def main(language, train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False, pseudoprojective=False,
L1=1e-6):
parser_cfg = dict(locals())
tagger_cfg = dict(locals())
entity_cfg = dict(locals())
lang = spacy.util.get_lang_class(language)
parser_cfg['features'] = lang.Defaults.parser_features
entity_cfg['features'] = lang.Defaults.entity_features
if not eval_only:
gold_train = list(read_json_file(train_loc))
gold_dev = list(read_json_file(dev_loc))
if n_sents > 0:
gold_train = gold_train[:n_sents]
train(lang, gold_train, gold_dev, model_dir, tagger_cfg, parser_cfg, entity_cfg,
n_sents=n_sents, gold_preproc=gold_preproc, corruption_level=corruption_level,
n_iter=n_iter)
if out_loc:
write_parses(lang, dev_loc, model_dir, out_loc)
scorer = evaluate(lang, list(read_json_file(dev_loc)),
model_dir, gold_preproc=gold_preproc, verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def main(language, train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False, pseudoprojective=False):
parser_cfg = dict(locals())
tagger_cfg = dict(locals())
entity_cfg = dict(locals())
lang = spacy.util.get_lang_class(language)
parser_cfg['features'] = lang.Defaults.parser_features
entity_cfg['features'] = lang.Defaults.entity_features
if not eval_only:
gold_train = list(read_json_file(train_loc))
gold_dev = list(read_json_file(dev_loc))
train(lang, gold_train, gold_dev, model_dir, tagger_cfg, parser_cfg, entity_cfg,
n_sents=n_sents, gold_preproc=gold_preproc, corruption_level=corruption_level,
n_iter=n_iter)
if out_loc:
write_parses(lang, dev_loc, model_dir, out_loc)
scorer = evaluate(lang, list(read_json_file(dev_loc)),
model_dir, gold_preproc=gold_preproc, verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def main(train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, verbose=False,
nv_word=10, nv_tag=10, nv_label=10, nv_hidden=10,
eta=0.1, mu=0.9, eval_only=False):
gold_train = list(read_json_file(train_loc, lambda doc: 'wsj' in doc['id']))
nlp = train(English, gold_train, model_dir,
feat_set='embed',
eta=eta, mu=mu,
nv_word=nv_word, nv_tag=nv_tag, nv_label=nv_label, nv_hidden=nv_hidden,
n_sents=n_sents, n_iter=n_iter,
verbose=verbose)
scorer = evaluate(nlp, list(read_json_file(dev_loc)))
print 'TOK', 100-scorer.token_acc
print 'POS', scorer.tags_acc
print 'UAS', scorer.uas
print 'LAS', scorer.las
print 'NER P', scorer.ents_p
print 'NER R', scorer.ents_r
print 'NER F', scorer.ents_f
def main(train_loc,
dev_loc,
model_dir,
n_sents=0,
n_iter=15,
out_loc="",
verbose=False,
debug=False,
corruption_level=0.0,
gold_preproc=False,
beam_width=1,
eval_only=False,
use_orig_arc_eager=False):
if use_orig_arc_eager:
English.ParserTransitionSystem = TreeArcEager
if not eval_only:
gold_train = list(read_json_file(train_loc))
train(English,
gold_train,
model_dir,
feat_set='basic' if not debug else 'debug',
gold_preproc=gold_preproc,
n_sents=n_sents,
corruption_level=corruption_level,
n_iter=n_iter,
beam_width=beam_width,
verbose=verbose,
use_orig_arc_eager=use_orig_arc_eager)
#if out_loc:
# write_parses(English, dev_loc, model_dir, out_loc, beam_width=beam_width)
scorer = evaluate(English,
list(read_json_file(dev_loc)),
model_dir,
gold_preproc=gold_preproc,
verbose=verbose,
beam_width=beam_width)
print 'TOK', scorer.token_acc
print 'POS', scorer.tags_acc
print 'UAS', scorer.uas
print 'LAS', scorer.las
print 'NER P', scorer.ents_p
print 'NER R', scorer.ents_r
print 'NER F', scorer.ents_f
def main(language,
train_loc,
dev_loc,
model_dir,
n_sents=0,
n_iter=15,
out_loc="",
verbose=False,
debug=False,
corruption_level=0.0,
gold_preproc=False,
eval_only=False,
pseudoprojective=False):
lang = {'en': English, 'de': German}.get(language)
if not eval_only:
gold_train = list(read_json_file(train_loc))
train(lang,
gold_train,
model_dir,
feat_set='basic' if not debug else 'debug',
gold_preproc=gold_preproc,
n_sents=n_sents,
corruption_level=corruption_level,
n_iter=n_iter,
verbose=verbose,
pseudoprojective=pseudoprojective)
if out_loc:
write_parses(lang, dev_loc, model_dir, out_loc)
scorer = evaluate(lang,
list(read_json_file(dev_loc)),
model_dir,
gold_preproc=gold_preproc,
verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def main(train_loc,
dev_loc,
model_dir,
n_sents=0,
n_iter=15,
verbose=False,
nv_word=10,
nv_tag=10,
nv_label=10,
nv_hidden=10,
eta=0.1,
mu=0.9,
eval_only=False):
gold_train = list(read_json_file(train_loc,
lambda doc: 'wsj' in doc['id']))
nlp = train(English,
gold_train,
model_dir,
feat_set='embed',
eta=eta,
mu=mu,
nv_word=nv_word,
nv_tag=nv_tag,
nv_label=nv_label,
nv_hidden=nv_hidden,
n_sents=n_sents,
n_iter=n_iter,
verbose=verbose)
scorer = evaluate(nlp, list(read_json_file(dev_loc)))
print 'TOK', 100 - scorer.token_acc
print 'POS', scorer.tags_acc
print 'UAS', scorer.uas
print 'LAS', scorer.las
print 'NER P', scorer.ents_p
print 'NER R', scorer.ents_r
print 'NER F', scorer.ents_f
def main(train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False):
if not eval_only:
gold_train = list(read_json_file(train_loc))
train(English, gold_train, model_dir,
feat_set='basic' if not debug else 'debug',
gold_preproc=gold_preproc, n_sents=n_sents,
corruption_level=corruption_level, n_iter=n_iter,
verbose=verbose)
#if out_loc:
# write_parses(English, dev_loc, model_dir, out_loc, beam_width=beam_width)
scorer = evaluate(English, list(read_json_file(dev_loc)),
model_dir, gold_preproc=gold_preproc, verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def main(train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False):
if not eval_only:
gold_train = list(read_json_file(train_loc))
train(English, gold_train, model_dir,
feat_set='basic' if not debug else 'debug',
gold_preproc=gold_preproc, n_sents=n_sents,
corruption_level=corruption_level, n_iter=n_iter,
verbose=verbose)
#if out_loc:
# write_parses(English, dev_loc, model_dir, out_loc, beam_width=beam_width)
scorer = evaluate(English, list(read_json_file(dev_loc)),
model_dir, gold_preproc=gold_preproc, verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def main(language, train_loc, dev_loc, model_dir, n_sents=0, n_iter=15, out_loc="", verbose=False,
debug=False, corruption_level=0.0, gold_preproc=False, eval_only=False, pseudoprojective=False):
lang = {'en':English, 'de':German}.get(language)
if not eval_only:
gold_train = list(read_json_file(train_loc))
train(lang, gold_train, model_dir,
feat_set='basic' if not debug else 'debug',
gold_preproc=gold_preproc, n_sents=n_sents,
corruption_level=corruption_level, n_iter=n_iter,
verbose=verbose,pseudoprojective=pseudoprojective)
if out_loc:
write_parses(lang, dev_loc, model_dir, out_loc)
scorer = evaluate(lang, list(read_json_file(dev_loc)),
model_dir, gold_preproc=gold_preproc, verbose=verbose)
print('TOK', scorer.token_acc)
print('POS', scorer.tags_acc)
print('UAS', scorer.uas)
print('LAS', scorer.las)
print('NER P', scorer.ents_p)
print('NER R', scorer.ents_r)
print('NER F', scorer.ents_f)
def write_parses(Language, dev_loc, model_dir, out_loc, beam_width=None):
nlp = Language(data_dir=model_dir)
if beam_width is not None:
nlp.parser.cfg.beam_width = beam_width
gold_tuples = read_json_file(dev_loc)
scorer = Scorer()
out_file = codecs.open(out_loc, "w", "utf8")
for raw_text, sents in gold_tuples:
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.entity(tokens)
nlp.parser(tokens)
else:
tokens = nlp(raw_text, merge_mwes=False)
gold = GoldParse(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=False)
for t in tokens:
out_file.write("%s\t%s\t%s\t%s\n" % (t.orth_, t.tag_, t.head.orth_, t.dep_))
return scorer
def write_parses(Language, dev_loc, model_dir, out_loc, beam_width=None):
nlp = Language(data_dir=model_dir)
if beam_width is not None:
nlp.parser.cfg.beam_width = beam_width
gold_tuples = read_json_file(dev_loc)
scorer = Scorer()
out_file = codecs.open(out_loc, 'w', 'utf8')
for raw_text, sents in gold_tuples:
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.entity(tokens)
nlp.parser(tokens)
else:
tokens = nlp(raw_text, merge_mwes=False)
gold = GoldParse(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=False)
for t in tokens:
out_file.write('%s\t%s\t%s\t%s\n' %
(t.orth_, t.tag_, t.head.orth_, t.dep_))
return scorer
def write_parses(Language, dev_loc, model_dir, out_loc):
nlp = Language(data_dir=model_dir)
gold_tuples = read_json_file(dev_loc)
scorer = Scorer()
out_file = io.open(out_loc, 'w', 'utf8')
for raw_text, sents in gold_tuples:
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.entity(tokens)
nlp.parser(tokens)
else:
tokens = nlp(raw_text)
#gold = GoldParse(tokens, annot_tuples)
#scorer.score(tokens, gold, verbose=False)
for sent in tokens.sents:
for t in sent:
if not t.is_space:
out_file.write(
'%d\t%s\t%s\t%s\t%s\n' %
(t.i, t.orth_, t.tag_, t.head.orth_, t.dep_))
out_file.write('\n')
def write_parses(Language, dev_loc, model_dir, out_loc):
nlp = Language(data_dir=model_dir)
gold_tuples = read_json_file(dev_loc)
scorer = Scorer()
out_file = io.open(out_loc, 'w', 'utf8')
for raw_text, sents in gold_tuples:
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.entity(tokens)
nlp.parser(tokens)
else:
tokens = nlp(raw_text)
#gold = GoldParse(tokens, annot_tuples)
#scorer.score(tokens, gold, verbose=False)
for sent in tokens.sents:
for t in sent:
if not t.is_space:
out_file.write(
'%d\t%s\t%s\t%s\t%s\n' % (t.i, t.orth_, t.tag_, t.head.orth_, t.dep_)
)
out_file.write('\n')
Developed and tested for spaCy 2.0.6. Updated for v2.2.2
"""
import random
import plac
import spacy
import os.path
from spacy.tokens import Doc
from spacy.gold import read_json_file, GoldParse
random.seed(0)
PWD = os.path.dirname(__file__)
TRAIN_DATA = list(
read_json_file(
os.path.join(PWD, "ner_example_data", "ner-sent-per-line.json")))
def get_position_label(i, words, tags, heads, labels, ents):
"""Return labels indicating the position of the word in the document.
"""
if len(words) < 20:
return "short-doc"
elif i == 0:
return "first-word"
elif i < 10:
return "early-word"
elif i < 20:
return "mid-word"
elif i == len(words) - 1:
return "last-word"
The specific example here is not necessarily a good idea --- but it shows
how an arbitrary objective function for some word can be used.
Developed and tested for spaCy 2.0.6
'''
import random
import plac
import spacy
import os.path
from spacy.gold import read_json_file, GoldParse
random.seed(0)
PWD = os.path.dirname(__file__)
TRAIN_DATA = list(read_json_file(os.path.join(PWD, 'training-data.json')))
def get_position_label(i, words, tags, heads, labels, ents):
'''Return labels indicating the position of the word in the document.
'''
if len(words) < 20:
return 'short-doc'
elif i == 0:
return 'first-word'
elif i < 10:
return 'early-word'
elif i < 20:
return 'mid-word'
elif i == len(words) - 1:
return 'last-word'
The specific example here is not necessarily a good idea --- but it shows
how an arbitrary objective function for some word can be used.
Developed and tested for spaCy 2.0.6
'''
import random
import plac
import spacy
import os.path
from spacy.gold import read_json_file, GoldParse
random.seed(0)
PWD = os.path.dirname(__file__)
TRAIN_DATA = list(read_json_file(os.path.join(PWD, 'training-data.json')))
def get_position_label(i, words, tags, heads, labels, ents):
'''Return labels indicating the position of the word in the document.
'''
if len(words) < 20:
return 'short-doc'
elif i == 0:
return 'first-word'
elif i < 10:
return 'early-word'
elif i < 20:
return 'mid-word'
elif i == len(words)-1:
