explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Finish text classifier example

Browse Source
This commit is contained in:
Matthew Honnibal 2017-07-23 00:34:12 +02:00
parent a88a7deffe
commit 54a539a113
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
examples/training/train_textcat.py
View File

@ -80,14 +80,14 @@ def load_data():
return (train_texts, train_cats), (dev_texts, dev_cats) return (train_texts, train_cats), (dev_texts, dev_cats)
def main(): def main(model_loc=None):
nlp = spacy.lang.en.English() nlp = spacy.lang.en.English()
tokenizer = nlp.tokenizer tokenizer = nlp.tokenizer
textcat = TextCategorizer(tokenizer.vocab, labels=['POSITIVE']) textcat = TextCategorizer(tokenizer.vocab, labels=['POSITIVE'])
print("Load IMDB data") print("Load IMDB data")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data() (train_texts, train_cats), (dev_texts, dev_cats) = load_data()
print("Itn.\tLoss\tP\tR\tF") print("Itn.\tLoss\tP\tR\tF")
progress = '{i:d} {loss:.3f} {textcat_p:.3f} {textcat_r:.3f} {textcat_f:.3f}' progress = '{i:d} {loss:.3f} {textcat_p:.3f} {textcat_r:.3f} {textcat_f:.3f}'
@ -95,6 +95,15 @@ def main():
train_texts, train_cats, train_texts, train_cats,
dev_texts, dev_cats, n_iter=20)): dev_texts, dev_cats, n_iter=20)):
print(progress.format(i=i, loss=loss, **scores)) print(progress.format(i=i, loss=loss, **scores))
# How to save, load and use
nlp.pipeline.append(textcat)
if model_loc is not None:
nlp.to_disk(model_loc)
nlp = spacy.load(model_loc)
doc = nlp(u'This movie sucked!')
print(doc.cats)
if __name__ == '__main__': if __name__ == '__main__':