extract-clusters-step 2026.9.17__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- extract_clusters_step-2026.9.17/AUTHORS.rst +5 -0
- extract_clusters_step-2026.9.17/CONTRIBUTING.rst +113 -0
- extract_clusters_step-2026.9.17/HISTORY.rst +19 -0
- extract_clusters_step-2026.9.17/LICENSE +31 -0
- extract_clusters_step-2026.9.17/MANIFEST.in +14 -0
- extract_clusters_step-2026.9.17/PKG-INFO +142 -0
- extract_clusters_step-2026.9.17/README.rst +76 -0
- extract_clusters_step-2026.9.17/docs/Makefile +177 -0
- extract_clusters_step-2026.9.17/docs/authors.rst +1 -0
- extract_clusters_step-2026.9.17/docs/conf.py +276 -0
- extract_clusters_step-2026.9.17/docs/contributing.rst +1 -0
- extract_clusters_step-2026.9.17/docs/developer/campaigns/2026-09-17/index.rst +91 -0
- extract_clusters_step-2026.9.17/docs/developer/index.rst +32 -0
- extract_clusters_step-2026.9.17/docs/history.rst +1 -0
- extract_clusters_step-2026.9.17/docs/index.rst +29 -0
- extract_clusters_step-2026.9.17/docs/installation.rst +51 -0
- extract_clusters_step-2026.9.17/docs/make.bat +242 -0
- extract_clusters_step-2026.9.17/docs/readme.rst +1 -0
- extract_clusters_step-2026.9.17/docs/usage.rst +7 -0
- extract_clusters_step-2026.9.17/docs/user/index.rst +76 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/__init__.py +37 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/_version.py +21 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/cluster_sampling.py +638 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/data/properties.csv +8 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/data/references.bib +40 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/extract_clusters.py +508 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/extract_clusters_parameters.py +280 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/extract_clusters_step.py +100 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/metadata.py +12 -0
- extract_clusters_step-2026.9.17/extract_clusters_step/tk_extract_clusters.py +345 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/PKG-INFO +142 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/SOURCES.txt +47 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/dependency_links.txt +1 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/entry_points.txt +5 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/requires.txt +6 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/top_level.txt +1 -0
- extract_clusters_step-2026.9.17/extract_clusters_step.egg-info/zip-safe +1 -0
- extract_clusters_step-2026.9.17/requirements.txt +6 -0
- extract_clusters_step-2026.9.17/requirements_dev.txt +10 -0
- extract_clusters_step-2026.9.17/requirements_install.txt +7 -0
- extract_clusters_step-2026.9.17/setup.cfg +27 -0
- extract_clusters_step-2026.9.17/setup.py +87 -0
- extract_clusters_step-2026.9.17/tests/__init__.py +3 -0
- extract_clusters_step-2026.9.17/tests/conftest.py +90 -0
- extract_clusters_step-2026.9.17/tests/test_cluster_sampling.py +126 -0
- extract_clusters_step-2026.9.17/tests/test_extract_clusters_step.py +78 -0
- extract_clusters_step-2026.9.17/tests/test_extract_nmers.py +256 -0
- extract_clusters_step-2026.9.17/versioneer.py +1883 -0
|
@@ -0,0 +1,113 @@
|
|
|
1
|
+
.. highlight:: shell
|
|
2
|
+
|
|
3
|
+
============
|
|
4
|
+
Contributing
|
|
5
|
+
============
|
|
6
|
+
|
|
7
|
+
Contributions are welcome, and they are greatly appreciated! Every
|
|
8
|
+
little bit helps, and credit will always be given.
|
|
9
|
+
|
|
10
|
+
You can contribute in many ways:
|
|
11
|
+
|
|
12
|
+
Types of Contributions
|
|
13
|
+
----------------------
|
|
14
|
+
|
|
15
|
+
Report Bugs
|
|
16
|
+
~~~~~~~~~~~
|
|
17
|
+
|
|
18
|
+
Report bugs at https://github.com/molssi-seamm/extract_clusters_step/issues.
|
|
19
|
+
|
|
20
|
+
If you are reporting a bug, please include:
|
|
21
|
+
|
|
22
|
+
* Your operating system name and version.
|
|
23
|
+
* Any details about your local setup that might be helpful in troubleshooting.
|
|
24
|
+
* Detailed steps to reproduce the bug.
|
|
25
|
+
|
|
26
|
+
Fix Bugs
|
|
27
|
+
~~~~~~~~
|
|
28
|
+
|
|
29
|
+
Look through the GitHub issues for bugs. Anything tagged with "bug"
|
|
30
|
+
and "help wanted" is open to whoever wants to implement it.
|
|
31
|
+
|
|
32
|
+
Implement Features
|
|
33
|
+
~~~~~~~~~~~~~~~~~~
|
|
34
|
+
|
|
35
|
+
Look through the GitHub issues for features. Anything tagged with "enhancement"
|
|
36
|
+
and "help wanted" is open to whoever wants to implement it.
|
|
37
|
+
|
|
38
|
+
Write Documentation
|
|
39
|
+
~~~~~~~~~~~~~~~~~~~
|
|
40
|
+
|
|
41
|
+
Extract Clusters Step could always use more documentation, whether as part of the
|
|
42
|
+
official Extract Clusters Step docs, in docstrings, or even on the web in blog posts,
|
|
43
|
+
articles, and such.
|
|
44
|
+
|
|
45
|
+
Submit Feedback
|
|
46
|
+
~~~~~~~~~~~~~~~
|
|
47
|
+
|
|
48
|
+
The best way to send feedback is to file an issue at https://github.com/molssi-seamm/extract_clusters_step/issues.
|
|
49
|
+
|
|
50
|
+
If you are proposing a feature:
|
|
51
|
+
|
|
52
|
+
* Explain in detail how it would work.
|
|
53
|
+
* Keep the scope as narrow as possible, to make it easier to implement.
|
|
54
|
+
* Remember that this is a volunteer-driven project, and that contributions
|
|
55
|
+
are welcome :)
|
|
56
|
+
|
|
57
|
+
Get Started!
|
|
58
|
+
------------
|
|
59
|
+
|
|
60
|
+
Ready to contribute? Here's how to set up `extract_clusters_step` for local development.
|
|
61
|
+
|
|
62
|
+
1. Fork the `extract_clusters_step` repo on GitHub.
|
|
63
|
+
2. Clone your fork locally::
|
|
64
|
+
|
|
65
|
+
$ git clone git@github.com:your_name_here/extract_clusters_step.git
|
|
66
|
+
|
|
67
|
+
3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development::
|
|
68
|
+
|
|
69
|
+
$ mkvirtualenv extract_clusters_step
|
|
70
|
+
$ cd extract_clusters_step/
|
|
71
|
+
$ python setup.py develop
|
|
72
|
+
|
|
73
|
+
4. Create a branch for local development::
|
|
74
|
+
|
|
75
|
+
$ git checkout -b name-of-your-bugfix-or-feature
|
|
76
|
+
|
|
77
|
+
Now you can make your changes locally.
|
|
78
|
+
|
|
79
|
+
5. When you're done making changes, check that your changes pass flake8 and the tests, including testing other Python versions with tox::
|
|
80
|
+
|
|
81
|
+
$ flake8 extract_clusters_step tests
|
|
82
|
+
$ python setup.py test or py.test
|
|
83
|
+
$ tox
|
|
84
|
+
|
|
85
|
+
To get flake8 and tox, just pip install them into your virtualenv.
|
|
86
|
+
|
|
87
|
+
6. Commit your changes and push your branch to GitHub::
|
|
88
|
+
|
|
89
|
+
$ git add .
|
|
90
|
+
$ git commit -m "Your detailed description of your changes."
|
|
91
|
+
$ git push origin name-of-your-bugfix-or-feature
|
|
92
|
+
|
|
93
|
+
7. Submit a pull request through the GitHub website.
|
|
94
|
+
|
|
95
|
+
Pull Request Guidelines
|
|
96
|
+
-----------------------
|
|
97
|
+
|
|
98
|
+
Before you submit a pull request, check that it meets these guidelines:
|
|
99
|
+
|
|
100
|
+
1. The pull request should include tests.
|
|
101
|
+
2. If the pull request adds functionality, the docs should be updated. Put
|
|
102
|
+
your new functionality into a function with a docstring, and add the
|
|
103
|
+
feature to the list in README.rst.
|
|
104
|
+
3. The pull request should work for Python 2.6, 2.7, 3.3, 3.4 and 3.5, and for PyPy. Check
|
|
105
|
+
https://travis-ci.org/molssi-seamm/extract_clusters_step/pull_requests
|
|
106
|
+
and make sure that the tests pass for all supported Python versions.
|
|
107
|
+
|
|
108
|
+
Tips
|
|
109
|
+
----
|
|
110
|
+
|
|
111
|
+
To run a subset of tests::
|
|
112
|
+
|
|
113
|
+
$ py.test tests.test_extract_clusters_step
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
=======
|
|
2
|
+
History
|
|
3
|
+
=======
|
|
4
|
+
2026.9.17 -- Initial release of the Extract Clusters step
|
|
5
|
+
* Extracts n-molecule clusters (trimers, tetramers, ... larger n-mers) from the
|
|
6
|
+
current, typically periodic, condensed-phase configuration as unwrapped,
|
|
7
|
+
centred, non-periodic configurations in a new system, e.g. many-body training
|
|
8
|
+
data and diagnostics for machine-learned force fields.
|
|
9
|
+
* Clusters are connected subgraphs of a molecular contact graph (molecules are in
|
|
10
|
+
contact if their contact atoms are within a cutoff, minimum image), so chains,
|
|
11
|
+
rings and stars all occur; several sizes can be extracted from one frame.
|
|
12
|
+
* Optional stratification so the set is flat in the radius of gyration or the
|
|
13
|
+
largest centroid separation, with bin edges from equal quantiles of a pilot
|
|
14
|
+
sample or given explicitly, and optional balancing over the contact-graph
|
|
15
|
+
motif.
|
|
16
|
+
* Provenance on every cluster: unique names ``<frame>_<seed>_<molecules>`` and
|
|
17
|
+
``#ExtractClusters#scan`` properties (size, spread, motif, contacts, bin,
|
|
18
|
+
source molecules) that survive SDF/extxyz export, plus a ``clusters.csv`` per
|
|
19
|
+
step.
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
|
|
2
|
+
BSD 3-Clause License
|
|
3
|
+
|
|
4
|
+
Copyright (c) 2026, Paul Saxe
|
|
5
|
+
All rights reserved.
|
|
6
|
+
|
|
7
|
+
Redistribution and use in source and binary forms, with or without
|
|
8
|
+
modification, are permitted provided that the following conditions are met:
|
|
9
|
+
|
|
10
|
+
1. Redistributions of source code must retain the above copyright notice, this
|
|
11
|
+
list of conditions and the following disclaimer.
|
|
12
|
+
|
|
13
|
+
2. Redistributions in binary form must reproduce the above copyright notice,
|
|
14
|
+
this list of conditions and the following disclaimer in the documentation
|
|
15
|
+
and/or other materials provided with the distribution.
|
|
16
|
+
|
|
17
|
+
3. Neither the name of the copyright holder nor the names of its
|
|
18
|
+
contributors may be used to endorse or promote products derived from
|
|
19
|
+
this software without specific prior written permission.
|
|
20
|
+
|
|
21
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
22
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
23
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
24
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
25
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
26
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
27
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
28
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
29
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
30
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
31
|
+
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
include AUTHORS.rst
|
|
2
|
+
include CONTRIBUTING.rst
|
|
3
|
+
include HISTORY.rst
|
|
4
|
+
include LICENSE
|
|
5
|
+
include README.rst
|
|
6
|
+
include requirements*
|
|
7
|
+
include versioneer.py
|
|
8
|
+
|
|
9
|
+
recursive-include extract_clusters_step/data *
|
|
10
|
+
recursive-include tests *
|
|
11
|
+
recursive-include docs *.rst conf.py Makefile make.bat *.jpg *.png *.gif
|
|
12
|
+
|
|
13
|
+
recursive-exclude * __pycache__
|
|
14
|
+
recursive-exclude * *.py[co]
|
|
@@ -0,0 +1,142 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: extract_clusters_step
|
|
3
|
+
Version: 2026.9.17
|
|
4
|
+
Summary: A SEAMM plugin for A SEAMM plug-in for extracting molecular clusters from a periodic cell of molecules
|
|
5
|
+
Home-page: https://github.com/molssi-seamm/extract_clusters_step
|
|
6
|
+
Author: Paul Saxe
|
|
7
|
+
Author-email: psaxe@molssi.org
|
|
8
|
+
License: BSD-3-Clause
|
|
9
|
+
Keywords: SEAMM,SEAMMplugin,flowchart
|
|
10
|
+
Platform: Linux
|
|
11
|
+
Platform: Mac OS-X
|
|
12
|
+
Platform: Unix
|
|
13
|
+
Platform: Windows
|
|
14
|
+
Classifier: Environment :: Plugins
|
|
15
|
+
Classifier: Development Status :: 2 - Pre-Alpha
|
|
16
|
+
Classifier: Intended Audience :: Science/Research
|
|
17
|
+
Classifier: Topic :: Scientific/Engineering :: Chemistry
|
|
18
|
+
Classifier: Topic :: Scientific/Engineering :: Physics
|
|
19
|
+
Classifier: License :: OSI Approved :: BSD License
|
|
20
|
+
Classifier: Natural Language :: English
|
|
21
|
+
Classifier: Programming Language :: Python :: 3 :: Only
|
|
22
|
+
Classifier: Programming Language :: Python :: 3.8
|
|
23
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
24
|
+
Description-Content-Type: text/x-rst
|
|
25
|
+
License-File: LICENSE
|
|
26
|
+
License-File: AUTHORS.rst
|
|
27
|
+
Requires-Dist: molsystem
|
|
28
|
+
Requires-Dist: numpy
|
|
29
|
+
Requires-Dist: scipy
|
|
30
|
+
Requires-Dist: seamm
|
|
31
|
+
Requires-Dist: seamm-util
|
|
32
|
+
Requires-Dist: seamm-widgets
|
|
33
|
+
Dynamic: author
|
|
34
|
+
Dynamic: author-email
|
|
35
|
+
Dynamic: classifier
|
|
36
|
+
Dynamic: description
|
|
37
|
+
Dynamic: description-content-type
|
|
38
|
+
Dynamic: home-page
|
|
39
|
+
Dynamic: keywords
|
|
40
|
+
Dynamic: license
|
|
41
|
+
Dynamic: license-file
|
|
42
|
+
Dynamic: platform
|
|
43
|
+
Dynamic: requires-dist
|
|
44
|
+
Dynamic: summary
|
|
45
|
+
|
|
46
|
+
==============================
|
|
47
|
+
SEAMM Extract Clusters Plug-in
|
|
48
|
+
==============================
|
|
49
|
+
|
|
50
|
+
.. image:: https://img.shields.io/github/issues-pr-raw/molssi-seamm/extract_clusters_step
|
|
51
|
+
:target: https://github.com/molssi-seamm/extract_clusters_step/pulls
|
|
52
|
+
:alt: GitHub pull requests
|
|
53
|
+
|
|
54
|
+
.. image:: https://github.com/molssi-seamm/extract_clusters_step/workflows/CI/badge.svg
|
|
55
|
+
:target: https://github.com/molssi-seamm/extract_clusters_step/actions
|
|
56
|
+
:alt: Build Status
|
|
57
|
+
|
|
58
|
+
.. image:: https://codecov.io/gh/molssi-seamm/extract_clusters_step/branch/master/graph/badge.svg
|
|
59
|
+
:target: https://codecov.io/gh/molssi-seamm/extract_clusters_step
|
|
60
|
+
:alt: Code Coverage
|
|
61
|
+
|
|
62
|
+
.. image:: https://img.shields.io/lgtm/grade/python/g/molssi-seamm/extract_clusters_step.svg?logo=lgtm&logoWidth=18
|
|
63
|
+
:target: https://lgtm.com/projects/g/molssi-seamm/extract_clusters_step/context:python
|
|
64
|
+
:alt: Code Quality
|
|
65
|
+
|
|
66
|
+
.. image:: https://github.com/molssi-seamm/extract_clusters_step/workflows/Documentation/badge.svg
|
|
67
|
+
:target: https://molssi-seamm.github.io/extract_clusters_step/index.html
|
|
68
|
+
:alt: Documentation Status
|
|
69
|
+
|
|
70
|
+
.. image:: https://pyup.io/repos/github/molssi-seamm/extract_clusters_step/shield.svg
|
|
71
|
+
:target: https://pyup.io/repos/github/molssi-seamm/extract_clusters_step/
|
|
72
|
+
:alt: Updates for Dependencies
|
|
73
|
+
|
|
74
|
+
.. image:: https://img.shields.io/pypi/v/extract_clusters_step.svg
|
|
75
|
+
:target: https://pypi.python.org/pypi/extract_clusters_step
|
|
76
|
+
:alt: PyPi VERSION
|
|
77
|
+
|
|
78
|
+
A SEAMM plug-in for extracting molecular clusters (trimers, tetramers, ... larger
|
|
79
|
+
n-mers) from a condensed-phase, typically periodic, configuration as unwrapped,
|
|
80
|
+
non-periodic structures -- e.g. many-body training data and diagnostics for
|
|
81
|
+
machine-learned force fields.
|
|
82
|
+
|
|
83
|
+
* Free software: BSD-3-Clause
|
|
84
|
+
* Documentation: https://molssi-seamm.github.io/extract_clusters_step/index.html
|
|
85
|
+
* Code: https://github.com/molssi-seamm/extract_clusters_step
|
|
86
|
+
|
|
87
|
+
Features
|
|
88
|
+
--------
|
|
89
|
+
|
|
90
|
+
* Clusters are **connected subgraphs of a molecular contact graph** (molecules
|
|
91
|
+
are in contact if their contact atoms are within a cutoff, minimum image), so
|
|
92
|
+
chains, rings and stars all occur -- not just the most compact cluster.
|
|
93
|
+
* Any cluster size, and several sizes per frame (e.g. ``3, 4``).
|
|
94
|
+
* **Stratification** so the set is flat in a spread coordinate (radius of
|
|
95
|
+
gyration or largest centroid separation), with bin edges from equal quantiles
|
|
96
|
+
of a pilot sample or given explicitly; optional balancing over the
|
|
97
|
+
contact-graph motif.
|
|
98
|
+
* Clusters are unwrapped across the periodic boundary, centred, non-periodic,
|
|
99
|
+
with molecules and bonds intact.
|
|
100
|
+
* Provenance on every configuration: unique names
|
|
101
|
+
``<frame>_<seed>_<m1-m2-...>`` and ``#ExtractClusters#scan`` properties (size,
|
|
102
|
+
spread, motif, contacts, source molecules) that survive SDF/extxyz export;
|
|
103
|
+
a ``clusters.csv`` summary per step.
|
|
104
|
+
* Works on any cell (orthorhombic fast path via a periodic KD-tree; exact
|
|
105
|
+
minimum image otherwise) and on non-periodic sources.
|
|
106
|
+
|
|
107
|
+
Acknowledgements
|
|
108
|
+
----------------
|
|
109
|
+
|
|
110
|
+
This package was created with Cookiecutter_ and the
|
|
111
|
+
`molssi-seamm/cookiecutter-seamm-plugin`_ project template.
|
|
112
|
+
|
|
113
|
+
.. _Cookiecutter: https://github.com/audreyr/cookiecutter
|
|
114
|
+
.. _`molssi-seamm/cookiecutter-seamm-plugin`: https://github.com/molssi-seamm/cookiecutter-seamm-plugin
|
|
115
|
+
|
|
116
|
+
Developed by the Molecular Sciences Software Institute (MolSSI_),
|
|
117
|
+
which receives funding from the `National Science Foundation`_ under
|
|
118
|
+
award ACI-1547580
|
|
119
|
+
|
|
120
|
+
.. _MolSSI: https://molssi.org
|
|
121
|
+
.. _`National Science Foundation`: https://www.nsf.gov
|
|
122
|
+
|
|
123
|
+
|
|
124
|
+
=======
|
|
125
|
+
History
|
|
126
|
+
=======
|
|
127
|
+
2026.9.17 -- Initial release of the Extract Clusters step
|
|
128
|
+
* Extracts n-molecule clusters (trimers, tetramers, ... larger n-mers) from the
|
|
129
|
+
current, typically periodic, condensed-phase configuration as unwrapped,
|
|
130
|
+
centred, non-periodic configurations in a new system, e.g. many-body training
|
|
131
|
+
data and diagnostics for machine-learned force fields.
|
|
132
|
+
* Clusters are connected subgraphs of a molecular contact graph (molecules are in
|
|
133
|
+
contact if their contact atoms are within a cutoff, minimum image), so chains,
|
|
134
|
+
rings and stars all occur; several sizes can be extracted from one frame.
|
|
135
|
+
* Optional stratification so the set is flat in the radius of gyration or the
|
|
136
|
+
largest centroid separation, with bin edges from equal quantiles of a pilot
|
|
137
|
+
sample or given explicitly, and optional balancing over the contact-graph
|
|
138
|
+
motif.
|
|
139
|
+
* Provenance on every cluster: unique names ``<frame>_<seed>_<molecules>`` and
|
|
140
|
+
``#ExtractClusters#scan`` properties (size, spread, motif, contacts, bin,
|
|
141
|
+
source molecules) that survive SDF/extxyz export, plus a ``clusters.csv`` per
|
|
142
|
+
step.
|
|
@@ -0,0 +1,76 @@
|
|
|
1
|
+
==============================
|
|
2
|
+
SEAMM Extract Clusters Plug-in
|
|
3
|
+
==============================
|
|
4
|
+
|
|
5
|
+
.. image:: https://img.shields.io/github/issues-pr-raw/molssi-seamm/extract_clusters_step
|
|
6
|
+
:target: https://github.com/molssi-seamm/extract_clusters_step/pulls
|
|
7
|
+
:alt: GitHub pull requests
|
|
8
|
+
|
|
9
|
+
.. image:: https://github.com/molssi-seamm/extract_clusters_step/workflows/CI/badge.svg
|
|
10
|
+
:target: https://github.com/molssi-seamm/extract_clusters_step/actions
|
|
11
|
+
:alt: Build Status
|
|
12
|
+
|
|
13
|
+
.. image:: https://codecov.io/gh/molssi-seamm/extract_clusters_step/branch/master/graph/badge.svg
|
|
14
|
+
:target: https://codecov.io/gh/molssi-seamm/extract_clusters_step
|
|
15
|
+
:alt: Code Coverage
|
|
16
|
+
|
|
17
|
+
.. image:: https://img.shields.io/lgtm/grade/python/g/molssi-seamm/extract_clusters_step.svg?logo=lgtm&logoWidth=18
|
|
18
|
+
:target: https://lgtm.com/projects/g/molssi-seamm/extract_clusters_step/context:python
|
|
19
|
+
:alt: Code Quality
|
|
20
|
+
|
|
21
|
+
.. image:: https://github.com/molssi-seamm/extract_clusters_step/workflows/Documentation/badge.svg
|
|
22
|
+
:target: https://molssi-seamm.github.io/extract_clusters_step/index.html
|
|
23
|
+
:alt: Documentation Status
|
|
24
|
+
|
|
25
|
+
.. image:: https://pyup.io/repos/github/molssi-seamm/extract_clusters_step/shield.svg
|
|
26
|
+
:target: https://pyup.io/repos/github/molssi-seamm/extract_clusters_step/
|
|
27
|
+
:alt: Updates for Dependencies
|
|
28
|
+
|
|
29
|
+
.. image:: https://img.shields.io/pypi/v/extract_clusters_step.svg
|
|
30
|
+
:target: https://pypi.python.org/pypi/extract_clusters_step
|
|
31
|
+
:alt: PyPi VERSION
|
|
32
|
+
|
|
33
|
+
A SEAMM plug-in for extracting molecular clusters (trimers, tetramers, ... larger
|
|
34
|
+
n-mers) from a condensed-phase, typically periodic, configuration as unwrapped,
|
|
35
|
+
non-periodic structures -- e.g. many-body training data and diagnostics for
|
|
36
|
+
machine-learned force fields.
|
|
37
|
+
|
|
38
|
+
* Free software: BSD-3-Clause
|
|
39
|
+
* Documentation: https://molssi-seamm.github.io/extract_clusters_step/index.html
|
|
40
|
+
* Code: https://github.com/molssi-seamm/extract_clusters_step
|
|
41
|
+
|
|
42
|
+
Features
|
|
43
|
+
--------
|
|
44
|
+
|
|
45
|
+
* Clusters are **connected subgraphs of a molecular contact graph** (molecules
|
|
46
|
+
are in contact if their contact atoms are within a cutoff, minimum image), so
|
|
47
|
+
chains, rings and stars all occur -- not just the most compact cluster.
|
|
48
|
+
* Any cluster size, and several sizes per frame (e.g. ``3, 4``).
|
|
49
|
+
* **Stratification** so the set is flat in a spread coordinate (radius of
|
|
50
|
+
gyration or largest centroid separation), with bin edges from equal quantiles
|
|
51
|
+
of a pilot sample or given explicitly; optional balancing over the
|
|
52
|
+
contact-graph motif.
|
|
53
|
+
* Clusters are unwrapped across the periodic boundary, centred, non-periodic,
|
|
54
|
+
with molecules and bonds intact.
|
|
55
|
+
* Provenance on every configuration: unique names
|
|
56
|
+
``<frame>_<seed>_<m1-m2-...>`` and ``#ExtractClusters#scan`` properties (size,
|
|
57
|
+
spread, motif, contacts, source molecules) that survive SDF/extxyz export;
|
|
58
|
+
a ``clusters.csv`` summary per step.
|
|
59
|
+
* Works on any cell (orthorhombic fast path via a periodic KD-tree; exact
|
|
60
|
+
minimum image otherwise) and on non-periodic sources.
|
|
61
|
+
|
|
62
|
+
Acknowledgements
|
|
63
|
+
----------------
|
|
64
|
+
|
|
65
|
+
This package was created with Cookiecutter_ and the
|
|
66
|
+
`molssi-seamm/cookiecutter-seamm-plugin`_ project template.
|
|
67
|
+
|
|
68
|
+
.. _Cookiecutter: https://github.com/audreyr/cookiecutter
|
|
69
|
+
.. _`molssi-seamm/cookiecutter-seamm-plugin`: https://github.com/molssi-seamm/cookiecutter-seamm-plugin
|
|
70
|
+
|
|
71
|
+
Developed by the Molecular Sciences Software Institute (MolSSI_),
|
|
72
|
+
which receives funding from the `National Science Foundation`_ under
|
|
73
|
+
award ACI-1547580
|
|
74
|
+
|
|
75
|
+
.. _MolSSI: https://molssi.org
|
|
76
|
+
.. _`National Science Foundation`: https://www.nsf.gov
|
|
@@ -0,0 +1,177 @@
|
|
|
1
|
+
# Makefile for Sphinx documentation
|
|
2
|
+
#
|
|
3
|
+
|
|
4
|
+
# You can set these variables from the command line.
|
|
5
|
+
SPHINXOPTS =
|
|
6
|
+
SPHINXBUILD = sphinx-build
|
|
7
|
+
PAPER =
|
|
8
|
+
BUILDDIR = _build
|
|
9
|
+
|
|
10
|
+
# User-friendly check for sphinx-build
|
|
11
|
+
ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
|
|
12
|
+
$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
|
|
13
|
+
endif
|
|
14
|
+
|
|
15
|
+
# Internal variables.
|
|
16
|
+
PAPEROPT_a4 = -D latex_paper_size=a4
|
|
17
|
+
PAPEROPT_letter = -D latex_paper_size=letter
|
|
18
|
+
ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
|
|
19
|
+
# the i18n builder cannot share the environment and doctrees with the others
|
|
20
|
+
I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
|
|
21
|
+
|
|
22
|
+
.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
|
|
23
|
+
|
|
24
|
+
help:
|
|
25
|
+
@echo "Please use \`make <target>' where <target> is one of"
|
|
26
|
+
@echo " html to make standalone HTML files"
|
|
27
|
+
@echo " dirhtml to make HTML files named index.html in directories"
|
|
28
|
+
@echo " singlehtml to make a single large HTML file"
|
|
29
|
+
@echo " pickle to make pickle files"
|
|
30
|
+
@echo " json to make JSON files"
|
|
31
|
+
@echo " htmlhelp to make HTML files and a HTML help project"
|
|
32
|
+
@echo " qthelp to make HTML files and a qthelp project"
|
|
33
|
+
@echo " devhelp to make HTML files and a Devhelp project"
|
|
34
|
+
@echo " epub to make an epub"
|
|
35
|
+
@echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
|
|
36
|
+
@echo " latexpdf to make LaTeX files and run them through pdflatex"
|
|
37
|
+
@echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
|
|
38
|
+
@echo " text to make text files"
|
|
39
|
+
@echo " man to make manual pages"
|
|
40
|
+
@echo " texinfo to make Texinfo files"
|
|
41
|
+
@echo " info to make Texinfo files and run them through makeinfo"
|
|
42
|
+
@echo " gettext to make PO message catalogs"
|
|
43
|
+
@echo " changes to make an overview of all changed/added/deprecated items"
|
|
44
|
+
@echo " xml to make Docutils-native XML files"
|
|
45
|
+
@echo " pseudoxml to make pseudoxml-XML files for display purposes"
|
|
46
|
+
@echo " linkcheck to check all external links for integrity"
|
|
47
|
+
@echo " doctest to run all doctests embedded in the documentation (if enabled)"
|
|
48
|
+
|
|
49
|
+
clean:
|
|
50
|
+
rm -rf $(BUILDDIR)/*
|
|
51
|
+
|
|
52
|
+
html:
|
|
53
|
+
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
|
|
54
|
+
@echo
|
|
55
|
+
@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
|
|
56
|
+
|
|
57
|
+
dirhtml:
|
|
58
|
+
$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
|
|
59
|
+
@echo
|
|
60
|
+
@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
|
|
61
|
+
|
|
62
|
+
singlehtml:
|
|
63
|
+
$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
|
|
64
|
+
@echo
|
|
65
|
+
@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
|
|
66
|
+
|
|
67
|
+
pickle:
|
|
68
|
+
$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
|
|
69
|
+
@echo
|
|
70
|
+
@echo "Build finished; now you can process the pickle files."
|
|
71
|
+
|
|
72
|
+
json:
|
|
73
|
+
$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
|
|
74
|
+
@echo
|
|
75
|
+
@echo "Build finished; now you can process the JSON files."
|
|
76
|
+
|
|
77
|
+
htmlhelp:
|
|
78
|
+
$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
|
|
79
|
+
@echo
|
|
80
|
+
@echo "Build finished; now you can run HTML Help Workshop with the" \
|
|
81
|
+
".hhp project file in $(BUILDDIR)/htmlhelp."
|
|
82
|
+
|
|
83
|
+
qthelp:
|
|
84
|
+
$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
|
|
85
|
+
@echo
|
|
86
|
+
@echo "Build finished; now you can run "qcollectiongenerator" with the" \
|
|
87
|
+
".qhcp project file in $(BUILDDIR)/qthelp, like this:"
|
|
88
|
+
@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/extract_clusters_step.qhcp"
|
|
89
|
+
@echo "To view the help file:"
|
|
90
|
+
@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/extract_clusters_step.qhc"
|
|
91
|
+
|
|
92
|
+
devhelp:
|
|
93
|
+
$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
|
|
94
|
+
@echo
|
|
95
|
+
@echo "Build finished."
|
|
96
|
+
@echo "To view the help file:"
|
|
97
|
+
@echo "# mkdir -p $$HOME/.local/share/devhelp/extract_clusters_step"
|
|
98
|
+
@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/extract_clusters_step"
|
|
99
|
+
@echo "# devhelp"
|
|
100
|
+
|
|
101
|
+
epub:
|
|
102
|
+
$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
|
|
103
|
+
@echo
|
|
104
|
+
@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
|
|
105
|
+
|
|
106
|
+
latex:
|
|
107
|
+
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
|
|
108
|
+
@echo
|
|
109
|
+
@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
|
|
110
|
+
@echo "Run \`make' in that directory to run these through (pdf)latex" \
|
|
111
|
+
"(use \`make latexpdf' here to do that automatically)."
|
|
112
|
+
|
|
113
|
+
latexpdf:
|
|
114
|
+
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
|
|
115
|
+
@echo "Running LaTeX files through pdflatex..."
|
|
116
|
+
$(MAKE) -C $(BUILDDIR)/latex all-pdf
|
|
117
|
+
@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
|
|
118
|
+
|
|
119
|
+
latexpdfja:
|
|
120
|
+
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
|
|
121
|
+
@echo "Running LaTeX files through platex and dvipdfmx..."
|
|
122
|
+
$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
|
|
123
|
+
@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
|
|
124
|
+
|
|
125
|
+
text:
|
|
126
|
+
$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
|
|
127
|
+
@echo
|
|
128
|
+
@echo "Build finished. The text files are in $(BUILDDIR)/text."
|
|
129
|
+
|
|
130
|
+
man:
|
|
131
|
+
$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
|
|
132
|
+
@echo
|
|
133
|
+
@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
|
|
134
|
+
|
|
135
|
+
texinfo:
|
|
136
|
+
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
|
|
137
|
+
@echo
|
|
138
|
+
@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
|
|
139
|
+
@echo "Run \`make' in that directory to run these through makeinfo" \
|
|
140
|
+
"(use \`make info' here to do that automatically)."
|
|
141
|
+
|
|
142
|
+
info:
|
|
143
|
+
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
|
|
144
|
+
@echo "Running Texinfo files through makeinfo..."
|
|
145
|
+
make -C $(BUILDDIR)/texinfo info
|
|
146
|
+
@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
|
|
147
|
+
|
|
148
|
+
gettext:
|
|
149
|
+
$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
|
|
150
|
+
@echo
|
|
151
|
+
@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
|
|
152
|
+
|
|
153
|
+
changes:
|
|
154
|
+
$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
|
|
155
|
+
@echo
|
|
156
|
+
@echo "The overview file is in $(BUILDDIR)/changes."
|
|
157
|
+
|
|
158
|
+
linkcheck:
|
|
159
|
+
$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
|
|
160
|
+
@echo
|
|
161
|
+
@echo "Link check complete; look for any errors in the above output " \
|
|
162
|
+
"or in $(BUILDDIR)/linkcheck/output.txt."
|
|
163
|
+
|
|
164
|
+
doctest:
|
|
165
|
+
$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
|
|
166
|
+
@echo "Testing of doctests in the sources finished, look at the " \
|
|
167
|
+
"results in $(BUILDDIR)/doctest/output.txt."
|
|
168
|
+
|
|
169
|
+
xml:
|
|
170
|
+
$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
|
|
171
|
+
@echo
|
|
172
|
+
@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
|
|
173
|
+
|
|
174
|
+
pseudoxml:
|
|
175
|
+
$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
|
|
176
|
+
@echo
|
|
177
|
+
@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
.. include:: ../AUTHORS.rst
|