黄聪：Python+NLTK自然语言处理学习（三）：计算机自动学习机制

import nltk
from nltk.book import *

def gender_features(word):
return {'last_letter':word[-1]}

from nltk.corpus import names
import random
names=([(name,'male') for name in names.words('male.txt')] + [(name,'female') for name in names.words('female.txt')])
random.shuffle(names)

f = [(gender_features(n),g) for (n,g) in names]
trainset,testset = f[500:],f[:500]
c = nltk.NaiveBayesClassifier.train(trainset)

c.classify(gender_features('Neo'))
c.classify(gender_features('Trinity'))