lif = label_instance_function[args.instances]
feats = []
test_feats = []
for label in labels:
texts = lif(categorized_corpus, label)
if args.instances == 'files':
# don't get list(texts) here since might have tons of files
stop = int(len(categorized_corpus.fileids())*args.fraction)
else:
texts = list(texts)
stop = int(len(texts)*args.fraction)
for t in itertools.islice(texts, stop):
feat = bag_of_words(norm_words(t))
feats.append(feat)
test_feats.append((feat, label))
print('accuracy:', accuracy(classifier, test_feats))
refsets, testsets = scoring.ref_test_sets(classifier, test_feats)
for label in labels:
ref = refsets[label]
test = testsets[label]
print('%s precision: %f' % (label, precision(ref, test) or 0))
print('%s recall: %f' % (label, recall(ref, test) or 0))
print('%s f-measure: %f' % (label, f_measure(ref, test) or 0))
else:
if args.instances == 'sents':
texts = categorized_corpus.sents()
label_instance_function = {
'sents': corpus.category_sent_words,
'paras': corpus.category_para_words,
'files': corpus.category_file_words
}
lif = label_instance_function[args.instances]
feats = []
test_feats = []
for label in labels:
texts = list(lif(categorized_corpus, label))
stop = int(len(texts)*args.fraction)
for t in texts[:stop]:
feat = bag_of_words(norm_words(t))
feats.append(feat)
test_feats.append((feat, label))
print 'accuracy:', accuracy(classifier, test_feats)
refsets, testsets = scoring.ref_test_sets(classifier, test_feats)
for label in labels:
ref = refsets[label]
test = testsets[label]
print '%s precision: %f' % (label, precision(ref, test) or 0)
print '%s recall: %f' % (label, recall(ref, test) or 0)
print '%s f-measure: %f' % (label, f_measure(ref, test) or 0)
else:
instance_function = {
'sents': categorized_corpus.sents,
def bag_of_bigrams_words(words, score_fn=BigramAssocMeasures.chi_sq, n=200):
bigram_finder = BigramCollocationFinder.from_words(words)
bigrams = bigram_finder.nbest(score_fn, n)
return bag_of_words(words + bigrams)
lif = label_instance_function[args.instances]
feats = []
test_feats = []
for label in labels:
texts = lif(categorized_corpus, label)
if args.instances == 'files':
# don't get list(texts) here since might have tons of files
stop = int(len(categorized_corpus.fileids()) * args.fraction)
else:
texts = list(texts)
stop = int(len(texts) * args.fraction)
for t in itertools.islice(texts, stop):
feat = bag_of_words(norm_words(t))
feats.append(feat)
test_feats.append((feat, label))
print('accuracy:', accuracy(classifier, test_feats))
refsets, testsets = scoring.ref_test_sets(classifier, test_feats)
for label in labels:
ref = refsets[label]
test = testsets[label]
print('%s precision: %f' % (label, precision(ref, test) or 0))
print('%s recall: %f' % (label, recall(ref, test) or 0))
print('%s f-measure: %f' % (label, f_measure(ref, test) or 0))
else:
if args.instances == 'sents':
texts = categorized_corpus.sents()
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':
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')
label_instance_function = {
"sents": corpus.category_sent_words,
"paras": corpus.category_para_words,
"files": corpus.category_file_words,
}
lif = label_instance_function[args.instances]
feats = []
test_feats = []
for label in labels:
texts = list(lif(categorized_corpus, label))
stop = int(len(texts) * args.fraction)
for t in texts[:stop]:
feat = bag_of_words(norm_words(t))
feats.append(feat)
test_feats.append((feat, label))
print "accuracy:", accuracy(classifier, test_feats)
refsets, testsets = scoring.ref_test_sets(classifier, test_feats)
for label in labels:
ref = refsets[label]
test = testsets[label]
print "%s precision: %f" % (label, precision(ref, test) or 0)
print "%s recall: %f" % (label, recall(ref, test) or 0)
print "%s f-measure: %f" % (label, f_measure(ref, test) or 0)
else:
instance_function = {
"sents": categorized_corpus.sents,
if not os.path.exists(args.target_corpus):
os.makedirs(args.target_corpus)
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
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':
path = os.path.join(args.target_corpus, '%s.txt' % label) if not os.path.exists(args.target_corpus): os.makedirs(args.target_corpus) 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 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 para in source_corpus.paras(): classify_write(list(itertools.chain(*para)))