An open-source library of algorithms to analyse time series in GPU and CPU.

Contains an implementation (sklearn API) of the algorithm proposed in "GENDIS: GEnetic DIscovery of Shapelets" and code to reproduce all experiments.

Code for "Generalised Interpretable Shapelets for Irregular Time Series"

A software package for statistically significant shapelet mining

Implementation of the Random Dilated Shapelet Transform algorithm along with interpretability tools. ReadTheDocs documentation is not up to date with the current version for now.

Uncertain Shapelet Transform Classification, a shapelet method for uncertain time series classification

This is an official pytorch implementation for paper "Learning Soft Sparse Shapes for Efficient Time-Series Classification" (ICML-25, Spotlight).

This repo contains useful links to research papers and implementations of shapelets discovery/learning techniques from different sources.

This is an official pytorch implementation for paper "A Unified Shape-Aware Foundation Model for Time Series Classification" (AAAI-26).

C# binding for Khiva library.

Scalable and Accurate Subsequence Transform

Repository for "Data Mining - Advanced Topics and Applications" projects exam.

Implementation of Fast Shapelets: A Scalable Algorithm for Discovering Time Series Shapelets

Multivariate Asynchronous Random Shapelets

Motif-guided time series counterfactual explanations (ICPR 2022)

Theoretically guaranteed shapelet-learning algorithm

Uncertain times séries classification

Implementation (VHDL) and verification of the accelerator proposed in the paper "Hardware Accelerator for Shapelet Distance Computation in Time-Series Classification", from May 2020

Explainable AI for time series: gradient-based counterfactual generation for the non-differentiable Random Shapelet Forest, using PyTorch surrogate models (Feedforward, LSTM, CNN, Transformer) and a Streamlit UI. Research internship, DSV — Stockholm University.