Data

Tools

Indexes

Applications

Experiments

Open Source Science

vip

Variable Importance Plots (VIPs)

https://github.com/koalaverse/vip

Science Score: 23.0%

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
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (19.7%) to scientific vocabulary

Keywords

interaction-effect machine-learning partial-dependence-plot supervised-learning-algorithms variable-importance variable-importance-plots

Keywords from Contributors

tidy-data black-box-model partial-dependence-function
Last synced: 6 months ago · JSON representation

Repository

Variable Importance Plots (VIPs)

Basic Info
Statistics
  • Stars: 189
  • Watchers: 9
  • Forks: 22
  • Open Issues: 21
  • Releases: 0
Topics
interaction-effect machine-learning partial-dependence-plot supervised-learning-algorithms variable-importance variable-importance-plots
Created over 8 years ago · Last pushed over 2 years ago
Metadata Files
Readme

README.Rmd 

---
output: github_document
---

```{r setup, echo = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.align = "center",
  fig.path = "man/figures"
)
```

# vip: Variable Importance Plots 


[![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/vip)](https://cran.r-project.org/package=vip)
[![R-CMD-check](https://github.com/koalaverse/vip/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/koalaverse/vip/actions/workflows/R-CMD-check.yaml)
[![Coverage Status](https://codecov.io/gh/koalaverse/vip/graph/badge.svg)](https://app.codecov.io/github/koalaverse/vip?branch=master)
[![Downloads](https://cranlogs.r-pkg.org/badges/vip)](https://cran.r-project.org/package=vip/)
[![The R Journal](https://img.shields.io/badge/The%20R%20Journal-10.32614%2FRJ--2020--013-brightgreen)](https://doi.org/10.32614/RJ-2020-013)


## Overview

[vip](https://koalaverse.github.io/vip/index.html) is an R package for constructing **v**ariable **i**mportance **p**lots (VIPs). VIPs are part of a larger framework referred to as *interpretable machine learning* (IML), which includes (but not limited to): partial dependence plots (PDPs) and individual conditional expectation (ICE) curves. While PDPs and ICE curves (available in the R package [pdp](https://cran.r-project.org/package=pdp)) help visualize feature effects, VIPs help visualize feature impact (either locally or globally). An in-progress, but comprehensive, overview of IML can be found here: https://github.com/christophM/interpretable-ml-book. 

Many supervised learning algorithms can naturally emit some measure of importance for the features used in the model, and these approaches are embedded in many different packages. The downside, however, is that each package uses a different function and interface and it can be challenging (and distracting) to have to remember each one (e.g., remembering to use `xgb.importance()` for [xgboost](https://cran.r-project.org/package=xgboost) models and `gbm.summary()` for [gbm](https://cran.r-project.org/package=gbm) models). With [vip](https://cran.r-project.org/package=vip) you get one consistent interface to computing variable importance for many types of supervised learning models across a number of packages. Additionally, [vip](https://koalaverse.github.io/vip/index.html) offers a number of *model-agnostic* procedures for computing feature importance (see the next section) as well an experimental function for quantifying the strength of potential interaction effects. For details and example usage, visit the [vip package website](https://koalaverse.github.io/vip/index.html).

```{r one-pkg, echo=FALSE, fig.width=6, out.width="50%"}
knitr::include_graphics("man/figures/one-pkg.png")
```


## Features

* **Model-based variable importance** - Compute variable importance specific to a particular model (like a *random forest*, *gradient boosted decision trees*, or *multivariate adaptive regression splines*) from a wide range of R packages (e.g., [randomForest](https://cran.r-project.org/package=randomForest), [ranger](https://cran.r-project.org/package=ranger), [xgboost](https://cran.r-project.org/package=xgboost), and many more). Also supports the [caret](https://cran.r-project.org/package=caret) and [parsnip](https://cran.r-project.org/package=parsnip) (starting with version 0.0.4) packages.

* **Permutation-based variable importance** - An efficient implementation of the permutation feature importance algorithm discussed in [this chapter](https://christophm.github.io/interpretable-ml-book/feature-importance.html) from [Christoph Molnar's *Interpretable Machine Learning* book](https://christophm.github.io/interpretable-ml-book/).

* **Shapley-based variable importance** - An efficient implementation of feature importance based on the popular [Shapley values](https://github.com/shap/shap) via the [fastshap](https://cran.r-project.org/package=fastshap) package. 

* **Variance-based variable importance** - Compute variable importance using a simple *feature importance ranking measure* (FIRM) approach. For details, see see [Greenwell et al. (2018)](https://arxiv.org/abs/1805.04755) and [Scholbeck et al. (2019)](https://arxiv.org/abs/1904.03959).


## Installation

```{r, eval=FALSE}
# The easiest way to get vip is to install it from CRAN:
install.packages("vip")

# Alternatively, you can install the development version from GitHub:
if (!requireNamespace("remotes")) {
  install.packages("remotes")
}
remotes::install_github("koalaverse/vip")
```

Owner

  • Name: koalaverse
  • Login: koalaverse
  • Kind: organization

A collection of koality code, software packages, and educational material for data science.

GitHub Events

Total
  • Issues event: 7
  • Watch event: 1
  • Issue comment event: 1
  • Push event: 4
  • Pull request event: 3
  • Create event: 1
Last Year
  • Issues event: 7
  • Watch event: 1
  • Issue comment event: 1
  • Push event: 4
  • Pull request event: 3
  • Create event: 1

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 328
  • Total Committers: 9
  • Avg Commits per committer: 36.444
  • Development Distribution Score (DDS): 0.381
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
bgreenwell g****n@g****m 203
b780620 B****l@8****m 93
Bernie Gray b****3@g****m 12
Bradley Boehmke b****e@8****m 9
Brandon Greenwell g****b@i****m 4
Max Kuhn m****n@g****m 3
Brandon Greenwell b****l@B****m 2
atusy 3****y 1
Brandon Greenwell b****l@p****n 1
Committer Domains (Top 20 + Academic)
8451.com: 2 pop-os.localdomain: 1 brandons-mbp-2.askey.com: 1 illuminationworksllc.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 94
  • Total pull requests: 33
  • Average time to close issues: about 1 year
  • Average time to close pull requests: 20 days
  • Total issue authors: 28
  • Total pull request authors: 8
  • Average comments per issue: 1.6
  • Average comments per pull request: 0.64
  • Merged pull requests: 29
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 2
  • Pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 2
  • Pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • bgreenwell (62)
  • bradleyboehmke (2)
  • vnijs (2)
  • balraadjsings (2)
  • juliasilge (2)
  • topepo (2)
  • Yu-Liu207 (1)
  • hanson1005 (1)
  • marioem (1)
  • HanLum (1)
  • agilebean (1)
  • ptaconet (1)
  • nipnipj (1)
  • jtr13 (1)
  • MasterLuke84 (1)
Pull Request Authors
  • bgreenwell (18)
  • bfgray3 (4)
  • bradleyboehmke (3)
  • topepo (3)
  • Athospd (2)
  • mrkaye97 (1)
  • atusy (1)
  • rdavis120 (1)
Top Labels
Issue Labels
question (9) enhancement (9) feature request (1)
Pull Request Labels

Packages

  • Total packages: 2
  • Total downloads:
    • cran 27,958 last-month
  • Total docker downloads: 23,262
  • Total dependent packages: 15
    (may contain duplicates)
  • Total dependent repositories: 34
    (may contain duplicates)
  • Total versions: 15
  • Total maintainers: 1
cran.r-project.org: vip

Variable Importance Plots

  • Versions: 10
  • Dependent Packages: 14
  • Dependent Repositories: 33
  • Downloads: 27,958 Last month
  • Docker Downloads: 23,262
Rankings
Stargazers count: 2.3%
Forks count: 3.2%
Dependent repos count: 4.6%
Dependent packages count: 4.6%
Downloads: 4.8%
Average: 7.0%
Docker downloads count: 22.5%
Maintainers (1)
greenwell.brandon@gmail.com
Last synced: 6 months ago
conda-forge.org: r-vip
  • Versions: 5
  • Dependent Packages: 1
  • Dependent Repositories: 1
Rankings
Dependent repos count: 24.4%
Stargazers count: 27.2%
Dependent packages count: 29.0%
Average: 29.1%
Forks count: 36.0%
Last synced: 6 months ago

Dependencies

DESCRIPTION cran
  • ggplot2 >= 0.9.0 imports
  • gridExtra * imports
  • magrittr * imports
  • plyr * imports
  • stats * imports
  • tibble * imports
  • utils * imports
  • C50 * suggests
  • Ckmeans.1d.dp * suggests
  • Cubist * suggests
  • DT * suggests
  • NeuralNetTools * suggests
  • RSNNS * suggests
  • caret * suggests
  • covr * suggests
  • doParallel * suggests
  • dplyr * suggests
  • earth * suggests
  • fastshap * suggests
  • gbm * suggests
  • glmnet * suggests
  • h2o * suggests
  • htmlwidgets * suggests
  • keras * suggests
  • knitr * suggests
  • lattice * suggests
  • mlbench * suggests
  • mlr * suggests
  • mlr3 * suggests
  • neuralnet * suggests
  • nnet * suggests
  • parsnip >= 0.1.7 suggests
  • party * suggests
  • partykit * suggests
  • pdp * suggests
  • pls * suggests
  • randomForest * suggests
  • ranger * suggests
  • rmarkdown * suggests
  • rpart * suggests
  • sparkline * suggests
  • sparklyr >= 0.8.0 suggests
  • tinytest * suggests
  • varImp * suggests
  • workflows >= 0.2.3 suggests
  • xgboost * suggests
.github/workflows/R-CMD-check.yaml actions
  • actions/cache v2 composite
  • actions/checkout v2 composite
  • actions/upload-artifact main composite
  • r-lib/actions/setup-pandoc v1 composite
  • r-lib/actions/setup-r v1 composite
  • r-lib/actions/setup-tinytex master composite
.github/workflows/test-coverage.yaml actions
  • actions/cache v2 composite
  • actions/checkout v2 composite
  • r-lib/actions/setup-pandoc v1 composite
  • r-lib/actions/setup-r v1 composite