Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Fancy up the CLI for the conll train script

This commit is contained in:
Matthew Honnibal 2016-02-02 22:58:06 +01:00
parent 59123443e2
commit e2ed6251d7
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
bin/parser/conll_train.py
View File

@ -129,10 +129,18 @@ def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic', seed=0
print('done') print('done')
def main(train_loc, dev_loc, model_dir): @plac.annotations(
train_loc=("Location of CoNLL 09 formatted training file"),
dev_loc=("Location of CoNLL 09 formatted development file"),
model_dir=("Location of output model directory"),
eval_only=("Skip training, and only evaluate", "flag", "e", bool),
n_iter=("Number of training iterations", "option", "i", int),
)
def main(train_loc, dev_loc, model_dir, n_iter=15):
with io.open(train_loc, 'r', encoding='utf8') as file_: with io.open(train_loc, 'r', encoding='utf8') as file_:
train_sents = read_conll(file_) train_sents = read_conll(file_)
#train(English, train_sents, model_dir) if not eval_only:
train(English, train_sents, model_dir, n_iter=n_iter)
nlp = English(data_dir=model_dir) nlp = English(data_dir=model_dir)
dev_sents = read_conll(io.open(dev_loc, 'r', encoding='utf8')) dev_sents = read_conll(io.open(dev_loc, 'r', encoding='utf8'))
scorer = Scorer() scorer = Scorer()