Skip to content

Separate data providers voor training/test #325

@wowtor

Description

@wowtor

See #315

Goal is to enable use-cases:

  • calculate LLRs on a separate data set (e.g. case LLRs)
  • use a pre-trained model (no training data required)

Current situation:

data:
  provider:
    method: parse_features_from_csv_url
    url: ...
  
  splits:
    strategy: cross_validation_sources
    folds: 5

New situation:

  • new property: data.training, data provider for training data
  • only one of data.splits or data.training is allowed
  • if data.training is available, use data.provider as test data
  • if both data.training and data.splits are unavailable, use all data as test data
data:
  training:
    method: parse_features_from_csv_url
    url: ...

  provider:
    method: parse_features_from_csv_url
    url: ...

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions