Welcome to the DTW Library, a high-performance implementation of the Dynamic Time Warping (DTW) algorithm written in Rust. This library allows you to perform time series analysis on both univariate and multivariate data sets, offering an intuitive and powerful tool for measuring similarity.
Note: This is a hobby project.
Dynamic Time Warping (DTW) is a mathematical technique used for measuring similarity between two temporal sequences which may vary in speed. For example, differences in speaking speeds in speech processing or varying heart rates in medical applications. DTW compares sequences of different lengths and aligns their points to minimize the total distance between them. This is particularly useful in time series analysis where the time sequences may not align exactly.
- Efficient computation of DTW for univariate and multivariate time series;
- Implemented in Rust for optimal performance;
- Simple and intuitive Python API;
- Supports customization for various distance measures.
This Rust library was implemented based on the DTW_cpp library. Thank you for making the code available.
dtw
is distributed under the MIT license. See LICENSE
for more details.