explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-13 09:42:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix inconsistent label freq cutoff for projectivisation

Browse Source
This commit is contained in:
Matthew Honnibal 2018-02-26 12:01:44 +01:00
parent 7b66ec896a
commit b8d52cb285
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/gold.pyx
View File

@ -133,10 +133,10 @@ class GoldCorpus(object):
def train_docs(self, nlp, gold_preproc=False, def train_docs(self, nlp, gold_preproc=False,
projectivize=False, max_length=None, projectivize=False, max_length=None,
noise_level=0.0): noise_level=0.0):
train_tuples = self.train_tuples train_tuples = list(self.train_tuples)
if projectivize: if projectivize:
train_tuples = nonproj.preprocess_training_data( train_tuples = nonproj.preprocess_training_data(
self.train_tuples, label_freq_cutoff=100) self.train_tuples, label_freq_cutoff=30)
random.shuffle(train_tuples) random.shuffle(train_tuples)
gold_docs = self.iter_gold_docs(nlp, train_tuples, gold_preproc, gold_docs = self.iter_gold_docs(nlp, train_tuples, gold_preproc,
max_length=max_length, max_length=max_length,