dtwParallel: A Python package to efficiently compute dynamic time warping between time series
Óscar Escudero-Arnanz,
Antonio G. Marques,
Cristina Soguero-Ruiz,
Inmaculada Mora-Jiménez,
Gregorio Robles
Affiliations
Óscar Escudero-Arnanz
Corresponding author.; Department of Signal Theory and Communications, Telematics and Computing Systems, King Juan Carlos University, Fuenlabrada 28942, Spain
Antonio G. Marques
Department of Signal Theory and Communications, Telematics and Computing Systems, King Juan Carlos University, Fuenlabrada 28942, Spain
Cristina Soguero-Ruiz
Department of Signal Theory and Communications, Telematics and Computing Systems, King Juan Carlos University, Fuenlabrada 28942, Spain
Inmaculada Mora-Jiménez
Department of Signal Theory and Communications, Telematics and Computing Systems, King Juan Carlos University, Fuenlabrada 28942, Spain
Gregorio Robles
Department of Signal Theory and Communications, Telematics and Computing Systems, King Juan Carlos University, Fuenlabrada 28942, Spain
dtwParallel is a Python package that computes the Dynamic Time Warping (DTW) distance between a collection of (multivariate) time series (MTS). dtwParallel incorporates the main functionalities available in current DTW libraries and novel functionalities such as parallelization, computation of similarity (kernel-based) values, and consideration of data with different types of features (categorical, real-valued, …). A low-floor, high-ceiling, and wide-walls software design principle has been adopted, envisioning uses in education, research, and industry. The source code and documentation of the package are available at https://github.com/oscarescuderoarnanz/dtwParallel.
