for fileid in input_corpus.fileids():
# TODO: use ~/nltk_data/corpora as dir prefix?
path = os.path.join(args.target_corpus, fileid)
dirname = os.path.dirname(path)
if not os.path.exists(dirname):
if args.trace:
print 'making directory %s' % dirname
os.makedirs(dirname)
with open(path, 'w') as outf:
if args.trace:
print 'translating file %s to %s' % (fileid, path)
for para in input_corpus.paras(fileids=[fileid]):
for sent in para:
# TODO: use intelligent joining (with punctuation)
text = join_words(sent)
if not text: continue
trans = translate(text, args.source, args.corpus, trace=args.trace,
sleep=args.sleep, retries=args.retries)
if not trans: continue
if args.trace > 1:
print text, '-->>', trans
outf.write(trans + ' ')
outf.write('\n\n')
labels = classifier.labels()
label_files = dict([(l, open(label_filename(l), 'a')) for l in labels])
# TODO: create a nltk.corpus.writer framework with some initial CorpusWriter classes
if args.target:
if args.trace:
print 'translating all text from %s to %s' % (args.source, args.target)
featx = lambda words: bag_of_words(
norm_words(
wordpunct_tokenize(
translate(join_words(words),
args.source,
args.target,
trace=args.trace,
sleep=args.sleep,
retries=args.retries))))
else:
featx = lambda words: bag_of_words(norm_words(words))
def classify_write(words):
feats = featx(words)
probs = classifier.prob_classify(feats)
label = probs.max()
if probs.prob(label) >= args.threshold:
label_files[label].write(join_words(words) + u'\n\n')
if args.trace: print 'filename for category %s: %s' % (label, path) return path labels = classifier.labels() label_files = dict([(l, open(label_filename(l), 'a')) for l in labels]) # TODO: create a nltk.corpus.writer framework with some initial CorpusWriter classes if args.target: if args.trace: print 'translating all text from %s to %s' % (args.source, args.target) featx = lambda words: bag_of_words(norm_words(wordpunct_tokenize(translate(join_words(words), args.source, args.target, trace=args.trace, sleep=args.sleep, retries=args.retries)))) else: featx = lambda words: bag_of_words(norm_words(words)) def classify_write(words): feats = featx(words) probs = classifier.prob_classify(feats) label = probs.max() if probs.prob(label) >= args.threshold: label_files[label].write(join_words(words) + u'\n\n') if args.trace: print 'classifying %s' % args.instances if args.instances == 'paras':
for fileid in input_corpus.fileids():
# TODO: use ~/nltk_data/corpora as dir prefix?
path = os.path.join(args.target_corpus, fileid)
dirname = os.path.dirname(path)
if not os.path.exists(dirname):
if args.trace:
print 'making directory %s' % dirname
os.makedirs(dirname)
with open(path, 'w') as outf:
if args.trace:
print 'translating file %s to %s' % (fileid, path)
for para in input_corpus.paras(fileids=[fileid]):
for sent in para:
# TODO: use intelligent joining (with punctuation)
text = join_words(sent)
if not text: continue
trans = translate(text, args.source, args.corpus, trace=args.trace,
sleep=args.sleep, retries=args.retries)
if not trans: continue
if args.trace > 1:
print text, '-->>', trans
outf.write(trans + ' ')
outf.write('\n\n')