Skip to content

Add toto2 ensemble#349

Open
elmartinj wants to merge 8 commits into
TimeCopilot:mainfrom
elmartinj:add-toto2-fnf
Open

Add toto2 ensemble#349
elmartinj wants to merge 8 commits into
TimeCopilot:mainfrom
elmartinj:add-toto2-fnf

Conversation

@elmartinj

Copy link
Copy Markdown
Contributor

Adds a general TimeCopilot implementation of the Toto 2.0 Family-and-Friends forecasting ensemble.

It runs compatible foundation-model forecasters, computes per-series tsfeatures, applies the published frequency and horizon-specific XGBoost gating model, and returns forecasts using the standard TimeCopilot output conventions.

Changes

  • Added Toto2FnF under timecopilot.models.ensembles
  • Added support for published FnF model aliases and quantiles
  • Added automatic short, medium, and long horizon-bucket selection
  • Added frequency normalization across pandas alias versions
  • Added support for using a subset of the published model pool with renormalized weights
  • Added XGBoost as a dependency
  • Exported Toto2FnF from the ensembles package

Added unit tests for:

  • frequency normalization
  • horizon-term inference
  • model alias validation
  • quantile validation
  • weighted forecast generation

Notes
The published FnF ensemble uses a fixed ten-model order. Existing compatible TimeCopilot forecasters can be supplied using their published aliases.

The current TimeCopilot Toto wrapper targets Toto 1.0. A separate Toto 2.0 wrapper will be needed to reproduce the complete published ten-model pool.

elmartinj and others added 8 commits March 13, 2026 11:25
This tutorial contains an example with multiple indexes and subsequent tampering to the data in order to show resiliency and a real life use case of TC applied on cryptocurrency prices up to 2021.
Fix to the issue raised on empty dataframe, resulting from an inner merge where the existing dataframe that accumulated results and the newer one had diferent indices. A subsequent issue must be raised to either:
1 report a single model failure (on index matching)
2 fix the moirai discrepancy (only model that showed this issue)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant