gluonts
Probabilistic time series modeling in Python.
Decision gist · record as of 2026-08-14
Yes. GluonTS is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. It is the right choice if you need probabilistic deep learning forecasts with confidence intervals and want a mature, well-documented framework. Install it if your use case requires neural time series models; skip it if you need only classical statistical forecasting or simple point predictions.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10–3.14.
- PyTorch must be available as a runtime dependency for model training.
- Low friction install with a pure-Python wheel.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most production and research contexts.
last release 2026-07-31 (14 days) · last repo commit 2026-07-31 · 5,224 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 8,522,129 downloads/mo, #1,611 on PyPI
Alternatives
Verify before relying
pip install gluonts
import pandas as pd
from gluonts.dataset.pandas import PandasDataset
from gluonts.torch import DeepAREstimator
df = pd.read_csv('data.csv', index_col=0, parse_dates=True)
dataset = PandasDataset(df, target='value')
model = DeepAREstimator(prediction_length=12, freq='M').train(dataset)
forecasts = list(model.predict(dataset))- Whether core functionality requires the [torch] extra or if CPU-only forecasting is viable without it
- Performance characteristics and scalability limits for large time series datasets
- Availability and quality of pretrained Chronos models mentioned in the description
What it is and what it does
GluonTS is a Python package for building and training probabilistic time series forecasting models using deep learning. It provides high-level estimators that learn patterns in historical time series data and generate full probability distributions over future values, rather than single-point predictions. The package handles data loading, train-test splitting, model training, and forecast generation through a unified API.
Typical usage involves loading time series data into a dataset object, splitting it for training and evaluation, instantiating an estimator with forecast parameters, training on historical data, and then generating probabilistic predictions with confidence intervals. The package depends on numpy, pandas, pydantic, toolz, tqdm, and typing-extensions, making it compatible with standard data science workflows.
Use it for
- Train a model on historical sales data to forecast demand with prediction intervals for inventory planning
- Build probabilistic forecasts for energy consumption to quantify uncertainty in grid load predictions
- Generate time series predictions for financial metrics where understanding forecast confidence is critical
- Benchmark multiple deep learning architectures on your own time series dataset using available estimators
- Integrate pretrained models for zero-shot forecasting on new time series without retraining
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
GluonTS is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. It is the right choice if you need probabilistic deep learning forecasts with confidence intervals and want a mature, well-documented framework. Install it if your use case requires neural time series models; skip it if you need only classical statistical forecasting or simple point predictions.
Install
gluonts on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance with a recent release (14 days old) and strong repository signals (5224 stars, last commit 2026-07-31). Requires Python 3.10–3.14; the package explicitly supports current Python versions.
Requires Python 3.10–3.14. PyTorch must be available as a runtime dependency for model training.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most production and research contexts.
Quickstart
pip install gluonts
import pandas as pd
from gluonts.dataset.pandas import PandasDataset
from gluonts.torch import DeepAREstimator
df = pd.read_csv('data.csv', index_col=0, parse_dates=True)
dataset = PandasDataset(df, target='value')
model = DeepAREstimator(prediction_length=12, freq='M').train(dataset)
forecasts = list(model.predict(dataset))Verify before relying
- Whether core functionality requires the [torch] extra or if CPU-only forecasting is viable without it
- Performance characteristics and scalability limits for large time series datasets
- Availability and quality of pretrained Chronos models mentioned in the description
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packagesnumpypandaspydantictoolztqdmtyping-extensions |
| Maintenance | Actively maintained 14 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 8,522,129 / month, #1,611 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: gluonts-0.17.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “time series forecasting deep learning”
- gluontsGluonTS provides deep learning models for probabilistic time series…
- autogluon.timeseriesAutoGluon TimeSeries automates machine learning for time series…
- pytorch-forecastingPyTorch Forecasting provides neural network models and utilities for…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also chronos-forecasting · pytorch-forecasting · autogluon.timeseries · darts · hierarchicalforecast · pyro-ppl · autogluon · neuralforecast · neuralprophet · skforecast