(s)
| 84 | return sentences, word2idx |
| 85 | |
| 86 | def my_tokenizer(s): |
| 87 | s = remove_punctuation(s) |
| 88 | s = s.lower() # downcase |
| 89 | return s.split() |
| 90 | |
| 91 | def get_wikipedia_data(n_files, n_vocab, by_paragraph=False): |
| 92 | prefix = '../large_files/' |
no outgoing calls
no test coverage detected