prio-data / views_pipeline

VIEWS forecasting pipeline for monthly prediction runs. Includes MLops and QA for all models/ensembles.
Other
3 stars 3 forks source link

Create Missing Querysets for PGM-Level Models Based on Model Catalogs #117

Closed Polichinel closed 2 weeks ago

Polichinel commented 2 weeks ago

Issue: Create Missing Querysets for PGM-Level Models Based on Model Catalogs

Description
Review the model catalogs for PGM-level models to identify and create any missing querysets required for model pipelines. Adhere to ADR 011 - Common Querysets for Model Pipelines to ensure consistency and compatibility. Where possible, prioritize developing general unit tests to validate the querysets.

Objectives and Requirements

  1. Reference Model Catalogs:

    • Use the PGM-level model catalog entries to identify the necessary querysets for PGM-level models.
    • Ensure that each queryset aligns with the requirements outlined in ADR 011.
  2. Adhere to Queryset Standards:

    • Follow the structure and guidelines in ADR 011 to maintain consistency across querysets.
    • Reference existing querysets only if needed to ensure adherence to standards.
  3. Develop Unit Tests:

    • Where feasible, develop general unit tests to validate the created querysets, ensuring they meet model pipeline requirements.

Tasks

Next Steps
Once querysets are created and validated, we will move on with the creation of missing model scaffolding and then get_data functions for each model

Labels
PGM-level, queryset creation, model catalog, validation