NL4DV is a Python toolkit that takes a natural language (NL) query about a given dataset as input and outputs a structured JSON object containing Data attributes, Analytic tasks, and Visualizations (Vega-Lite specifications).
Project description
NL4DV
- Create Visualizations (Vis) in Python using Natural Language (NL)
- Add an NL interface to your existing Vis systems.
NL4DV stands for Natural Language toolkit for Data Visualization. It takes a natural language query about a given dataset as input and outputs a structured JSON object containing:
- Data attributes,
- Analytic tasks, and
- Visualizations (Vega-Lite specifications)
The preprint of the Research Paper due to appear at IEEE VIS'20 can be downloaded from here.
The Documentation, Usage, and Examples can be found here.
Credits
NL4DV was created by Arpit Narechania, Arjun Srinivasan, and John Stasko of the Georgia Tech Visualization Lab.
We thank Rishab Mitra for helping build some of our debugger applications and members of the Georgia Tech Visualization Lab for their support and constructive feedback.
Citation
@article{narechaniaNL4DV2020,
title = {{{NL4DV}}: A {{Toolkit}} for Generating {{Analytic Specifications}} for {{Data Visualization}} from {{Natural Language}} Queries},
shorttitle = {{{NL4DV}}},
author = {{{Narechania}}, Arpit and {{Srinivasan}}, Arjun and {{Stasko}}, John},
journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)},
doi = {10.1109/TVCG.2020.3030378},
year = {2020},
publisher = {IEEE}
}
License
The software is available under the MIT License.
Contact
If you have any questions, feel free to open an issue or contact Arpit Narechania.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file nl4dv-0.0.4.tar.gz
.
File metadata
- Download URL: nl4dv-0.0.4.tar.gz
- Upload date:
- Size: 35.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.24.0 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3ee74e2f354956df6af620c0c2f1d37edc8409129e9037361ff6f82bd4d7b2ef |
|
MD5 | f6f481cd2df65e393fe3faf169619d8c |
|
BLAKE2b-256 | 9a85a624706cc1f2ffcbaa9af68bdb750dd053756548937fd8f39d022fb440b9 |