sktime/sktime

A unified framework for machine learning with time series

What it solves

sktime is a Python library designed to provide a unified interface for various time series analysis tasks. It solves the problem of fragmented ecosystems where different algorithms and libraries for forecasting, classification, and clustering are inconsistent in their APIs, making it difficult to build, tune, and validate models across different techniques.

How it works

It provides a standardized API for multiple time series learning tasks, including forecasting, classification, regression, clustering, and anomaly/changepoint detection. The library includes its own dedicated time series algorithms and offers interfaces to other popular libraries like scikit-learn, statsmodels, and fbprophet. It also supports composite model building through pipelining, ensembling, and reduction techniques, allowing users to apply algorithms designed for one task to another.

Who it’s for

Data scientists and machine learning engineers who work with time series data and need a consistent framework for building and evaluating time series models.

Highlights

  • Unified Interface: A single API for forecasting, classification, regression, and clustering.
  • Interoperability: Compatible with scikit-learn and provides interfaces to other libraries like statsmodels and tsfresh.
  • Composite Model Building: Tools for pipelining, tuning, and ensembling.
  • Extensibility: Provides extension templates to allow users to add their own algorithms compatible with the API.

Related

  • Project
    skforecast/skforecast

    A Python library for time series forecasting that provides a unified API for scikit-learn compatible ML models, statistical methods, and zero-shot foundation models.

  • Project
    aeon-toolkit/aeon

    A scikit-learn compatible Python library for time series machine learning, providing state-of-the-art algorithms for classification, forecasting, and clustering.

  • Project
    sktime/skpro

    A Python library for supervised probabilistic prediction that provides tools for tabular regression, survival analysis, and uncertainty quantification with scikit-learn compatible interfaces.

  • Project
    Nixtla/mlforecast

    A scalable framework for time series forecasting that allows any scikit-learn compatible machine learning model to be used for forecasting millions of series.

  • Project
    mikekeith52/scalecast

    A time series forecasting library that provides a uniform interface for ML and deep learning models, simplifying model selection, validation, and pipeline creation.