cellflow.model.CellFlow.prepare_validation_data

CellFlow.prepare_validation_data(adata, name, n_conditions_on_log_iteration=None, n_conditions_on_train_end=None, predict_kwargs=None)[source]

Prepare the validation data.

Parameters:

  • adata (AnnData) – An AnnData object.

  • name (str) – Name of the validation data defining the key in cellflow.model.CellFlow.validation_data.

  • n_conditions_on_log_iteration (int | None) – Number of conditions to use for computation callbacks at each logged iteration. If None, use all conditions.

  • n_conditions_on_train_end (int | None) – Number of conditions to use for computation callbacks at the end of training. If None, use all conditions.

  • predict_kwargs (dict[str, Any] | None) – Keyword arguments for the prediction function cellflow.solvers._otfm.OTFlowMatching.predict() or cellflow.solvers._genot.GENOT.predict() used during validation.

Return type:

None

Returns:

: None, and updates the following fields: