def test( self, test_sequence, verbose = False, **kwargs ):
"""
Tests the HiddenMarkovModelTagger instance.
:param test_sequence: a sequence of labeled test instances
:type test_sequence: list(list)
:param verbose: boolean flag indicating whether training should be
verbose or include printed output
:type verbose: bool
"""
def words( sent ):
return [ word for (word, tag) in sent ]
def tags( sent ):
return [ tag for (word, tag) in sent ]
def flatten( seq ):
return list( itertools.chain( *seq ) )
test_sequence = self._transform( test_sequence )
predicted_sequence = list( imap( self._tag, imap( words, test_sequence ) ) )
if verbose:
for test_sent, predicted_sent in izip( test_sequence, predicted_sequence ):
print( 'Test:',
' '.join( '%s/%s' % (token, tag)
for (token, tag) in test_sent ) )
print( )
print( 'Untagged:',
' '.join( "%s" % token for (token, tag) in test_sent ) )
print( )
print( 'HMM-tagged:',
' '.join( '%s/%s' % (token, tag)
for (token, tag) in predicted_sent ) )
print( )
print( 'Entropy:',
self.entropy( [ (token, None) for
(token, tag) in predicted_sent ] ) )
print( )
print( '-' * 60 )
test_tags = flatten( imap( tags, test_sequence ) )
predicted_tags = flatten( imap( tags, predicted_sequence ) )
acc = accuracy( test_tags, predicted_tags )
count = sum( len( sent ) for sent in test_sequence )
print( 'accuracy over %d tokens: %.2f' % (count, acc * 100) )
def test(self, test_sequence, verbose=False, **kwargs):
"""
Tests the HiddenMarkovModelTagger instance.
:param test_sequence: a sequence of labeled test instances
:type test_sequence: list(list)
:param verbose: boolean flag indicating whether training should be
verbose or include printed output
:type verbose: bool
"""
def words(sent):
return [word for (word, tag) in sent]
def tags(sent):
return [tag for (word, tag) in sent]
def flatten(seq):
return list(itertools.chain(*seq))
test_sequence = self._transform(test_sequence)
predicted_sequence = list(imap(self._tag, imap(words, test_sequence)))
if verbose:
for test_sent, predicted_sent in izip(test_sequence,
predicted_sequence):
print(
'Test:', ' '.join('%s/%s' % (token, tag)
for (token, tag) in test_sent))
print()
print('Untagged:',
' '.join("%s" % token for (token, tag) in test_sent))
print()
print(
'HMM-tagged:',
' '.join('%s/%s' % (token, tag)
for (token, tag) in predicted_sent))
print()
print(
'Entropy:',
self.entropy([(token, None)
for (token, tag) in predicted_sent]))
print()
print('-' * 60)
test_tags = flatten(imap(tags, test_sequence))
predicted_tags = flatten(imap(tags, predicted_sequence))
acc = accuracy(test_tags, predicted_tags)
count = sum(len(sent) for sent in test_sequence)
print('accuracy over %d tokens: %.2f' % (count, acc * 100))
def nsmallest(n, iterable, key=None):
"""Find the n smallest elements in a dataset.
Equivalent to: sorted(iterable, key=key)[:n]
"""
if key is None:
it = izip(iterable, count()) # decorate
result = _nsmallest(n, it)
return map(itemgetter(0), result) # undecorate
in1, in2 = tee(iterable)
it = izip(imap(key, in1), count(), in2) # decorate
result = _nsmallest(n, it)
return map(itemgetter(2), result) # undecorate