explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add write_parses function

Browse Source
This commit is contained in:
Matthew Honnibal 2015-03-20 01:14:20 +01:00
parent 0c91dd9e15
commit 52429625f0
1 changed files with 22 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
bin/parser/train.py
View File

@ -237,6 +237,7 @@ def train(Language, train_loc, model_dir, n_iter=15, feat_set=u'basic', seed=0,
nlp.parser.model.end_training() nlp.parser.model.end_training()
nlp.entity.model.end_training() nlp.entity.model.end_training()
nlp.tagger.model.end_training() nlp.tagger.model.end_training()
print nlp.vocab.strings['NMOD']
def evaluate(Language, dev_loc, model_dir, gold_preproc=False, verbose=True): def evaluate(Language, dev_loc, model_dir, gold_preproc=False, verbose=True):
@ -251,16 +252,34 @@ def evaluate(Language, dev_loc, model_dir, gold_preproc=False, verbose=True):
return scorer return scorer
def write_parses(Language, dev_loc, model_dir, out_loc):
nlp = Language()
gold_tuples = read_docparse_file(dev_loc)
scorer = Scorer()
out_file = codecs.open(out_loc, 'w', 'utf8')
for raw_text, segmented_text, annot_tuples in gold_tuples:
tokens = nlp(raw_text)
for t in tokens:
out_file.write(
'%s\t%s\t%s\t%s\n' % (t.orth_, t.tag_, t.head.orth_, t.dep_)
)
print nlp.vocab.strings['NMOD']
return scorer
@plac.annotations( @plac.annotations(
train_loc=("Training file location",), train_loc=("Training file location",),
dev_loc=("Dev. file location",), dev_loc=("Dev. file location",),
model_dir=("Location of output model directory",), model_dir=("Location of output model directory",),
out_loc=("Out location", "option", "o", str),
n_sents=("Number of training sentences", "option", "n", int), n_sents=("Number of training sentences", "option", "n", int),
verbose=("Verbose error reporting", "flag", "v", bool), verbose=("Verbose error reporting", "flag", "v", bool),
) )
def main(train_loc, dev_loc, model_dir, n_sents=0, verbose=False): def main(train_loc, dev_loc, model_dir, n_sents=0, out_loc="", verbose=False):
train(English, train_loc, model_dir, #train(English, train_loc, model_dir,
gold_preproc=False, force_gold=False, n_sents=n_sents) # gold_preproc=False, force_gold=False, n_sents=n_sents)
if out_loc:
write_parses(English, dev_loc, model_dir, out_loc)
scorer = evaluate(English, dev_loc, model_dir, gold_preproc=False, verbose=verbose) scorer = evaluate(English, dev_loc, model_dir, gold_preproc=False, verbose=verbose)
print 'POS', scorer.tags_acc print 'POS', scorer.tags_acc
print 'UAS', scorer.uas print 'UAS', scorer.uas