annotated_set)
if len_aa_set != 0 and len_aa_set != len_all_aa_list:
if cn.coding_value in all_cats_used_list:
raise Exception(
"Category was already added to this list. Such redundancies could interfer later with training "
"where categories are used as keys for dictionaries.")
all_cats_used_list.append(cn.coding_value)
return all_cats_used_list
gold_data_container.cats_list = filter_out_unused_cats(
root_coding_node, article_annotated_list)
return gold_data_container
def run():
eval_data_container = main.load_gold_data(ConfigLoadG8)
eval_data_container = main.transform_gold_data(ConfigLoadG8, eval_data_container)
modelVR = main.init_trainer(ConfigLoadVRModel)
main.log_manager.info_global(
"--------------------------------\n"
"Evaluating mo11 over the entire dataset g8: \n"
)
scores_spacy, scores_manual = modelVR.evaluate(eval_data_container)
# only look at those examples that mo9 predicts as either AF=SM or AF=SC
modelAF = main.init_trainer(ConfigLoadAFModel)
gdis_to_keep = []
for gdi in eval_data_container.gold_data_item_list:
doc = modelAF.nlp(gdi.text)
for cat in ['AF: Social Companions', 'AF: Soziale Medien']:
if doc.cats[cat] > 0.5:
gdis_to_keep.append(gdi)
break
eval_data_container2 = GoldDataContainer()
eval_data_container2.cats_list = eval_data_container.cats_list
eval_data_container2.gold_data_item_list = gdis_to_keep
main.log_manager.info_global(
"--------------------------------\n"
"Evaluating mo11 over those texts in g8 that mo9 predicts to be AF=SM or AF=SC: \n"
)
scores_spacy2, scores_manual2 = modelVR.evaluate(eval_data_container2)
# only look at those examples that were annotated as AF=SM or AF=SC
# we need to reload the data to undo the transformation that removes AF
eval_data_container = main.load_gold_data(ConfigLoadG8)
gdis_to_keep = []
for gdi in eval_data_container.gold_data_item_list:
for cat in ['AF: Social Companions', 'AF: Soziale Medien']:
if gdi.cats[cat] == 1:
gdis_to_keep.append(gdi)
break
eval_data_container3 = GoldDataContainer()
eval_data_container3.cats_list = eval_data_container.cats_list
eval_data_container3.gold_data_item_list = gdis_to_keep
# now apply the transformation that removes all categories except VR
eval_data_container3 = main.transform_gold_data(ConfigLoadG8, eval_data_container3)
main.log_manager.info_global(
"--------------------------------\n"
"Evaluating mo11 over those texts in g8 that were annotated as AF=SM or AF=SC: \n"
)
scores_spacy3, scores_manual3 = modelVR.evaluate(eval_data_container3)
embed()