cellflow.data.PredictionData¶

class cellflow.data.PredictionData(cell_data, split_covariates_mask, split_idx_to_covariates, perturbation_idx_to_covariates, perturbation_idx_to_id, condition_data, control_to_perturbation, max_combination_length, null_value, data_manager)[source]¶

Data container to perform prediction.

Parameters:

src_data – Dictionary with data for source cells.
condition_data (dict[str, ndarray[tuple[Any, ...], dtype[float64]]]) – Dictionary with embeddings for conditions.
control_to_perturbation (dict[int, ndarray[tuple[Any, ...], dtype[float64]]]) – Mapping from control index to target distribution indices.
covariate_encoder – Encoder for the primary covariate.
max_combination_length (int) – Maximum number of covariates in a combination.
null_value (Any) – Token to use for masking null_value.
cell_data (Array)
split_covariates_mask (Array)
split_idx_to_covariates (dict[int, tuple[Any, ...]])
perturbation_idx_to_covariates (dict[int, tuple[str, ...]])
perturbation_idx_to_id (dict[int, Any])
data_manager (Any)

Methods

Attributes

`n_controls`	Returns the number of control covariate values.
`n_perturbation_covariates`	Returns the number of perturbation covariates.
`n_perturbations`	Returns the number of perturbation covariate combinations.
`cell_data`
`split_covariates_mask`
`split_idx_to_covariates`
`perturbation_idx_to_covariates`
`perturbation_idx_to_id`
`condition_data`
`control_to_perturbation`
`max_combination_length`
`null_value`
`data_manager`