cellflow.data.ValidationData¶
- class cellflow.data.ValidationData(cell_data, split_covariates_mask, split_idx_to_covariates, perturbation_covariates_mask, perturbation_idx_to_covariates, perturbation_idx_to_id, condition_data, control_to_perturbation, max_combination_length, null_value, data_manager, n_conditions_on_log_iteration=None, n_conditions_on_train_end=None)[source]¶
Data container for the validation data.
- Parameters:
cell_data (
ndarray) – The representation of cell data, e.g. PCA of gene expression data.split_covariates_mask (
ndarray) – Mask of the split covariates.split_idx_to_covariates (
dict[int,tuple[Any,...]]) – Dictionary explaining values insplit_covariates_mask.perturbation_covariates_mask (
ndarray) – Mask of the perturbation covariates.perturbation_idx_to_covariates (
dict[int,tuple[str,...]]) – Dictionary explaining values inperturbation_covariates_mask.condition_data (
dict[str,ndarray]) – Dictionary with embeddings for conditions.control_to_perturbation (
dict[int,ndarray]) – Mapping from control index to target distribution indices.max_combination_length (
int) – Maximum number of covariates in a combination.data_manager (
Any) – The data managern_conditions_on_log_iteration (
int|None) – Number of conditions to use for computation callbacks at each logged iteration. IfNone, use all conditions.n_conditions_on_train_end (
int|None) – Number of conditions to use for computation callbacks at the end of training. IfNone, use all conditions.null_value (Any)
Methods
Attributes
Returns the number of control covariate values.
Returns the number of perturbation covariates.
Returns the number of perturbation covariate combinations.