How to format PCA plot

[Ellenz]

Hi all,
I am working on PCA analysis and am wondering how to format the figure? For example, I use the code below to plot the figure, as shown below. How to edit the x and y axis titles? For example, I want x-axis to be PC1 instead of Dim1 (41.%), how to realize this? Second, how to remove the background grids and use a rectangular box? Thanks for your help.

library("FactoMineR")
library("factoextra")
library("corrplot")
library("corrplot")

data(decathlon2)
# It contains 27 individuals (athletes) described by 13 variables.

decathlon2.active <- decathlon2[1:23, 1:10]
head(decathlon2.active[, 1:6], 4)

res.pca <- PCA(decathlon2.active, graph = FALSE)
print(res.pca)

fviz_eig(res.pca, addlabels = TRUE, ylim = c(0, 50))

# plot the variables
fviz_pca_var(res.pca, col.var = "black")

[Ellenz]

I have another question regarding to this problem.
If I use the code below to create a PCA plot of PC3~PC4, and get the figure. How to put the two figures in one panel in R directly? Thanks again.

fviz_pca_var(res.pca, col.var = "black",axes=c(3,4))

[Asmith]

Since it is a ggplot you can add features such as axis labels and theme elements. Try this code

plot1 <- fviz_pca_var(res.pca, col.var = "black")
plot1 + xlab("PC1") + ylab("PC2") +
   theme_bw() + theme(panel.grid.major = element_line(linetype = "blank"))
 

[Ellenz]

Thanks, it works. How to plot the loadings of each variable in PC1, PC2, etc? Thanks.

[Asmith]

there is a biplot function and others - see the examples at fviz_pca: Quick Principal Component Analysis data visualization - R software and data mining - Easy Guides - Wiki - STHDA