Last active
September 5, 2016 19:48
-
-
Save micvbang/806fb2fd93a21aaa67d90046dfdc7c3b to your computer and use it in GitHub Desktop.
This file contains hidden or 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 python2.7 | |
| import os | |
| import codecs | |
| from sklearn.cluster import KMeans | |
| from sklearn.feature_extraction.text import CountVectorizer | |
| from nltk.stem.snowball import DanishStemmer | |
| here = lambda *x: os.path.join(os.path.dirname(os.path.realpath(__file__)), *x) | |
| def readlines(path, removenewline=True, codec='utf8'): | |
| return (l.strip('\n') for l in codecs.open(path, 'r', 'utf8')) | |
| def vectorize(data): | |
| vectorizer = CountVectorizer(ngram_range=(2, 3), max_features=100) | |
| return vectorizer.fit_transform(data) | |
| raw = list(readlines(here('unclassified.txt'))) | |
| data = vectorize(raw) | |
| kmeans = KMeans() | |
| for l, c in zip(raw, kmeans.fit_predict(data)): | |
| print u"{}, {}".format(c, l).encode('utf8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment