def evaluate(Language, gold_tuples, model_dir, gold_preproc=False, verbose=False,
beam_width=None, cand_preproc=None):
print("Load parser", model_dir)
nlp = Language(path=model_dir)
if nlp.lang == 'de':
nlp.vocab.morphology.lemmatizer = lambda string,pos: set([string])
if beam_width is not None:
nlp.parser.cfg.beam_width = beam_width
scorer = Scorer()
for raw_text, sents in gold_tuples:
if gold_preproc:
raw_text = None
else:
sents = merge_sents(sents)
for annot_tuples, brackets in sents:
if raw_text is None:
tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])
nlp.tagger(tokens)
nlp.parser(tokens)
nlp.entity(tokens)
else:
tokens = nlp(raw_text)
gold = GoldParse.from_annot_tuples(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=verbose)
return scorer
def main(n_iter=10):
nlp = spacy.blank('en')
ner = nlp.create_pipe('ner')
ner.add_multitask_objective(get_position_label)
nlp.add_pipe(ner)
print("Create data", len(TRAIN_DATA))
optimizer = nlp.begin_training(get_gold_tuples=lambda: TRAIN_DATA)
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for text, annot_brackets in TRAIN_DATA:
annotations, _ = annot_brackets
doc = nlp.make_doc(text)
gold = GoldParse.from_annot_tuples(doc, annotations[0])
nlp.update(
[doc], # batch of texts
[gold], # batch of annotations
drop=0.2, # dropout - make it harder to memorise data
sgd=optimizer, # callable to update weights
losses=losses)
print(losses.get('nn_labeller', 0.0), losses['ner'])
# test the trained model
for text, _ in TRAIN_DATA:
doc = nlp(text)
print('Entities', [(ent.text, ent.label_) for ent in doc.ents])
print('Tokens', [(t.text, t.ent_type_, t.ent_iob) for t in doc])
def main(n_iter=10):
nlp = spacy.blank("en")
ner = nlp.create_pipe("ner")
ner.add_multitask_objective(get_position_label)
nlp.add_pipe(ner)
print(nlp.pipeline)
print("Create data", len(TRAIN_DATA))
optimizer = nlp.begin_training(get_gold_tuples=lambda: TRAIN_DATA)
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for text, annot_brackets in TRAIN_DATA:
for annotations, _ in annot_brackets:
doc = Doc(nlp.vocab, words=annotations[1])
gold = GoldParse.from_annot_tuples(doc, annotations)
nlp.update(
[doc], # batch of texts
[gold], # batch of annotations
drop=0.2, # dropout - make it harder to memorise data
sgd=optimizer, # callable to update weights
losses=losses,
)
print(losses.get("nn_labeller", 0.0), losses["ner"])
# test the trained model
for text, _ in TRAIN_DATA:
if text is not None:
doc = nlp(text)
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
def main(n_iter=10):
nlp = spacy.blank('en')
ner = nlp.create_pipe('ner')
ner.add_multitask_objective(get_position_label)
nlp.add_pipe(ner)
print("Create data", len(TRAIN_DATA))
optimizer = nlp.begin_training(get_gold_tuples=lambda: TRAIN_DATA)
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for text, annot_brackets in TRAIN_DATA:
annotations, _ = annot_brackets
doc = nlp.make_doc(text)
gold = GoldParse.from_annot_tuples(doc, annotations[0])
nlp.update(
[doc], # batch of texts
[gold], # batch of annotations
drop=0.2, # dropout - make it harder to memorise data
sgd=optimizer, # callable to update weights
losses=losses)
print(losses.get('nn_labeller', 0.0), losses['ner'])
# test the trained model
for text, _ in TRAIN_DATA:
doc = nlp(text)
print('Entities', [(ent.text, ent.label_) for ent in doc.ents])
print('Tokens', [(t.text, t.ent_type_, t.ent_iob) for t in doc])