Prepare v0.5.0 release

CHANGELOG.md

@@ -7,11 +7,25 @@ and [Element](https://github.com/vector-im/element-android)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+
+
+## [0.5.0] - 2025-11-11
+### API changes warning ⚠️:
+- The `kmedoids` clustering mode has been deprecated and removed. Users should use `CPM`, `modularity`, or `linkage` modes instead.
+- Dropped Python 3.8 support
+- Removed `scikit-learn-extra` dependency (was used for k-medoids clustering)
+- Switched to numpy 2.x (minimum version is now `numpy>=2.0.0`)
+
 ### Added Features and Improvements 🙌:
 - Added trogon terminal user interface for easier usage of CI
+- Added support for Python 3.12, 3.13, and 3.14
+
+### Bugfix 🐛:
+- Fixed matplotlib plotting error in CLI (typo: `vim` → `vmin`), fixing [#28](/../../issues/28)
 
 ### Other changes:
 - Fixed minor issues in docs
+- Updated copyright year to 2024 in source files
 
 ### Bugfix 🐛:
 - Fix broken documentation by increasing Python version
@@ -168,7 +182,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Initial release
 
 
-[Unreleased]: https://github.com/moldyn/MoSAIC/compare/v0.4.1...main
+[Unreleased]: https://github.com/moldyn/MoSAIC/compare/v0.5.0...main
+[0.5.0]: https://github.com/moldyn/MoSAIC/compare/v0.4.1...v0.5.0
 [0.4.1]: https://github.com/moldyn/MoSAIC/compare/v0.4.0...v0.4.1
 [0.4.0]: https://github.com/moldyn/MoSAIC/compare/v0.3.2...v0.4.0
 [0.3.2]: https://github.com/moldyn/MoSAIC/compare/v0.3.1...v0.3.2

CITATION.cff

@@ -5,7 +5,7 @@ authors:
     family-names: "Nagel"
     orcid: "https://orcid.org/0000-0002-2863-2646"
 title: "MoSAIC: Molecular Systems Automated Identification of Cooperativity"
-version: 0.2.1
+version: 0.5.0
 url: "https://moldyn.github.io/MoSAIC"
 preferred-citation:
   type: article

README.md

@@ -102,11 +102,11 @@ The module brings a rich CI using [click](https://click.palletsprojects.com). Ea
 $ python -m mosaic
 Usage: python -m mosaic [OPTIONS] COMMAND [ARGS]...
 
-  MoSAIC motion v0.4.1
+  MoSAIC motion v0.5.0
 
   Molecular systems automated identification of collective motion, is
   a correlation based feature selection framework for MD data.
-  Copyright (c) 2021-2023, Georg Diez and Daniel Nagel
+  Copyright (c) 2021-2025, Georg Diez and Daniel Nagel
 
 Options:
   --help  Show this message and exit.
@@ -162,7 +162,7 @@ sim.fit(X)
 
 # Cluster matrix
 clust = mosaic.Clustering(
-    mode='CPM',  # or 'modularity
+    mode='CPM',  # or 'modularity', 'linkage'
 )
 clust.fit(sim.matrix_)
 

docs/faq.md

@@ -37,6 +37,10 @@ Yes, simply use the `score` method implemented in the `Clustering` class.
 This is still possible if you switch to the version 0.3.2. We removed that feature in newer versions.
 
 
+### What happened to the k-medoids clustering mode?
+The k-medoids clustering mode (`mode='kmedoids'`) has been deprecated and removed in version 0.5.0. We recommend using one of the following clustering modes instead: `CPM`, `modularity`, or `linkage`. These modes provide more robust and efficient clustering capabilities for correlation-based feature selection.
+
+
 ### Feature X is missing
 If you believe that a crucial functionality/method is missing, feel free to [open an issue](https://github.com/moldyn/MoSAIC/issues) and describe the missing functionality and why it should be added. Alternatively, you can implement it yourself and create a PR to add it to this package, see [contributing guide](../contributing).
 

setup.py

@@ -58,7 +58,7 @@ def remove_gh_dark_mode_only_tags(text, tag='#gh-dark-mode-only'):
 # This call to setup() does all the work
 setuptools.setup(
     name='mosaic-clustering',
-    version='0.4.1',
+    version='0.5.0',
     description='Correlation based feature selection for MD data',
     long_description=README,
     long_description_content_type='text/markdown',

src/mosaic/__init__.py

@@ -30,8 +30,8 @@ class that enables the calculation of similarity measures based on different
 - [**clustering**][mosaic.clustering] This submodule is the most central
 component of MoSAIC that offers various techniques for analyzing similarity
 matrices. It provides different modes for clustering a correlation matrix,
-including the Leiden algorithm with different objective functions,
-linkage clustering, and k-medoids, and supports both weighted and unweighted,
+including the Leiden algorithm with different objective functions
+and linkage clustering, and supports both weighted and unweighted,
 as well as full and sparse graphs.
 The resulting clusters and labels can be accessed through the attributes of
 the class.
@@ -60,4 +60,4 @@ class that enables the calculation of similarity measures based on different
 from .similarity import Similarity
 
 
-__version__ = '0.4.1'
+__version__ = '0.5.0'