4.7 Computer Tasks

1. Look at this computational trick https://www.robots.ox.ac.uk/~albanie/notes/Euclidean_distance_trick.pdf for computing the distance matrix.

2. Do UK map?

mds <- cmdscale(distances)
plot(mds[,2], mds[,1])
text(mds[,2], mds[,1], labels=city$Name, pos=3)

cmdscale

3. http://www.sthda.com/english/articles/31-principal-component-methods-in-r-practical-guide/122-multidimensional-scaling-essentials-algorithms-and-r-code/ Visualizing a correlation matrix using Multidimensional Scaling

MDS can be also used to reveal a hidden pattern in a correlation matrix.

Correlation actually measures similarity, but it is easy to transform it to a measure of dissimilarity. Distance between objects can be calculated as 1 - res.cor.

res.cor <- cor(mtcars, method = "spearman")
mds.cor <-cmdscale((1 - res.cor) ) 
colnames(mds.cor) <- c("Dim.1", "Dim.2")

library(ggpubr)
ggscatter(mds.cor, x = "Dim.1", y = "Dim.2", 
          label = rownames(swiss),
          size = 1,
          repel = TRUE)