Last active
August 30, 2019 16:04
-
-
Save Lexie88rus/41ce576b5841061381d53af4b305b3e1 to your computer and use it in GitHub Desktop.
Create a vocabulary for kernel titles
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def create_vocabulary(titles): | |
| ''' | |
| Function to create a vocabulary out of a list of titles | |
| ''' | |
| vocab = set() | |
| for title in titles: | |
| if (clean_title(title) != ''): | |
| words = extract_words(title) | |
| vocab.update(words) | |
| word_list = list(vocab) | |
| word_list.append(end_of_sentence) | |
| vocabulary = {word_list[n]:n for n in range(0,len(word_list))} | |
| return vocabulary | |
| # create vocabulary out of popular kernel titles | |
| vocab = create_vocabulary(popular_kernel_titles) | |
| vocab_size = len(vocab) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment