Note

Go to the end to download the full example code. or to run this example in your browser via Binder

绘制分类概率#

绘制不同分类器的分类概率。我们使用一个包含3个类别的数据集，并使用支持向量分类器、L1和L2惩罚的逻辑回归（多项式多类）、基于逻辑回归的一对多版本以及高斯过程分类来对其进行分类。

线性SVC默认不是一个概率分类器，但在此示例中启用了内置校准选项（ probability=True ）。

一对多逻辑回归默认不是一个多类分类器。因此，它在区分类别2和类别3时比其他估计器更困难。

Class 0, Class 1, Class 2, Class 0, Class 1, Class 2, Class 0, Class 1, Class 2, Class 0, Class 1, Class 2, Class 0, Class 1, Class 2, Probability

Accuracy (train) for L1 logistic: 83.3%
Accuracy (train) for L2 logistic (Multinomial): 82.7%
Accuracy (train) for L2 logistic (OvR): 79.3%
Accuracy (train) for Linear SVC: 82.0%
Accuracy (train) for GPC: 82.7%

# 作者：scikit-learn 开发者
# SPDX-License-Identifier：BSD-3-Clause

import matplotlib.pyplot as plt
import numpy as np
from matplotlib import cm

from sklearn import datasets
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.inspection import DecisionBoundaryDisplay
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.multiclass import OneVsRestClassifier
from sklearn.svm import SVC

iris = datasets.load_iris()
X = iris.data[:, 0:2]  # we only take the first two features for visualization
y = iris.target

n_features = X.shape[1]

C = 10
kernel = 1.0 * RBF([1.0, 1.0])  # for GPC

# 创建不同的分类器。
classifiers = {
    "L1 logistic": LogisticRegression(C=C, penalty="l1", solver="saga", max_iter=10000),
    "L2 logistic (Multinomial)": LogisticRegression(
        C=C, penalty="l2", solver="saga", max_iter=10000
    ),
    "L2 logistic (OvR)": OneVsRestClassifier(
        LogisticRegression(C=C, penalty="l2", solver="saga", max_iter=10000)
    ),
    "Linear SVC": SVC(kernel="linear", C=C, probability=True, random_state=0),
    "GPC": GaussianProcessClassifier(kernel),
}

n_classifiers = len(classifiers)

fig, axes = plt.subplots(
    nrows=n_classifiers,
    ncols=len(iris.target_names),
    figsize=(3 * 2, n_classifiers * 2),
)
for classifier_idx, (name, classifier) in enumerate(classifiers.items()):
    y_pred = classifier.fit(X, y).predict(X)
    accuracy = accuracy_score(y, y_pred)
    print(f"Accuracy (train) for {name}: {accuracy:0.1%}")
    for label in np.unique(y):
        # 绘制分类器提供的概率估计
        disp = DecisionBoundaryDisplay.from_estimator(
            classifier,
            X,
            response_method="predict_proba",
            class_of_interest=label,
            ax=axes[classifier_idx, label],
            vmin=0,
            vmax=1,
        )
        axes[classifier_idx, label].set_title(f"Class {label}")
        # 绘制预测属于给定类别的数据
        mask_y_pred = y_pred == label
        axes[classifier_idx, label].scatter(
            X[mask_y_pred, 0], X[mask_y_pred, 1], marker="o", c="w", edgecolor="k"
        )
        axes[classifier_idx, label].set(xticks=(), yticks=())
    axes[classifier_idx, 0].set_ylabel(name)

ax = plt.axes([0.15, 0.04, 0.7, 0.02])
plt.title("Probability")
_ = plt.colorbar(
    cm.ScalarMappable(norm=None, cmap="viridis"), cax=ax, orientation="horizontal"
)

plt.show()