tsfast 0.3.0

Deep learning library for time series analysis and system identification

TSFast

Description

tsfast is an open-source deep learning library for time series analysis and system identification tasks. Built on PyTorch, it offers efficient deep learning models and utilities.

tsfast is an open-source deep learning package that focuses on system identification and time series analysis tasks. Built on PyTorch, it provides efficient implementations of various deep learning models and utilities.

Key Features

• Specialized Data Handling for Time Series:
  • HDF5-backed data pipeline with signal blocks for flexible sequence data processing.
  • Includes a range of transforms tailored for sequences, such as noise injection and normalization adapted for time series tensors.
  • Features advanced data loading with TBPTT (Truncated Backpropagation Through Time) support.
• Predefined Datasets & Helpers: Offers easy-to-use benchmark datasets (e.g., create_dls_silverbox from identibench) for rapid prototyping and experimentation.
• Tailored Time Series Models: Provides implementations of Recurrent Neural Networks (RNNs, including DenseNet_RNN, ResidualBlock_RNN), Convolutional Neural Networks (TCNs, CausalConv1d), and combined architectures (CRNN, SeperateCRNN) specifically designed for sequence modeling. Includes building blocks like SeqLinear and layer normalization.
• Integrated Training: Features RNNLearner, TCNLearner, CRNNLearner, etc., with a lightweight pure-PyTorch training loop, custom time-series losses (e.g., fun_rmse, nrmse), and composable transforms for augmentation and regularization.
• System Identification & Prediction:
  • Supports simulation (prediction based on inputs) and N-step ahead forecasting.
  • Includes specialized models for system identification tasks like FRANSYS (FranSys, FranSysLearner) and AR models (AR_Model, ARProg).
  • Provides an InferenceWrapper for easier model deployment and prediction.
• Hyperparameter Optimization: Integrates with Ray Tune via HPOptimizer for efficient hyperparameter searching.

Installation

You can install the latest stable version using:

pip install tsfast

For development installation:

git clone https://github.com/daniel-om-weber/tsfast
cd tsfast
pip install -e '.[dev]'
# or using uv:
uv sync --extra dev

Quick Start

Here is a quick example using a benchmark dataloader. It demonstrates loading and visualizing data, training a RNN, and visualizing the results.

from tsfast.basics import *

# Load benchmark dataset
dls = create_dls_silverbox()

# Train an RNN and visualize results
lrn = RNNLearner(dls)
lrn.fit_flat_cos(1)
lrn.show_results(max_n=1)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

Citation

If you use tsfast in your research, please cite:

@Misc{tsfast,
author = {Daniel O.M. Weber},
title = {tsfast - A deep learning library for time series analysis and system identification},
howpublished = {Github},
year = {2024},
url = {https://github.com/daniel-om-weber/tsfast}
}