jaccard 0.1.0

Utilities related to Jaccard/Tanimoto coefficients.

jaccard.py

Utilities related to Jaccard/Tanimoto coefficients.

🗺️ Overview

jaccard.py is a pure-Python package providing Jaccard index computation.

This library only depends on NumPy and is available for all modern Python versions (3.6+).

📋 Features

Agnostic interface using duck-typing: all functions should be available for NumPy arrays, MLX arrays, or PyTorch tensors, unless noted otherwise.

The following functions are implemented:

• Jaccard similarity[1]: measure similarity between boolean vectors, similar to scipy.spatial.distance.jaccard.
• probabilistic Jaccard similarity[2]: measure similarity between probability vectors while quantifying uncertainty.
• centered Jaccard similarity and Jaccard testing[3]: identify non-random co-occurences between samples with robust statistical testing.
• collision probability Jaccard index [4]: measure similarity between positive indices, using a metric that is scale invariant, sensitive to changes in support, and computable as a collision probability.

🔧 Installing

Install the jaccard package directly from PyPi which hosts universal wheels that can be installed with pip:

$ pip install jaccard

💭 Feedback

⚠️ Issue Tracker

Found a bug ? Have an enhancement request ? Head over to the GitHub issue tracker if you need to report or ask something. If you are filing in on a bug, please include as much information as you can about the issue, and try to recreate the same bug in a simple, easily reproducible situation.

🏗️ Contributing

Contributions are more than welcome! See CONTRIBUTING.md for more details.

⚖️ License

This library is provided under the MIT License.

This project was developed by Martin Larralde during his PhD project at the Leiden University Medical Center in the Zeller team.

📚 References

• [1] Jaccard, P. "Étude comparative de la distribution florale dans une portion des Alpes et du Jura." Bulletin de la Société Vaudoise des Sciences Naturelles 37, 547–579 (1901). doi:10.1111/j.1469-8137.1912.tb05611.x
• [2] Martire, I., Da Silva, P. N., Plastino, A., Fabris, F. & Freitas, A. A. "A novel probabilistic Jaccard distance measure for classification of sparse and uncertain data". Proceedings of the 5th Symposium on Knowledge Discovery, Mining and Learning, 81-88 (2017).
• [3] Chung, N. C., Miasojedow, B., Startek, M. & Gambin, A. "Jaccard/Tanimoto similarity test and estimation methods for biological presence-absence data". BMC Bioinformatics 20, 644 (2019). doi:10.1186/s12859-019-3118-5
• [4] 1. Moulton, R. & Jiang, Y. "Maximally Consistent Sampling and the Jaccard Index of Probability Distributions". in 2018 IEEE International Conference on Data Mining (ICDM) 347–356 (2018). doi:10.1109/ICDM.2018.00050.