Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ppdebreuck/modnet

MODNet: a framework for machine learning materials properties

https://github.com/ppdebreuck/modnet

Science Score: 36.0%

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
    Found 6 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (15.3%) to scientific vocabulary

Keywords

machine-learning materials-science

Keywords from Contributors

interactive projection sequences materials-informatics chemistry genomics observability autograding hacking shellcodes
Last synced: 10 months ago · JSON representation

Repository

MODNet: a framework for machine learning materials properties

Basic Info
  • Host: GitHub
  • Owner: ppdebreuck
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage:
  • Size: 48.3 MB
Statistics
  • Stars: 92
  • Watchers: 6
  • Forks: 34
  • Open Issues: 35
  • Releases: 21
Topics
machine-learning materials-science
Created over 6 years ago · Last pushed about 1 year ago
Metadata Files
Readme License

README.md

modnet-logo
# MODNet: Material Optimal Descriptor Network [![arXiv](https://img.shields.io/badge/arXiv-2004.14766-brightgreen)](https://arxiv.org/abs/2004.14766) [![Build Status](https://img.shields.io/github/actions/workflow/status/ppdebreuck/modnet/ci.yml?logo=github&branch=main)](https://github.com/ppdebreuck/modnet/actions?query=branch%3Amaster+) [![Read the Docs](https://img.shields.io/readthedocs/modnet)](https://modnet.readthedocs.io/en/latest/)

Introduction

This repository contains the Python (3.8+) package implementing the Material Optimal Descriptor Network (MODNet). It is a supervised machine learning framework for learning material properties from either the composition or crystal structure. The framework is well suited for limited datasets and can be used for learning multiple properties together by using joint learning.

MODNet appears on the MatBench leaderboard. As of 11/11/2021, MODNet provides the best performance of all submitted models on 7 out of 13 tasks.

This repository also contains two pretrained models that can be used for predicting the refractive index and vibrational thermodynamics from any crystal structure.

See the MODNet papers and repositories below for more details:

MODNet schematic

Figure 1. Schematic representation of the MODNet.

How to install

First, create a virtual environment (e.g., named modnet) with Python (3.8+) using your favourite environment manager (the following instructions use conda):

shell conda create -n modnet python=3.9

Activate the environment:

shell conda activate modnet

Finally, install MODNet from PyPI with pip:

shell pip install modnet

Warning We strongly recommend pinning your Python environment when using MODNet across multiple machines, or multiple MODNet versions, as changes to the dependencies and sub-dependencies can lead to different values for particular features.

This can be achieved with conda export or pip freeze.

For development (or if you wish to use pinned versions of direct dependencies that MODNet has been tested with), you can clone this git repository and make an editable install inside your chosen environment with pip:

shell git clone git@github.com:ppdebreuck/modnet cd modnet conda create -n modnet python=3.9 conda activate modnet pip install -r requirements.txt # optionally use pinned requirements pip install -e .

Documentation

The documentation is available at ReadTheDocs.

Changelog

A brief changelog can be found in the release summaries on GitHub.

Author

This software was written by Pierre-Paul De Breuck and Matthew Evans with contributions from David Waroquiers and Gregoire Heymans. For an up-to-date list, see the Contributors on GitHub.

License

MODNet is released under the MIT License.

Owner

  • Name: Pierre-Paul De Breuck
  • Login: ppdebreuck
  • Kind: user

PhD student @modl-uclouvain. Computational materials scientist specialized in Machine Learning for materials discovery.

GitHub Events

Total
  • Create event: 16
  • Issues event: 9
  • Watch event: 13
  • Delete event: 13
  • Member event: 1
  • Issue comment event: 30
  • Push event: 35
  • Pull request review event: 11
  • Pull request review comment event: 6
  • Pull request event: 47
  • Fork event: 4
Last Year
  • Create event: 16
  • Issues event: 9
  • Watch event: 13
  • Delete event: 13
  • Member event: 1
  • Issue comment event: 30
  • Push event: 35
  • Pull request review event: 11
  • Pull request review comment event: 6
  • Pull request event: 47
  • Fork event: 4

Committers

Last synced: over 3 years ago

All Time
  • Total Commits: 214
  • Total Committers: 6
  • Avg Commits per committer: 35.667
  • Development Distribution Score (DDS): 0.547
Top Committers
Name Email Commits
ppdebreuck p****k@s****e 97
Matthew Evans g****t@m****e 96
dependabot[bot] 4****] 12
davidwaroquiers d****s@g****m 6
Sterling Baird 4****d 2
Gregoire Heymans 6****s 1
Committer Domains (Top 20 + Academic)
ml-evs.science: 1 student.uclouvain.be: 1

Issues and Pull Requests

Last synced: over 2 years ago

All Time
  • Total issues: 26
  • Total pull requests: 107
  • Average time to close issues: 3 months
  • Average time to close pull requests: about 2 months
  • Total issue authors: 8
  • Total pull request authors: 6
  • Average comments per issue: 2.46
  • Average comments per pull request: 0.92
  • Merged pull requests: 50
  • Bot issues: 0
  • Bot pull requests: 56
Past Year
  • Issues: 11
  • Pull requests: 60
  • Average time to close issues: about 2 months
  • Average time to close pull requests: about 1 month
  • Issue authors: 5
  • Pull request authors: 4
  • Average comments per issue: 2.18
  • Average comments per pull request: 0.7
  • Merged pull requests: 19
  • Bot issues: 0
  • Bot pull requests: 39
View more stats
Top Authors
Issue Authors
  • ml-evs (11)
  • sgbaird (5)
  • ppdebreuck (5)
  • kaueltzen (4)
  • FedeOtto (2)
  • gbrunin (2)
  • naik-aakash (2)
  • rogeriog (1)
  • github-ML-fan (1)
  • AndrewFalkowski (1)
  • dependabot[bot] (1)
  • kyledmiller (1)
  • Pepe-Marquez (1)
  • shivang-22 (1)
Pull Request Authors
  • dependabot[bot] (87)
  • ml-evs (30)
  • ppdebreuck (26)
  • gbrunin (11)
  • naik-aakash (4)
  • rogeriog (3)
  • kaueltzen (3)
  • gregheymans (2)
  • sgbaird (2)
  • VicTrqt (1)
  • kyledmiller (1)
  • yqdleiyi (1)
Top Labels
Issue Labels
enhancement (1) bug (1) question (1) dependency_updates (1)
Pull Request Labels
dependency_updates (72) python (4)

Packages

  • Total packages: 2
  • Total downloads:
    • pypi 649 last-month
  • Total dependent packages: 0
    (may contain duplicates)
  • Total dependent repositories: 1
    (may contain duplicates)
  • Total versions: 45
  • Total maintainers: 2
proxy.golang.org: github.com/ppdebreuck/modnet
  • Versions: 21
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 5.5%
Average: 5.6%
Dependent repos count: 5.8%
Last synced: 11 months ago
pypi.org: modnet

MODNet, the Material Optimal Descriptor Network for materials properties prediction.

  • Versions: 24
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 649 Last month
Rankings
Forks count: 7.5%
Stargazers count: 8.6%
Dependent packages count: 10.0%
Average: 13.9%
Downloads: 21.6%
Dependent repos count: 21.7%
Maintainers (2)
ppdebreuck ml-evs
Last synced: 11 months ago

Dependencies

docs/requirements.txt pypi
  • sphinx *
  • sphinx-rtd-theme *
  • sphinxcontrib-napoleon *
setup.py pypi
  • matminer >=0.6.2
  • numpy >=1.18.3
  • pandas >=0.25.3
  • pymatgen >=2020,<2020.9
  • scikit-learn >=0.23,<0.24
  • tensorflow >=2.4
  • tensorflow-probability >=0.12
.github/workflows/ci.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
docs/setup.py pypi
requirements.txt pypi
  • matminer ==0.8.0
  • numpy >=1.20
  • pandas ==1.5.2
  • pymatgen ==2023.7.20
  • scikit-learn ==1.2.0
  • tensorflow ==2.11.0
  • tensorflow-probability ==0.19.0