localice

Local Individual Conditional Expectation (localICE) is a local explanation approach from the field of eXplainable Artificial Intelligence (XAI)

https://github.com/viadee/localice

Science Score: 10.0%

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
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (15.4%) to scientific vocabulary

Keywords

ai explainable-ai ggplot machine-learning r visualization

Last synced: 6 months ago · JSON representation

Repository

Local Individual Conditional Expectation (localICE) is a local explanation approach from the field of eXplainable Artificial Intelligence (XAI)

Basic Info

Host: GitHub
Owner: viadee
License: other
Language: R
Default Branch: master
Size: 378 KB

Statistics

Stars: 7
Watchers: 11
Forks: 0
Open Issues: 0
Releases: 0

Topics

ai explainable-ai ggplot machine-learning r visualization

Created about 7 years ago · Last pushed about 5 years ago

Metadata Files

Readme License

localICE

Local Individual Conditional Expectation (localICE) is a local explanation approach from the field of eXplainable Artificial Intelligence (XAI). This is the repository of the R-package localICE.

Introduction

Idea

localICE is a model-agnostic XAI approach which provides three-dimensional local explanations for particular data instances. The approach is proposed in the master thesis of Martin Walter as an extension to ICE (see Reference). The three dimensions are the two features at the horizontal and vertical axes as well as the target represented by different colors. The approach is applicable for classification and regression problems to explain interactions of two features towards the target. For classification models, the number of classes can be more than two and each class is added as a different color to the plot. The given instance is added to the plot as two dotted lines according to the feature values. The localICE-package can explain features of type factor and numeric of any machine learning model. Automatically supported machine learning packages are mlr, randomForest, caret or all other with an S3 predict function. For further model types from other packages, a predict function has to be provided as an argument in order to get access to the model, as described below by means of an example with the h2o library.

Reference

Alex Goldstein et al. “Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation”. In: Journal of Computational and Graphical Statistics 24.1 (2013), pp. 44–65. URL: http://arxiv.org/abs/1309.6392

Examples

Regression

regression

Classification

classification

Using `localICE` with any machine learning library, in this case with `h2o`:

```splus if(require("h2o") && require("mlbench")){ h2o.init()

# Wrapping the h2o predict function and data type: predict.fun = function(model,newdata){ prediction = h2o.predict(model, as.h2o(newdata)) prediction = as.data.frame(prediction) return(prediction$predict) }

# Get data and train a random forest data("PimaIndiansDiabetes") rf = h2o.randomForest(y = "glucose", training_frame = as.h2o(PimaIndiansDiabetes))

# Get explanation explanation = localICE( instance = PimaIndiansDiabetes[1, ], data = PimaIndiansDiabetes, feature1 = "age", feature2 = "diabetes", target = "glucose", model = rf, regression = TRUE, predict.fun = predict.fun, step_1 = 5 ) plot(explanation) h2o.shutdown(prompt = FALSE) } ```

Installation

For official version, install via CRAN: splus install.packages("localICE") require("localICE") help("localICE") For developmental version, install via GitHub: splus if(require("devtools")){ install_github("viadee/localICE") }

License

BSD 3-Clause License

Authors

Martin Walter - Initial work

Owner

Name: viadee IT-Unternehmensberatung AG
Login: viadee
Kind: organization
Location: Münster, Köln/Germany

Website: https://viadee.de/
Twitter: viadee_it
Repositories: 96
Profile: https://github.com/viadee

GitHub Events

Total

Last Year

Issues and Pull Requests

Last synced: 7 months ago

All Time

Total issues: 0
Total pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Total issue authors: 0
Total 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

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

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- cran 190 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 2
Total maintainers: 1

cran.r-project.org: localICE

Local Individual Conditional Expectation

Homepage: https://github.com/viadee/localICE
Documentation: http://cran.r-project.org/web/packages/localICE/localICE.pdf
License: BSD_3_clause + file LICENSE
Latest release: 0.1.1
published about 6 years ago

Versions: 2
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 190 Last month

Rankings

Stargazers count: 19.8%

Forks count: 28.8%

Dependent packages count: 29.8%

Dependent repos count: 35.5%

Average: 38.2%

Downloads: 77.0%

Maintainers (1)

mf-walter@web.de