Open Source

landmarker: PyTorch-based toolkit for landmark detection

Landmarker is a PyTorch-based toolkit for (anatomical) landmark detection in images. It is designed to be easy to use and to provide a flexible framework for state-of-the-art landmark detection algorithms for small and large datasets. Landmarker was developed for landmark detection in medical images. Interested? Take a look at our docs!

plotly-resampler: Visualizing large sequences

A Python toolkit which builds upon the Plotly graphing library to enable visualization of large time series. The visualizations are achieved by (1) separating the data between front- & back-end and (2) performing computational aggregation (downsampling) in te front-end. Take a look at our docs!

PowerShap

powershap is a feature selection method that uses statistical hypothesis testing and power calculations on Shapley values, enabling fast and intuitive wrapper-based feature selection. powershap is built to be intuitive, it supports various models including linear, tree-based, and even deep learning models for classification and regression tasks.

RR-GCN: Random Relational Graph Convolutional Networks

RR-GCN is an extension of Relational Graph Convolutional Networks (R-GCN) in which the weights are randomly initialised and kept frozen (i.e. no training step is required). As such, our technique is unsupervised and the produced embeddings can be used for any downstream ML task/model. Surprisingly, empirical results indicate that the embeddings produced by our RR-GCN can be competitive to, and even sometimes outperform, end-to-end R-GCNs.

Series Distance Matrix

A Python library for pattern based time series analysis. This library started as an implementation of the Matrix Profile, and has since grown to bundles many Matrix Profile related publications. It is described in the paper A generalized matrix profile framework with support for contextual series analysis.

tsflex: flexible time series operations

A Python library for flexible time series operations. Leverages numpy & pandas to perform efficient time-series feature extraction and processing, making few assumptions. Take a look at our docs! The preprint paper can be found on arxiv.