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
#merges the most frequent pair in the corpus | |
#accepts the corpus and best pair | |
#returns the modified corpus | |
import re | |
def merge_vocab(pair, corpus_in): | |
corpus_out = {} | |
bigram = re.escape(' '.join(pair)) | |
p = re.compile(r'(?<!\S)' + bigram + r'(?!\S)') | |
for word in corpus_in: | |
w_out = p.sub(''.join(pair), word) | |
corpus_out[w_out] = corpus_in[word] | |
return corpus_out |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment