# pollen-robotics/dtw

DTW (Dynamic Time Warping) python module

Repository: https://github.com/pollen-robotics/dtw
Canonical: https://ross.abutalabs.com/products/dtw
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: python, dtw, distance-measures, distance-metric, distance
Last push: 2024-03-29T11:30:12+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4419, "days_push": 887, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1230, forks 236 (observed 2026-08-28T04:04:03.755586+00:00)

## What it is
A small Python module implementing Dynamic Time Warping (DTW), a similarity measure between temporal sequences. It offers a basic pure-Python/NumPy implementation plus an accelerated version using scipy's cdist, with utilities to visualize accumulated cost matrices and alignment paths.

## Use cases
- compare similarity between two time series sequences
- simple speech recognition with DTW and MFCC features
- measure distance between audio signals for sound matching
- align and match gesture or motion sensor data
- visualize DTW cost matrix and optimal warping path
- compute DTW distance between numpy arrays

## When to choose
- you need a lightweight, easy-to-use DTW implementation in Python with numpy/scipy
- you want to visualize accumulated cost matrices and warping paths
- you're doing simple template-based speech or audio comparison
- your sequences are small enough that a basic DTW implementation suffices

## When to avoid
- you need highly optimized or GPU-accelerated DTW for very long sequences
- you need advanced DTW variants like subsequence DTW, derivative DTW, or soft-DTW
- you need a maintained library with recent Python version support (tested only up to Python 3.6)
- you need DTW integrated into a larger machine-learning pipeline with gradient support

## Facets
- artifact type: library
- maturity: maintenance
- function: math, machine-learning, audio-processing
- domain: machine-learning, speech-processing, data-science
- platform: python, cross-platform
- tags: dynamic-time-warping, similarity-measure, numpy, scipy, time-series, algorithms

## Member repositories
- pollen-robotics/dtw (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.755586+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:03.087419+00:00, confidence not recorded.
  - readme: https://github.com/pollen-robotics/dtw (fetched 2026-08-28T04:04:03.755586+00:00, sha 20beb8bdb882)
- Data as of 2026-08-30T08:39:29.467469+00:00.