{ "arguments": { "data": { "type_value": "Array", "description": "The data for which null values will be imputed." }, "lower": { "type_value": "Array", "default_python": "None", "default_rust": "None", "description": "A lower bound on data elements for each column. Used only if `categories` is `None`." }, "upper": { "type_value": "Array", "default_python": "None", "default_rust": "None", "description": "An upper bound on data elements for each column. Used only if `categories` is `None`." }, "categories": { "default_python": "None", "type_value": "Jagged", "default_rust": "None", "description": "The set of categories you want to be represented for each column of the data, if the data is categorical. Atomic type must match atomic type of data." }, "null_values": { "default_python": "None", "type_value": "Jagged", "default_rust": "None", "description": "The set of values that are considered null for each column of the data, if the data is categorical. Atomic type must match atomic type of data." }, "weights": { "default_python": "None", "type_value": "Jagged", "default_rust": "None", "description": "Optional. The weight of each category when imputing. Uniform weights are used if not specified." }, "distribution": { "type_value": "String", "default_python": "None", "default_rust": "None", "description": "The distribution to be used when imputing records. Used only if `categories` is `None`." }, "shift": { "type_value": "Array", "default_python": "None", "default_rust": "None", "description": "The expectation of the Gaussian distribution to be used for imputation. Used only if `distribution` is `Gaussian`." }, "scale": { "type_value": "Array", "default_python": "None", "default_rust": "None", "description": "The standard deviation of the Gaussian distribution to be used for imputation. Used only if `distribution` is `Gaussian`." } }, "id": "Impute", "name": "impute", "options": {}, "return": { "type_value": "Array", "description": "Data with null values replaced by imputed values." }, "description": "Replaces null values with draws from a specified distribution.\n\nIf the `categories` argument is provided, the data are considered to be categorical regardless of atomic type and the elements provided in `null_value` will be replaced with those in `categories` according to `weights`.\n\nIf the `categories` argument is not provided, the data are considered to be numeric and elements that are `f64::NAN` will be replaced according to the specified distribution.", "proto_id": 27 }