I’ve been working on additional scatter plot matrix plotting capabilities for the imCorrelations module.
Here is a little preview of a modified gpairs function from the YaleToolkit R package which is used to visualize the Iris data set. This scatterplot matrix allows for many interesting combinations of plots, which can be annotated with colors based on categorical variable(s).
The upper and lower matrix triangles can be modified with a variety of inputs:
- scatterplots: points, best-fit-line, loess, qqplot for linear model residuals, best-fit-line confidence interval, correlation statistics
- conditional plots: boxplot, stripplot, barcode
This can be easily modified to rapidly visualize and overview variable dependencies.