https://github.com/suncat-center/catlearn

A machine learning environment for atomic-scale modeling in surface science and catalysis.

Science Score: 33.0%

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: arxiv.org, aps.org, zenodo.org
✓
Committers with academic emails
4 of 20 committers (20.0%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (19.9%) to scientific vocabulary

Keywords

atomistic-machine-learning catalysis catalyst computational-chemistry machine-learning materials-informatics materials-science nanotechnology python

Keywords from Contributors

chemical-kinetics catalysis-informatics chemical-engineering chemical-reaction-networks combinatorics

Last synced: 5 months ago · JSON representation

Repository

A machine learning environment for atomic-scale modeling in surface science and catalysis.

Basic Info

Host: GitHub
Owner: SUNCAT-Center
License: gpl-3.0
Language: Python
Default Branch: master
Homepage: http://catlearn.readthedocs.io/
Size: 89.9 MB

Statistics

Stars: 114
Watchers: 18
Forks: 67
Open Issues: 11
Releases: 8

Topics

atomistic-machine-learning catalysis catalyst computational-chemistry machine-learning materials-informatics materials-science nanotechnology python

Created almost 8 years ago · Last pushed over 1 year ago

Metadata Files

Readme Changelog Contributing License Code of conduct

CatLearn

An environment for atomistic machine learning in Python for applications in catalysis.

In general, any data prepared in this fashion can be fed to the GP routines, a number of additional functions have been added that interface with ASE. This integration allows for the manipulation of atoms objects through GP predictions, as well as dynamic generation of descriptors through use of the many ASE functions.

CatLearn also includes the MLNEB algorithm for efficient transition state search, and the MLMIN algorithm for efficient atomic structure optimization.

Please see the tutorials for a detailed overview of what the code can do and the conventions used in setting up the predictive models. For an overview of all the functionality available, please read the documentation.

Installation
Tutorials
Usage
Functionality
How to cite
Contribution

Installation

(Back to top)

The easiest way to install the code is with:

shell $ pip install catlearn

This will automatically install the code as well as the dependencies.

Installation without dependencies

(Back to top)

If you want to install catlearn without dependencies, you can do:

shell $ pip install catlearn --no-deps

MLMIN and MLNEB will not need anything apart from ASE 3.17.0 or newer to run, but there are other parts of the code, which need the dependencies listed in requirements.txt

Developer installation

shell $ git clone https://github.com/SUNCAT-Center/CatLearn.git

And then put the <install_dir>/ into your $PYTHONPATH environment variable.

You can install dependencies in with:

shell $ pip install -r requirements.txt

Docker

To use the docker image, it is necessary to have docker installed and running. After cloning the project, build and run the image as follows:

shell $ docker build -t catlearn .

Then it is possible to use the image in two ways. It is possible to run the docker image as a bash environment in which CatLearn can be used will all dependencies in place.

shell $ docker run -it catlearn bash

Or python can be run from the docker image.

shell $ docker run -it catlearn python2 [file.py] $ docker run -it catlearn python3 [file.py]

Use Ctrl + d to exit the docker image when done.

Optional Dependencies

The tutorial scripts will generally output some graphical representations of the results etc. For these scripts, it is advisable to have at least matplotlib installed:

shell $ pip install matplotlib seaborn

Tutorials

(Back to top)

Helpful examples and test scripts are present in tutorials.

Usage

(Back to top)

Set up CatLearn's Gaussian Process model and make some predictions using the following lines of code:

```python import numpy as np from catlearn.regression import GaussianProcess

Define some input data.

trainfeatures = np.arange(200).reshape(50, 4) target = np.random.randomsample((50,)) test_features = np.arange(100).reshape(25, 4)

Setup the kernel.

kernel = [{'type': 'gaussian', 'width': 0.5}]

Train the GP model.

gp = GaussianProcess(kernellist=kernel, regularization=1e-3, trainfp=trainfeatures, traintarget=target, optimize_hyperparameters=True)

Get the predictions.

prediction = gp.predict(testfp=testfeatures) ```

Functionality

(Back to top)

There is much functionality in CatLearn to assist in handling atom data and building optimal models. This includes:

API to other codes:
- Atomic simulation environment API
- Magpie API
- NetworkX API
Fingerprint generators:
- Bulk systems
- Support/slab systems
- Discrete systems
Preprocessing routines:
- Data cleaning
- Feature elimination
- Feature engineering
- Feature extraction
- Feature scaling
Regression methods:
- Regularized ridge regression
- Gaussian processes regression
Cross-validation:
- K-fold cv
- Ensemble k-fold cv
Machine Learning Algorithms
- Machine Learning Nudged Elastic Band (ML-NEB) algorithm.
General utilities:
- K-means clustering
- Neighborlist generators
- Penalty functions
- SQLite db storage

How to cite CatLearn

(Back to top)

If you find CatLearn useful in your research, please cite

1) M. H. Hansen, J. A. Garrido Torres, P. C. Jennings, 
   Z. Wang, J. R. Boes, O. G. Mamun and T. Bligaard.
   An Atomistic Machine Learning Package for Surface Science and Catalysis.
   https://arxiv.org/abs/1904.00904

If you use CatLearn's ML-NEB module, please cite:

2) J. A. Garrido Torres, M. H. Hansen, P. C. Jennings,
   J. R. Boes and T. Bligaard. Phys. Rev. Lett. 122, 156001.
   https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.122.156001

Contribution

(Back to top)

Anyone is welcome to contribute to the project. Please see the contribution guide for help setting up a local copy of the code. There are some TODO items in the README files for the various modules that give suggestions on parts of the code that could be improved.

Owner

Name: SUNCAT-Center
Login: SUNCAT-Center
Kind: organization

Website: http://suncat.stanford.edu/
Repositories: 9
Profile: https://github.com/SUNCAT-Center

GitHub Events

Total

Watch event: 11
Fork event: 5

Last Year

Watch event: 11
Fork event: 5

Committers

Last synced: almost 3 years ago

All Time

Total Commits: 1,580
Total Committers: 20
Avg Commits per committer: 79.0
Development Distribution Score (DDS): 0.439

Past Year

Commits: 11
Committers: 3
Avg Commits per committer: 3.667
Development Distribution Score (DDS): 0.545

Top Committers

Name	Email	Commits
Paul C. Jennings	j**c@g**m	886
mhangaard	m**d@g**m	532
Jose A Garrido Torres	j**t@s**u	82
Jacob Boes	j**s@g**m	13
schlexer	p**r@g**m	11
Jose A. Garrido Torres	3**s@u**m	9
Raul Flores	r**2@g**m	7
Andrew Doyle	a**5@g**m	6
Martin Hangaard Hansen	h**d@s**u	6
Martin Hangaard Hansen	m**n@t**m	5
Ziyun Wang	z**g@l**m	5
Vladilsav Ivanistsev	5**v@u**m	4
Max Hoffmann	m**n@g**m	3
Vieri Wijaya	5**6@u**m	2
Igor Kowalec	5**c@u**m	2
dependabot[bot]	4**]@u**m	2
Markus Ekvall	m**l@d**u	2
Markus Ekvall	m**l@M**l	1
mamunm	m**m@s**u	1
Jiang Li	4**t@u**m	1

Committer Domains (Top 20 + Academic)

stanford.edu: 3 dhcp-visitor-enr-116-223.slac.stanford.edu: 1 topsoe.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 26
Total pull requests: 77
Average time to close issues: 5 months
Average time to close pull requests: about 1 month
Total issue authors: 15
Total pull request authors: 14
Average comments per issue: 1.65
Average comments per pull request: 1.18
Merged pull requests: 68
Bot issues: 0
Bot pull requests: 3

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

pcjennings (5)
mhangaard (4)
jagarridotorres (3)
kimrojas (2)
mhoffman (2)
mustafaalsalmi1999 (1)
jan-janssen (1)
keeeto (1)
zyt0y (1)
schumannj (1)
ehermes (1)
vieri2006 (1)
ssyrnyk (1)
lixinyuu (1)
raulf2012 (1)

Pull Request Authors

mhangaard (37)
pcjennings (13)
jagarridotorres (6)
schlexer (3)
dependabot[bot] (3)
mamunm (2)
vladislavivanistsev (2)
jianglst (2)
Sudo-Raheel (2)
vieri2006 (2)
mhoffman (2)
raulf2012 (2)
jboes (1)
ikowalec (1)

Top Labels

Issue Labels

enhancement (5) bug (3) help wanted (2)

Pull Request Labels

enhancement (4) dependencies (3) bug (1) duplicate (1)

Packages

Total packages: 2
Total downloads:
- pypi 127 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 1
(may contain duplicates)
Total versions: 28
Total maintainers: 3

pypi.org: catlearn

Machine Learning using atomic-scale calculations.

Homepage: https://github.com/SUNCAT-Center/CatLearn
Documentation: https://catlearn.readthedocs.io/
License: GPL-3.0
Latest release: 0.6.2
published almost 6 years ago

Versions: 25
Dependent Packages: 0
Dependent Repositories: 1
Downloads: 127 Last month

Rankings

Forks count: 5.5%

Stargazers count: 7.3%

Dependent packages count: 10.0%

Average: 11.4%

Downloads: 12.5%

Dependent repos count: 21.7%

Maintainers (3)

jagarridotorres mhangaard pauljennings

Last synced: 6 months ago

conda-forge.org: catlearn

Utilities for building and testing atomic machine learning models. Gaussian Processes (GP) regression machine learning routines are implemented. These will take any numpy array of training and test feature matrices along with a vector of target values. In general, any data prepared in this fashion can be fed to the GP routines, a number of additional functions have been added that interface with ASE. This integration allows for the manipulation of atoms objects through GP predictions, as well as dynamic generation of descriptors through use of the many ASE functions.

Homepage: https://github.com/SUNCAT-Center/CatLearn
License: GPL-3.0
Latest release: 0.6.2
published almost 6 years ago

Versions: 3
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Forks count: 22.8%

Stargazers count: 32.3%

Dependent repos count: 34.0%

Average: 35.1%

Dependent packages count: 51.2%

Last synced: 6 months ago

Dependencies

Pipfile pypi

gpflow * develop
matplotlib * develop
piprot * develop
pyinstrument * develop
pytest-cov * develop
recommonmark * develop
seaborn * develop
setuptools * develop
sphinx * develop
sphinx-autobuild * develop
sphinx-rtd-theme * develop
sphinxcontrib-napoleon * develop
sty ==1.0.0b6 develop
twine * develop
ase >=3.17.0
h5py >=2.7.1
networkx >=2.1.0
numpy >=1.14.3
pandas >=0.23.0
scikit-learn >=0.19.1
scipy >=1.1.0
tqdm *

Pipfile.lock pypi

alabaster ==0.7.10 develop
argh ==0.26.2 develop
attrs ==18.1.0 develop
babel ==2.5.3 develop
certifi ==2018.4.16 develop
chardet ==3.0.4 develop
commonmark ==0.5.4 develop
coverage ==4.5.1 develop
cycler ==0.10.0 develop
docutils ==0.14 develop
gpflow ==1.1.1 develop
idna ==2.6 develop
imagesize ==1.0.0 develop
jinja2 >=2.10.1 develop
kiwisolver ==1.0.1 develop
livereload ==2.5.2 develop
markupsafe ==1.0 develop
matplotlib ==2.2.2 develop
more-itertools ==4.1.0 develop
multipledispatch ==0.5.0 develop
numpy ==1.14.3 develop
packaging ==17.1 develop
pandas ==0.23.0 develop
pathtools ==0.1.2 develop
piprot ==0.9.10 develop
pkginfo ==1.4.2 develop
pluggy ==0.6.0 develop
pockets ==0.6.2 develop
port-for ==0.3.1 develop
py ==1.5.3 develop
pygments ==2.2.0 develop
pyinstrument ==2.0.2 develop
pyinstrument-cext ==0.1.6 develop
pyparsing ==2.2.0 develop
pytest ==3.5.1 develop
pytest-cov ==2.5.1 develop
python-dateutil ==2.7.3 develop
pytz ==2018.4 develop
pyyaml >=4.2b1 develop
recommonmark ==0.4.0 develop
requests >=2.20.0 develop
requests-futures ==0.9.7 develop
requests-toolbelt ==0.8.0 develop
scipy ==1.1.0 develop
seaborn ==0.8.1 develop
six ==1.11.0 develop
snowballstemmer ==1.2.1 develop
sphinx ==1.7.4 develop
sphinx-autobuild ==0.7.1 develop
sphinx-rtd-theme ==0.3.1 develop
sphinxcontrib-napoleon ==0.6.1 develop
sphinxcontrib-websupport ==1.0.1 develop
sty ==1.0.0b6 develop
tornado ==5.0.2 develop
tqdm ==4.23.3 develop
twine ==1.11.0 develop
urllib3 >=1.23 develop
watchdog ==0.8.3 develop
ase ==3.16.0
click ==6.7
cycler ==0.10.0
decorator ==4.3.0
flask ==1.0.2
h5py ==2.7.1
itsdangerous ==0.24
jinja2 >=2.10.1
kiwisolver ==1.0.1
markupsafe ==1.0
matplotlib ==2.2.2
networkx ==2.1.0
numpy ==1.14.3
pandas ==0.23.0
pyparsing ==2.2.0
python-dateutil ==2.7.3
pytz ==2018.4
scikit-learn ==0.19.1
scipy ==1.1.0
six ==1.11.0
tqdm ==4.23.3
werkzeug >=0.15.3

requirements.txt pypi

ase >=3.17.0
click >=6.7
cycler >=0.10.0
decorator >=4.3.0
flask >=1.0.2
h5py >=2.7.1
itsdangerous >=0.24
jinja2 >=2.10
kiwisolver >=1.0.1
markupsafe >=1.0
networkx >=2.1.0
numpy >=1.14.3
pandas >=0.24.0
psutil >=5.4.3
pyparsing >=2.2.0
python-dateutil >=2.7.3
pytz >=2018.4
scikit-learn >=0.19.1
scipy >=1.1.0
six >=1.11.0
tqdm >=4.23.3
werkzeug >=0.14.1

Dockerfile docker

jenningspc/catlearn latest build

setup/Dockerfile docker

ubuntu latest build

https://github.com/suncat-center/catlearn

Science Score: 33.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

CatLearn

Table of contents

Installation

Installation without dependencies

Developer installation

Docker

Optional Dependencies

Tutorials

Usage

Define some input data.

Setup the kernel.

Train the GP model.

Get the predictions.

Functionality

How to cite CatLearn

Contribution

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: catlearn

Rankings

Maintainers (3)

conda-forge.org: catlearn

Rankings

Dependencies