https://github.com/ctuavastlab/jsongrinder.jl
Machine learning with Mill.jl for JSON documents
https://github.com/ctuavastlab/jsongrinder.jl
flux hierarchical-data json julia machine-learning multi-instance-learning
Last synced: 3 months ago
JSON representation
Machine learning with Mill.jl for JSON documents
- Host: GitHub
- URL: https://github.com/ctuavastlab/jsongrinder.jl
- Owner: CTUAvastLab
- License: other
- Created: 2018-08-27T09:38:55.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2025-01-05T11:48:07.000Z (6 months ago)
- Last Synced: 2025-04-09T09:08:10.427Z (3 months ago)
- Topics: flux, hierarchical-data, json, julia, machine-learning, multi-instance-learning
- Language: Julia
- Homepage: https://ctuavastlab.github.io/JsonGrinder.jl/stable/
- Size: 35.5 MB
- Stars: 49
- Watchers: 3
- Forks: 9
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.md
Awesome Lists containing this project
README
---
[](https://github.com/CTUAvastLab/JsonGrinder.jl/blob/master/LICENSE.md)
[](https://CTUAvastLab.github.io/JsonGrinder.jl/stable)
[](https://github.com/CTUAvastLab/JsonGrinder.jl/actions/workflows/ci.yml)
[](https://codecov.io/gh/CTUAvastLab/JsonGrinder.jl)
`JsonGrinder.jl` is a library that facilitates processing of JSON documents into
[`Mill.jl`](https://github.com/CTUAvastLab/Mill.jl) structures for machine learning. It provides
functionality for JSON schema inference, extraction of JSON documents to a suitable representation
for machine learning, and constructing a model operating on this data.
Watch our [introductory talk](https://www.youtube.com/watch?v=Bf0CvltIDbE) from JuliaCon 2021.
## Installation
Run the following in REPL:
```julia
] add JsonGrinder
```
## Getting Started
- [Documentation](https://ctuavastlab.github.io/JsonGrinder.jl/stable/)
- [API Reference](https://ctuavastlab.github.io/JsonGrinder.jl/stable/api/schema/)
- [Examples](https://ctuavastlab.github.io/JsonGrinder.jl/stable/examples/mutagenesis/mutagenesis/)
## Citation
Kindly cite our work with the following entries if you find it interesting, please:
* [*JsonGrinder.jl: automated differentiable neural architecture for embedding arbitrary JSON
data*](https://jmlr.org/papers/v23/21-0174.html)
```
@article{Mandlik2022,
author = {{\v{S}}imon Mandl{\'{i}}k and Mat{\v{e}}j Ra{\v{c}}insk{\'{y}} and Viliam Lis{\'{y}} and Tom{\'{a}}{\v{s}} Pevn{\'{y}}},
issn = {1533-7928},
issue = {298},
journal = {Journal of Machine Learning Research},
pages = {1-5},
title = {JsonGrinder.jl: automated differentiable neural architecture for embedding arbitrary JSON data},
volume = {23},
url = {http://jmlr.org/papers/v23/21-0174.html},
year = {2022},
}
```
* [*Malicious Internet Entity Detection Using Local Graph
Inference*](https://ieeexplore.ieee.org/document/10418120) (practical `Mill.jl` and
`JsonGrinder.jl` application)
```
@article{Mandlik2024,
author = {{\v{S}}imon Mandl{\'{i}}k and Tom{\'{a}}{\v{s}} Pevn{\'{y}} and V{\'{a}}clav {\v{S}}m{\'{i}}dl and Luk{\'{a}}{\v{s}} Bajer},
journal = {IEEE Transactions on Information Forensics and Security},
title = {Malicious Internet Entity Detection Using Local Graph Inference},
year = {2024},
volume = {19},
pages = {3554-3566},
doi = {10.1109/TIFS.2024.3360867}
}
```
* this implementation (fill in the used `version`)
```
@software{JsonGrinder,
author = {{\v{S}}imon Mandl{\'{i}}k and Tom{\'{a}}{\v{s}} Pevn{\'{y}} and Mat{\v{e}}j Ra{\v{c}}insk{\'{y}}},
title = {JsonGrinder.jl: a flexible library for automated feature engineering and conversion of JSONs to Mill.jl structures},
url = {https://github.com/CTUAvastLab/JsonGrinder.jl},
version = {...},
}
```
## Contribution guidelines
If you want to contribute to JsonGrinder.jl, be sure to review the
[contribution guidelines](CONTRIBUTING.md).
We use [GitHub issues](https://github.com/CTUAvastLab/JsonGrinder.jl/issues) for
tracking requests and bugs.