This chapter will cover the following topics:本章将涵盖以下主题：
1、 Doing basic classifications with Decision Trees 用决策树做基本分类
2、 Tuning a Decision Tree model 调试决策树模型
3、 Using many Decisions Trees – random forests 使用多个决策树-随机森林
4、 Tuning a random forest model 调试随机森林模型
5、 Classifying data with support vector machines 使用支持向量机分类数据
6、 Generalizing with multiclass classification 概述多分类问题
7、 Using LDA for classification 使用LDA进行分类
8、 Working with QDA – a nonlinear LDA 使用QDA-一个非线性LDA
9、 Using Stochastic Gradient Descent for classification 使用随机梯度下降来分类
10、 Classifying documents with Naïve Bayes 使用朴素贝叶斯分类文档
11、 Label propagation with semi-supervised learning 标签传播算法-半监督学习
Introduction介绍
Classification can be very important in a lot of contexts. For example, if we want to automate some decision-making process, we can utilize classification. In cases where we need to investigate a fraud, there are so many transactions that it is impractical for a person to check all of them. Therefore, we can automate such decisions with classification.
分类问题在很多情景中都非常重要，例如，我们想要自动化一些决策过程，我们能利用分类模型。如果我们要侦查欺诈，有太多的交易以至于一个人没办法完全的检测他们，所以，我们就能使用分类算法来自动完成决策。
