def extract_features(inputfile, outputfile):
fi = open(inputfile, 'r')
fo = open(outputfile, 'w')
crfutils.main(feature_extractor,
fields=fields,
sep=separator,
fi=fi,
fo=fo)
fi.close()
fo.close()
v['pref'] = a[0:3].encode('utf-8')
#else:
# v['pref'] = ''
if len(a) <= 3:
v['len'] = '1'
else:
v['len'] = '0'
if c == 0:
v['fir'] = '1'
else:
v['fir'] = '0'
def feature_extractor(X):
c = 0
for x in X:
observation(x, c)
c = c + 1
# 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)
features = OrderedDict()
for i in feature_set:
features[i[0]] = i[1]
for w, _ in features.items():
if w in trigrams:
features[w] = [[[w, -1]], [[w, 0]], [[w, 1]]]
feature_keys = features.keys()
feature_items = features.values()
input_columns = ' '.join(feature_keys) + ' chunk y'
attribute_templates = []
for i in feature_items:
attribute_templates += i
print("Using features: {}.".format(str(attribute_templates)))
feature_extractor = lambda x: crfutils.apply_templates(x, attribute_templates)
for fi, txt in [(train_csv, "train"), (devel_csv, "devel"), (test_csv, "test")]:
write_to = path.join(trigram_path, txt + "_trigrams_" + str(mode) + ".crfsuite")
fo = open(write_to, "w+")
print("Writing to {}...".format(write_to))
crfutils.main(feature_extractor, fi, fo, fields=input_columns, sep='\t')
fo.close()
train_csv.close()
devel_csv.close()
test_csv.close()
(('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)
def generate(infile, outfile):
sys.stderr.write("Generating features.\n")
crfutils.main(feature_extractor, fields, separator, open(infile, 'r'),
open(outfile, 'w'))
return features
def Featurizer(X):
global DF
if X:
sent = []
for t in range(len(X)):
sent.append(X[t]['w'])
for t in range(len(X)):
w = X[t]['w']
feats = DF.GetDictFeatures(sent, t) + GetOrthographicFeatures(w)
for f in feats:
X[t]['F'].append('%s' % (f))
def FeatureExtractor(X):
"""apply attribute templates to obtain features (in fact, attributes)"""
crfutils.apply_templates(X, templates)
Featurizer(X)
if X:
X[0]['F'].append('__BOS__') # BOS feature
X[-1]['F'].append('__EOS__') # EOS feature
if __name__ == '__main__':
DF = DictionaryFeatures("./lexicon")
crfutils.main(FeatureExtractor, fields=fields, sep=separator)
def generate(infile, outfile):
sys.stderr.write("Generating features.\n")
crfutils.main(feature_extractor, fields, separator, open(infile, 'r'), open(outfile, 'w'))
def extract_features(inputfile,outputfile): fi = open(inputfile,'r') fo = open(outputfile,'w') crfutils.main(feature_extractor,fields=fields,sep=separator,fi=fi,fo=fo) fi.close() fo.close()
def main(argv):
crfutils.main(feature_extractor, fields='w y', sep='\t')
def Featurizer(X):
#print 'Featurizer called with X ', X
global DF
if X:
entire= []
for t in range(len(X)):
entire.append(X[t]['w'])
for t in range(len(X)):
w = X[t]['w']
feats = DF.GetDictFeatures(entire,t) + GetOrthographicFeatures(w)
for f in feats:
X[t]['F'].append('%s'%(f))
def FeatureExtractor(X):
"""apply attribute templates to obtain features (in fact, attributes)"""
#print 'FeatureExtractor called with X ', X
crfutils.apply_templates(X, templates)
Featurizer(X)
#print X
if X:
#print 'in if X'
X[0]['F'].append('__BOS__') # BOS feature
X[-1]['F'].append('__EOS__') # EOS feature
if __name__ == '__main__':
DF = DictionaryFeatures("./lexicon")
#print 'Running main crf module ********************'
crfutils.main(FeatureExtractor, fields=fields, sep=separator)
(('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)),
)
def feature_extractor(X):
template.apply(X, templates)
if X:
X[0]['F'].append('__BOS__')
X[-1]['F'].append('__EOS__')
if __name__ == '__main__':
crfutils.main(feature_extractor, fields='w pos y', sep=' ')
(('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 re
templates = (
(('w', 0, re.compile(r'^\d{2}$')), ('w', 1, re.compile(r'年'))),
(('w', -1, re.compile(r'^\d{2}$')), ('w', 0, re.compile(r'年'))),
)
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__':
import sys
input_file = sys.argv[1]
crfutils.main(feature_extractor, input_file=input_file, fields=fields, sep=separator)
