Sha256: f9516fea2a8632aeb37f41274816fa49e9b187050d1a94ebce8d9a58b9b20fa4
Contents?: true
Size: 1.15 KB
Versions: 21
Compression:
Stored size: 1.15 KB
Contents
#!/usr/bin/env python
"""
A feature extractor for chunking.
Copyright 2010,2011 Naoaki Okazaki.
"""
# Separator of field values.
separator = ' '
# Field names of the input data.
fields = 'w pos y'
# Attribute templates.
templates = (
(('w', -2), ),
(('w', -1), ),
(('w', 0), ),
(('w', 1), ),
(('w', 2), ),
(('w', -1), ('w', 0)),
(('w', 0), ('w', 1)),
(('pos', -2), ),
(('pos', -1), ),
(('pos', 0), ),
(('pos', 1), ),
(('pos', 2), ),
(('pos', -2), ('pos', -1)),
(('pos', -1), ('pos', 0)),
(('pos', 0), ('pos', 1)),
(('pos', 1), ('pos', 2)),
(('pos', -2), ('pos', -1), ('pos', 0)),
(('pos', -1), ('pos', 0), ('pos', 1)),
(('pos', 0), ('pos', 1), ('pos', 2)),
)
import crfutils
def feature_extractor(X):
# Apply attribute templates to obtain features (in fact, attributes)
crfutils.apply_templates(X, templates)
if X:
# Append BOS and EOS features manually
X[0]['F'].append('__BOS__') # BOS feature
X[-1]['F'].append('__EOS__') # EOS feature
if __name__ == '__main__':
crfutils.main(feature_extractor, fields=fields, sep=separator)
Version data entries
21 entries across 21 versions & 2 rubygems