Data

Tools

Indexes

Applications

Experiments

Open Source Science

fairadapt

Fair data adaptation using causal graphical models with R.

https://github.com/dplecko/fairadapt

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
    2 of 7 committers (28.6%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (18.0%) to scientific vocabulary

Keywords

causal-inference fairness machine-learning r
Last synced: 6 months ago · JSON representation

Repository

Fair data adaptation using causal graphical models with R.

Basic Info
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Topics
causal-inference fairness machine-learning r
Created over 6 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.Rmd 

---
output:
  github_document:
    html_preview: false
---



```{r setup, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
```

# [fairadapt](https://dplecko.github.io/fairadapt/)


[![Lifecycle](https://img.shields.io/badge/lifecycle-stable-brightgreen.svg)](https://lifecycle.r-lib.org/articles/stages.html#stable)
[![R build status](https://github.com/dplecko/fairadapt/workflows/build/badge.svg)](https://github.com/dplecko/fairadapt/actions?query=workflow%3Abuild)
[![R check status](https://github.com/dplecko/fairadapt/workflows/check/badge.svg)](https://github.com/dplecko/fairadapt/actions?query=workflow%3Acheck)
[![pkgdown build status](https://github.com/dplecko/fairadapt/workflows/pkgdown/badge.svg)](https://github.com/dplecko/fairadapt/actions?query=workflow%3Apkgdown)
[![covr status](https://github.com/dplecko/fairadapt/workflows/coverage/badge.svg)](https://github.com/dplecko/fairadapt/actions?query=workflow%3Acoverage)
[![Codecov test coverage](https://codecov.io/gh/dplecko/fairadapt/branch/main/graph/badge.svg?token=8A0EL5N4RE)](https://app.codecov.io/gh/dplecko/fairadapt)


The R package fairadapt is intended for removing bias from machine learning algorithms. In particular, it implements the pre-processing procedure described in [Plecko & Meinshausen, 2019](https://arxiv.org/abs/1911.06685) (all the code used for producing the figures in the paper can be found in the `jmlr-paper` folder). The main idea is to adapt the training and testing data in a way which prevents any further training procedure from learning an undesired bias. The package currently offers the pre-processing step, after which the user can use the adapted data to train any classifier. However, some caution on the training step is still advised, so for more involved applications with resolving variables, the user should refer to the original paper.

## Installation

You can install the released version of fairadapt from [CRAN](https://CRAN.R-project.org) with:

```{r, eval = FALSE}
install.packages("fairadapt")
```

## Example




An example of how fairadapt can be used is demonstrated below on the UCI Adult dataset.

```{r, example}
# loading the package
library(fairadapt)

vars <- c("sex", "age", "native_country", "marital_status", "education_num",
          "workclass", "hours_per_week", "occupation", "income")

# initialising the adjacency matrix
adj.mat <- c(
  0, 0, 0, 1, 1, 1, 1, 1, 1, # sex
  0, 0, 0, 1, 1, 1, 1, 1, 1, # age
  0, 0, 0, 1, 1, 1, 1, 1, 1, # native_country
  0, 0, 0, 0, 1, 1, 1, 1, 1, # marital_status
  0, 0, 0, 0, 0, 1, 1, 1, 1, # education_num
  0, 0, 0, 0, 0, 0, 0, 0, 1, # workclass
  0, 0, 0, 0, 0, 0, 0, 0, 1, # hours_per_week
  0, 0, 0, 0, 0, 0, 0, 0, 1, # occupation
  0, 0, 0, 0, 0, 0, 0, 0, 0  # income
)

adj.mat <- matrix(adj.mat, nrow = length(vars), ncol = length(vars),
                  dimnames = list(vars, vars), byrow = TRUE)

# reading in the UCI Adult data
adult <- readRDS(
  system.file("extdata", "uci_adult.rds", package = "fairadapt")
)
n <- nrow(adult) / 2

mod <- fairadapt(income ~ ., 
                 train.data = head(adult[, vars], n = n),
                 test.data = tail(adult[, vars], n = n), 
                 prot.attr = "sex", adj.mat = adj.mat, 
                 res.vars = "hours_per_week")

adapt.train <- adaptedData(mod)
adapt.test  <- adaptedData(mod, train = FALSE)

summary(mod)
```

Owner

  • Login: dplecko
  • Kind: user

GitHub Events

Total
Last Year

Committers

Last synced: over 2 years ago

All Time
  • Total Commits: 186
  • Total Committers: 7
  • Avg Commits per committer: 26.571
  • Development Distribution Score (DDS): 0.71
Past Year
  • Commits: 6
  • Committers: 1
  • Avg Commits per committer: 6.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Drago Plecko w****o@g****m 54
Nicolas Bennett n****t@s****h 50
Drago Plecko d****o@s****h 40
Nicolas Bennett n****t@i****m 34
Drago Plecko p****d@D****l 4
Drago Plecko p****d@D****l 3
Nicolas Bennett n****t@z****h 1
Committer Domains (Top 20 + Academic)
stat.math.ethz.ch: 2 zeus.nbenn.ch: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 1
  • Total pull requests: 6
  • Average time to close issues: 3 months
  • Average time to close pull requests: 3 days
  • Total issue authors: 1
  • Total pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.17
  • Merged pull requests: 6
  • 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
  • nbenn (1)
Pull Request Authors
  • nbenn (6)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • cran 333 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 10
  • Total maintainers: 1
cran.r-project.org: fairadapt

Fair Data Adaptation with Quantile Preservation

  • Versions: 10
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 333 Last month
Rankings
Forks count: 17.8%
Dependent packages count: 29.8%
Average: 31.8%
Stargazers count: 35.2%
Dependent repos count: 35.5%
Downloads: 40.6%
Maintainers (1)
www.plecko@gmail.com
Last synced: 6 months ago

Dependencies

DESCRIPTION cran
  • R >= 3.5.0 depends
  • assertthat * imports
  • cowplot * imports
  • ggplot2 * imports
  • igraph * imports
  • qrnn * imports
  • quantreg * imports
  • ranger >= 0.13.1 imports
  • scales * imports
  • ggraph * suggests
  • knitr * suggests
  • magick * suggests
  • microbenchmark * suggests
  • mvtnorm * suggests
  • pdftools * suggests
  • rmarkdown * suggests
  • rticles * suggests
  • testthat >= 3.0.3 suggests
  • xtable * suggests