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

GluonTS requires Python 3.6 or newer, and the easiest way to install it is via pip:

# support for mxnet models, faster datasets
pip install "gluonts[mxnet,pro]"

# support for torch models, faster datasets
pip install "gluonts[torch,pro]"

To illustrate how to use GluonTS, we train a DeepAR-model and make predictions using the simple "airpassengers" dataset. The dataset consists of a single time-series, containing monthly international passengers between the years 1949 and 1960, a total of 144 values (12 years * 12 months). We split the dataset into train and test parts, by removing the last three years (36 month) from the train data. Thus, we will train a model on just the first nine years of data.

import matplotlib.pyplot as plt
from gluonts.dataset.util import to_pandas
from gluonts.dataset.pandas import PandasDataset
from gluonts.dataset.repository.datasets import get_dataset
from gluonts.model.deepar import DeepAREstimator
from gluonts.mx import Trainer

dataset = get_dataset("airpassengers")

deepar = DeepAREstimator(prediction_length=12, freq="M", trainer=Trainer(epochs=5))
model = deepar.train(dataset.train)

# Make predictions
true_values = to_pandas(list(dataset.test)[0])
true_values.to_timestamp().plot(color="k")

prediction_input = PandasDataset([true_values[:-36], true_values[:-24], true_values[:-12]])
predictions = model.predict(prediction_input)

for color, prediction in zip(["green", "blue", "purple"], predictions):
    prediction.plot(color=f"tab:{color}")

plt.legend(["True values"], loc="upper left", fontsize="xx-large")

Note that the forecasts are displayed in terms of a probability distribution: The shaded areas represent the 50% and 90% prediction intervals, respectively, centered around the median.

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

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:

@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}
}

• Documentation (stable)
• Documentation (development)

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

• Tutorial at IJCAI 2021 (with videos) with YouTube link.
• Tutorial at WWW 2020 (with videos)
• Tutorial at SIGMOD 2019
• Tutorial at KDD 2019
• Tutorial at VLDB 2018
• Neural Time Series with GluonTS
• International Symposium of Forecasting: Deep Learning for Forecasting workshop