yanwu2014/swne: Similarity Weighted Nonnegative Embedding: A method for visualizing high dimensional datasets

Uses NMF to reduce high dimenensional dataset into NMF components, embeds NMF components in a 2D space for visualization, and then embeds the data points based on their NMF component magnitudes, using a similarity matrix to ensure that data points close in the high dimensional space are also close in the 2D visualization. Because the NMFs are embedded in the visualization as well, they can be interpreted via correlation with the features in the dataset.

Getting started

Package details

AuthorYan Wu
MaintainerYan Wu <[email protected]>
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
yanwu2014/swne documentation built on Jan. 11, 2019, 5:42 p.m.