Implementation:Scikit learn Scikit learn Exceptions

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

Overview

Concrete tool for providing custom warnings and error classes used across scikit-learn.

Description

The sklearn.exceptions module defines custom exception and warning classes used throughout scikit-learn. Key classes include NotFittedError (raised when an estimator is used before fitting), ConvergenceWarning (for convergence issues), DataConversionWarning, FitFailedWarning, UndefinedMetricWarning, and UnsetMetadataPassedError for metadata routing errors.

Usage

Use these exception and warning classes when you need to handle scikit-learn-specific errors, such as catching NotFittedError to check if an estimator has been fitted, or filtering specific warnings during model training and evaluation.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/exceptions.py

Signature

class NotFittedError(ValueError, AttributeError):
class ConvergenceWarning(UserWarning):
class DataConversionWarning(UserWarning):
class DataDimensionalityWarning(UserWarning):
class EfficiencyWarning(UserWarning):
class FitFailedWarning(RuntimeWarning):
class UndefinedMetricWarning(UserWarning):
class UnsetMetadataPassedError(ValueError):
    def __init__(self, *, message, unrequested_params, routed_params):

Import

from sklearn.exceptions import NotFittedError, ConvergenceWarning

I/O Contract

Inputs

Name	Type	Required	Description
message	str	Yes	The error or warning message (for UnsetMetadataPassedError)
unrequested_params	dict	Yes	Parameters provided but not requested (for UnsetMetadataPassedError)
routed_params	dict	Yes	Dictionary of routed parameters (for UnsetMetadataPassedError)

Outputs

Name	Type	Description
exception	Exception	Raised exception to be caught by the caller

Usage Examples

Basic Usage

from sklearn.svm import LinearSVC
from sklearn.exceptions import NotFittedError

try:
    LinearSVC().predict([[1, 2], [2, 3]])
except NotFittedError as e:
    print("Estimator not fitted:", e)

Related Pages

• Principle:Scikit_learn_Scikit_learn_Metric_Evaluation