Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/qi-max/amlearn

Machine Learning Package Targeted for Amorphous Materials.

https://github.com/qi-max/amlearn

Science Score: 23.0%

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

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: nature.com
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.9%) to scientific vocabulary

Keywords

amorphous-materials machine-learning materials-science
Last synced: 6 months ago · JSON representation

Repository

Machine Learning Package Targeted for Amorphous Materials.

Basic Info
  • Host: GitHub
  • Owner: Qi-max
  • License: other
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 33.8 MB
Statistics
  • Stars: 19
  • Watchers: 1
  • Forks: 8
  • Open Issues: 1
  • Releases: 0
Topics
amorphous-materials machine-learning materials-science
Created over 7 years ago · Last pushed about 5 years ago
Metadata Files
Readme License

README.md

amlearn

Machine Learning Package for Amorphous Materials (WIP).

To featurize the heterogeneous atom site environments in amorphous materials, we can use amlearn to derive 1k+ candidate features that encompass short- (SRO) and medium-range order (MRO) to describe the packing heterogeneity around each atom site. (See the following example figure for combining site features and machine learning (ML) to predict the deformation heterogeneity in metallic glasses).

Candidate features include recognized signatures such as coordination number (CN), Voronoi indices, characteristic motifs, volume metrics (atomic/cluster packing efficiency), i-fold symmetry indices, bond-orientational orders and symmetry functions (originally proposed to fit ML interatomic potentials and recently gained success in featurizing disordered materials). We also include our recently proposed highly interpretable and generalizable distance/area/volume interstice distribution features in amlearn (see A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses. Qi Wang and Anubhav Jain. Nature Communications 10, 5537 (2019)).

In amlearn, We integrate Fortran90 with Python (using f2py) to achieve combination of the flexibility and fast-computation (>10x times faster than pure Python) of features. Please refer to the SRO and MRO feature representations in amlearn.featurize. We also include an IntersticeDistribution class as a site featurizer in matminer, a comprehensive Python library for ML in materials science.

amlearn

 

Installation

Before installing amlearn, please install numpy (version 1.7.0 or greater) first.

We recommend to use the conda install.

sh conda install numpy

or you can find numpy installation guide from Numpy installation instructions.

Then, you can install amlearn. There are two ways to install amlearn:

Install amlearn from PyPI (recommended):

sh pip install amlearn

Alternatively: install amlearn from the GitHub source:

First, clone amlearn using git:

sh git clone https://github.com/Qi-max/amlearn

Then, cd to the amlearn folder and run the setup.py:

sh cd amlearn sudo python setup.py install

References

Qi Wang and Anubhav Jain. A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses. Nature Communications 10, 5537 (2019). doi:10.1038/s41467-019-13511-9

Owner

  • Name: Qi Wang
  • Login: Qi-max
  • Kind: user
  • Location: Berkeley, CA
  • Company: Lawrence Berkeley National Lab

GitHub Events

Total
  • Fork event: 2
Last Year
  • Fork event: 2

Committers

Last synced: almost 3 years ago

All Time
  • Total Commits: 196
  • Total Committers: 2
  • Avg Commits per committer: 98.0
  • Development Distribution Score (DDS): 0.031
Top Committers
Name Email Commits
Qi-max w****1@g****m 190
Qi Wang 3****x@u****m 6

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 2
  • Total pull requests: 0
  • Average time to close issues: 11 months
  • 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
View more stats
Top Authors
Issue Authors
  • Qi-max (2)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 79 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 13
  • Total maintainers: 1
pypi.org: amlearn

Machine Learning package for amorphous materials.

  • Versions: 13
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 79 Last month
Rankings
Dependent packages count: 10.1%
Forks count: 13.3%
Stargazers count: 14.6%
Average: 16.4%
Dependent repos count: 21.5%
Downloads: 22.7%
Maintainers (1)
Qi-max
Last synced: 6 months ago

Dependencies

setup.py pypi
  • imbalanced-learn ==0.5.0
  • lockfile >=0.12.2
  • numpy >=1.7.0
  • pandas >=0.20.2
  • scikit-learn >=0.22.0
  • scipy >=0.19.0
  • six >=1.10.0
  • tqdm >=4.11.2