def convert_MC28(self, input_file, output_file, delimiter=';'):
fio = FileManipulation()
ranges = RangeData()
tokens = []
with open(input_file, 'r', encoding='utf-8') as fin:
for line in fin:
token = TokenData()
block = line.split(delimiter)
token.word1 = block[0]
token.word2 = block[1]
token.simvalue = float(block[2].strip('\n'))
new_range = ranges.range_category['cos']
old_range = ranges.range_category['mc28']
token.simvalue = numpy.interp(token.simvalue, old_range, new_range)
tokens.append(token)
fio.writeSimilarityWord(output_file, tokens)
def convert_SCWS(self, input_file, output_file, delimiter='\t'):
fio = FileManipulation()
ranges = RangeData()
tokens = []
with open(input_file, 'r', encoding='utf-8') as fin:
for line in fin:
token = TokenData()
block = line.split(delimiter)
token.word1 = block[1]
token.word2 = block[3]
token.sent1 = block[5] # target word1 between <b> </b>
token.sent2 = block[6] # target word2 between <b> </b>
token.simvalue = float(block[7].strip('\n'))
new_range = ranges.range_category['cos']
old_range = ranges.range_category['scws']
token.simvalue = numpy.interp(token.simvalue, old_range, new_range)
tokens.append(token)
fio.writeSimilarityContext(output_file, tokens) # specific writer for SCWS