用Python实例分类多项式朴素贝叶斯分类器

Implementing Bag-of-Words Naive-Bayes classifier in NLTK

import numpy as np
from nltk.probability import FreqDist
from nltk.classify import SklearnClassifier
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_selection import SelectKBest,chi2
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline

pipeline = Pipeline([('tfidf',TfidfTransformer()),('chi2',SelectKBest(chi2,k=1000)),('nb',MultinomialNB())])
classif = SklearnClassifier(pipeline)

from nltk.corpus import movie_reviews
pos = [FreqDist(movie_reviews.words(i)) for i in movie_reviews.fileids('pos')]
neg = [FreqDist(movie_reviews.words(i)) for i in movie_reviews.fileids('neg')]
add_label = lambda lst,lab: [(x,lab) for x in lst]
#Original code from thread:
#classif.train(add_label(pos[:100],'pos') + add_label(neg[:100],'neg'))
classif.train(add_label(pos,'pos') + add_label(neg,'neg'))#Made changes here

#Original code from thread:    
#l_pos = np.array(classif.batch_classify(pos[100:]))
#l_neg = np.array(classif.batch_classify(neg[100:]))
l_pos = np.array(classif.batch_classify(pos))#Made changes here
l_neg = np.array(classif.batch_classify(neg))#Made changes here
print "Confusion matrix:n%dt%dn%dt%d" % (
          (l_pos == 'pos').sum(),(l_pos == 'neg').sum(),(l_neg == 'pos').sum(),(l_neg == 'neg').sum())

运行此示例后,我收到了警告.

C:Python27libsite-packagesscikit_learn-0.13.1-py2.7-win32.eggsklearnfeature_selectionunivariate_selection.py:327: 
UserWarning: Duplicate scores. Result may depend on feature ordering.There are probably duplicate features,or you used a classification score for a regression task.
warn("Duplicate scores. Result may depend on feature ordering."

Confusion matrix:
876 124
63  937

所以,我的问题是……

>有谁能告诉我这个错误信息是什么意思？
>我对原始代码进行了一些更改,但为什么混淆矩阵的结果比原始代码中的结果要高得多呢？
>如何测试此分类器的准确性？