skforecast/skforecast

Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models

What it solves

Skforecast 簡化了時間序列預測的過程，讓使用者能夠在統一的框架內利用機器學習模型、統計方法和基礎模型。它彌補了標準 scikit-learn 相容估計器與時間序列數據的特定需求（例如滯後生成和遞歸預測策略）之間的差距。

How it works

該函式庫提供 "Forecaster" 物件，作為訓練和預測的容器。它支援多種策略，包括遞歸和直接預測，並可以處理單個或多個時間序列。它能與任何 scikit-learn 相容的估計器（例如 LightGBM, XGBoost, 或 CatBoost）無縫整合，並也支援深度學習 (RNN/LSTM)、統計模型 (ARIMA, ETS) 以及基礎模型。

Who it's for

它是為需要使用 Python 構建、驗證和部署生產級時間序列預測模型的數據科學家和機器學習工程師而設計的。

Highlights

  • Scikit-learn Compatibility: Works with any estimator that follows the scikit-learn API.
  • Diverse Forecaster Types: Offers specialized forecasters for recursive, direct, multivariate, and classification tasks.
  • Comprehensive Tooling: Includes built-in tools for feature engineering, hyperparameter tuning, and backtesting for realistic performance evaluation.
  • Flexible Modalities: Supports exogenous features, window features, and probabilistic predictions.