Contents

gluonts 0.15.1

0

Probabilistic time series modeling in Python.

Probabilistic time series modeling in Python.

Stars: 4571, Watchers: 4571, Forks: 750, Open Issues: 431

The awslabs/gluonts repo was created 5 years ago and the last code push was 2 months ago.
The project is very popular with an impressive 4571 github stars!

How to Install gluonts

You can install gluonts using pip

pip install gluonts

or add it to a project with poetry

poetry add gluonts

Package Details

Author
Amazon
License
Apache License 2.0
Homepage
https://github.com/awslabs/gluonts/
PyPi:
https://pypi.org/project/gluonts/
Documentation:
https://ts.gluon.ai/stable/
GitHub Repo:
https://github.com/awslabs/gluon-ts
No  gluonts  pypi packages just yet.

Errors

A list of common gluonts errors.

Code Examples

Here are some gluonts code examples and snippets.

GitHub Issues

The gluonts package has 431 open issues on GitHub

  • integrate with Lightning ecosystem CI
  • Predictor error with lead_time >0
  • Deprecate validated
  • RuntimeError: Cannot serialize type lightgbm.sklearn.LGBMRegressor.
  • Monte carlo em masking notebook
  • Adding torch.MQF2 (multivariate in time series)
  • pytorch: use distribution transforms when sampling
  • Add Deep NPTS model
  • Adding torch.deepvar
  • Bug in NPTS.log_weighted_distance_kernel - np.ndarray instead of np.array
  • ETS why are only additive models available?
  • Recommendations for scaling real features with DeepAR?
  • Support for Dynamic Real Features in Multivariate Grouper
  • Compute metrics from user forecasts
  • NaN losses leads to overfitting

See more issues on GitHub

Related Packages & Articles

thinc 9.1.1

A refreshing functional take on deep learning, compatible with your favorite libraries

spacy 3.8.2

Industrial-strength Natural Language Processing (NLP) in Python

keras 3.6.0

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. The core data structures of Keras are layers and models. The philosophy is to keep simple things simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code via subclassing).

fastai 2.7.17

fastai simplifies training fast and accurate neural nets using modern best practices

easyocr 1.7.2

End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution