def featurize_file(filename):
# Create the file handler:
fi_handler = open(filename, 'r')
# # Apply the hashing trick
# hf = FeatureHasher(input_type='string',non_negative=True)
X = crfutils.get_features(feature_extractor, fields=fields, sep=' ', fi=fi_handler)
# X = crfutils.get_features(feature_extractor, fields=fields, sep=separator)
# doc = []
Y = set()
for x in X:
for entry in x:
Y.add(entry['y'])
# doc.append(entry['F'])
# return X, hf.transform(doc)
return X, list(Y)
X = crfutils.get_features(feature_extractor, fields=fields, sep=' ', fi=fi_handler)
# X = crfutils.get_features(feature_extractor, fields=fields, sep=separator)
# doc = []
Y = set()
for x in X:
for entry in x:
Y.add(entry['y'])
# doc.append(entry['F'])
# return X, hf.transform(doc)
return X, list(Y)
if __name__ == '__main__':
# pass
# crfutils.main(feature_extractor, fields=fields, sep=separator)
X = crfutils.get_features(feature_extractor, fields=fields, sep=separator)
# Apply the hashing trick
hf = FeatureHasher(input_type='string',non_negative=True)
# # List of dictionaries:
# x_set = set()
# # Iterate over each of the tokens features:
doc = []
for x in X:
# sg_tv.transform(x)
for entry in x:
# print entry['F']
doc+=entry['F']
# vec = sg_tv.transform(doc)
print hf.transform(doc)
