Contents

neuralforecast 1.7.3

0

Time series forecasting suite using deep learning models

Time series forecasting suite using deep learning models

Stars: 2760, Watchers: 2760, Forks: 320, Open Issues: 119

The Nixtla/neuralforecast repo was created 3 years ago and the last code push was an hour ago.
The project is very popular with an impressive 2760 github stars!

How to Install neuralforecast

You can install neuralforecast using pip

pip install neuralforecast

or add it to a project with poetry

poetry add neuralforecast

Package Details

Author
Nixtla
License
Apache Software License 2.0
Homepage
https://github.com/Nixtla/neuralforecast/
PyPi:
https://pypi.org/project/neuralforecast/
GitHub Repo:
https://github.com/Nixtla/neuralforecast

Classifiers

No  neuralforecast  pypi packages just yet.

Errors

A list of common neuralforecast errors.

Code Examples

Here are some neuralforecast code examples and snippets.

GitHub Issues

The neuralforecast package has 119 open issues on GitHub

  • Resources on Temporal Normalization
  • 'pydantic.fields' deprecated
  • How to interpret the trained model?
  • v1.6.0 conda package is broken
  • [FEAT] Unified DeepAR decoder with common.MLP.
  • Code stuck on "initalizing ddp" when using more than one gpu on neuralforecast AutoTFT, AutoNHITs
  • Predictions using missing value input (available_mask==0) and scalers ('minmax', 'robust')
  • Add monitor parameter for early stopping
  • Feature/insample test
  • Can't disable logging when using predict(...) method for a model.
  • [TimesNet]
  • [Recurrent] validation_step does not scale back the loss for point losses
  • Is there any plan to put TiDE algorithm into neuralforecast

See more issues on GitHub

Related Packages & Articles

onnx 1.16.1

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring).

PennyLane 0.37.0

PennyLane is a cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Train a quantum computer the same way as a neural network.

orbit-ml 1.1.4.9

Orbit is a package for Bayesian time series modeling and inference.

kornia 0.7.3

Open Source Differentiable Computer Vision Library for PyTorch