SYMBOL INDEX (15 symbols across 3 files)

FILE: make_corpus.py
  function main (line 18) | def main(args):

FILE: tokenization.py
  class BaseTokenizer (line 4) | class BaseTokenizer(object):
    method __init__ (line 5) | def __init__(self, do_lower_case=False, preserved_pattern=None):
    method tokenize_words (line 9) | def tokenize_words(self, text):
    method tokenize (line 12) | def tokenize(self, text):
  class RegExpTokenizer (line 36) | class RegExpTokenizer(BaseTokenizer):
    method __init__ (line 37) | def __init__(self, pattern=r'\w+|\S', do_lower_case=False, preserved_p...
    method tokenize_words (line 41) | def tokenize_words(self, text):
  class NLTKTokenizer (line 46) | class NLTKTokenizer(BaseTokenizer):
    method __init__ (line 47) | def __init__(self, do_lower_case=False, preserved_pattern=None):
    method tokenize_words (line 52) | def tokenize_words(self, text):
  class MeCabTokenizer (line 57) | class MeCabTokenizer(BaseTokenizer):
    method __init__ (line 58) | def __init__(self, mecab_option='', do_lower_case=False, preserved_pat...
    method tokenize_words (line 64) | def tokenize_words(self, text):

FILE: train.py
  function main (line 16) | def main(args):