plotting pairwise scatter plot for high throughput data

Question

I have 13 variables that each of them has up to 1000000 elements. I want to draw a pairwise scatterplot for them but I couldn't do that because the size of my data was large. Any idea to do such thing? I have tried this:

pairs(data.mat)
graphics.off()

library(GGally)
ggpairs(data.mat, colour='Species', alpha=0.4)

and it couldn't do that and came out from R software.

Could you share, what you have tried? And what is the error you face? — rar, Jul 05 '16 at 09:25
Did you see http://stackoverflow.com/questions/10945707/speed-up-plot-function-for-large-dataset? — Qaswed, Jul 05 '16 at 09:28

score 1 · Answer 1 · answered Jul 05 '16 at 09:46

1) Use a subset of your dataset. You're not going to make meaningful conclusions from 1 million points that you cannot from many fewer.

2) Use pch=".", it speeds things up a surprising amount.

3) Consider plotting the joint distributions rather than the individual points.

plotting pairwise scatter plot for high throughput data

1 Answers1