Skip to content

MUC 7 Corpus reader Crashes #3

@aboSamoor

Description

@aboSamoor

r = LazyCorpusLoader('muc_7/', MUCCorpusReader, 'data/..ne.eng.keys.')
r.iob_sents()
[[('Like', 'O'), ('most', 'O'), ('of', 'O'), ('the', 'O'), ('two', 'O'), ('million', 'O'), ('infants', 'O'), ('under', 'O'), ('2', 'O'), ('who', 'O'), ('fly', 'O'), ('with', 'O'), ('their', 'O'), ('parents', 'O'), ('every', 'O'), ('year', 'O'), (',', 'O'), ('Danasia', 'B-PERSON'), ('was', 'O'), ('traveling', 'O'), ('for', 'O'), ('free', 'O'), (',', 'O'), ('seated', 'O'), ('on', 'O'), ('her', 'O'), ('mother', 'O'), ("'s", 'O'), ('lap', 'O'), ('.', 'O')], [('As', 'O'), ('the', 'O'), ('DC-9', 'O'), ('approached', 'O'), ('the', 'O'), ('airport', 'O'), ('on', 'O'), ('July', 'B-DATE'), ('2', 'I-DATE'), (',', 'I-DATE'), ('1994', 'I-DATE'), (',', 'O'), ('wind', 'O'), ('shear', 'O'), ('slammed', 'O'), ('the', 'O'), ('plane', 'O'), ('to', 'O'), ('the', 'O'), ('ground', 'O'), ('.', 'O')], ...]
len(r.iob_sents())
[Tree('S', ['The', Tree('ORGANIZATION', ['Unicef']), 'Flyer', 'flight', 'suffered', 'a', 'setback', Tree('DATE', ['Dec', '.'])]), Tree('DATE', ['Dec', '.'])]
Traceback (most recent call last):
File "", line 1, in
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in len
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 807, in len
if len(self._offsets) <= len(self._list):
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in len
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 807, in len
if len(self._offsets) <= len(self._list):
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in len
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/util.py", line 966, in
return max(len(lst) for lst in self._lists)
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/corpus/reader/util.py", line 379, in len
for tok in self.iterate_from(self._offsets[-1]): pass
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/corpus/reader/util.py", line 401, in iterate_from
for tok in piece.iterate_from(max(0, start_tok-offset)):
File "/usr/local/lib/python2.7/dist-packages/nltk-2.0.1rc4-py2.7.egg/nltk/corpus/reader/util.py", line 298, in iterate_from
tokens = self.read_block(self._stream)
File "/usr/local/lib/python2.7/dist-packages/nltk_contrib/coref/muc.py", line 419, in _read_parsed_block
return map(self._parse, self._read_block(stream))
File "/usr/local/lib/python2.7/dist-packages/nltk_contrib/coref/muc.py", line 428, in _parse
tree = mucstr2tree(doc, top_node='DOC')
File "/usr/local/lib/python2.7/dist-packages/nltk_contrib/coref/muc.py", line 468, in mucstr2tree
'text': _muc_read_text(match.group('text'), top_node),
File "/usr/local/lib/python2.7/dist-packages/nltk_contrib/coref/muc.py", line 534, in _muc_read_text
tree[-1].append(_muc_read_words(sent, 'S'))
File "/usr/local/lib/python2.7/dist-packages/nltk_contrib/coref/muc.py", line 558, in _muc_read_words
assert len(stack) == 1
AssertionError

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions