主成分分析FactoMineR图数据

Question

我正在运行一个R脚本，使用FactorMineR生成主成分分析的曲线图。

我想输出生成的PCA图的坐标，但我很难找到正确的坐标。我找到了results1$ind$coord和results1$var$coord，但它们看起来都不像默认的绘图。

我找到了http://www.statistik.tuwien.ac.at/public/filz/students/seminar/ws1011/hoffmann_ausarbeitung.pdf和http://factominer.free.fr/classical-methods/principal-components-analysis.html，但都没有描述由PCA创建的变量的内容

library(FactoMineR)
data1 <- read.table(file=args[1], sep='\t', header=T, row.names=1)
result1 <- PCA(data1,ncp = 4, graph=TRUE) # graphs generated automatically
plot(result1)

Answer 1

我发现$ind$coord[,1]和$ind$coord[,2]是PCA对象中的前两个pca coord。下面是一个工作示例，其中包括您可能想要对PCA输出执行的其他一些操作……

# Plotting the output of FactoMineR's PCA using ggplot2
#
# load libraries
library(FactoMineR)
library(ggplot2)
library(scales)
library(grid)
library(plyr)
library(gridExtra)
#
# start with a clean slate
rm(list=ls(all=TRUE)) 
#
# load example data
data(decathlon)
#
# compute PCA
res.pca <- PCA(decathlon, quanti.sup = 11:12, quali.sup=13, graph = FALSE)
#
# extract some parts for plotting
PC1 <- res.pca$ind$coord[,1]
PC2 <- res.pca$ind$coord[,2]
labs <- rownames(res.pca$ind$coord)
PCs <- data.frame(cbind(PC1,PC2))
rownames(PCs) <- labs
#
# Just showing the individual samples...
ggplot(PCs, aes(PC1,PC2, label=rownames(PCs))) + 
  geom_text() 

​

​

# Now get supplementary categorical variables
cPC1 <- res.pca$quali.sup$coor[,1]
cPC2 <- res.pca$quali.sup$coor[,2]
clabs <- rownames(res.pca$quali.sup$coor)
cPCs <- data.frame(cbind(cPC1,cPC2))
rownames(cPCs) <- clabs
colnames(cPCs) <- colnames(PCs)
#
# Put samples and categorical variables (ie. grouping
# of samples) all together
p <- ggplot() + theme(aspect.ratio=1) + theme_bw(base_size = 20) 
# no data so there's nothing to plot...
# add on data 
p <- p + geom_text(data=PCs, aes(x=PC1,y=PC2,label=rownames(PCs)), size=4) 
p <- p + geom_text(data=cPCs, aes(x=cPC1,y=cPC2,label=rownames(cPCs)),size=10)
p # show plot with both layers

​

​

# Now extract the variables
#
vPC1 <- res.pca$var$coord[,1]
vPC2 <- res.pca$var$coord[,2]
vlabs <- rownames(res.pca$var$coord)
vPCs <- data.frame(cbind(vPC1,vPC2))
rownames(vPCs) <- vlabs
colnames(vPCs) <- colnames(PCs)
#
# and plot them
#
pv <- ggplot() + theme(aspect.ratio=1) + theme_bw(base_size = 20) 
# no data so there's nothing to plot
# put a faint circle there, as is customary
angle <- seq(-pi, pi, length = 50) 
df <- data.frame(x = sin(angle), y = cos(angle)) 
pv <- pv + geom_path(aes(x, y), data = df, colour="grey70") 
#
# add on arrows and variable labels
pv <- pv + geom_text(data=vPCs, aes(x=vPC1,y=vPC2,label=rownames(vPCs)), size=4) + xlab("PC1") + ylab("PC2")
pv <- pv + geom_segment(data=vPCs, aes(x = 0, y = 0, xend = vPC1*0.9, yend = vPC2*0.9), arrow = arrow(length = unit(1/2, 'picas')), color = "grey30")
pv # show plot 

​

​

# Now put them side by side in a single image
#
grid.arrange(p,pv,nrow=1)
# 
# Now they can be saved or exported...

​

​

Answer 2

在Ben的回答中添加了一些额外的东西。您将注意到，在Ben的响应中的第一个图表中，标签有些重叠。maptools包中的pointLabel()函数尝试查找标签的位置，而不会重叠。它并不完美，但如果需要，您可以调整new数据帧中的位置(见下文)以进行微调。(此外，当您加载地图工具时，您会得到一个关于gpclibPermit()的注释。如果您担心受限制的许可证，可以忽略它)。下面脚本的第一部分是Ben的脚本。

# load libraries
library(FactoMineR)
library(ggplot2)
library(scales)
library(grid)
library(plyr)
library(gridExtra)
#
# start with a clean slate
# rm(list=ls(all=TRUE)) 
#
# load example data
data(decathlon)
#
# compute PCA
res.pca <- PCA(decathlon, quanti.sup = 11:12, quali.sup=13, graph = FALSE)
#
# extract some parts for plotting
PC1 <- res.pca$ind$coord[,1]
PC2 <- res.pca$ind$coord[,2]
labs <- rownames(res.pca$ind$coord)
PCs <- data.frame(cbind(PC1,PC2))
rownames(PCs) <- labs 
#

# Now, the code to produce Ben's first chart but with less overlap of the labels.

library(maptools)

PCs$label=rownames(PCs)

# Base plot first for pointLabels() to get locations
plot(PCs$PC1, PCs$PC2, pch = 20, col = "red")
new = pointLabel(PCs$PC1, PCs$PC2, PCs$label, cex = .7)
new = as.data.frame(new)
new$label = PCs$label

# Then plot using ggplot2
(p = ggplot(data = PCs) + 
   geom_hline(yintercept = 0, linetype = 3, colour = "grey20") +
   geom_vline(xintercept = 0, linetype = 3, colour = "grey20") +
   geom_point(aes(PC1, PC2), shape = 20, col = "red") +
   theme_bw())

(p = p +  geom_text(data = new, aes(x, y, label = label), size = 3))

结果是：

​

​

Answer 3

另一种方法是使用CoreR中的biplot函数或心理包中的biplot.psych。这将把组件和数据放在同一张图上。

对于十项全能数据集，使用心理包中的主体和biplot：

 library(FactoMineR) #needed to get the example data
 library(psych)  #needed for principal 
 data(decathlon)  #the data set
 pc2 <- principal(decathlon[1:10],2) #just the first 10 columns
 biplot(pc2,labels = rownames(decathlon),cex=.5, main="Biplot of Decathlon results") 
 #this is a call to biplot.psych which in turn calls biplot.
 #adjust the cex parameter to change the type size of the labels.

这看起来像这样：

帐单