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

Fix ud-train script

This commit is contained in:
Matthew Honnibal 2018-03-11 01:26:45 +01:00
parent 2cab4d6517
commit 5dddb30e5b
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/cli/ud_train.py
View File

@ -310,7 +310,7 @@ def initialize_pipeline(nlp, docs, golds, config):
class Config(object): class Config(object):
def __init__(self, vectors=None, max_doc_length=10, multitask_tag=True, def __init__(self, vectors=None, max_doc_length=10, multitask_tag=True,
multitask_sent=True, nr_epoch=30, batch_size=1000, dropout=0.2): multitask_sent=True, nr_epoch=30, batch_size=1000, dropout=0.2):
for key, value in locals(): for key, value in locals().items():
setattr(self, key, value) setattr(self, key, value)
@classmethod @classmethod
@ -352,10 +352,11 @@ class TreebankPaths(object):
corpus=("UD corpus to train and evaluate on, e.g. en, es_ancora, etc", corpus=("UD corpus to train and evaluate on, e.g. en, es_ancora, etc",
"positional", None, str), "positional", None, str),
parses_dir=("Directory to write the development parses", "positional", None, Path), parses_dir=("Directory to write the development parses", "positional", None, Path),
config=("Path to json formatted config file", "positional", None, Config.load), config=("Path to json formatted config file", "positional"),
limit=("Size limit", "option", "n", int) limit=("Size limit", "option", "n", int)
) )
def main(ud_dir, parses_dir, config, corpus, limit=0): def main(ud_dir, parses_dir, config, corpus, limit=0):
config = Config.load(config)
paths = TreebankPaths(ud_dir, corpus) paths = TreebankPaths(ud_dir, corpus)
if not (parses_dir / corpus).exists(): if not (parses_dir / corpus).exists():
(parses_dir / corpus).mkdir() (parses_dir / corpus).mkdir()