Contents

hdbscan 0.8.33

0

Clustering based on density with variable density clusters

Clustering based on density with variable density clusters

Stars: 2654, Watchers: 2654, Forks: 482, Open Issues: 345

The scikit-learn-contrib/hdbscan repo was created 8 years ago and the last code push was 1 months ago.
The project is very popular with an impressive 2654 github stars!

How to Install hdbscan

You can install hdbscan using pip

pip install hdbscan

or add it to a project with poetry

poetry add hdbscan

Package Details

Author
License
BSD
Homepage
http://github.com/scikit-learn-contrib/hdbscan
PyPi:
https://pypi.org/project/hdbscan/
GitHub Repo:
https://github.com/scikit-learn-contrib/hdbscan

Classifiers

  • Scientific/Engineering
  • Software Development
No  hdbscan  pypi packages just yet.

Errors

A list of common hdbscan errors.

Code Examples

Here are some hdbscan code examples and snippets.

GitHub Issues

The hdbscan package has 345 open issues on GitHub

  • Installation issue
  • generate_prediction_data logic to choose tree_type does not respect algorithm chosen
  • (Pickling Error) ValueError: buffer source array is read-only
  • Test Errors
  • Use t-sne result as input encountering un-serialized error
  • Python 3.10 support? ImportError
  • Strange behaviour clustering 1D data
  • Missing tag 0.8.27 from git, but the release exists in PyPi
  • Slow behavior of approximate_predict()
  • ERROR: Failure: ValueError (numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject)
  • ValueError: numpy.ndarray size changed when calling import hdbscan
  • Bug: min_samples should include self, but does not
  • Sum of membership_vector not equal to 1

See more issues on GitHub

Related Packages & Articles

h2o 3.46.0.1

H2O, Fast Scalable Machine Learning, for python

flair 0.13.1

A very simple framework for state-of-the-art NLP