ggplot2画点和连线展示主成分分析的结果简单小例子

df<-read.csv("kaggle/Seed_Data.csv")

df.pca<-prcomp(df[,1:7],scale. = T)
pca.results<-data.frame(df.pca$x)[,1:2]
pca.results$target<-paste0('cultivar',df$target)

centroid <- aggregate(cbind(PC1,PC2) ~ target,
                     data = pca.results,
                     FUN = mean)

pca.results1<-dplyr::left_join(pca.results, centroid, by = "target", 
                       suffix = c("",".cen"))

library(RColorBrewer)
show_col(brewer.pal(3, "Set1"))
cols = brewer.pal(3, "Set1")
cols

library(ggplot2)
ggtheme = theme(legend.title = element_blank(),
                axis.text.y = element_text(colour="black", size=14),
                axis.text.x = element_text(colour="black", size=14),
                axis.title = element_text(colour="black", size=14),
                legend.position = "right",
                legend.text = element_text(size=15),
                legend.key = element_rect(fill = NA),
                legend.key.size = unit(0.7, "cm"),
                legend.box.spacing = unit(0, "cm"),
                panel.border = element_rect(colour="black", fill=NA, size=1),
                panel.background = element_blank(),
                # title centered
                plot.title = element_text(hjust=0.5, size=25) 
)

ggplot(pca.results1,aes(x=PC1,y=PC2))+
  geom_vline(xintercept = 0,lty="dashed")+
  geom_hline(yintercept = 0,lty="dashed")+
  geom_point(aes(color=target))+
  geom_segment(aes(xend=PC1.cen,yend=PC2.cen,color=target),
               show.legend = F)+
  ggtheme+
  scale_colour_manual(values = cols)+
  geom_label(data = centroid, 
             aes(label = target, fill = target), size = 5, 
             show.legend = FALSE,
             color="white")+
  scale_fill_manual(values = cols)+
  theme(legend.position = "top")