単にあなたのfeaturizerを変更
from nltk import ngrams
def create_ngram_features(words, n=2):
ngram_vocab = ngrams(words, n)
my_dict = dict([(ng, True) for ng in ngram_vocab])
return my_dict
ところで、あなたのコードは、あなたのストップワードリストのセットを使用して行うと、一度だけ、それを初期化するために、あなたのfeaturizerを変更した場合、多く速くなります。
stoplist = set(stopwords.words("english"))
def create_word_features(words):
useful_words = [word for word in words if word not in stoplist]
my_dict = dict([(word, True) for word in useful_words])
return my_dict
誰かが本当にそれは「技術的に」独特のリスト(すなわち、セット)ですので、セットタイプにストップワードリストを変換するために、NLTKの人々に伝える必要があります。
import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk import ngrams
def create_ngram_features(words, n=2):
ngram_vocab = ngrams(words, n)
my_dict = dict([(ng, True) for ng in ngram_vocab])
return my_dict
for n in [1,2,3,4,5]:
pos_data = []
for fileid in movie_reviews.fileids('pos'):
words = movie_reviews.words(fileid)
pos_data.append((create_ngram_features(words, n), "positive"))
neg_data = []
for fileid in movie_reviews.fileids('neg'):
words = movie_reviews.words(fileid)
neg_data.append((create_ngram_features(words, n), "negative"))
train_set = pos_data[:800] + neg_data[:800]
test_set = pos_data[800:] + neg_data[800:]
classifier = NaiveBayesClassifier.train(train_set)
accuracy = nltk.classify.util.accuracy(classifier, test_set)
print(str(n)+'-gram accuracy:', accuracy)
ベンチマークの楽し[出力]の場合
>>> from nltk.corpus import stopwords
>>> type(stopwords.words('english'))
<class 'list'>
>>> type(set(stopwords.words('english')))
<class 'set'>
:
1-gram accuracy: 0.735
2-gram accuracy: 0.7625
3-gram accuracy: 0.8275
4-gram accuracy: 0.8125
5-gram accuracy: 0.74
あなたの元のコードは、0.725の精度を返します。 ngrams
import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk import everygrams
def create_ngram_features(words, n=2):
ngram_vocab = everygrams(words, 1, n)
my_dict = dict([(ng, True) for ng in ngram_vocab])
return my_dict
for n in range(1,6):
pos_data = []
for fileid in movie_reviews.fileids('pos'):
words = movie_reviews.words(fileid)
pos_data.append((create_ngram_features(words, n), "positive"))
neg_data = []
for fileid in movie_reviews.fileids('neg'):
words = movie_reviews.words(fileid)
neg_data.append((create_ngram_features(words, n), "negative"))
train_set = pos_data[:800] + neg_data[:800]
test_set = pos_data[800:] + neg_data[800:]
classifier = NaiveBayesClassifier.train(train_set)
accuracy = nltk.classify.util.accuracy(classifier, test_set)
print('1-gram to', str(n)+'-gram accuracy:', accuracy)
の
使っより受注[外]:
1-gram to 1-gram accuracy: 0.735
1-gram to 2-gram accuracy: 0.7625
1-gram to 3-gram accuracy: 0.7875
1-gram to 4-gram accuracy: 0.8
1-gram to 5-gram accuracy: 0.82
投稿を見ました:[ngrams単純ベイズ分類器で](https://stackoverflow.com/質問/ 14003291/n-gram-with-naive-bayes-classifier)? – Sax
または:[Naive Bayesクラシファイアエラーのnグラム](https://stackoverflow.com/questions/19209895/n-grams-with-naive-bayes-classifier-error) – Sax