https://github.com/ornl/icat
Interactive machine learning dashboard for textual data exploration
https://github.com/ornl/icat
Last synced: about 2 months ago
JSON representation
Interactive machine learning dashboard for textual data exploration
- Host: GitHub
- URL: https://github.com/ornl/icat
- Owner: ORNL
- License: bsd-3-clause
- Created: 2022-09-27T20:31:39.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-02-24T13:34:40.000Z (3 months ago)
- Last Synced: 2025-03-24T20:23:11.971Z (2 months ago)
- Language: Python
- Homepage: https://ornl.github.io/icat/
- Size: 2.03 MB
- Stars: 4
- Watchers: 3
- Forks: 1
- Open Issues: 18
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
README
# Interactive Corpus Analysis Tool
[](https://github.com/psf/black)
[](https://badge.fury.io/py/icat-iml)
[](https://github.com/ORNL/icat/actions/workflows/tests.yml)
[](https://github.com/ORNL/curifactory/blob/main/LICENSE)
[](https://joss.theoj.org/papers/0528d60ff4f251069d15456fdb83bd0f)
The Interactive Corpus Analysis Tool (ICAT) is an interactive machine learning (IML) dashboard for unlabeled text datasets that allows a user to iteratively and visually define features, explore and label instances of their dataset, and train a logistic regression model on the fly as they do so to assist in filtering, searching, and labeling tasks.
ICAT is implemented using holoviz's [panel](https://panel.holoviz.org/) library, so it can either directly be rendered like a widget in a jupyter lab instance, or incorporated as part of a standalone panel website.
## Installation
ICAT can be installed via `pip` with:
```
pip install icat-iml
```
## Documentation
The user guide and API documentation can be found at [https://ornl.github.io/icat](https://ornl.github.io/icat).
## Visualization
The primary ring visualization is called AnchorViz, a technique from IML literature. (See Chen, Nan-Chen, et al. "[AnchorViz: Facilitating classifier error discovery through interactive semantic data exploration](https://dl.acm.org/doi/abs/10.1145/3172944.3172950)")
We implemented an ipywidget version of AnchorViz and use it in this project, it can be found separately at [https://github.com/ORNL/ipyanchorviz](https://github.com/ORNL/ipyanchorviz)
## Contributing
Contributions for improving ICAT are welcome! If you run into any problems, find
bugs, or think of useful improvements and enhancements, feel free to open an
[issue](https://github.com/ORNL/icat/issues).
If you add a feature or fix a bug yourself and want it considered for
integration, feel free to open a pull request with the changes. Please provide
a detailed description of what the pull request is doing and briefly list any
significant changes made. If it's in regards to a specific issue, please include
or link the issue number.
## Citation
To cite usage of ICAT, please use the following bibtex:
```bibtex
@misc{doecode_105653,
title = {Interactive Corpus Analysis Tool},
author = {Martindale, Nathan and Stewart, Scott},
abstractNote = {The Interactive Corpus Analysis Tool (ICAT) is an interactive machine learning dashboard for unlabeled text/natural language processing datasets that allows a user to iteratively and visually define features, explore and label instances of their dataset, and simultaneously train a logistic regression model. ICAT was created to allow subject matter experts in a specific domain to directly train their own models for unlabeled datasets visually, without needing to be a machine learning expert or needing to know how to code the models themselves. This approach allows users to directly leverage the power of machine learning, but critically, also involves the user in the development of the machine learning model.},
year = {2023},
month = {apr}
}
```