giotto-tda-nightly

Toolbox for Machine Learning using Topological Data Analysis.


Keywords
machine learning, topological data analysis, persistent homology, persistence diagrams, Mapper, computational-topology, machine-learning, scikit-learn, tda, topological-data-analysis, topological-machine-learning, topology
License
GPL-3.0-only
Install
pip install giotto-tda-nightly==20200302.12

Documentation

Azure Azure-cov Azure-test binder

giotto-learn

giotto-learn is a high performance topological toolbox for machine learning in Python built on top of scikit-learn and is distributed under the Apache 2.0 license. It is part of the Giotto open-source project.

Project Governance

The project was started jointly by Learn To Forecast - L2F, EPFL Laboratory for topology and neuroscience and the Reconfigurable and Embedded Digital Systems at heig-vd.

The code is under active development and is maintained and developed by members of those three institutions. See the GOVERNANCE.rst file for a list of the Giotto team members.

Website: http://www.giotto.ai

Installation

Dependencies

giotto-learn requires:

  • Python (>= 3.5)
  • scikit-learn (>= 0.21.3)
  • NumPy (>= 1.11.0)
  • SciPy (>= 0.17.0)
  • joblib (>= 0.11)

For running the examples jupyter, matplotlib and plotly are required.

User installation

If you already have a working installation of numpy and scipy, the easiest way to install giotto-learn is using pip

pip install -U giotto-learn

Documentation

Contributing

We welcome new contributors of all experience levels. The Giotto community goals are to be helpful, welcoming, and effective. To learn more about making a contribution to giotto-learn, please see the CONTRIBUTING.rst file.

Developer installation

C++ dependencies:
  • C++14 compatible compiler
  • CMake >= 3.9
  • Boost >= 1.56
Source code

You can check the latest sources with the command:

git clone https://github.com/giotto-learn/giotto-learn.git
To install:
cd giotto-learn
pip install -e .

From there any change in the library files will be immediately available on your machine.

Testing

After installation, you can launch the test suite from outside the source directory:

pytest giotto

Changelog

See the RELEASE.rst file for a history of notable changes to giotto-learn.

Important links

Contacts:

maintainers@giotto.ai