小编Yv *_*eng的帖子

import nltk
from nltk.corpus import movie_reviews
from nltk.tokenize import word_tokenize

documents = [(list(movie_reviews.words(fileid)), category)
             for category in movie_reviews.categories()
             for fileid in movie_reviews.fileids(category)]


all_words = []

for w in movie_reviews.words():
    all_words.append(w.lower())

all_words = nltk.FreqDist(all_words)

word_features = list(all_words.keys())[:3000]

def find_features(document):
    words = set(document)
    features = {}
    for w in word_features:
        features[w] = (w in words)

    return features

featuresets = [(find_features(rev), category) for (rev, category) in documents]

training_set = featuresets[500:1500]
testing_set = featuresets[:1500]

classifier = nltk.DecisionTreeClassifier.train(training_set)

print "Classifier accuracy percent:",(nltk.classify.accuracy(classifier, testing_set))*100 , "%" …