If we take The Cannon to large numbers of labels (say chemical abundances), the model complexity grows very fast. At the same time, we know that most chemicals affect very few wavelengths in the spectrum; that is, we know that the problem is sparse. Here we use standard methods to discover and enforce sparsity.
- Andrew R. Casey (Cambridge)
- David W. Hogg (NYU) (MPIA) (SCDA)
- Melissa Ness (MPIA)
Copyright 2015, 2016 the authors.
The code in this repository is released under the open-source MIT License.
See the file LICENSE
for more details.
pip install https://github.com/andycasey/AnniesLasso/archive/master.zip
Note that the code is actively being developed in the develop
branch,
which represents the most up-to-date version. When the develop
branch
is stable and has complete test coverage, it will be merged into
master
and tagged as the first version release.