ranjanmanish
/ tfidf.py
Created
February 27, 2016 03:17
— forked from sloria/tfidf.py
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
| import math | |
| from text.blob import TextBlob as tb | |
| def tf(word, blob): | |
| return blob.words.count(word) / len(blob.words) | |
| def n_containing(word, bloblist): | |
| return sum(1 for blob in bloblist if word in blob) | |
| def idf(word, bloblist): |