Skip to content

Home

DeepTS_Forecasting

Release Status CI Status Documentation Status

Deepts_forecasting is a Easy-to-use package for time series forecasting with deep Learning models. It contains a variety of models, from classics such as seq2seq to more complex deep neural networks. The models can all be used in the same way, using fit() and predict() functions,

  • Free software: MIT

Documentation

Features

  • Univariate model and multivariate model
  • Point estimation and interval estimation
  • Unified modelling with Multiple items

Models list

Model Paper
Seq2Seq Sequence to Sequence Learning with Neural Networks
DeepAR DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
Lstnet Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
MQ-RNN A Multi-Horizon Quantile Recurrent Forecaster
N-Beats N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
TCN An empirical evaluation of generic convolutional and recurrent networks for sequence modeling
Transformer Attention Is All You Need
Informer Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Autoformer Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
TFT Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
MAE Masked Autoencoders Are Scalable Vision Learners

LICENSE

This project is licensed under the MIT License - see the LICENSE file for details.

Credits

This package was created with Cookiecutter and the zillionare/cookiecutter-pypackage project template.