我正在尝试为线性判别分析(LDA)创建一个双标图。我正在使用从此处https://stats.stackexchange.com/questions/82497/can-the-scaling-values-in-a-linear-discriminant-analysis-lda-be-used-to-plot-e
获取的修改版代码然而,我有80个变量,使得biplot非常难以阅读。由于它们的箭头长度非常长而其余的标签在中间被碾碎,因此这会因为高度贡献的变量而恶化。
所以我想要实现的是双标图,其中所有可变箭头的长度相等,并且它们的相对贡献(标度)通过分级颜色来区分。
到目前为止,我已经设法获得了渐变的颜色,但我找不到使箭头长度相同的方法。据我所知,geom_text
和geom_segment
使用LD1和LD2值来确定箭头的长度和方向。如何覆盖长度?
CODE:
library(ggplot2)
library(grid)
library(MASS)
data(iris)
iris.lda <- lda(as.factor(Species)~.,
data=iris)
#Project data on linear discriminants
iris.lda.values <- predict(iris.lda, iris[,-5])
#Extract scaling for each predictor and
data.lda <- data.frame(varnames=rownames(coef(iris.lda)), coef(iris.lda))
#coef(iris.lda) is equivalent to iris.lda$scaling
data.lda$length <- with(data.lda, sqrt(LD1^2+LD2^2))
#Plot the results
p <- qplot(data=data.frame(iris.lda.values$x),
main="LDA",
x=LD1,
y=LD2,
colour=iris$Species)+stat_ellipse(geom="polygon", alpha=.3, aes(fill=iris$Species))
p <- p + geom_hline(aes(yintercept=0), size=.2) + geom_vline(aes(xintercept=0), size=.2)
p <- p + theme(legend.position="right")
p <- p + geom_text(data=data.lda,
aes(x=LD1, y=LD2,
label=varnames,
shape=NULL, linetype=NULL,
alpha=length, position="identity"),
size = 4, vjust=.5,
hjust=0, color="red")
p <- p + geom_segment(data=data.lda,
aes(x=0, y=0,
xend=LD1, yend=LD2,
shape=NULL, linetype=NULL,
alpha=length),
arrow=arrow(length=unit(0.1,"mm")),
color="red")
p <- p + coord_flip()
print(p)
答案 0 :(得分:1)
这样的事情怎么样?我们必须做一些三角函数来使长度相等。请注意,相等性在绘图坐标中,因此如果您希望实际显示相同的大小,则需要添加coord_equal
。
(我清理了你的绘图代码,因为很多都是一团糟。)
rad <- 3 # This sets the length of your lines.
data.lda$length <- with(data.lda, sqrt(LD1^2+LD2^2))
data.lda$angle <- atan2(data.lda$LD1, data.lda$LD2)
data.lda$x_start <- data.lda$y_start <- 0
data.lda$x_end <- cos(data.lda$angle) * rad
data.lda$y_end <- sin(data.lda$angle) * rad
#Plot the results
ggplot(cbind(iris, iris.lda.values$x),
aes(y = LD1, x = LD2, colour = Species)) +
stat_ellipse(aes(fill = Species), geom = "polygon", alpha = .3) +
geom_point() +
geom_hline(yintercept = 0, size = .2) +
geom_vline(xintercept = 0, size = .2) +
geom_text(aes(y = y_end, x = x_end, label = varnames, alpha = length),
data.lda, size = 4, vjust = .5, hjust = 0, colour = "red") +
geom_spoke(aes(x_start, y_start, angle = angle, alpha = length), data.lda,
color = "red", radius = rad, size = 1) +
ggtitle("LDA") +
theme(legend.position = "right")
答案 1 :(得分:1)
我认为我有一个更简单的代码来实现双标图。我希望下面的代码有所帮助。我使用IRIS数据集进行分析
library(readr)
IR <- read_csv("D:/Keerthesh/R Folder/DataSet/Iris.csv")
# --- data partition -- #
set.seed(555)
IRSam <- sample.int(n = nrow(IR), size = floor(.60*nrow(IR)), replace = FALSE, prob = NULL)
IRTrain <- IR[IRSam,]
IRTest <- IR[-IRSam,]
library(MASS)
IR.lda <- lda(Species~. -Id, data=IRTrain)
print(IR.lda)
为了绘制biplot,您需要从github安装ggord包。
library(devtools)
install_github('fawda123/ggord') --- Used to install ggord from github we need to run devtools to achieve this.
library(ggord)
ggord(IR.lda, IRTrain$Species, ylim=c(-5,5), xlim=c(-10,10))