####################################################################################
#This is a file with executable R code for chapter 18 of Natalia Levshina's (2015) 
#How to Do Linguistics with R. Amsterdam/Philadelphia: John Benjamins. 
####################################################################################


###Section 18.2

##Main text

install.packages(c("psych", "FactoMineR"))

library(Rling);library(psych); library(FactoMineR)

data(reg_bnc)

str(reg_bnc)

rownames(reg_bnc)

round(cor(reg_bnc[, -1]), 2)

cortest.bartlett(reg_bnc[, -1])

reg.pca <- PCA(reg_bnc, quali.sup = 1, graph = FALSE)

head(reg.pca$eig)

barplot(reg.pca$eig[,2], names = 1:nrow(reg.pca$eig), xlab = "components", ylab = "Percentage of explained variance")

plot(reg.pca, choix = "var", cex = 0.8)

dimdesc(reg.pca)

plot(reg.pca, axes = c(2,3), choix = "var", cex = 0.8)

plot(reg.pca, cex = 0.8, col.ind = "grey", col.quali = "black")

plot(reg.pca, axes = c(2, 3), cex = 0.8, col.ind = "grey", col.quali = "black")

plotellipses(reg.pca, label = "quali")

reg.fa <- factanal(reg_bnc[, -1], factors = 3)

reg.fa

reg.fa <- factanal(reg_bnc[, -1], factors = 3, scores = "Bartlett")

plot(reg.fa$scores[, 2:3], type = "n")

text(reg.fa$scores[, 2:3], rownames(reg_bnc), cex = 0.7)