Random Forest on Small Numbers of Observations

Neil Saunders takes us through an interesting problem:

A recent question on Stack Overflow [r] asked why a random forest model was not working as expected. The questioner was working with data from an experiment in which yeast was grown under conditions where (a) the growth rate could be controlled and (b) one of 6 nutrients was limited. Their dataset consisted of 6 rows – one per nutrient – and several thousand columns, with values representing the activity (expression) of yeast genes. Could the expression values be used to predict the limiting nutrient?

The random forest was not working as expected: not one of the nutrients was correctly classified. I pointed out that with only one case for each outcome, this was to be expected – as the random forest algorithm samples a proportion of the rows, no correct predictions are likely in this case. As sometimes happens the question was promptly deleted, which was unfortunate as we could have further explored the problem.

Neil decided to explore the problem further regardless and came to some interesting conclusions.

Related Posts


Nina Zumel announces a new version of WVPlots on CRAN: WVPlots was originally a catch-all package of ggplot2 visualizations that we at Win-Vector tended to use repeatedly, and wanted to turn into “one-liners.” A consequence of this is that the older visualizations had our preferred color schemes hard-coded in. More recent additions to the package sometimes had palette […]

Read More

Icon Maps in R

Laura Ellis shows how you can build maps full of little icons: That was ok, but we should try to make the images more aesthetically pleasing using the magick package. We make each image transparent with the image_transparent() function. We can also make the resulting image a specific color with image_colorize(). I then saved the […]

Read More


June 2019
« May Jul »