DimReduce: Dimensionality Reduction of Very Large Datasets

Discussion topics for individual codes
Post Reply
User avatar
owlice
Guardian of the Codes
Posts: 1135
Joined: Wed Aug 04, 2004 4:18 pm
Location: Washington, DC

DimReduce: Nonlinear Dimensionality Reduction of Very Large Datasets with Locally Linear Embedding (LLE) and its Variant

Post by owlice » Sat Oct 16, 2010 2:37 pm

[c]DimReduce: Nonlinear Dimensionality Reduction of Very Large Datasets with Locally Linear Embedding (LLE) and its Variants[/c][/b]
Abstract: DimReduce is a C++ package for performing nonlinear dimensionality reduction of very large datasets with Locally Linear Embedding (LLE) and its variants. DimReduce is built for speed, using the optimized linear algebra packages BLAS, LAPACK, and ARPACK. Because of the need for storing very large matrices (1000 by 10000, for our SDSS LLE work), DimReduce is designed to use binary FITS files as inputs and outputs. This means that using the code is a bit more cumbersome. For smaller-scale LLE, where speed of computation is not as much of an issue, the Modular Data Processing toolkit may be a better choice. It is a python toolkit with some LLE functionality, which VanderPlas contributed.

This code has been rewritten and included in scikit-learn and an improved version is included in http://mmp2.github.io/megaman/

Credit: VanderPlas, J. T.; Connolly, A. J.

Site: http://web.archive.org/web/201007101911 ... h/software
http://adsabs.harvard.edu/abs/2009AJ....138.1365V

Bibcode: 2010ascl.soft10031V

ID: ascl:1010.031
Last edited by Ada Coda on Sun Aug 06, 2017 2:44 pm, edited 1 time in total.
Reason: Updated code entry.
Code-seeking owl at your service

Post Reply