liveBook · Manning

GluonTS

As explained in Time Series Forecasting Using Foundation Models

GluonTS is an open-source Python toolkit for building, training, and evaluating probabilistic time-series models.

GluonTS is an open-source Python toolkit for time-series analysis and forecasting. In probabilistic forecasting workflows, it can provide the data interface expected by models such as Lag-Llama. section 4.2

A typical workflow converts tabular observations into a PandasDataset. For example, Walmart sales data can be read with Pandas, converted to float32, and grouped by Store before being passed to a forecasting estimator. section 4.2.2

How Time Series Forecasting Using Foundation Models covers it

How deep it goes
Demonstrates dataset conversion and inference integration, but defers GluonTS internals and general model training workflows.
Examples
Uses Walmart store sales, eight-week horizons, CPU inference, and prediction intervals as concrete forecasting artifacts.
What it assumes
Assumes basic Python and tabular-data handling, while demonstrating dataset formatting and inference setup explicitly.
What you can do after
Apply it via PandasDataset to format time-series data for compatible probabilistic forecasting models.
How it connects
Connects Pandas, PandasDataset, Lag-Llama, estimators, predictors, and PyTorch Lightning.
Cover of Time Series Forecasting Using Foundation Models
liveBookmanning.com
Read Time Series Forecasting Using Foundation Models on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Time Series Forecasting Using Foundation Models. The section links point to the parts of the book it draws on.