print 'Unknown words: %d' % len(unknown_words) if args.trace and unknown_words: print ', '.join(sorted(unknown_words)) print '' print ' '.join(['Tag'.center(taglen), 'Found'.center(9), 'Actual'.center(10), 'Precision'.center(13), 'Recall'.center(13)]) print ' '.join(['='*taglen, '='*9, '='*10, '='*13, '='*13]) for tag in sorted(set(tags_found.keys()) | set(tags_actual.keys())): found = tags_found[tag] actual = tags_actual[tag] precision = nltk.metrics.precision(tag_word_refs[tag], tag_word_test[tag]) recall = nltk.metrics.recall(tag_word_refs[tag], tag_word_test[tag]) print ' '.join([tag.ljust(taglen), str(found).rjust(9), str(actual).rjust(10), str(precision).ljust(13)[:13], str(recall).ljust(13)[:13]]) print ' '.join(['='*taglen, '='*9, '='*10, '='*13, '='*13]) else: sents = corpus.sents(**kwargs) taglen = 7 if args.fraction != 1.0: cutoff = int(math.ceil(len(sents) * args.fraction)) sents = sents[:cutoff] for sent in sents: for word, tag in tagger.tag(sent): tags_found.inc(tag)
print('Unknown words: %d' % len(unknown_words))
if args.trace and unknown_words:
print(', '.join(sorted(unknown_words)))
print('')
print(' '.join(['Tag'.center(taglen), 'Found'.center(9), 'Actual'.center(10),
'Precision'.center(13), 'Recall'.center(13)]))
print(' '.join(['='*taglen, '='*9, '='*10, '='*13, '='*13]))
for tag in sorted(set(tags_found.keys()) | set(tags_actual.keys())):
found = tags_found[tag]
actual = tags_actual[tag]
precision = nltk.metrics.precision(tag_word_refs[tag], tag_word_test[tag])
recall = nltk.metrics.recall(tag_word_refs[tag], tag_word_test[tag])
print(' '.join([tag.ljust(taglen), str(found).rjust(9), str(actual).rjust(10),
str(precision).ljust(13)[:13], str(recall).ljust(13)[:13]]))
print(' '.join(['='*taglen, '='*9, '='*10, '='*13, '='*13]))
else:
sents = corpus.sents(**kwargs)
taglen = 7
if args.fraction != 1.0:
cutoff = int(math.ceil(len(sents) * args.fraction))
sents = sents[:cutoff]
for sent in sents:
for word, tag in tagger.tag(sent):
tags_found[tag] += 1
print ''
print ' '.join([
'Tag'.center(taglen), 'Found'.center(9), 'Actual'.center(10),
'Precision'.center(13), 'Recall'.center(13)
])
print ' '.join(['=' * taglen, '=' * 9, '=' * 10, '=' * 13, '=' * 13])
for tag in sorted(set(tags_found.keys()) | set(tags_actual.keys())):
found = tags_found[tag]
actual = tags_actual[tag]
precision = nltk.metrics.precision(tag_word_refs[tag],
tag_word_test[tag])
recall = nltk.metrics.recall(tag_word_refs[tag], tag_word_test[tag])
print ' '.join([
tag.ljust(taglen),
str(found).rjust(9),
str(actual).rjust(10),
str(precision).ljust(13)[:13],
str(recall).ljust(13)[:13]
])
print ' '.join(['=' * taglen, '=' * 9, '=' * 10, '=' * 13, '=' * 13])
else:
sents = corpus.sents(**kwargs)
taglen = 7
if args.fraction != 1.0:
cutoff = int(math.ceil(len(sents) * args.fraction))
sents = sents[:cutoff]
if args.trace:
print ", ".join(sorted(unknown_words))
print ""
print " Tag Found Actual Precision Recall "
print "======= ========= ========== ============= =========="
for tag in sorted(set(tags_found.keys()) | set(tags_actual.keys())):
found = tags_found[tag]
actual = tags_actual[tag]
precision = nltk.metrics.precision(tag_word_refs[tag], tag_word_test[tag])
recall = nltk.metrics.recall(tag_word_refs[tag], tag_word_test[tag])
print " ".join(
[
tag.ljust(7),
str(found).rjust(9),
str(actual).rjust(10),
str(precision).ljust(13)[:13],
str(recall).ljust(10)[:13],
]
)
print "======= ========= ========== ============= =========="
else:
sents = corpus.sents()
if args.fraction != 1.0:
cutoff = int(math.ceil(len(sents) * args.fraction))
sents = sents[:cutoff]