検証曲線 (Validation Curve)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

from __future__ import annotations

import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import validation_curve
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

def plot_validation_curve_for_svc() -> None:
    """SVC の正則化係数に対する検証曲線を描画して保存する。"""
    features, labels = make_classification(
        n_samples=1200,
        n_features=20,
        n_informative=5,
        n_redundant=2,
        n_repeated=0,
        n_classes=2,
        weights=[0.6, 0.4],
        flip_y=0.02,
        class_sep=1.2,
        random_state=42,
    )

    model = make_pipeline(StandardScaler(), SVC(kernel="rbf", gamma="scale"))
    param_range = np.logspace(-3, 2, 10)

    train_scores, valid_scores = validation_curve(
        estimator=model,
        X=features,
        y=labels,
        param_name="svc__C",
        param_range=param_range,
        scoring="roc_auc",
        cv=5,
        n_jobs=None,
    )

    train_mean = train_scores.mean(axis=1)
    train_std = train_scores.std(axis=1)
    valid_mean = valid_scores.mean(axis=1)
    valid_std = valid_scores.std(axis=1)

    plt.figure(figsize=(7, 5))
    plt.semilogx(param_range, train_mean, label="Train score", color="#1d4ed8")
    plt.fill_between(
        param_range,
        train_mean - train_std,
        train_mean + train_std,
        alpha=0.2,
        color="#1d4ed8",
    )
    plt.semilogx(param_range, valid_mean, label="Validation score", color="#ea580c")
    plt.fill_between(
        param_range,
        valid_mean - valid_std,
        valid_mean + valid_std,
        alpha=0.2,
        color="#ea580c",
    )
    plt.title("Validation Curve for SVC (ROC-AUC)")
    plt.xlabel("Regularization parameter C")
    plt.ylabel("Score")
    plt.ylim(0.5, 1.05)
    plt.legend(loc="best")
    plt.grid(alpha=0.3)

plot_validation_curve_for_svc()