gender_id.py

import random
import nltk
from nltk.corpus import names
from nltk.corpus import movie_reviews

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

def gender_features2(name):
    features = {}
    features["first_letter"] = name[0].lower()
    features["last_letter"] = name[-1].lower()
    for letter in 'abcdefghijklmnopqrstuvwxyz':
        features["count({})".format(letter)] = name.lower().count(letter)
        features["has({})".format(letter)] = (letter in name.lower())
    return features

#cargar data y poner en el formato ('texto','tag')
labeled_names = ([(name, 'male') for name in names.words('male.txt')] + [(name, 'female') for name in names.words('female.txt')])
random.shuffle(labeled_names)

#transformar a formato ([caracteristicas],'tag')
featuresets = [(gender_features(n), gender) for (n, gender) in labeled_names]
train_set, test_set = featuresets[500:], featuresets[:500]
classifier = nltk.NaiveBayesClassifier.train(train_set)

print(nltk.classify.accuracy(classifier, test_set))