pyclustering
pyclustering copied to clipboard
annoviko
pyclustering is a Python, C++ data mining library.
**Introduction** Incorrect indexes could be returned by 'allocate_sync_ensembles' due to wrong size of 'descriptors' where spike description is stored for each oscillator. The bug was corrected during review. Unit-tests should...
**Introduction** Any data set almost always contains outliers. CURE algorithm provides mechanism to eliminate them. **Resources** - Article: **CURE: An Efficient Clustering Algorithm for Large Databases** - Sudipto Guha, Rajeev...
**Introduction** Each class/function/etc. of the library should documented and included to doxygen build for automatic documentation generation. Content of the file 'pyclustering/utils/dimension.py' does not satisfy the previous statement. **Description** 1....
**Introduction** The was a topic on **stackoverflow** referred to **pyclustering** where Ward's method was mentioned. It is a method that is used as criterion for choosing pair of clusters for...
https://github.com/annoviko/pyclustering/blob/906532e4a5422479cc6813e852f9c3cb48ea7a64/pyclustering/utils/metric.py#L460-L481 in defenition of distance should be the absolute value of diferences betwen two points (distance += abs(point1[i] - point2[i])) also for numpy implementation should be the np.absolute.
Are there any plans to support ARM64 architecture? If not, is [this](https://towardsdatascience.com/how-to-manage-conda-environments-on-an-apple-silicon-m1-mac-1e29cb3bad12) the best way to get it to work?
Fix for #700. I ran `python -m unittest pyclustering/nnet/tests/unit/ut_fsync.py` which failed before the fix and passed afterwards. It turned out to be a very simple problem which is great ✨...
Running the following code with numpy 1.2+ ``` from pyclustering.nnet.fsync import fsync_network # Prepare oscillatory network parameters. amount_oscillators = 3; frequency = 1.0; radiuses = [1.0, 2.0, 3.0]; coupling_strength =...
Build fix: #include <limits> [GH issue 690] See: https://github.com/annoviko/pyclustering/issues/690
newer NumPy removes warnings module from the main namespace, therefore numpy.warnings results in error https://github.com/annoviko/pyclustering/blob/bf4f51a472622292627ec8c294eb205585e50f52/pyclustering/cluster/center_initializer.py#L248 Since warnings module is already imported here, the "numpy." specifier should be removed. The change...
