| Name | qmllib JSON |
| Version |
1.1.5
JSON |
| download |
| home_page | None |
| Summary | Python/Fortran toolkit for representation of molecules and solids for machine learning of properties of molecules and solids. |
| upload_time | 2024-11-12 18:52:20 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | None |
| keywords |
qml
quantum chemistry
machine learning
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
===============
What is qmllib?
===============
``qmllib`` is a Python/Fortran toolkit for representation of molecules and solids
for machine learning of properties of molecules and solids. The library is not
a high-level framework where you can do ``model.train()``, but supplies the
building blocks to carry out efficient and accurate machine learning. As such,
the goal is to provide usable and efficient implementations of concepts such as
representations and kernels.
==============
QML or qmllib?
==============
``qmllib`` represents the core library functionality derived from the original
QML package, providing a powerful toolkit for quantum machine learning
applications, but without the high-level abstraction, for example SKLearn.
This package is and should stay free-function design oriented.
If you are moving from ``qml`` to ``qmllib``, note that there are breaking
changes to the interface to make it more consistent with both argument orders
and function naming.
==============
How to install
==============
You need a fortran compiler and math library. Default is `gfortran` and `openblas`.
.. code-block:: bash
sudo apt install libopenblas-dev gcc
You can install it via PyPi
.. code-block:: bash
pip install qmllib
or directly from github
.. code-block:: bash
pip install git+https://github.com/qmlcode/qmllib
or if you want a specific feature branch
.. code-block:: bash
pip install git+https://github.com/qmlcode/qmllib@feature_branch
=================
How to contribute
=================
Know a issue and want to get started developing? Fork it, clone it, make it , test it.
.. code-block:: bash
git clone your_repo qmllib.git
cd qmllib.git
make # setup env
make compile # compile
You know have a conda environment in `./env` and are ready to run
.. code-block:: bash
make test
happy developing
==========
How to use
==========
Notebook examples are coming. For now, see test files in ``tests/*``.
===========
How to cite
===========
Please cite the representation that you are using accordingly.
- **Implementation**
Toolkit for Quantum Chemistry Machine Learning,
https://github.com/qmlcode/qmllib, <version or git commit>
- **FCHL19** ``generate_fchl19``
FCHL revisited: Faster and more accurate quantum machine learning,
Christensen, Bratholm, Faber, Lilienfeld,
J. Chem. Phys. 152, 044107 (2020),
https://doi.org/10.1063/1.5126701
- **FCHL18** ``generate_fchl18``
Alchemical and structural distribution based representation for universal quantum machine learning,
Faber, Christensen, Huang, Lilienfeld,
J. Chem. Phys. 148, 241717 (2018),
https://doi.org/10.1063/1.5020710
- **Columb Matrix** ``generate_columnb_matrix_*``
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning,
Rupp, Tkatchenko, Müller, Lilienfeld,
Phys. Rev. Lett. 108, 058301 (2012)
DOI: https://doi.org/10.1103/PhysRevLett.108.058301
- **Bag of Bonds (BoB)** ``generate_bob``
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies,
Hansen, Montavon, Biegler, Fazli, Rupp, Scheffler, Lilienfeld, Tkatchenko, Müller,
J. Chem. Theory Comput. 2013, 9, 8, 3404–3419
https://doi.org/10.1021/ct400195d
- **SLATM** ``generate_slatm``
Understanding molecular representations in machine learning: The role of uniqueness and target similarity,
Huang, Lilienfeld,
J. Chem. Phys. 145, 161102 (2016)
https://doi.org/10.1063/1.4964627
- **ACSF** ``generate_acsf``
Atom-centered symmetry functions for constructing high-dimensional neural network potentials,
Behler,
J Chem Phys 21;134(7):074106 (2011)
https://doi.org/10.1063/1.3553717
- **AARAD** ``generate_aarad``
Alchemical and structural distribution based representation for universal quantum machine learning,
Faber, Christensen, Huang, Lilienfeld,
J. Chem. Phys. 148, 241717 (2018),
https://doi.org/10.1063/1.5020710
===================
What is left to do?
===================
- Compile based on ``FCC`` env variable
- if ``ifort`` find the right flags
- Find MKL from env (for example conda)
- Find what numpy has been linked too (lapack or mkl)
- Notebook examples
Raw data
{
"_id": null,
"home_page": null,
"name": "qmllib",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "qml, quantum chemistry, machine learning",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/be/68/41b1554affcb70fafc5d0871829f2f2f2fdc8ea68e0595912e530b2442ce/qmllib-1.1.5.tar.gz",
"platform": null,
"description": "===============\nWhat is qmllib?\n===============\n\n``qmllib`` is a Python/Fortran toolkit for representation of molecules and solids\nfor machine learning of properties of molecules and solids. The library is not\na high-level framework where you can do ``model.train()``, but supplies the\nbuilding blocks to carry out efficient and accurate machine learning. As such,\nthe goal is to provide usable and efficient implementations of concepts such as\nrepresentations and kernels.\n\n==============\nQML or qmllib?\n==============\n\n``qmllib`` represents the core library functionality derived from the original\nQML package, providing a powerful toolkit for quantum machine learning\napplications, but without the high-level abstraction, for example SKLearn.\n\nThis package is and should stay free-function design oriented.\n\nIf you are moving from ``qml`` to ``qmllib``, note that there are breaking\nchanges to the interface to make it more consistent with both argument orders\nand function naming.\n\n\n==============\nHow to install\n==============\n\nYou need a fortran compiler and math library. Default is `gfortran` and `openblas`.\n\n\n.. code-block:: bash\n\n sudo apt install libopenblas-dev gcc\n\nYou can install it via PyPi\n\n.. code-block:: bash\n\n pip install qmllib\n\nor directly from github\n\n.. code-block:: bash\n\n pip install git+https://github.com/qmlcode/qmllib\n\nor if you want a specific feature branch\n\n.. code-block:: bash\n\n pip install git+https://github.com/qmlcode/qmllib@feature_branch\n\n\n=================\nHow to contribute\n=================\n\nKnow a issue and want to get started developing? Fork it, clone it, make it , test it.\n\n.. code-block:: bash\n\n git clone your_repo qmllib.git\n cd qmllib.git\n make # setup env\n make compile # compile\n\nYou know have a conda environment in `./env` and are ready to run\n\n.. code-block:: bash\n\n make test\n\nhappy developing\n\n\n==========\nHow to use\n==========\n\nNotebook examples are coming. For now, see test files in ``tests/*``.\n\n===========\nHow to cite\n===========\n\nPlease cite the representation that you are using accordingly.\n\n- **Implementation**\n\n Toolkit for Quantum Chemistry Machine Learning,\n https://github.com/qmlcode/qmllib, <version or git commit>\n\n- **FCHL19** ``generate_fchl19``\n\n FCHL revisited: Faster and more accurate quantum machine learning,\n Christensen, Bratholm, Faber, Lilienfeld,\n J. Chem. Phys. 152, 044107 (2020),\n https://doi.org/10.1063/1.5126701\n\n- **FCHL18** ``generate_fchl18``\n\n Alchemical and structural distribution based representation for universal quantum machine learning,\n Faber, Christensen, Huang, Lilienfeld,\n J. Chem. Phys. 148, 241717 (2018),\n https://doi.org/10.1063/1.5020710\n\n- **Columb Matrix** ``generate_columnb_matrix_*``\n\n Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning,\n Rupp, Tkatchenko, M\u00fcller, Lilienfeld,\n Phys. Rev. Lett. 108, 058301 (2012)\n DOI: https://doi.org/10.1103/PhysRevLett.108.058301\n\n- **Bag of Bonds (BoB)** ``generate_bob``\n\n Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies,\n Hansen, Montavon, Biegler, Fazli, Rupp, Scheffler, Lilienfeld, Tkatchenko, M\u00fcller,\n J. Chem. Theory Comput. 2013, 9, 8, 3404\u20133419\n https://doi.org/10.1021/ct400195d\n\n- **SLATM** ``generate_slatm``\n\n Understanding molecular representations in machine learning: The role of uniqueness and target similarity,\n Huang, Lilienfeld,\n J. Chem. Phys. 145, 161102 (2016)\n https://doi.org/10.1063/1.4964627\n\n- **ACSF** ``generate_acsf``\n\n Atom-centered symmetry functions for constructing high-dimensional neural network potentials,\n Behler,\n J Chem Phys 21;134(7):074106 (2011)\n https://doi.org/10.1063/1.3553717\n\n- **AARAD** ``generate_aarad``\n\n Alchemical and structural distribution based representation for universal quantum machine learning,\n Faber, Christensen, Huang, Lilienfeld,\n J. Chem. Phys. 148, 241717 (2018),\n https://doi.org/10.1063/1.5020710\n\n\n===================\nWhat is left to do?\n===================\n\n- Compile based on ``FCC`` env variable\n- if ``ifort`` find the right flags\n- Find MKL from env (for example conda)\n- Find what numpy has been linked too (lapack or mkl)\n- Notebook examples\n",
"bugtrack_url": null,
"license": null,
"summary": "Python/Fortran toolkit for representation of molecules and solids for machine learning of properties of molecules and solids.",
"version": "1.1.5",
"project_urls": {
"Homepage": "https://qmlcode.org"
},
"split_keywords": [
"qml",
" quantum chemistry",
" machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "be6841b1554affcb70fafc5d0871829f2f2f2fdc8ea68e0595912e530b2442ce",
"md5": "92fb97c55dd90098eb642a017e076df2",
"sha256": "7e605d984c112bbad574f691d47ca1ff5371be2307fe64419f618525c7e7413d"
},
"downloads": -1,
"filename": "qmllib-1.1.5.tar.gz",
"has_sig": false,
"md5_digest": "92fb97c55dd90098eb642a017e076df2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 99151,
"upload_time": "2024-11-12T18:52:20",
"upload_time_iso_8601": "2024-11-12T18:52:20.441635Z",
"url": "https://files.pythonhosted.org/packages/be/68/41b1554affcb70fafc5d0871829f2f2f2fdc8ea68e0595912e530b2442ce/qmllib-1.1.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-12 18:52:20",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "qmllib"
}
