问交叉验证误差

EN

from nltk.corpus import movie_reviews
import random
import nltk
from sklearn import cross_validation
from nltk.corpus import stopwords
import string
from nltk.classify import apply_features

def document_features(document):
    document_words = set(document)
    features = {}
    for word in unigrams:
        features['contains({})'.format(word)] = (word in document_words)
    return features

documents = [(list(movie_reviews.words(fileid)), category)
             for category in movie_reviews.categories()
             for fileid in movie_reviews.fileids(category)]
random.shuffle(documents)
stop = stopwords.words('english')
all_words = nltk.FreqDist(w.lower() for w in movie_reviews.words() if w.lower() not in stop and w.lower() not in string.punctuation)
unigrams = list(all_words)[:200]
featuresets = [(document_features(d), c) for (d,c) in documents]

training_set = nltk.classify.apply_features(featuresets, documents)
cv = cross_validation.KFold(len(training_set), n_folds=10, shuffle=True, random_state=None)

for traincv, testcv in cv:
    classifier = nltk.NaiveBayesClassifier.train(training_set[traincv[0]:traincv[len(traincv)-1]])
    result = nltk.classify.util.accuracy(classifier, training_set[testcv[0]:testcv[len(testcv)-1]])
    print 'Accuracy:', result

classifier = nltk.NaiveBayesClassifier.train(training_set[traincv[0]:traincv[len(traincv)-1]])