Implementation:Scikit learn Scikit learn ParamValidation

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Parameter Validation
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete utility module for validating estimator parameter types and values provided by scikit-learn.

Description

The _param_validation module provides a framework for declaring and enforcing parameter constraints on scikit-learn estimators and functions. It includes the validate_parameter_constraints function, the InvalidParameterError exception, and constraint classes like Interval, StrOptions, Options, HasMethods, and Hidden that describe valid parameter values.

Usage

Use these utilities when implementing scikit-learn estimators that need to validate their constructor parameters. Declare a _parameter_constraints dictionary and use the @validate_params decorator or call validate_parameter_constraints directly.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/utils/_param_validation.py

Signature

class InvalidParameterError(ValueError, TypeError):
    ...

def validate_parameter_constraints(parameter_constraints, params, caller_name):
    ...

def validate_params(prefer_skip_nested_validation):
    ...

class Interval:
    ...

class StrOptions:
    ...

class Options:
    ...

class HasMethods:
    ...

class Hidden:
    ...

Import

from sklearn.utils._param_validation import (
    Interval,
    InvalidParameterError,
    StrOptions,
    validate_params,
)

I/O Contract

Inputs

Name	Type	Required	Description
parameter_constraints	dict	Yes	Dictionary mapping parameter names to lists of constraints
params	dict	Yes	Dictionary of parameter name to parameter value pairs to validate
caller_name	str	Yes	Name of the estimator or function for error messages

Outputs

Name	Type	Description
None	None	Raises InvalidParameterError if any parameter is invalid

Usage Examples

Basic Usage

from sklearn.utils._param_validation import validate_parameter_constraints, Interval
from numbers import Integral

constraints = {
    "n_neighbors": [Interval(Integral, 1, None, closed="left")],
}
params = {"n_neighbors": 5}
validate_parameter_constraints(constraints, params, caller_name="KNeighborsClassifier")

Related Pages

• Principle:Scikit_learn_Scikit_learn_Model_Instantiation