Skip to content

gciccarelli3/fast-jlt

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fast Johnson-Lindenstrauss Transform (FJLT)

Cython and python implementation of the Fast JLT. Uses FFTW.

  1. Dependencies

  • FFTW, a fast DFT library, available from the fftw website.
  • Cython
  1. Install

python setup.py install

  1. Usage

From python use the class SubsampledRandomizedFourrierTransform in SubsampledRandomizedFourrierTransform.py It follows the scikit-learn interface. From cython use SubsampledRandomizedFourrierTransform1d in SubsampledRandomizedFourrierTransform1d.pyx or the functions in random_projection_fast.pyx directly.

See demo.py for a quick demo.

  1. Authors / Contact

Gabriel Krummenacher

http://people.inf.ethz.ch/kgabriel/software.html

About

Fast Johnson-Lindenstrauss Transform (FJLT)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C 52.8%
  • Python 47.2%