nickseedorff/totalvis: totalvis: A Principal Components Approach to Visualizing Total Effects in Black Box Models
A principal components based extension to partial depedence plots (PDPS) that visually summarizes the total effects of groups of predictors in black-box models. The method uses PCA to explore the structure of the training data, but does not intend for PCA to be a part of the model under investigation.
Getting started
Browse package contents
Package details |
|
|---|---|
| Author | Nick Seedorff |
| Maintainer | Nick Seedorff <nickseedorff@gmail.com> |
| License | GPL-3 |
| Version | 0.0.0.9000 |
| Package repository | View on GitHub |
| Installation |
Install the latest version of this package by entering the following in R:
|
