Metadata-Version: 2.1
Name: sage-importance
Version: 0.0.1
Summary: For calculating global feature importance using Shapley values.
Home-page: https://github.com/icc2115/sage/
Author: Ian Covert
Author-email: icovert@cs.washington.edu
License: UNKNOWN
Description: 
                SAGE (Shapley Additive Global importancE) is a game theoretic approach 
                for understanding black-box machine learning models. It summarizes the 
                importance of each feature based on the predictive power it 
                contributes, accounting for complex interactions by using the Shapley 
                value from cooperative game theory. See the 
                [GitHub page](https://github.com/icc2115/sage/) for examples, and see 
                the [paper](https://arxiv.org/abs/2004.00668) for more details.
            
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Requires-Python: >=3.6
Description-Content-Type: text/markdown
