alkaline-ml/pmdarima

A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.

What it solves

It addresses the lack of comprehensive time series analysis tools in Python by providing a statistical library for forecasting and analysis, specifically bringing the functionality of R's auto.arima to the Python ecosystem.

How it works

It wraps the statsmodels library but provides a scikit-learn-style interface. This allows users to build pipelines that include data transformers (like Box-Cox or Fourier transformations), statistical tests for stationarity and seasonality, and automated ARIMA model selection.

Who it’s for

Data scientists and analysts who need to perform time series forecasting and analysis using a familiar scikit-learn-like API.

Highlights

  • Automated Model Selection: Includes auto_arima to automatically find the best ARIMA parameters.
  • Scikit-learn Integration: Supports pipelines to consolidate estimators for easier productionization.
  • Comprehensive Toolset: Provides stationarity/seasonality tests, time series decompositions, and cross-validation utilities.
  • Built-in Datasets: Includes a collection of time series datasets for rapid prototyping.

Related

  • Project
    EnzymeAD/Enzyme

    A high-performance automatic differentiation plugin for LLVM and MLIR that synthesizes fast gradients for optimized code, including GPU kernels and parallel programs.

  • Project
    lightly-ai/lightly-train

    LightlyTrain is a framework for the entire computer vision model lifecycle, enabling users to pretrain, fine-tune, and distill state-of-the-art models for detection and segmentation tasks with support for edge deployment.

  • Project
    facebookresearch/multimodal

    A PyTorch library for training state-of-the-art multimodal models at scale, providing modular building blocks and pretrained weights for models like CLIP and BLIP-2.

  • Project
    KEV0143/Comparative-analysis-of-hourly-load-forecasting-using-PatchTST-TFT-NHiTS-and-CatBoost

    A Python research project that compares four modern time‑series models (PatchTST, TFT, N‑HiTS, CatBoost) for hour‑by‑hour electricity‑load forecasting using real Russian utility data. Includes data preprocessing, training pipelines, statistical analysis, and visualisation, and is released under Apache 2.0.