utils.helper.Eval_Imputation

utils.helper.Eval_Imputation(data, data_imp, x, y, ind)[source]

Calculates the median L1 distance between the original dataset and the imputed values for corrupted entries only.

Parameters

datanumpy ndarray: The data.
data_impnumpy ndarray: The imputed data.
x, y, indint: The indices of where corruption is applied.

Returns

L1float: The median L1 distance between original and imputed datasets at given

indices.