chronocratic-models

Ready-to-use time series models implemented in PyTorch and Lightning.

Note: The PyPI package name uses a hyphen (chronocratic-models), but the import uses the chronocratic.models namespace.

Installation

pip install chronocratic-models

Quick Links

• Quick Start — Get started with a TS2Vec encoding example

• API Reference — Full API reference with autodoc

• Changelog — Release history and changelog

• Contributing — How to contribute to the project

Models

The library provides ten pre-trained encoders organized by architecture family:

Convolutional (Dilated): Dilated Convolutional Models — TS2Vec, CoST, AutoTCL

Convolutional (Standard): Standard Convolutional Models — Series2Vec, TSTCC, FCN

Transformer: Transformer Models — TST

Recurrent: Recurrent Models — TimeNet

Generative: Generative Models — TimeVAE

Supervised: Supervised Fine-tuning — SupervisedModule with factory functions

Features

• Polymorphic augmentation producer contract — models accept any augmentation through a unified interface, eliminating enum-based branching.

• Lightning integration — all models are built on PyTorch Lightning for clean training loops and extensibility.

• Self-supervised representation learning — pre-trained encoders ready for downstream tasks without labeled data.

• Pre-configured model parameters — each model ships with tested default configuration dataclasses.

• NumPy and PyTorch tensor support — flexible input handling for both frameworks.