Welcome¶

About

MLZ, “Machine Learning and photo-Z” is a parallel python framework that computes fast and robust photometric redshift PDFs using Machine Learning algorithms. In particular, it uses a supervised technique with prediction trees and random forest through TPZ or a unsupervised methods with self organizing maps and random atlas through SOMz. It can be easily extended to other regression or classification problems. We recently have added an additional feature that allows high compressed representation of the photo-z PDFs using sparse representation. This allow to efficiently store and handle a large number of PDF from different techniques

References¶

These are the references related to this framework where detailed information about these methods can be found.

Carrasco Kind, M., & Brunner, R. J., 2013 “TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests”, MNRAS, 432, 1483 (Link)

Carrasco Kind, M., & Brunner, R. J., 2014, “SOMz : photometric redshift PDFs with self organizing maps and random atlas” , MNRAS, 438, 3409 (Link)

Carrasco Kind, M., & Brunner, R. J., 2014, “Exhausting the Information: Novel Bayesian Combination of Photometric Redshift PDFs”, MNRAS, 442, 3380 (Link)

Carrasco Kind, M., & Brunner, R. J., 2014, “Sparse Representation of Photometric Redshift PDFs: Preparing for Petascale Astronomy”, MNRAS, 441, 3550 (Link)

Contact¶

Here you can find my contact information for questions or comments.

Current Version¶

Current version 1.2 (Check github page for update and changes)

Now on GitHub¶

We have uploaded MLZ to GitHub Here you can get the latest MLZ version

Contents¶

This is a brief documentation of MLZ and the routines included