PyPulse: A Python Library for Biosignal Imputation

TL;DR

PyPulse is a user-friendly Python library that simplifies biosignal data imputation, offering pre-trained methods, easy workflow execution, and interactive comparison tools for researchers and practitioners.

Contribution

The paper introduces PyPulse, a modular, extendable Python package that enables easy biosignal imputation, including pre-trained models and interactive comparison features.

Findings

Supports custom datasets with pre-trained models

Simplifies training and testing workflows

Provides interactive visualization for method comparison

Abstract

We introduce PyPulse, a Python package for imputation of biosignals in both clinical and wearable sensor settings. Missingness is commonplace in these settings and can arise from multiple causes, such as insecure sensor attachment or data transmission loss. PyPulse's framework provides a modular and extendable framework with high ease-of-use for a broad userbase, including non-machine-learning bioresearchers. Specifically, its new capabilities include using pre-trained imputation methods out-of-the-box on custom datasets, running the full workflow of training or testing a baseline method with a single line of code, and comparing baseline methods in an interactive visualization tool. We released PyPulse under the MIT License on Github and PyPI. The source code can be found at: https://github.com/rehg-lab/pulseimpute.