rollshap
1.0.1Rolling Shapley Values
Overview
Analytical computation of rolling and expanding Shapley values for time-series data. The 'rollshap' package decomposes the coefficient of determination (R-squared) of a linear regression into nonnegative contributions from each explanatory variable using the Shapley value from cooperative game theory (Shapley, 1953, doi:10.1515/9781400881970-018). For each window, the exact Shapley value is computed by fitting all subsets of the explanatory variables and averaging the marginal contribution to R-squared across all orderings, which returns an order-invariant attribution that sums to the full-model R-squared. Use cases include variable importance, factor attribution, and feature selection in time-series regression. The package supports rolling and expanding windows, weights, and handling of missing values via 'min_obs', 'complete_obs', and 'na_restore' arguments. The implementation uses the online and offline algorithms from the 'roll' package to compute rolling and expanding cross-products efficiently with parallelism across columns and windows provided by 'RcppParallel'.
Install
Health
- OK2026-08-0413 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
- NOTE2026-08-0112 OK · 1 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
- OK2026-05-225 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
Documentation
- Examples that run
- 100%
- Documented parameters
- 100%
- Return-value docs
- 100%
- References docs
- 0%
Downloads
Repository
Stars over time
Repository practices
1 development-tooling and community-health practice detected across 1 family in the upstream repository
Checks run against github.com/jasonjfoster/rollshap on 2026-08-03.
Dependencies
Nothing depends on this yet.
Code & Tests
People & History
1 release. R releases are shown for context.
- 1.0.1Latest2026-05-21 · current release
- RR 4.6.0 released · 2026-04-24
Package metadata
- First published
- 2026-05-21
- Total releases
- 1 / 1 yrs
- License
- GPL (>= 2) OSI
- Minimum R
- ≥ 3.0.2
- Download size
- not tracked yet
- Installed size
- not tracked yet
- With dependencies
- not tracked yet