https://github.com/awslabs/gluonts

Probabilistic time series modeling in Python

Science Score: 46.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
✓
Committers with academic emails
7 of 116 committers (6.0%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (16.0%) to scientific vocabulary

Keywords

artificial-intelligence aws data-science deep-learning forecasting machine-learning mxnet neural-networks pytorch sagemaker time-series time-series-forecasting time-series-prediction timeseries torch

Keywords from Contributors

hyperparameter-optimization automated-machine-learning automl gluon tabular-data ensemble-learning transfer-learning autogluon structured-data transformers

Last synced: 5 months ago · JSON representation

Repository

Probabilistic time series modeling in Python

Basic Info

Host: GitHub
Owner: awslabs
License: apache-2.0
Language: Python
Default Branch: dev
Homepage: https://ts.gluon.ai
Size: 13.9 MB

Statistics

Stars: 4,982
Watchers: 77
Forks: 791
Open Issues: 444
Releases: 111

Topics

artificial-intelligence aws data-science deep-learning forecasting machine-learning mxnet neural-networks pytorch sagemaker time-series time-series-forecasting time-series-prediction timeseries torch

Created almost 7 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Code of conduct

GluonTS - Probabilistic Time Series Modeling in Python

📢 BREAKING NEWS: We released Chronos, a suite of pretrained models for zero-shot time series forecasting. Chronos can generate accurate probabilistic predictions for new time series not seen during training. Check it out here!

GluonTS is a Python package for probabilistic time series modeling, focusing on deep learning based models, based on PyTorch and MXNet.

Installation

GluonTS requires Python 3.7 or newer, and the easiest way to install it is via pip:

```bash

install with support for torch models

pip install "gluonts[torch]"

install with support for mxnet models

pip install "gluonts[mxnet]" ```

See the documentation for more info on how GluonTS can be installed.

Simple Example

To illustrate how to use GluonTS, we train a DeepAR-model and make predictions using the airpassengers dataset. The dataset consists of a single time series of monthly passenger numbers between 1949 and 1960. We train the model on the first nine years and make predictions for the remaining three years.

```py import pandas as pd import matplotlib.pyplot as plt

from gluonts.dataset.pandas import PandasDataset from gluonts.dataset.split import split from gluonts.torch import DeepAREstimator

Load data from a CSV file into a PandasDataset

df = pd.readcsv( "https://raw.githubusercontent.com/AileenNielsen/" "TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv", indexcol=0, parse_dates=True, ) dataset = PandasDataset(df, target="#Passengers")

Split the data for training and testing

trainingdata, testgen = split(dataset, offset=-36) testdata = testgen.generateinstances(predictionlength=12, windows=3)

Train the model and make predictions

model = DeepAREstimator( predictionlength=12, freq="M", trainerkwargs={"maxepochs": 5} ).train(trainingdata)

forecasts = list(model.predict(test_data.input))

Plot predictions

plt.plot(df["1954":], color="black") for forecast in forecasts: forecast.plot() plt.legend(["True values"], loc="upper left", fontsize="xx-large") plt.show() ```

[train-test]

Note, the forecasts are displayed in terms of a probability distribution and the shaded areas represent the 50% and 90% prediction intervals.

Contributing

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

Citing

If you use GluonTS in a scientific publication, we encourage you to add the following references to the related papers, in addition to any model-specific references that are relevant for your work:

bibtex @article{gluonts_jmlr, author = {Alexander Alexandrov and Konstantinos Benidis and Michael Bohlke-Schneider and Valentin Flunkert and Jan Gasthaus and Tim Januschowski and Danielle C. Maddix and Syama Rangapuram and David Salinas and Jasper Schulz and Lorenzo Stella and Ali Caner Türkmen and Yuyang Wang}, title = {{GluonTS: Probabilistic and Neural Time Series Modeling in Python}}, journal = {Journal of Machine Learning Research}, year = {2020}, volume = {21}, number = {116}, pages = {1-6}, url = {http://jmlr.org/papers/v21/19-820.html} }

bibtex @article{gluonts_arxiv, author = {Alexandrov, A. and Benidis, K. and Bohlke-Schneider, M. and Flunkert, V. and Gasthaus, J. and Januschowski, T. and Maddix, D. C. and Rangapuram, S. and Salinas, D. and Schulz, J. and Stella, L. and Türkmen, A. C. and Wang, Y.}, title = {{GluonTS: Probabilistic Time Series Modeling in Python}}, journal = {arXiv preprint arXiv:1906.05264}, year = {2019} }

Links

Documentation

References

JMLR MLOSS Paper
ArXiv Paper
Collected Papers from the group behind GluonTS: a bibliography.

Tutorials and Workshops

Owner

Name: Amazon Web Services - Labs
Login: awslabs
Kind: organization
Location: Seattle, WA

Website: http://amazon.com/aws/
Repositories: 914
Profile: https://github.com/awslabs

AWS Labs

GitHub Events

Total

Create event: 7
Issues event: 18
Release event: 4
Watch event: 389
Delete event: 1
Issue comment event: 25
Push event: 12
Pull request review comment event: 12
Pull request review event: 25
Pull request event: 31
Fork event: 42

Last Year

Create event: 7
Issues event: 18
Release event: 4
Watch event: 389
Delete event: 1
Issue comment event: 25
Push event: 12
Pull request review comment event: 12
Pull request review event: 25
Pull request event: 31
Fork event: 42

Committers

Last synced: 9 months ago

All Time

Total Commits: 1,481
Total Committers: 116
Avg Commits per committer: 12.767
Development Distribution Score (DDS): 0.726

Past Year

Commits: 18
Committers: 6
Avg Commits per committer: 3.0
Development Distribution Score (DDS): 0.5

Top Committers

Name	Email	Commits
Jasper	s**e@a**e	406
Lorenzo Stella	s**o@a**m	379
Kashif Rasul	k**l@g**m	54
Syama Sundar Rangapuram	r**r@g**m	43
Alexander Alexandrov	a**e@a**m	40
Valentin Flunkert	v****l	39
Danielle Robinson	d**x@g**m	33
Abdul Fatir	A**s@g**m	32
Konstantinos Benidis	b**k@g**m	25
Aaron Spieler	2****r	25
Pedro Mercado	3****o	24
Jan Gasthaus	g**s@a**m	21
Oleksandr Shchur	s**o@a**m	21
Leonardo Araneda Freccero	a****g	18
zoolhasson	4****n	17
Pascal	6****n	16
Caner Turkmen	t**c@g**m	12
David Salinas	g****o	12
Michael Bohlke-Schneider	m**3@g**m	10
Bernie Wang	y**g@a**m	10
Eduard	e**3@g**t	10
Nils Kiele	n**e@a**e	9
RSNirwan	r**n@g**m	9
Oliver Borchert	o**e@a**m	9
Stephan Rabanser	r**s@a**m	8
yx1215	3****5	8
Shubham Kapoor	s****r	8
Sheng Zha	s****a	7
Elena Ehrlich	7****h	7
tim	3****i	6
and 86 more...

Committer Domains (Top 20 + Academic)

amazon.com: 11 amazon.de: 3 gmx.net: 1 yahoo.com.sg: 1 cs.ucsb.edu: 1 yandex.ru: 1 nyu.edu: 1 yma.io: 1 cs.ucla.edu: 1 cornell.edu: 1 usal.es: 1 vanderbilt.edu: 1 uni-potsdam.de: 1 c3.ai: 1 math.tu-berlin.de: 1 lausen.nl: 1 gmx.de: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 170
Total pull requests: 327
Average time to close issues: about 1 month
Average time to close pull requests: 13 days
Total issue authors: 113
Total pull request authors: 38
Average comments per issue: 2.52
Average comments per pull request: 1.05
Merged pull requests: 268
Bot issues: 0
Bot pull requests: 6

Past Year

Issues: 20
Pull requests: 25
Average time to close issues: 18 days
Average time to close pull requests: about 11 hours
Issue authors: 16
Pull request authors: 6
Average comments per issue: 0.6
Average comments per pull request: 0.36
Merged pull requests: 14
Bot issues: 0
Bot pull requests: 3

View more stats

Top Authors

Issue Authors

jaheba (12)
lostella (10)
shchur (7)
moghadas76 (7)
ArianKhorasani (5)
Serendipity31 (5)
satyrmipt (3)
300LiterPropofol (2)
LiPingYen (2)
hanlaoshi (2)
abdulfatir (2)
baniasbaabe (2)
pablovicente (2)
PaulRabich (2)
supersaiyajin7 (2)

Pull Request Authors

lostella (154)
jaheba (58)
shchur (29)
abdulfatir (17)
melopeo (16)
rshyamsundar (15)
Borda (15)
kashif (10)
dependabot[bot] (7)
leica2023 (7)
moghadas76 (3)
mcbaron (2)
sebasmos (2)
pantanurag555 (2)
ddelange (2)

Top Labels

Issue Labels

bug (78) enhancement (48) question (22) discussion (9) torch (5) documentation (3) API change (3) good first issue (3) dependency (2) datasets (2) pending v0.14.x backport (1) tests (1) RFC (1) model accuracy (1) regression (1) refactoring (1) multivariate (1) mxnet (1)

Pull Request Labels

backport (67) enhancement (47) bug fix (32) new feature (25) dependency (22) BREAKING (21) documentation (19) torch (19) models (16) CI (12) pr:docs-build-notebook (12) tests (10) datasets (9) plotting (7) pending v0.15.x backport (6) pr:test-r (5) pending v0.14.x backport (5) pending v0.16.x backport (4) dev setup (4) python (3) dependencies (3) mxnet (3) security fix (2) pending v0.12.x backport (2) pending v0.11.x backport (2) other change (2) pending v0.13.x backport (1) RFC (1) performance improvement (1) API change (1)

Packages

Total packages: 3
Total downloads:
- pypi 680,459 last-month
Total docker downloads: 1,058

Total dependent packages: 18
(may contain duplicates)
Total dependent repositories: 77
(may contain duplicates)
Total versions: 220
Total maintainers: 3

pypi.org: gluonts

Probabilistic time series modeling in Python.

Homepage: https://github.com/awslabs/gluonts/
Documentation: https://ts.gluon.ai/stable/
License: Apache License 2.0
Latest release: 0.16.2
published 8 months ago

Versions: 111
Dependent Packages: 18
Dependent Repositories: 77
Downloads: 680,459 Last month
Docker Downloads: 1,058

Rankings

Dependent packages count: 0.6%

Downloads: 0.8%

Stargazers count: 1.2%

Average: 1.3%

Forks count: 1.6%

Dependent repos count: 1.7%

Docker downloads count: 1.7%

Maintainers (3)

gluonts jaheba lostella

Last synced: 6 months ago

proxy.golang.org: github.com/awslabs/gluonts

Documentation: https://pkg.go.dev/github.com/awslabs/gluonts#section-documentation
License: apache-2.0
Latest release: v0.16.2
published 8 months ago

Versions: 104
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.4%

Average: 5.6%

Dependent repos count: 5.8%

Last synced: 6 months ago

anaconda.org: gluonts

GluonTS is a Python package for probabilistic time series modeling, focusing on deep learning based models, based on PyTorch and MXNet.

Homepage: https://ts.gluon.ai/stable/
License: Apache-2.0
Latest release: 0.16.0
published 11 months ago

Versions: 5
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 39.8%

Average: 48.7%

Dependent repos count: 57.7%

Last synced: 6 months ago

Dependencies

.github/workflows/codeql.yml actions

actions/checkout v3 composite
github/codeql-action/analyze v2 composite
github/codeql-action/autobuild v2 composite
github/codeql-action/init v2 composite

.github/workflows/docs.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
aws-actions/configure-aws-credentials v2 composite
extractions/setup-just v1 composite

.github/workflows/doctests.yaml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/flake8.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/mxnet_nightly.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/pypi.yml actions

actions/checkout v4 composite
actions/setup-python v4 composite
pypa/gh-action-pypi-publish release/v1 composite

.github/workflows/style_type_checks.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
extractions/setup-just v1 composite

.github/workflows/test_release_unix_nightly.yml actions

actions/setup-python v4 composite

.github/workflows/test_release_win32_nightly.yml actions

actions/setup-python v4 composite

.github/workflows/tests-nixtla.yaml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/tests-nursery.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/tests-prophet.yaml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/tests-r.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
r-lib/actions/setup-r v2 composite

.github/workflows/tests-torch.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/tests-xgboost.yaml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/tests.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

examples/dockerfiles/Dockerfile docker

python 3.7 build

src/gluonts/nursery/tsbench/Dockerfile docker

python 3.8.12-buster build

src/gluonts/nursery/tsbench/package-lock.json npm

pyright 1.1.206 development

src/gluonts/nursery/tsbench/package.json npm

pyright ^1.1.206 development

pyproject.toml pypi

requirements/requirements-arrow.txt pypi

pyarrow *

requirements/requirements-docs.txt pypi

black *
click *
docutils <=0.16
furo ==2022.6.4.1
holidays *
ipykernel *
ipython *
m2r2 *
matplotlib *
myst-parser *
nbconvert *
nbsphinx *
notedown *
optuna *
orjson *
pytest-runner *
recommonmark *
sphinx *

requirements/requirements-extras-anomaly-evaluation.txt pypi

numba *
scikit-learn *

requirements/requirements-extras-autogluon.txt pypi

autogluon ==0.2.0

requirements/requirements-extras-cpflows.txt pypi

requirements/requirements-extras-hierarchicalforecast.txt pypi

hierarchicalforecast *
statsforecast *

requirements/requirements-extras-m-competitions.txt pypi

statsmodels *

requirements/requirements-extras-prophet.txt pypi

prophet *

requirements/requirements-extras-r.txt pypi

rpy2 *

requirements/requirements-extras-sagemaker-sdk.txt pypi

fsspec *
s3fs *
sagemaker *

requirements/requirements-extras-shell.txt pypi

flask *
waitress *

requirements/requirements-extras-statsforecast.txt pypi

statsforecast *

requirements/requirements-mxnet.txt pypi

mxnet *
numpy <1.24

requirements/requirements-pytorch.txt pypi

protobuf *
pytorch-lightning >=1.5,<3
scipy *
torch >=1.9,<3

requirements/requirements-rotbaum-extra-methods.txt pypi

lightgbm >=2.3.1
scikit-garden >=0.1.2

requirements/requirements-rotbaum.txt pypi

scikit-learn >=0.22,<2
xgboost >=0.90,<2

requirements/requirements-test.txt pypi

flaky * test
holidays * test
matplotlib * test
orjson * test
pandas >=1.1 test
pytest >=6.0 test
pytest-cov ==2.6. test
pytest-timeout * test
pytest-xdist * test
requests * test
ujson * test

requirements/requirements.txt pypi

numpy *
pandas >=1.0,<3
pydantic *
toolz *
tqdm *
typing-extensions *

setup.py pypi

src/gluonts/nursery/SCott/requirements.txt pypi

numpy *
pytorchts ==0.2.0
tensorboard *
torch >=1.5.0

src/gluonts/nursery/daf/requirements.txt pypi

matplotlib ==3.3.2
numpy ==1.22.0
pandas ==1.1.5
scikit-learn ==0.23.2
scipy ==1.10.0
tensorboard ==2.3.0
torch ==1.13.1

src/gluonts/nursery/few_shot_prediction/pyproject.toml pypi

src/gluonts/nursery/tsbench/pyproject.toml pypi

test/ext/hierarchicalforecast/require-packages.txt pypi

hierarchicalforecast * test
statsforecast * test

test/ext/naive_2/require-packages.txt pypi

statsmodels * test

test/ext/prophet/require-packages.txt pypi

prophet * test

test/ext/rotbaum/require-packages.txt pypi

xgboost * test

test/ext/statsforecast/require-packages.txt pypi

statsforecast * test

test/mx/require-packages.txt pypi

mxnet * test

test/nursery/anomaly_detection/supervised_metrics/require-packages.txt pypi

sklearn * test

test/nursery/autogluon_tabular/require-packages.txt pypi

autogluon.tabular * test

test/nursery/sagemaker_sdk/require-packages.txt pypi

s3fs * test
sagemaker * test

test/shell/require-packages.txt pypi

flask * test
requests * test
waitress * test

test/torch/require-packages.txt pypi

torch * test

https://github.com/awslabs/gluonts

Science Score: 46.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

GluonTS - Probabilistic Time Series Modeling in Python

Installation

install with support for torch models

install with support for mxnet models

Simple Example

Load data from a CSV file into a PandasDataset

Split the data for training and testing

Train the model and make predictions

Plot predictions

Contributing

Citing

Links

Documentation

References

Tutorials and Workshops

Owner

GitHub Events

Total

Last Year

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: gluonts

Rankings

Maintainers (3)

proxy.golang.org: github.com/awslabs/gluonts

Rankings

anaconda.org: gluonts

Rankings

Dependencies