Correlogram

Using the GGally package

The GGally package offers great options to build correlograms. The ggpairs() function build a classic correlogram with scatterplot, correlation coefficient and variable distribution. On top of that, it is possible to inject ggplot2 code, for instance to color categories.

Scatterplot matrix

Basic scatteprlot matrix with the ggpairs() function.

Pearson correlation

Visualize correlation with ggcorr().

Show groups

You can use the ggplot2 syntax to add aesthetics and ths map color to categories.

Using the corrgram package

The corrgram is another great alternative to build correlograms. You can choose what to display in the upper, lower and diagonal part of the figure: scatterplot, pie chart, text, ellipse and more.

Square and Pie

How to use the corrgram() function to represent correlation with square and pie charts.

Ellipse + Scatterplot

Visualize correlation with corrgram(). Use ellipses and scatterplots

Half matrix

You can display correlation in half the matrix only.

Other methods

Lesser known ways to build correlogram with R, like the ellipse package, the plot() function and the car package.

Ellipse package

The ellipse package allows to visualize a correlation matrix with ellipses.

plot() function

The plot function is straightforward way to build a basic scatterplot matrix.

car package

The car package probides a scatterplotMatrix function to build correlogram.