https://github.com/ctuavastlab/jsongrinderexamples

Examples of use of JsonGrinder on different problems

https://github.com/ctuavastlab/jsongrinderexamples

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.2%) to scientific vocabulary

Keywords from Contributors

flux the-human-brain hierarchical-data multi-instance-learning
Last synced: 10 months ago · JSON representation

Repository

Examples of use of JsonGrinder on different problems

Basic Info
  • Host: GitHub
  • Owner: CTUAvastLab
  • Language: Julia
  • Default Branch: main
  • Size: 1.59 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 4 years ago · Last pushed about 3 years ago
Metadata Files
Readme

README.md

JsonGrinderExamples

This repo contains examples of use of the JsonGrinder.jl library from JsonGrinder.jl: automated differentiable neural architecture for embedding arbitrary JSON data, Mandlík, Račinský, Lisý, and Tomáš Pevný, 2022.

Julia v1.7.2 was used in all experiments. Each directory contains the Project.toml and Manifest.toml for reproducibility. To make sure that all dependencies have same versions, run julia --project=. -e "using Pkg; Pkg.instantiate()"

in the directory.

To reproduce the results, it is sufficient to run in appropriate directory. For baseline results, run julia --project=. baseline.jl for tuned results, run julia --project=. tuned.jl

Mutagenesis

Mutagenesis is a small dataset from biology, which describes molecules trialed for mutagenicity on Salmonella typhimurium. It is very small and contains only 100 training samples.

Ember

Ember is a problem from a computer security, where the goal is to classify samples to malware and clean. Data are available at https://github.com/endgameinc/ember. The problem is large, therefore the scripts are adapted to take advantage of multi-threadding in the data preparation phase (hence run julia with -t option with correct number of threads). Because of this, scripts depart a bit from the usual examples.

Warning: The ember dataset is large. By default, it will be downloaded to a temporary directory in /tmp. Make sure you have at least 10Gb of free space.

Execute julia -t auto --project=. -e 'include("prepare_data.jl"); prepare_data()' to download the data and cache the result of extraction.

Owner

  • Name: Joint research lab of Czech Technical University in Prague and Avast
  • Login: CTUAvastLab
  • Kind: organization
  • Location: Prague

GitHub Events

Total
Last Year

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 19
  • Total Committers: 3
  • Avg Commits per committer: 6.333
  • Development Distribution Score (DDS): 0.421
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Šimon Mandlík s****k@g****m 11
Pevnak p****k@g****m 7
Matěj Račinský m****y@a****m 1
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: about 2 hours
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 1.0
  • 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
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels