PCA (Principal Component Analysis) - plot, analysis, and prediction

PCA.r

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

mydata = LifeCycleSavings

mypca = PCA(mydata, scale.unit = TRUE, graph = FALSE)
mypca$eig

fviz_pca_var(mypca, col.var = "cos2", gradient.cols = c("blue", "red"), repel = TRUE)
fviz_pca_var(mypca, col.var = "contrib", gradient.cols = c("blue", "red"), repel = TRUE)

corrplot(mypca$var$cos2, addCoef.col = "gray")
corrplot(mypca$var$contrib, is.corr = FALSE, addCoef.col = "gray")

fviz_pca_ind(mypca, repel = TRUE)
fviz_cos2(mypca, choice = "ind", axes = 1:2)
fviz_pca_ind(mypca, repel = TRUE, select.ind = list(cos2 = 0.8))

fviz_pca_biplot(
  mypca,
  col.var = "blue",
  col.ind = "cos2",
  gradient.cols = c("blue", "red"),
  repel = TRUE, 
  select.ind = list(cos2 = 0.8))

mypca = PCA(mydata, ind.sup = 23, quanti.sup = 1 ,scale.unit = TRUE, graph = FALSE)
mypca$ind.sup
mypca$quanti.sup

myplot = fviz_pca_biplot(
  mypca,
  col.var = "orange",
  col.ind = "cos2",
  gradient.cols = c("gray", "green"),
  repel = TRUE, 
  select.ind = list(cos2 = 0.8))
myplot = fviz_add(myplot, mypca$ind.sup$cos2, color = "blue", repel = TRUE)
myplot|