Bayesian classification algorithm for the ten algorithms of data mining

1. Introduction

Bayesian classification algorithm is a classification method of statistics, it is a kind of algorithm that uses probability statistic knowledge to classify. In many cases, naive Bayesian (na?ve BAYES,NB) classification algorithm can be compared with decision tree and neural Network classification algorithm, the algorithm can be used in large-scale database, and the method is simple, high classification accuracy rate, fast.
Since Bayesian theorem assumes that the effect of a property value on a given class is independent of the value of other properties, this assumption is often not true in practice, so its classification accuracy rate may decrease. For this reason, many Bayesian classification algorithms, such as the tan (tree augmented Bayes Network) algorithm, are derived to reduce the independence hypothesis.

2, an example to describe the naive Bayesian classification algorithm:

Title: The following examples are divided into 3 categories: {Short,tall,medium},height is a continuous attribute, assuming that the attribute obeys a Gaussian distribution, and the dataset is shown in table 4-5, use the Bayesian classification method to classify example t= (adam,m,1.95m).

Solution:

Data samples are described with attributes Name,gender and height. The category Label property output has {Short,tall,medium} three different values.

Set: C1 class corresponds to output= "short", C2 class corresponds to output= "Tall", C3 class corresponds to output= "Medium"

A known sample of the desired classification is: t= (adam,m,1.95m)

3. Word Document Download

(1) http://download.csdn.net/detail/u012339743/8829507

Original Joe Chael

Original address: http://blog.csdn.net/qingdujun/article/details/46598187

Bayesian classification algorithm for the ten algorithms of data mining