iancovert/fastshap iancovert/fastshap

  • Stars
    star
    86
  • Rank 382,193 (Top 8 %)
  • Language
    Python
  • License
    MIT License
  • Created over 3 years ago
  • Updated 12 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
iancovert/fastshap
github

iancovert

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

An amortized approach for calculating local Shapley value explanations

More Repositories

1

sage

For calculating global feature importance using Shapley values.
Python
236
star
2

Neural-GC

Granger causality discovery for neural networks.
Python
188
star
3

shapley-regression

For calculating Shapley values via linear regression.
Python
58
star
4

removal-explanations

A lightweight implementation of removal-based explanations for ML models.
Python
55
star
5

dynamic-selection

Dynamic feature selection based on conditional mutual information
Python
19
star
6

persist

Python
14
star
7

dl-selection

Feature selection for deep learning models.
Python
13
star
8

sage-experiments

Code for experiments in SAGE paper (NeurIPS 2020)
Python
6
star
9

Sparse-NN

Python
3
star
10

propose

Python
3
star
11

easy-ensemble

For learning optimal model ensembles
Python
3
star
12

amortized-valuation

Python
3
star
13

nonlinear-gc

Python
2
star
14

data-scaling

Python
1
star