for i in range(n):
try:
segments.append(iterator.next())
except StopIteration:
break
return segments
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Cluster segments')
parser.add_argument('clustermodel', type=unicode, help='The clusterer model to use.')
args = parser.parse_args()
setstorage = MongoSettingsStorage()
docstorage = MongoDocumentStorage()
segstorage = MongoSegmentStorage()
logger.info('Loading clusterer model')
settings = setstorage.load(encode_name(args.clustermodel))
dictionary = Dictionary.load(os.path.join(DICTIONARY_PATH, settings[DICTIONARY]))
ngram_size = len(dictionary[0])
transformer = NgramTransformer(ngram_size)
ldamodel = LdaModel.load(os.path.join(LDA_PATH, settings[LDA_MODEL]))
logger.info('Clusterer model loaded!')
kwargs = {'dictionary': dictionary,
'ngramtransformer': transformer,
'ldamodel': ldamodel,
'method': 'LDA'}
def emptystorage(self):
storage = MongoSegmentStorage('test_db')
storage.delete()
return storage