https://github.com/nixtla/neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

Keywords

baselines baselines-zoo deep-learning deep-neural-networks deepar esrnn forecasting hierarchical-forecasting hint machine-learning nbeats nbeatsx neural-network nhits probabilistic-forecasting pytorch robust-regression tft time-series transformer

Keywords from Contributors

prediction automl econometrics anomaly-detection arima ets exponential-smoothing fbprophet mstl naive

Last synced: 5 months ago · JSON representation

Repository

Scalable and user friendly neural :brain: forecasting algorithms.

Basic Info

Host: GitHub
Owner: Nixtla
License: apache-2.0
Language: Python
Default Branch: main
Homepage: https://nixtlaverse.nixtla.io/neuralforecast
Size: 138 MB

Statistics

Stars: 3,716
Watchers: 38
Forks: 451
Open Issues: 118
Releases: 26

Topics

baselines baselines-zoo deep-learning deep-neural-networks deepar esrnn forecasting hierarchical-forecasting hint machine-learning nbeats nbeatsx neural-network nhits probabilistic-forecasting pytorch robust-regression tft time-series transformer

Created almost 5 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Code of conduct

README.md

Nixtla

Neural 🧠 Forecast

User friendly state-of-the-art neural forecasting models

[![CI](https://github.com/Nixtla/neuralforecast/actions/workflows/ci.yaml/badge.svg?branch=main)](https://github.com/Nixtla/neuralforecast/actions/workflows/ci.yaml) [![Python](https://img.shields.io/pypi/pyversions/neuralforecast)](https://pypi.org/project/neuralforecast/) [![PyPi](https://img.shields.io/pypi/v/neuralforecast?color=blue)](https://pypi.org/project/neuralforecast/) [![conda-nixtla](https://img.shields.io/conda/vn/conda-forge/neuralforecast?color=seagreen&label=conda)](https://anaconda.org/conda-forge/neuralforecast) [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Nixtla/neuralforecast/blob/main/LICENSE) [![docs](https://img.shields.io/website-up-down-green-red/http/nixtla.github.io/neuralforecast.svg?label=docs)](https://nixtla.github.io/neuralforecast/) [![All Contributors](https://img.shields.io/badge/all_contributors-11-orange.svg?style=flat-square)](#contributors-) **NeuralForecast** offers a large collection of neural forecasting models focusing on their performance, usability, and robustness. The models range from classic networks like RNNs to the latest transformers: `MLP`, `LSTM`, `GRU`, `RNN`, `TCN`, `TimesNet`, `BiTCN`, `DeepAR`, `NBEATS`, `NBEATSx`, `NHITS`, `TiDE`, `DeepNPTS`, `TSMixer`, `TSMixerx`, `MLPMultivariate`, `DLinear`, `NLinear`, `TFT`, `Informer`, `AutoFormer`, `FedFormer`, `PatchTST`, `iTransformer`, `StemGNN`, and `TimeLLM`.

Installation

You can install NeuralForecast with:

python pip install neuralforecast

or

python conda install -c conda-forge neuralforecast

Vist our Installation Guide for further details.

Quick Start

Minimal Example

```python from neuralforecast import NeuralForecast from neuralforecast.models import NBEATS from neuralforecast.utils import AirPassengersDF

nf = NeuralForecast( models = [NBEATS(inputsize=24, h=12, maxsteps=100)], freq = 'ME' )

nf.fit(df=AirPassengersDF) nf.predict() ```

Get Started with this quick guide.

Why?

There is a shared belief in Neural forecasting methods' capacity to improve forecasting pipeline's accuracy and efficiency.

Unfortunately, available implementations and published research are yet to realize neural networks' potential. They are hard to use and continuously fail to improve over statistical methods while being computationally prohibitive. For this reason, we created NeuralForecast, a library favoring proven accurate and efficient models focusing on their usability.

Features

Fast and accurate implementations of more than 30 state-of-the-art models. See the entire collection here.
Support for exogenous variables and static covariates.
Interpretability methods for trend, seasonality and exogenous components.
Probabilistic Forecasting with adapters for quantile losses and parametric distributions.
Train and Evaluation Losses with scale-dependent, percentage and scale independent errors, and parametric likelihoods.
Automatic Model Selection with distributed automatic hyperparameter tuning.
Familiar sklearn syntax: .fit and .predict.

Highlights

Official NHITS implementation, published at AAAI 2023. See paper and experiments.
Official NBEATSx implementation, published at the International Journal of Forecasting. See paper.
Unified withStatsForecast, MLForecast, and HierarchicalForecast interface NeuralForecast().fit(Y_df).predict(), inputs and outputs.
Built-in integrations with utilsforecast and coreforecast for visualization and data-wrangling efficient methods.
Integrations with Ray and Optuna for automatic hyperparameter optimization.
Predict with little to no history using Transfer learning. Check the experiments here.

Missing something? Please open an issue or write us in

Examples and Guides

The documentation page contains all the examples and tutorials.

📈 Automatic Hyperparameter Optimization: Easy and Scalable Automatic Hyperparameter Optimization with Auto models on Ray or Optuna.

🌡️ Exogenous Regressors: How to incorporate static or temporal exogenous covariates like weather or prices.

🔌 Transformer Models: Learn how to forecast with many state-of-the-art Transformers models.

👑 Hierarchical Forecasting: forecast series with very few non-zero observations.

👩‍🔬 Add Your Own Model: Learn how to add a new model to the library.

Models

See the entire collection here.

Missing a model? Please open an issue or write us in

How to contribute

If you wish to contribute to the project, please refer to our contribution guidelines.

References

This work is highly influenced by the fantastic work of previous contributors and other scholars on the neural forecasting methods presented here. We want to highlight the work of Boris Oreshkin, Slawek Smyl, Bryan Lim, and David Salinas. We refer to Benidis et al. for a comprehensive survey of neural forecasting methods.

🙏 How to cite

If you enjoy or benefit from using these Python implementations, a citation to the repository will be greatly appreciated.

bibtex @misc{olivares2022library_neuralforecast, author={Kin G. Olivares and Cristian Challú and Azul Garza and Max Mergenthaler Canseco and Artur Dubrawski}, title = {{NeuralForecast}: User friendly state-of-the-art neural forecasting models.}, year={2022}, howpublished={{PyCon} Salt Lake City, Utah, US 2022}, url={https://github.com/Nixtla/neuralforecast} }

Contributors ✨

Thanks goes to these wonderful people (emoji key):

_azul 💻 🚧	_{Cristian Challu} 💻 🚧	_{José Morales} 💻 🚧	_mergenthaler 📖 💻	_Kin 💻 🐛 🔣	_{Greg DeVos} 🤔	_Alejandro 💻
_stefanialvs 🎨	_{Ikko Ashimine} 🐛	_vglaucus 🐛	_{Pietro Monticone} 🐛

This project follows the all-contributors specification. Contributions of any kind welcome!

Owner

Name: Nixtla
Login: Nixtla
Kind: organization
Email: ops@nixtla.io
Location: United States of America

Website: https://www.nixtla.io/
Twitter: nixtlainc
Repositories: 13
Profile: https://github.com/Nixtla

Open Source Time Series Ecosystem

Committers

Last synced: 9 months ago

All Time

Total Commits: 1,006
Total Committers: 49
Avg Commits per committer: 20.531
Development Distribution Score (DDS): 0.629

Past Year

Commits: 95
Committers: 14
Avg Commits per committer: 6.786
Development Distribution Score (DDS): 0.695

Top Committers

Name	Email	Commits
FedericoGarza	f**z@g**m	373
kdgutier	k**s@g**m	143
Cristian	c**u@g**m	96
mergenthaler	m**m@g**m	79
José Morales	j**2@g**m	75
Olivier Sprangers	4****t	45
allcontributors[bot]	4****]	34
Marco	m**o@n**o	24
dependabot[bot]	4****]	14
David Luo	6****o	11
npredrag	d**4@g**m	11
FedericoGarza	F**a@g**m	10
Ubuntu	u**u@i**l	10
Ubuntu	u**u@i**l	9
t-minus	g**g@g**m	9
alejandroxag	a**4@g**m	8
kdgutier	k**r@g**g	6
Stefania La Vattiata	s**a@K**l	5
shibzhou	s**3@g**m	5
jasminerienecker	9****r	5
Kin Gtz Olivares	k**s@K**l	3
Tyler Nisonoff	t**f@g**m	3
Mariana Menchero García	4****o	2
YanisA	8****4	1
Vinish M	v**a@g**m	1
Tyler Blume	t**e@h**m	1
Tracy Teal	t**l@g**m	1
Todd Gleason	t****k	1
Ronan McCarter	6****r	1
Pietro Monticone	3****e	1
and 19 more...

Committer Domains (Top 20 + Academic)

cornell.edu: 1 nunatac.it: 1 fazi.rs: 1 gpu6.int.autonlab.org: 1 ip-172-31-72-96.ec2.internal: 1 ip-172-31-93-236.ec2.internal: 1 github.com: 1 nixtla.io: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 443
Total pull requests: 504
Average time to close issues: 2 months
Average time to close pull requests: 15 days
Total issue authors: 270
Total pull request authors: 55
Average comments per issue: 2.09
Average comments per pull request: 2.04
Merged pull requests: 382
Bot issues: 0
Bot pull requests: 27

Past Year

Issues: 107
Pull requests: 165
Average time to close issues: 16 days
Average time to close pull requests: 9 days
Issue authors: 82
Pull request authors: 23
Average comments per issue: 1.66
Average comments per pull request: 1.73
Merged pull requests: 113
Bot issues: 0
Bot pull requests: 24

View more stats

Top Authors

Issue Authors

cchallu (22)
kdgutier (19)
iamyihwa (8)
candalfigomoro (8)
sdmishra123 (7)
ZhikangLai (7)
PotosnakW (7)
jmoralez (6)
Antoine-Schwartz (6)
LeonTing1010 (6)
yarnabrina (5)
elephaint (5)
kkckk1110 (5)
TDL77 (4)
tinased95 (4)

Pull Request Authors

jmoralez (95)
elephaint (90)
marcopeix (66)
cchallu (40)
kdgutier (31)
dependabot[bot] (27)
JQGoh (21)
FedericoGarza (13)
jasminerienecker (12)
carusyte (8)
LeonEthan (6)
AzulGarza (6)
cargecla1 (6)
tylernisonoff (5)
dluuo (4)

Top Labels

Issue Labels

bug (183) enhancement (88) feature (78) awaiting response (51) documentation (49) question (12) help wanted (11) fix (4) ⚔️ Quest (4) good first issue (3) requested (3) discussion (3)

Pull Request Labels

fix (54) feature (37) dependencies (35) enhancement (31) documentation (24) bug (7) ⚔️ Quest (7) breaking change (3) losses (1)

Packages

Total packages: 4
Total downloads:
- pypi 90,963 last-month
Total docker downloads: 260

Total dependent packages: 9
(may contain duplicates)
Total dependent repositories: 21
(may contain duplicates)
Total versions: 95
Total maintainers: 3

pypi.org: neuralforecast

Time series forecasting suite using deep learning models

Homepage: https://github.com/Nixtla/neuralforecast/
Documentation: https://neuralforecast.readthedocs.io/
License: Apache Software License 2.0
Latest release: 3.0.2
published 8 months ago

Versions: 33
Dependent Packages: 8
Dependent Repositories: 21
Downloads: 90,963 Last month
Docker Downloads: 260

Rankings

Stargazers count: 1.6%

Dependent packages count: 2.2%

Average: 2.8%

Downloads: 2.9%

Docker downloads count: 3.1%

Dependent repos count: 3.2%

Forks count: 3.7%

Maintainers (3)

fgarzar capybara MergenthalerMax

Last synced: 6 months ago

proxy.golang.org: github.com/nixtla/neuralforecast

Documentation: https://pkg.go.dev/github.com/nixtla/neuralforecast#section-documentation
License: apache-2.0
Latest release: v3.0.2+incompatible
published 8 months ago

Versions: 28
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 7.0%

Last synced: 6 months ago

proxy.golang.org: github.com/Nixtla/neuralforecast

Documentation: https://pkg.go.dev/github.com/Nixtla/neuralforecast#section-documentation
License: apache-2.0
Latest release: v3.0.2+incompatible
published 8 months ago

Versions: 28
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 7.0%

Last synced: 6 months ago

conda-forge.org: neuralforecast

State-of-the-art time series forecasting for PyTorch. `NeuralForecast` is a Python library for time series forecasting with deep learning models. It includes *benchmark datasets*, *data-loading utilities*, *evaluation functions*, statistical *tests*, univariate *model benchmarks* and *SOTA* models implemented in PyTorch and PyTorchLightning. PyPI: [https://pypi.org/project/neuralforecast/](https://pypi.org/project/neuralforecast/)

Homepage: https://github.com/Nixtla/neuralforecast/tree/main/
License: GPL-3.0-only
Latest release: 1.1.0
published over 3 years ago

Versions: 6
Dependent Packages: 1
Dependent Repositories: 0

Rankings

Stargazers count: 12.0%

Forks count: 18.1%

Average: 23.2%

Dependent packages count: 28.8%

Dependent repos count: 34.0%

Last synced: 6 months ago

https://github.com/nixtla/neuralforecast

Science Score: 46.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Nixtla

Neural 🧠 Forecast

User friendly state-of-the-art neural forecasting models

Installation

Quick Start

Why?

Features

Highlights

Examples and Guides

Models

How to contribute

References

🙏 How to cite

Contributors ✨

Owner

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: neuralforecast

Rankings

Maintainers (3)

proxy.golang.org: github.com/nixtla/neuralforecast

Rankings

proxy.golang.org: github.com/Nixtla/neuralforecast

Rankings

conda-forge.org: neuralforecast

Rankings