Created
April 4, 2015 12:14
-
-
Save otobrglez/c39bb6b70007b83fed84 to your computer and use it in GitHub Desktop.
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 | |
# http://bogdan-ivanov.com/recipe-text-clustering-using-nltk-and-scikit-learn/ | |
#!/usr/bin/env python | |
import nltk | |
import string | |
import collections | |
from data.feeds import feed | |
from math import sqrt, ceil, floor | |
import string | |
import collections | |
from nltk import word_tokenize | |
from nltk.stem import PorterStemmer | |
from nltk.corpus import stopwords | |
from sklearn.cluster import KMeans | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
from pprint import pprint | |
from datetime import datetime | |
def process_text(text, stem=True): | |
""" Tokenize text and stem words removing punctuation """ | |
text = text.translate(string.punctuation) | |
tokens = word_tokenize(text) | |
if stem: | |
stemmer = PorterStemmer() | |
tokens = [stemmer.stem(t) for t in tokens] | |
return tokens | |
def extended_stopwords(): | |
words = stopwords.words('english') | |
words = words + ['umek','dj', 'mix', 'remix', 'promo', 'episode', 'club', 'live'] | |
return words | |
def cluster_texts(texts, clusters=3): | |
""" Transform texts to Tf-Idf coordinates and cluster texts using K-Means """ | |
vectorizer = TfidfVectorizer(tokenizer=process_text, | |
stop_words=extended_stopwords(), | |
max_df=0.7, | |
min_df=0.1, | |
#use_idf=True, | |
lowercase=True) | |
tfidf_model = vectorizer.fit_transform(texts) | |
km_model = KMeans(n_clusters=clusters) | |
km_model.fit(tfidf_model) | |
clustering = collections.defaultdict(list) | |
for idx, label in enumerate(km_model.labels_): | |
clustering[label].append(idx) | |
return clustering | |
if __name__ == "__main__": | |
from data.feeds import feed | |
items = [x for x in feed("./data/umek_music_feed.csv")] | |
item_names = ["%s %s %s" % (datetime.strptime(x['created_at'].split(".")[0],"%Y-%m-%d %H:%M:%S").\ | |
strftime("%Y-%m"),\ | |
x['name'],\ | |
"") for x in items] | |
# print(item_names[0]) | |
# exit(0) | |
k = int(ceil(sqrt(len(item_names)/2))) | |
k = 26 | |
#k = 60 | |
clusters = cluster_texts(item_names, k) | |
i = len(clusters) | |
# Pump-up 'K' for k-means algorithm | |
optimize_k = False | |
if optimize_k: | |
ks, cs = [], [] | |
while(True): | |
print "K=%d, Clusters=%d" % (k, i) | |
k += 2 | |
clusters = cluster_texts(item_names, k) | |
i = len(clusters) | |
ks.append(k) | |
cs.append(i) | |
if len(ks) > 2: | |
if [cs[-2], cs[-1]] == [i, i]: | |
break | |
clusters_dict = dict(clusters) | |
a = [[items[i] for i in clusters_dict[item]] for item in clusters_dict] | |
for cluster in a: | |
for item in sorted(cluster, key=lambda p: datetime.strptime(p['created_at'].split(".")[0],"%Y-%m-%d %H:%M:%S"), reverse=True): | |
print "%s %s %s" % (item['channel'], datetime.strptime(item['created_at'].split(".")[0],"%Y-%m-%d %H:%M:%S").strftime("%Y-%m-%d"), item['name']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment