/py-codacore

Primary LanguagePythonMIT LicenseMIT

py-codacore

A self-contained implementation of CoDaCoRe, in python, by the original authors.

Note that a more up-to-date implementation is available in the R programming language, at R-codacore. If you are interested in reproducing the results in the original paper, check this repo.

Note this repository is under active development. If you would like to use CoDaCoRe on your dataset, and have any questions regarding the installation, usage, implementation, or model itself, do not hesitate to contact eg2912@columbia.edu. Contributions and fixes are also welcome -- please create an issue, submit a pull request, or email me.

How to run CoDaCoRe

  1. To install codacore:
git clone https://github.com/egr95/py-codacore.git
cd py-codacore/
pip install .
  1. To fit codacore on some data:
from codacore.model import CodaCore
from codacore.datasets import simulate_hts
x, y = simulate_hts(1000, 100)
model = CodaCore(objective='binary_classification', type='balance')
model.fit(x, y)
model.summary()

Unsupervised learning

Coming soon... If you would like access to an early version, get in touch.

Multi-omics

Coming soon... If you would like access to an early version, get in touch.