Last active
March 31, 2021 03:32
-
-
Save piyush01123/12cc6a24ee8bcf2f56937abaf257dd35 to your computer and use it in GitHub Desktop.
TF-IDF implementation
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
| from sklearn.feature_extraction.text import TfidfTransformer | |
| import numpy as np | |
| counts = [[3, 0, 1], | |
| [2, 0, 0], | |
| [3, 0, 0], | |
| [4, 0, 0], | |
| [3, 2, 0], | |
| [3, 0, 2]] | |
| counts = np.array(counts) | |
| temp = counts*(np.log(len(counts) / (counts>0).sum(0))+1).reshape(1,-1) | |
| tfidf = temp/np.linalg.norm(temp,axis=1).reshape(-1,1) | |
| transformer = TfidfTransformer(smooth_idf=False) | |
| tfidf_skl = transformer.fit_transform(counts) | |
| tfidf_skl = tfidf_skl.toarray() | |
| print(np.allclose(tfidf, tfidf_skl)) | |
| temp = counts*(np.log((len(counts)+1) / ((counts>0).sum(0)+1))+1).reshape(1,-1) | |
| tfidf_smooth = temp/np.linalg.norm(temp,axis=1).reshape(-1,1) | |
| transformer = TfidfTransformer() | |
| tfidf_skl_smooth = transformer.fit_transform(counts) | |
| tfidf_skl_smooth = tfidf_skl_smooth.toarray() | |
| print(np.allclose(tfidf_smooth, tfidf_skl_smooth)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment