Easy-to-use Bayesian full and partial correlation estimator
Project description
Decorrelator
Analysing correlations between parameters whilst controlling for the effects of others.
(Fancy partial correlation)
Installation
create new environment
conda create -n NAME python=3.7
activate
source activate NAME
install high-performance libraries
conda install numpy mkl scipy
install correlator
pip install git+https://github.com/philastrophist/decorrelator.git
Use
Please see example.py for an example which uses nearly all functionality
There are two objects of interest: * decorrelator.LinearRelation * decorrelator.CorrelationModel
You may use them together as demonstrated in example.py or indivdually as shown in their home modules under if __name__ == "__main__"
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for decorrelator-1.0.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b3fbea2c16c800860f11b46e5d2eb0cfb388a258371e106bf4ce18dac7610021 |
|
MD5 | 8411d0c2bc63010b74d617e8a64f6f14 |
|
BLAKE2b-256 | bbc93bd8c2ba50eeb9d7ea1dafff6097f70853108ac3a4cfa5dfe77f2181aaa2 |