Я использую NLTK для кластеризации kmeans в моем текстовом файле, в котором каждая строка рассматривается как документ. Например, мой текстовый файл выглядит примерно так:
belong finger death punch <br>
hasty <br>
mike hasty walls jericho <br>
jägermeister rules <br>
rules bands follow performing jägermeister stage <br>
approach
Теперь я пытаюсь запустить демонстрационный код:
import sys
import numpy
from nltk.cluster import KMeansClusterer, GAAClusterer, euclidean_distance
import nltk.corpus
from nltk import decorators
import nltk.stem
stemmer_func = nltk.stem.EnglishStemmer().stem
stopwords = set(nltk.corpus.stopwords.words('english'))
@decorators.memoize
def normalize_word(word):
return stemmer_func(word.lower())
def get_words(titles):
words = set()
for title in job_titles:
for word in title.split():
words.add(normalize_word(word))
return list(words)
@decorators.memoize
def vectorspaced(title):
title_components = [normalize_word(word) for word in title.split()]
return numpy.array([
word in title_components and not word in stopwords
for word in words], numpy.short)
if __name__ == '__main__':
filename = 'example.txt'
if len(sys.argv) == 2:
filename = sys.argv[1]
with open(filename) as title_file:
job_titles = [line.strip() for line in title_file.readlines()]
words = get_words(job_titles)
# cluster = KMeansClusterer(5, euclidean_distance)
cluster = GAAClusterer(5)
cluster.cluster([vectorspaced(title) for title in job_titles if title])
# NOTE: This is inefficient, cluster.classify should really just be
# called when you are classifying previously unseen examples!
classified_examples = [
cluster.classify(vectorspaced(title)) for title in job_titles
]
for cluster_id, title in sorted(zip(classified_examples, job_titles)):
print cluster_id, title
(который также можно найти здесь)
Я получаю следующую ошибку:
Traceback (most recent call last):
File "cluster_example.py", line 40, in
words = get_words(job_titles)
File "cluster_example.py", line 20, in get_words
words.add(normalize_word(word))
File "", line 1, in
File "/usr/local/lib/python2.7/dist-packages/nltk/decorators.py", line 183, in memoize
result = func(*args)
File "cluster_example.py", line 14, in normalize_word
return stemmer_func(word.lower())
File "/usr/local/lib/python2.7/dist-packages/nltk/stem/snowball.py", line 694, in stem
word = (word.replace(u"\u2019", u"\x27")
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 13: ordinal not in range(128)
Что здесь происходит?