sklearn.model_selection.learning_curve

learning_curve(
    estimator,
    X,
    y,
    *,
    groups=None,
    train_sizes=array([0.1  , 0.325, 0.55 , 0.775, 1.   ]),
    cv=None,
    scoring=None,
    exploit_incremental_learning=False,
    n_jobs=None,
    pre_dispatch='all',
    verbose=0,
    shuffle=False,
    random_state=None,
    error_score=nan,
    return_times=False,
    fit_params=None,
)

import numpy as np
import matplotlib.pyplot as plt
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_val_score


def true_fun(X):
    return np.cos(1.5 * np.pi * X)


np.random.seed(0)

n_samples = 30
degrees = [1, 4, 15]

X = np.sort(np.random.rand(n_samples))
y = true_fun(X) + np.random.randn(n_samples) * 0.1

plt.figure(figsize=(14, 5))
for i in range(len(degrees)):
    ax = plt.subplot(1, len(degrees), i + 1)
    plt.setp(ax, xticks=(), yticks=())

    polynomial_features = PolynomialFeatures(degree=degrees[i], include_bias=False)
    linear_regression = LinearRegression()
    pipeline = Pipeline(
        [
            ("polynomial_features", polynomial_features),
            ("linear_regression", linear_regression),
        ]
    )
    pipeline.fit(X[:, np.newaxis], y)

    # Evaluate the models using crossvalidation
    scores = cross_val_score(
        pipeline, X[:, np.newaxis], y, scoring="neg_mean_squared_error", cv=10
    )

    X_test = np.linspace(0, 1, 100)
    plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
    plt.plot(X_test, true_fun(X_test), label="True function")
    plt.scatter(X, y, edgecolor="b", s=20, label="Samples")
    plt.xlabel("x")
    plt.ylabel("y")
    plt.xlim((0, 1))
    plt.ylim((-2, 2))
    plt.legend(loc="best")
    plt.title(
        "Degree {}\nMSE = {:.2e}(+/- {:.2e})".format(
            degrees[i], -scores.mean(), scores.std()
        )
    )
plt.show()

>>> import numpy as np
>>> from sklearn.model_selection import validation_curve
>>> from sklearn.datasets import load_iris
>>> from sklearn.linear_model import Ridge

>>> np.random.seed(0)
>>> X, y = load_iris(return_X_y=True)
>>> indices = np.arange(y.shape[0])
>>> np.random.shuffle(indices)
>>> X, y = X[indices], y[indices]

>>> train_scores, valid_scores = validation_curve(
...     Ridge(), X, y, param_name="alpha", param_range=np.logspace(-7, 3, 3),
...     cv=5)
>>> train_scores
array([[0.93..., 0.94..., 0.92..., 0.91..., 0.92...],
       [0.93..., 0.94..., 0.92..., 0.91..., 0.92...],
       [0.51..., 0.52..., 0.49..., 0.47..., 0.49...]])
>>> valid_scores
array([[0.90..., 0.84..., 0.94..., 0.96..., 0.93...],
       [0.90..., 0.84..., 0.94..., 0.96..., 0.93...],
       [0.46..., 0.25..., 0.50..., 0.49..., 0.52...]])

import matplotlib.pyplot as plt
import numpy as np

from sklearn.datasets import load_digits
from sklearn.svm import SVC
from sklearn.model_selection import validation_curve

X, y = load_digits(return_X_y=True)
subset_mask = np.isin(y, [1, 2])  # binary classification: 1 vs 2
X, y = X[subset_mask], y[subset_mask]

param_range = np.logspace(-6, -1, 5)
train_scores, test_scores = validation_curve(
    SVC(),
    X,
    y,
    param_name="gamma",
    param_range=param_range,
    scoring="accuracy",
    n_jobs=2,
)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)

plt.title("Validation Curve with SVM")
plt.xlabel(r"$\gamma$")
plt.ylabel("Score")
plt.ylim(0.0, 1.1)
lw = 2
plt.semilogx(
    param_range, train_scores_mean, label="Training score", color="darkorange", lw=lw
)
plt.fill_between(
    param_range,
    train_scores_mean - train_scores_std,
    train_scores_mean + train_scores_std,
    alpha=0.2,
    color="darkorange",
    lw=lw,
)
plt.semilogx(
    param_range, test_scores_mean, label="Cross-validation score", color="navy", lw=lw
)
plt.fill_between(
    param_range,
    test_scores_mean - test_scores_std,
    test_scores_mean + test_scores_std,
    alpha=0.2,
    color="navy",
    lw=lw,
)
plt.legend(loc="best")
plt.show()

>>> from sklearn.model_selection import learning_curve
>>> from sklearn.svm import SVC

>>> train_sizes, train_scores, valid_scores = learning_curve(
...     SVC(kernel='linear'), X, y, train_sizes=[50, 80, 110], cv=5)
>>> train_sizes
array([ 50, 80, 110])
>>> train_scores
array([[0.98..., 0.98 , 0.98..., 0.98..., 0.98...],
       [0.98..., 1.   , 0.98..., 0.98..., 0.98...],
       [0.98..., 1.   , 0.98..., 0.98..., 0.99...]])
>>> valid_scores
array([[1. ,  0.93...,  1. ,  1. ,  0.96...],
       [1. ,  0.96...,  1. ,  1. ,  0.96...],
       [1. ,  0.96...,  1. ,  1. ,  0.96...]])

- None, to use the default 5-fold cross validation,
- int, to specify the number of folds in a `(Stratified)KFold`,
- :term:`CV splitter`,
- An iterable yielding (train, test) splits as arrays of indices.

For int/None inputs, if the estimator is a classifier and ``y`` is
either binary or multiclass, :class:`StratifiedKFold` is used. In all
other cases, :class:`KFold` is used. These splitters are instantiated
with `shuffle=False` so the splits will be the same across calls.

Refer :ref:`User Guide <cross_validation>` for the various
cross-validation strategies that can be used here.

.. versionchanged:: 0.22
    ``cv`` default value if None changed from 3-fold to 5-fold.

.. versionadded:: 0.20

.. versionadded:: 0.24