explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add verbose flag for Scorer, for debugging, and fix ent_strings bug

Browse Source
This commit is contained in:
Matthew Honnibal 2015-03-11 02:27:22 -04:00
parent f21ab2d7fb
commit 8f7eeb1c2d
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
bin/parser/train.py
View File

@ -215,7 +215,8 @@ def train(Language, train_loc, model_dir, n_iter=15, feat_set=u'basic', seed=0,
nlp = Language() nlp = Language()
ent_strings = [None] * (max(nlp.entity.moves.label_ids.values()) + 1) ent_strings = [None] * (max(nlp.entity.moves.label_ids.values()) + 1)
for label, i in nlp.entity.moves.label_ids.items(): for label, i in nlp.entity.moves.label_ids.items():
ent_strings[i] = label if i >= 0:
ent_strings[i] = label
print "Itn.\tUAS\tNER F.\tTag %" print "Itn.\tUAS\tNER F.\tTag %"
for itn in range(n_iter): for itn in range(n_iter):
@ -243,8 +244,7 @@ def train(Language, train_loc, model_dir, n_iter=15, feat_set=u'basic', seed=0,
nlp.tagger.model.end_training() nlp.tagger.model.end_training()
def evaluate(Language, dev_loc, model_dir, gold_preproc=False): def evaluate(Language, dev_loc, model_dir, gold_preproc=False, verbose=False):
global loss
assert not gold_preproc assert not gold_preproc
nlp = Language() nlp = Language()
gold_tuples = read_docparse_file(dev_loc) gold_tuples = read_docparse_file(dev_loc)
@ -252,11 +252,10 @@ def evaluate(Language, dev_loc, model_dir, gold_preproc=False):
for raw_text, segmented_text, annot_tuples in gold_tuples: for raw_text, segmented_text, annot_tuples in gold_tuples:
tokens = nlp(raw_text) tokens = nlp(raw_text)
gold = GoldParse(tokens, annot_tuples) gold = GoldParse(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=False) scorer.score(tokens, gold, verbose=verbose)
return scorer 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",),
@ -266,7 +265,7 @@ def evaluate(Language, dev_loc, model_dir, gold_preproc=False):
def main(train_loc, dev_loc, model_dir, n_sents=0): def main(train_loc, dev_loc, model_dir, n_sents=0):
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)
scorer = evaluate(English, dev_loc, model_dir, gold_preproc=False) scorer = evaluate(English, dev_loc, model_dir, gold_preproc=False, verbose=False)
print 'POS', scorer.tags_acc print 'POS', scorer.tags_acc
print 'UAS', scorer.uas print 'UAS', scorer.uas
print 'LAS', scorer.las print 'LAS', scorer.las