liveBook · Manning

PandasDataset

As explained in Time Series Forecasting Using Foundation Models

PandasDataset is a GluonTS dataset representation that stores time-series data in a format compatible with GluonTS models.

PandasDataset is GluonTS’s representation for organizing pandas time-series data so forecasting models such as Lag-Llama and Moirai can consume it. Build one from a long DataFrame by specifying the target column and item identifier; for Moirai, use the date column as the index. section 4.2.2 section 6.3.1

Weekly store sales

For Walmart weekly sales, create a dataset with Weekly_Sales as the target and Store as item_id. The resulting dataset represents separate store series and can be supplied to zero-shot Lag-Llama or Moirai forecasting.

How Time Series Forecasting Using Foundation Models covers it

How deep it goes
Defines construction from long DataFrames and date indexing, but defers forecasting-model internals.
Examples
Uses Walmart weekly sales, with Weekly_Sales as target and Store as the series identifier.
What it assumes
Assumes pandas DataFrame handling and requires identifying dates, targets, and series identifiers.
What you can do after
Apply it via GluonTS to prepare multiple dated series for Lag-Llama or Moirai prediction.
How it connects
Connects pandas DataFrame, GluonTS, Lag-Llama, Moirai, and zero-shot forecasting.
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.