A python module to reduce features using correlation matrix
Project description
corrfeatred
reduce features using correlation matrix
Installation
pip install corrfeatred
Usage
from corrfeatred import reduce_features
correlation_matrix = #correlation matrix
feature_set = reduce_features(correlation_matrix, threshhold=0.8, policy='min')
# if you want another set of features for same correlation matrix, then use random seed to change the output.
different_feature_set = reduce_features(correlation_matrix, threshhold=0.8, policy='min', random_seed = 42)
Workflow
Currently there is only one function which takes correlation matrix and threshholds as input and then constructs a graph.
There after we find maximal cliques in the graph and our goal is to have at max one feature from each clique.
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
corrfeatred-0.0.3.tar.gz
(3.9 kB
view hashes)
Built Distribution
Close
Hashes for corrfeatred-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6fa028eacc4003157a88df823d156ecd75a0f313ad7cd572046851d12d5a0fe8 |
|
MD5 | d68cfdcc42487a8b99f2e1d9e25b3969 |
|
BLAKE2b-256 | 12ce2daec67d260dd933715a43408de545dd5b94095a83fd700410c215a84478 |