TanaT Documentation#

TanaT is an extensible Python library for temporal sequence analysis with a primary focus on patient care pathways.

It gathers a collection of tools for analysing timed sequences (also called trajectories): building pools of sequences from heterogeneous data sources, manipulating sequence objects, computing dedicated distance, metrics, clustering, and producing publication-ready visualisations. Inspired by TraMineR (R) and time-series libraries like aeon and tslearn, TanaT brings these capabilities to Python with first-class support for multi-sequence trajectories that combine three temporal data types: events, intervals, and states.

More features will be implemented in the future and we also aim at creating a community of developpers that would contribute to this project. If you are interested in being involved please reach out.

On this page