def evaluate(nlp, text_loc, gold_loc, sys_loc, limit=None):
with text_loc.open("r", encoding="utf8") as text_file:
texts = split_text(text_file.read())
docs = list(nlp.pipe(texts))
with sys_loc.open("w", encoding="utf8") as out_file:
write_conllu(docs, out_file)
with gold_loc.open("r", encoding="utf8") as gold_file:
gold_ud = conll17_ud_eval.load_conllu(gold_file)
with sys_loc.open("r", encoding="utf8") as sys_file:
sys_ud = conll17_ud_eval.load_conllu(sys_file)
scores = conll17_ud_eval.evaluate(gold_ud, sys_ud)
return scores
def evaluate(nlp, text_loc, gold_loc, sys_loc, limit=None):
if text_loc.parts[-1].endswith(".conllu"):
docs = []
with text_loc.open(encoding="utf8") as file_:
for conllu_doc in read_conllu(file_):
for conllu_sent in conllu_doc:
words = [line[1] for line in conllu_sent]
docs.append(Doc(nlp.vocab, words=words))
for name, component in nlp.pipeline:
docs = list(component.pipe(docs))
else:
with text_loc.open("r", encoding="utf8") as text_file:
texts = split_text(text_file.read())
docs = list(nlp.pipe(texts))
with sys_loc.open("w", encoding="utf8") as out_file:
write_conllu(docs, out_file)
with gold_loc.open("r", encoding="utf8") as gold_file:
gold_ud = conll17_ud_eval.load_conllu(gold_file)
with sys_loc.open("r", encoding="utf8") as sys_file:
sys_ud = conll17_ud_eval.load_conllu(sys_file)
scores = conll17_ud_eval.evaluate(gold_ud, sys_ud)
return docs, scores
