Created
June 27, 2013 20:40
-
-
Save bbengfort/5880193 to your computer and use it in GitHub Desktop.
Quick concordance search for a corpus.
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
#!/usr/bin/env python | |
from nltk import Text | |
from nltk.corpus import PlaintextCorpusReader | |
CORPUS_ROOT = '/Users/benjamin/Development/corpora/gutenburg/' | |
if __name__ == "__main__": | |
reader = PlaintextCorpusReader(CORPUS_ROOT, '.*') | |
text = Text(reader.words()) | |
while True: | |
word = raw_input('Enter word: ') | |
print (word); | |
text.concordance(word) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment