Implementation:DistrictDataLabs Yellowbrick ValidationCurve Visualizer

Knowledge Sources	Yellowbrick Yellowbrick Docs
Domains	Machine_Learning, Model_Selection, Visualization
Last Updated	2026-02-08 00:00 GMT

Overview

Concrete tool for diagnosing the effect of a single hyperparameter on model performance via validation curve visualization, provided by the Yellowbrick library.

Description

The ValidationCurve visualizer wraps scikit-learn's sklearn.model_selection.validation_curve utility and produces a plot showing how training and cross-validated test scores vary across a range of values for a single hyperparameter. For each hyperparameter value, it computes k-fold cross-validated scores, then plots the mean score with a shaded region representing one standard deviation of variability. Two curves are drawn: one for the training score and one for the cross-validation score.

The class extends ModelVisualizer from the Yellowbrick base module. On calling fit(X, y), the visualizer delegates to scikit-learn's validation_curve function, stores the resulting training and test score arrays, computes their means and standard deviations, and calls draw() to render the plot. The x-axis can optionally use a logarithmic scale via the logx parameter, which is useful for hyperparameters that span several orders of magnitude (e.g. regularization coefficients).

Usage

Use this visualizer when you want to visually tune a single hyperparameter for any scikit-learn estimator that implements fit and predict (or score). It is appropriate for classifiers, regressors, and clusterers with a valid scoring metric.

Code Reference

Source Location

• Repository: yellowbrick
• File: yellowbrick/model_selection/validation_curve.py
• Class Lines: L34-293 (class), L157-171 (__init__), L196-246 (fit)
• Quick Method Lines: L300-431

Signature

class ValidationCurve(ModelVisualizer):
    def __init__(
        self,
        estimator,
        param_name,
        param_range,
        ax=None,
        logx=False,
        groups=None,
        cv=None,
        scoring=None,
        n_jobs=1,
        pre_dispatch="all",
        markers='-d',
        **kwargs
    ):

Import

from yellowbrick.model_selection import ValidationCurve

I/O Contract

Inputs

Name	Type	Required	Description
estimator	scikit-learn estimator	Yes	An object implementing fit and predict. Cloned for each validation.
param_name	string	Yes	Name of the hyperparameter to vary.
param_range	array-like, shape (n_values,)	Yes	The values of the hyperparameter to evaluate.
ax	matplotlib.Axes	No	The axes object to plot the figure on.
logx	boolean	No	If True, plots x-axis with logarithmic scale. Default: False.
groups	array-like, shape (n_samples,)	No	Group labels for samples used in train/test splitting.
cv	int, CV generator, or iterable	No	Cross-validation splitting strategy. Default: None (3-fold).
scoring	string, callable, or None	No	Scoring metric. Default: None (estimator's default scorer).
n_jobs	integer	No	Number of parallel jobs. Default: 1.
pre_dispatch	integer or string	No	Number of predispatched jobs. Default: "all".
markers	string	No	Matplotlib marker style. Default: '-d'.

The fit(X, y) method accepts:

Name	Type	Required	Description
X	array-like, shape (n_samples, n_features)	Yes	Training feature matrix.
y	array-like, shape (n_samples,)	No	Target values. None for unsupervised learning.

Outputs

Name	Type	Description
train_scores_	array, shape (n_ticks, n_cv_folds)	Raw scores on training sets for each param value and fold.
train_scores_mean_	array, shape (n_ticks,)	Mean training score for each hyperparameter value.
train_scores_std_	array, shape (n_ticks,)	Standard deviation of training scores for each hyperparameter value.
test_scores_	array, shape (n_ticks, n_cv_folds)	Raw scores on test sets for each param value and fold.
test_scores_mean_	array, shape (n_ticks,)	Mean cross-validated test score for each hyperparameter value.
test_scores_std_	array, shape (n_ticks,)	Standard deviation of cross-validated test scores for each hyperparameter value.

Usage Examples

Basic Usage

import numpy as np
from sklearn.svm import SVC
from yellowbrick.model_selection import ValidationCurve

# Define the hyperparameter range
param_range = np.logspace(-6, -1, 5)

# Create and fit the visualizer
viz = ValidationCurve(
    SVC(), param_name="gamma", param_range=param_range, cv=5, scoring="accuracy"
)
viz.fit(X_train, y_train)
viz.show()

Quick Method

from yellowbrick.model_selection import validation_curve
from sklearn.svm import SVC
import numpy as np

validation_curve(
    SVC(), X_train, y_train,
    param_name="gamma", param_range=np.logspace(-6, -1, 5), cv=5
)

Related Pages

Implements Principle

• Principle:DistrictDataLabs_Yellowbrick_Validation_Curve_Analysis

Requires Environment

• Environment:DistrictDataLabs_Yellowbrick_Python_Scikit_Learn_Environment