【机器学习】KNN分类

分类的概念

《数据挖掘:概念与技术(中文第三版)》第8

数据挖掘:概念与技术(中文第三版)PDF

http://vdisk.weibo.com/s/zDFQH9cZskXOL

课件

http://wenku.baidu.com/view/50ff9078aaea998fcc220e78.html

 

kNN classifiers

http://www.fon.hum.uva.nl/praat/manual/kNN_classifiers.html

 

--------分类的指标--------

我们一般使用准确率、召回率、F1。

分类指标准确率(Precision)和正确率(Accuracy)的区别

http://blog.sciencenet.cn/blog-460603-785098.html

信息检索(IR)的评价指标介绍 - 准确率、召回率、F1、mAP、ROC、AUC

http://blog.csdn.net/marising/article/details/6543943

Accuracy and precision(wiki)

http://en.wikipedia.org/wiki/Accuracy_and_precision

Classification Accuracy is Not Enough: More Performance Measures You Can Use

http://machinelearningmastery.com/classification-accuracy-is-not-enough-more-performance-measures-you-can-use/

 

Precision is the number of True Positives divided by the number of True Positives and False Positives.

Precision=TP/(TP+FP)

Recall is the number of True Positives divided by the number of True Positives and the number of False Negatives.

Recall=TP/(TP+FN)

The F1 Score is the 2*((precision*recall)/(precision+recall)).

 

一种基于EEPS的中文文本自动分类算法

http://www.doc88.com/p-119785355465.html

KNN策略

分类系统的评价

 

多分类问题中每一类的Precision-Recall Curve曲线以及ROC的Matlab画法

http://www.zhizhihu.com/html/y2010/2447.html

计算Precision、Recall、F1的Matlab代码,山东大学信息检索实验室

https://github.com/lipiji/PG_Curve

 

混淆矩阵(Confusion Matrix)

posted @ 2014-10-21 09:41  kaoyanmp3  阅读(322)  评论(0编辑  收藏  举报