iBreakDown

Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)

https://github.com/modeloriented/ibreakdown

Science Score: 20.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
✓
Committers with academic emails
1 of 11 committers (9.1%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.8%) to scientific vocabulary

Keywords

breakdown iml interpretability shapley xai

Keywords from Contributors

interactive explainable explainable-ai explainable-machine-learning explanatory-model-analysis human interpretable interpretable-machine-learning learning machine

Last synced: 6 months ago · JSON representation

Repository

Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)

Basic Info

Host: GitHub
Owner: ModelOriented
License: gpl-3.0
Language: R
Default Branch: master
Homepage: https://ModelOriented.github.io/iBreakDown/
Size: 102 MB

Statistics

Stars: 83
Watchers: 9
Forks: 15
Open Issues: 4
Releases: 0

Topics

breakdown iml interpretability shapley xai

Created over 7 years ago · Last pushed about 2 years ago

Metadata Files

Readme Contributing License

Model Agnostic Local Attributions

Overview

The iBreakDown package is a model agnostic tool for explanation of predictions from black boxes ML models. Break Down Table shows contributions of every variable to a final prediction. Break Down Plot presents variable contributions in a concise graphical way. SHAP (Shapley Additive Attributions) values are calculated as average from random Break Down profiles. This package works for binary classifiers as well as regression models.

iBreakDown is a successor of the breakDown package. It is faster (complexity O(p) instead of O(p^2)). It supports variable interactions and interactive explanations with D3.js visualizations. It is imported and used to compute model explanations in multiple packages e.g. DALEX, modelStudio, arenar.

Methodology behind the iBreakDown package is described in the arXiv paper and Explanatory Model Analysis book. It is a part of DrWhy.AI universe.

Installation

```{r}

the easiest way to get iBreakDown is to install it from CRAN:

install.packages("iBreakDown")

Or the the development version from GitHub:

install.packages("devtools")

devtools::install_github("ModelOriented/iBreakDown") ```

Learn more

Find more examples in the EMA book: https://ema.drwhy.ai/.

This version also works with D3: see an example and demo.

plotD3

Acknowledgments

Work on this package was financially supported by the NCN Opus grant 2016/21/B/ST6/02176.

Owner

Name: Model Oriented
Login: ModelOriented
Kind: organization
Location: MI2DataLab @ Warsaw University of Technology

Website: https://mi2.ai/
Repositories: 41
Profile: https://github.com/ModelOriented

GitHub Events

Total

Watch event: 4

Last Year

Watch event: 4

Committers

Last synced: over 2 years ago

All Time

Total Commits: 221
Total Committers: 11
Avg Commits per committer: 20.091
Development Distribution Score (DDS): 0.462

Past Year

Commits: 3
Committers: 2
Avg Commits per committer: 1.5
Development Distribution Score (DDS): 0.333

Top Committers

Name	Email	Commits
Przemysław Biecek	p**k@g**m	119
hbaniecki	h**i@s**l	26
komosinskid	3**d@u**m	24
Hubert Baniecki	h**i@g**m	15
Hubert Baniecki	3**i@u**m	13
Przemysław Biecek	p**k@u**m	13
Adam Izdebski	4**i@u**m	5
jusira	a**a@g**m	3
MrDomani	4**i@u**m	1
Nicholas Spyrison	s**n@g**m	1
T	3**z@u**m	1

Committer Domains (Top 20 + Academic)

student.mini.pw.edu.pl: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 57
Total pull requests: 45
Average time to close issues: 2 months
Average time to close pull requests: 4 days
Total issue authors: 20
Total pull request authors: 8
Average comments per issue: 2.11
Average comments per pull request: 1.2
Merged pull requests: 37
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

pbiecek (18)
hbaniecki (13)
agosiewska (4)
GerardMeester (4)
agilebean (2)
sandeshregmi (2)
kmario23 (1)
komosinskid (1)
anuradham7 (1)
brunocarlin (1)
alexanderjwhite (1)
chipsin87 (1)
mklienz (1)
SimonDedman (1)
tcbakker (1)

Pull Request Authors

hbaniecki (22)
komosinskid (13)
AdamIzdebski (5)
nspyrison (1)
agosiewska (1)
maksymiuks (1)
learningasigoxyz (1)
MrDomani (1)

Top Labels

Issue Labels

invalid ❕ (8) feature 💡 (8) documentation 📚 (5) bug 💣 (4) maintenance 🔨 (3) question ❔ (1)

Pull Request Labels

Packages

Total packages: 2
Total downloads:
- cran 4,740 last-month
Total docker downloads: 42,142

Total dependent packages: 6
(may contain duplicates)
Total dependent repositories: 8
(may contain duplicates)
Total versions: 12
Total maintainers: 1

cran.r-project.org: iBreakDown

Model Agnostic Instance Level Variable Attributions

Homepage: https://ModelOriented.github.io/iBreakDown/
Documentation: http://cran.r-project.org/web/packages/iBreakDown/iBreakDown.pdf
License: GPL-3
Latest release: 2.1.2
published about 2 years ago

Versions: 9
Dependent Packages: 4
Dependent Repositories: 8
Downloads: 4,740 Last month
Docker Downloads: 42,142

Rankings

Stargazers count: 4.6%

Forks count: 4.8%

Downloads: 6.7%

Dependent packages count: 9.3%

Dependent repos count: 10.5%

Average: 10.6%

Docker downloads count: 27.4%

Maintainers (1)

przemyslaw.biecek@gmail.com

Last synced: 6 months ago

conda-forge.org: r-ibreakdown

Homepage: https://ModelOriented.github.io/iBreakDown/, https://github.com/ModelOriented/iBreakDown
License: GPL-3.0-only
Latest release: 2.0.1
published almost 5 years ago

Versions: 3
Dependent Packages: 2
Dependent Repositories: 0

Rankings

Dependent packages count: 19.5%

Average: 31.4%

Stargazers count: 33.0%

Dependent repos count: 34.0%

Forks count: 39.0%

Last synced: 6 months ago

Dependencies

DESCRIPTION cran

R >= 3.5 depends
ggplot2 * imports
DALEX * suggests
covr * suggests
e1071 * suggests
jsonlite * suggests
knitr * suggests
nnet * suggests
r2d3 * suggests
randomForest * suggests
ranger * suggests
rmarkdown * suggests
testthat * suggests

.github/workflows/R-CMD-check.yaml actions

actions/cache v1 composite
actions/checkout v2 composite
actions/upload-artifact master composite
r-lib/actions/setup-pandoc master composite
r-lib/actions/setup-r master composite

.github/workflows/pkgdown.yaml actions

actions/cache v1 composite
actions/checkout v2 composite
r-lib/actions/setup-pandoc v2 composite
r-lib/actions/setup-r v2 composite

.github/workflows/pr-commands.yaml actions

actions/checkout v2 composite
r-lib/actions/pr-fetch master composite
r-lib/actions/pr-push master composite
r-lib/actions/setup-r master composite

.github/workflows/test-coverage.yaml actions

actions/cache v1 composite
actions/checkout v2 composite
r-lib/actions/setup-pandoc master composite
r-lib/actions/setup-r master composite

iBreakDown

Science Score: 20.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Model Agnostic Local Attributions

Overview

Installation

the easiest way to get iBreakDown is to install it from CRAN:

Or the the development version from GitHub:

install.packages("devtools")

Learn more

Acknowledgments

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

cran.r-project.org: iBreakDown

Rankings

Maintainers (1)

conda-forge.org: r-ibreakdown

Rankings

Dependencies