[博文精选]Computing and visualizing PCA in R

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Following my introduction to PCA, I will demonstrate how to apply and visualize PCA in R. There are many packages and functions that can apply PCA in R. In this post I will use the function prcomp from the stats package. I will also show how to visualize PCA in R using Base R graphics. However, my favorite visualization function for PCA is ggbiplot, which is implemented byVince Q. Vu and available on github. Please, let me know if you have better ways to visualize PCA in R.

本帖隐藏的内容

Computing and Visualizing PCA in R.pdf (444.05 KB)

2016-1-24 02:11:57 上传

1. # Load data
   
2. data(iris)
   
3. head(iris, 3)

复制代码

1. # log transform
   
2. log.ir <- log(iris[, 1:4])
   
3. ir.species <- iris[, 5]
   
4. 
   
5. # apply PCA - scale. = TRUE is highly
   
6. # advisable, but default is FALSE.
   
7. ir.pca <- prcomp(log.ir,
   
8.                  center = TRUE,
   
9.                  scale. = TRUE)

复制代码

1. # print method
   
2. print(ir.pca)

复制代码

1. # summary method
   
2. summary(ir.pca)

复制代码

1. # Predict PCs
   
2. predict(ir.pca,
   
3.         newdata=tail(log.ir, 2))

复制代码

1. library(devtools)
   
2. install_github("ggbiplot", "vqv")
   
3. 
   
4. library(ggbiplot)
   
5. g <- ggbiplot(ir.pca, obs.scale = 1, var.scale = 1,
   
6.               groups = ir.species, ellipse = TRUE,
   
7.               circle = TRUE)
   
8. g <- g + scale_color_discrete(name = '')
   
9. g <- g + theme(legend.direction = 'horizontal',
   
10.                legend.position = 'top')
    
11. print(g)

复制代码

1. require(caret)
   
2. trans = preProcess(iris[,1:4],
   
3.                    method=c("BoxCox", "center",
   
4.                             "scale", "pca"))
   
5. PC = predict(trans, iris[,1:4])
   
6. # Retained PCs
   
7. head(PC, 3)

复制代码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏3 回帖

关键词：Visualizing computing Comput Visual comp available function package better

Computing and visualizing PCA in R

kankan

thanks for sharing

thanks for your sharing.