Metadata-Version: 2.1
Name: dsbox-corex
Version: 1.2.0
Summary: Return components/latent factors that explain the most multivariate mutual information in the data under Linear Gaussian model. For comparison, PCA returns components explaining the most variance in the data.
Home-page: https://gitlab.com/datadrivendiscovery/contrib/dsbox-corex
Author: Rob Brekelmans/Greg Ver Steeg
Author-email: brekelma@usc.edu
License: Apache-2.0
Keywords: d3m_primitive
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Description-Content-Type: text/markdown
Requires-Dist: GitPython
Requires-Dist: d3m
Requires-Dist: d3m-common-primitives
Requires-Dist: keras
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: scipy
Requires-Dist: six
Requires-Dist: tensorflow

Corex featurization and modeling primitives for D3M envrionments

Featurization:
(featurization with information regularization for continuous data (linear Gaussian model) and text (similar to LDA))
Corex continuous
Corex text

Regression:
(echo provides mutual information regularization: linear regression and neural network modeling primitives provided)
EchoLinear 
EchoRegression
EchoClassification


