基于属性加权的朴素贝叶斯分类算法

朴素贝叶斯分类是一种简单而高效的方法，但是它的属性独立性假设，影响了它的分类性能。通过放松朴素贝叶斯假设可以增强其分类效果，但通常会导致计算代价大幅提高。提出了属性加权朴素贝叶斯算法，该算法通过属性加权来提高朴素贝叶斯分类器性能，加权参数直接从训练数据中学习得到。权值可以看作是计算某个类的后验概率时，某属性取值对该类别的影响程度。实验结果表明，该算法可行而且有效。

Attribute weighted Naïve Bayes classification

Naïve Bayes classifier is a simple and effective classification method，but its attribute independence assumption makes it unable to express the dependence among attributes in the real world，and affects its classification performance.Many enhancements to the basic algorithm have been proposed to help mitigate its primary weakness.All of them improve the performance of Naïve Bayes at the expense（to a greater or lesser degree） of execution time and/or simplicity of the final model.In this paper a simple method for setting attribute weights for using with Naïve Bayes is presented.Experimental results show that Naïve Bayes with attribute weights rarely degrades the quality of the model compared to standard Naïve Bayes，and in many cases，improves it dramatically.