For calculating global feature importance using Shapley values.
Project description
SAGE (Shapley Additive Global importancE) is a game theoretic approach
for understanding black-box machine learning models. It summarizes each
feature's importance based on the predictive power it contributes, and
it accounts for complex interactions using the Shapley value from
cooperative game theory. See the
[GitHub page](https://github.com/iancovert/sage/) for examples, and see
the [paper](https://arxiv.org/abs/2004.00668) for more details.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
sage-importance-0.0.4.tar.gz
(21.7 kB
view hashes)
Built Distribution
Close
Hashes for sage_importance-0.0.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c32f7ba2534b2cb507d684960b6afbe05dbe1f1ef4713925d88a4d9ce1239bd2 |
|
MD5 | ed338a3cb800b9a0b629830f39c9ef44 |
|
BLAKE2b-256 | 99cc207b9d3c5192841700ff5490f9794e05575fd993dfb8f9960910a6326d98 |