GluonTS - Probabilistic Time Series Modeling in Python

GluonTS is a Python toolkit for probabilistic time series modeling,
built around Apache MXNet (incubating).

GluonTS provides utilities for loading and iterating over time series datasets,
state of the art models ready to be trained, and building blocks to define
your own models and quickly experiment with different solutions.

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

pip install --upgrade mxnet~=1.7 gluonts

Dockerfiles

Dockerfiles compatible with Amazon Sagemaker can be found in the examples/dockerfiles folder.

Quick start guide

This simple example illustrates how to train a model from GluonTS on some data,
and then use it to make predictions. As a first step, we need to collect
some data: in this example we will use the volume of tweets mentioning the
AMZN ticker symbol.

We can now prepare a training dataset for our model to train on.
Datasets in GluonTS are essentially iterable collections of
dictionaries: each dictionary represents a time series
with possibly associated features. For this example, we only have one
entry, specified by the "start" field which is the timestamp of the
first datapoint, and the "target" field containing time series data.
For training, we will use data up to midnight on April 5th, 2015.

A forecasting model in GluonTS is a predictor object. One way of obtaining
predictors is by training a correspondent estimator. Instantiating an
estimator requires specifying the frequency of the time series that it will
handle, as well as the number of time steps to predict. In our example
we're using 5 minutes data, so freq="5min",
and we will train a model to predict the next hour, so prediction_length=12.
We also specify some minimal training options.

During training, useful information about the progress will be displayed.
To get a full overview of the available options, please refer to the
documentation of DeepAREstimator (or other estimators) and Trainer.

We're now ready to make predictions: we will forecast the hour following
the midnight on April 15th, 2015.

Note that the forecast is displayed in terms of a probability distribution:
the shaded areas represent the 50% and 90% prediction intervals, respectively,
centered around the median (dark green line).

Further examples

The following are good entry-points to understand how to use
many features of GluonTS:

If you use GluonTS in a scientific publication, we encourage you to add
the following references to the related papers:

@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}
}

@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}
}

## awslabs/gluon-ts

## GluonTS - Probabilistic Time Series Modeling in Python

GluonTS is a Python toolkit for probabilistic time series modeling, built around Apache MXNet (incubating).

GluonTS provides utilities for loading and iterating over time series datasets, state of the art models ready to be trained, and building blocks to define your own models and quickly experiment with different solutions.

## Installation

GluonTS requires Python 3.7, and the easiest way to install it is via

`pip`

:## Dockerfiles

Dockerfiles compatible with Amazon Sagemaker can be found in the examples/dockerfiles folder.

## Quick start guide

This simple example illustrates how to train a model from GluonTS on some data, and then use it to make predictions. As a first step, we need to collect some data: in this example we will use the volume of tweets mentioning the AMZN ticker symbol.

The first 100 data points look like follows:

We can now prepare a training dataset for our model to train on. Datasets in GluonTS are essentially iterable collections of dictionaries: each dictionary represents a time series with possibly associated features. For this example, we only have one entry, specified by the

`"start"`

field which is the timestamp of the first datapoint, and the`"target"`

field containing time series data. For training, we will use data up to midnight on April 5th, 2015.A forecasting model in GluonTS is a

predictorobject. One way of obtaining predictors is by training a correspondentestimator. Instantiating an estimator requires specifying the frequency of the time series that it will handle, as well as the number of time steps to predict. In our example we're using 5 minutes data, so`freq="5min"`

, and we will train a model to predict the next hour, so`prediction_length=12`

. We also specify some minimal training options.During training, useful information about the progress will be displayed. To get a full overview of the available options, please refer to the documentation of

`DeepAREstimator`

(or other estimators) and`Trainer`

.We're now ready to make predictions: we will forecast the hour following the midnight on April 15th, 2015.

Note that the forecast is displayed in terms of a probability distribution: the shaded areas represent the 50% and 90% prediction intervals, respectively, centered around the median (dark green line).

## Further examples

The following are good entry-points to understand how to use many features of GluonTS:

The following modules illustrate how custom models can be implemented:

`gluonts.model.seasonal_naive`

: how to implement simple models using just NumPy and Pandas.`gluonts.model.simple_feedforward`

: how to define a trainable, Gluon-based model.## 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:

## Video

## Further Reading

## Overview tutorials

## Introductory material