n-TARP: Binary clustering of big/small data

Project member? Login to members area.


n-TARP is a method to cluster data into two clusters (binary clustering). It works by projecting the data on a random one-dimensional subspace and thresholding the projected the data. This process is repeated n times, and the best clustering is selected. Thus the name n-TARP= Thresholding after Random Projection. This project is develop and share code implementing the n-TARP clustering method.



The Purdue University Research Repository (PURR) is a university core research facility provided by the Purdue University Libraries, the Office of the Executive Vice President for Research and Partnerships, and Information Technology at Purdue (ITaP).