evalml.pipelines.components.Imputer

class evalml.pipelines.components.Imputer(categorical_impute_strategy='most_frequent', categorical_fill_value=None, numeric_impute_strategy='mean', numeric_fill_value=None, random_seed=0, **kwargs)

Imputes missing data according to a specified imputation strategy.

name = 'Imputer'

model_family = 'none'

hyperparameter_ranges = {'categorical_impute_strategy': ['most_frequent'], 'numeric_impute_strategy': ['mean', 'median', 'most_frequent']}

default_parameters = {'categorical_fill_value': None, 'categorical_impute_strategy': 'most_frequent', 'numeric_fill_value': None, 'numeric_impute_strategy': 'mean'}

Instance attributes

needs_fitting
parameters	Returns the parameters which were used to initialize the component

Methods:

__init__	Initalizes an transformer that imputes missing data according to the specified imputation strategy.”
clone	Constructs a new component with the same parameters and random state.
describe	Describe a component and its parameters
fit	Fits imputer to data. ‘None’ values are converted to np.nan before imputation and are
fit_transform	Fits on X and transforms X
load	Loads component at file path
save	Saves component at file path
transform	Transforms data X by imputing missing values. ‘None’ values are converted to np.nan before imputation and are

Class Inheritance

evalml.pipelines.components.PerColumnImputer.transform evalml.pipelines.components.Imputer.__init__