cvplot
Understand machine learning models with Contribution-Value plots
Science Score: 57.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.0%) to scientific vocabulary
Keywords
Repository
Understand machine learning models with Contribution-Value plots
Basic Info
- Host: GitHub
- Owner: iamDecode
- License: bsd-2-clause
- Language: Vue
- Default Branch: master
- Homepage: https://explaining.ml/cvplots
- Size: 392 KB
Statistics
- Stars: 6
- Watchers: 1
- Forks: 2
- Open Issues: 1
- Releases: 0
Topics
Metadata Files
README.md
Contribution-Value plots
The Contribution-Value plot is a visual encoding for interpreting machine learning models. [more information]
Demo
Installation
To install use pip:
$ pip install cvplot
If you use jupyter lab, also run:
$ jupyter labextension install cvplot
for classic jupyter notebooks, run:
jupyter nbextension install --py --symlink --overwrite --sys-prefix cvplot
jupyter nbextension enable --py --sys-prefix cvplot
Development
For a development installation (requires npm or yarn),
$ git clone https://github.com/iamDecode/cvplot.git
$ cd cvplot
You may want to (create and) activate a virtual environment before continuing with:
$ pip install -e .
$ jupyter labextension install js
$ jupyter nbextension install --py --symlink --overwrite --sys-prefix cvplot
$ jupyter nbextension enable --py --sys-prefix cvplot
When actively developing your extension, build Jupyter Lab with the command:
$ jupyter lab --watch
This takes a minute or so to get started, but then automatically rebuilds JupyterLab when your javascript changes.
Citation
If you want to refer to our visualization, please cite our paper using the following BibTeX entry:
bibtex
@article{collaris2021comparative,
title={Comparative Evaluation of Contribution-Value Plots for Machine Learning Understanding},
author={Collaris, Dennis and van Wijk, Jarke J.},
journal={Journal of Visualization},
year={2021},
issn={1875-8975},
doi={10.1007/s12650-021-00776-w},
url={https://doi.org/10.1007/s12650-021-00776-w}
}
License
This project is licensed under the BSD 2-Clause License - see the LICENSE file for details.
Owner
- Name: Dennis Collaris
- Login: iamDecode
- Kind: user
- Location: Brainport, The Netherlands
- Company: Eindhoven University of Technology
- Website: de.co.de
- Repositories: 53
- Profile: https://github.com/iamDecode
Citation (CITATION.cff)
cff-version: 1.2.0
message: If you use this software, please cite it using these metadata.
title: Comparative evaluation of contribution-value plots for machine learning understanding
abstract: The field of explainable artificial intelligence aims to help experts understand complex machine learning models. One key approach is to show the impact of a feature on the model prediction. This helps experts to verify and validate the predictions the model provides. However, many challenges remain open. For example, due to the subjective nature of interpretability, a strict definition of concepts such as the contribution of a feature remains elusive. Different techniques have varying underlying assumptions, which can cause inconsistent and conflicting views. In this work, we introduce local and global contribution-value plots as a novel approach to visualize feature impact on predictions and the relationship with feature value. We discuss design decisions and show an exemplary visual analytics implementation that provides new insights into the model. We conducted a user study and found the visualizations aid model interpretation by increasing correctness and confidence and reducing the time taken to obtain an insight.
authors:
- family-names: Collaris
given-names: Dennis
orcid: "https://orcid.org/0000-0001-7612-9319"
- family-names: van Wijk
given-names: Jarke J.
orcid: "https://orcid.org/0000-0002-5128-976X"
doi: 10.1007/s12650-021-00776-w
date-released: 2021-09-11
license: BSD-2-Clause
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Committers
Last synced: 7 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Dennis Collaris | d****s@m****m | 23 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 1
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 1
- Total pull request authors: 0
- Average comments per issue: 9.0
- 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
Top Authors
Issue Authors
- kalkite (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- pypi 7 last-month
- npm 1 last-month
-
Total dependent packages: 1
(may contain duplicates) -
Total dependent repositories: 1
(may contain duplicates) - Total versions: 3
- Total maintainers: 2
pypi.org: cvplot
Understand machine learning models with Contribution-Value plots
- Homepage: https://github.com/iamDecode/cvplot
- Documentation: https://cvplot.readthedocs.io/
- License: bsd-2-clause
-
Latest release: 0.0.2
published about 4 years ago
Rankings
Maintainers (1)
npmjs.org: cvplot
Understand machine learning models with Contribution-Value plots
- Homepage: https://github.com/iamDecode/cvplot#readme
- License: BSD-2-Clause
-
Latest release: 0.0.2
published about 4 years ago
Rankings
Maintainers (1)
Dependencies
- css-loader ^3.6.0 development
- rimraf ^2.6.1 development
- vue-loader ^15.9.6 development
- vue-template-compiler ^2.6.12 development
- webpack ^3.12.0 development
- @jupyter-widgets/base ^1.1 || ^2 || ^3
- d3 ^5.9.7
- lodash ^4.17.4
- pixi.js ^5.2.1
- robust-segment-intersect ^1.0.1
- vue ^2.6.10
- 499 dependencies
- ipywidgets >=7.0.0
- pandas *
- scikit-learn *
- tqdm *