二分类 AdaBoost#

此示例在由两个“高斯分位数”簇组成的非线性可分分类数据集上拟合 AdaBoost 决策树桩（请参阅 sklearn.datasets.make_gaussian_quantiles），并绘制决策边界和决策分数。决策分数的分布分别针对 A 类和 B 类的样本显示。每个样本的预测类别标签由决策分数的符号决定。决策分数大于零的样本被分类为 B，否则被分类为 A。决策分数的大小决定了与预测类别标签的相似程度。此外，可以构建一个包含所需 B 类纯度的新数据集，例如，仅选择决策分数高于某个值的样本。

# Author: Noel Dawe <[email protected]>
#
# License: BSD 3 clause

import matplotlib.pyplot as plt
import numpy as np

from sklearn.datasets import make_gaussian_quantiles
from sklearn.ensemble import AdaBoostClassifier
from sklearn.inspection import DecisionBoundaryDisplay
from sklearn.tree import DecisionTreeClassifier

# Construct dataset
X1, y1 = make_gaussian_quantiles(
    cov=2.0, n_samples=200, n_features=2, n_classes=2, random_state=1
)
X2, y2 = make_gaussian_quantiles(
    mean=(3, 3), cov=1.5, n_samples=300, n_features=2, n_classes=2, random_state=1
)
X = np.concatenate((X1, X2))
y = np.concatenate((y1, -y2 + 1))

# Create and fit an AdaBoosted decision tree
bdt = AdaBoostClassifier(
    DecisionTreeClassifier(max_depth=1), algorithm="SAMME", n_estimators=200
)

bdt.fit(X, y)

plot_colors = "br"
plot_step = 0.02
class_names = "AB"

plt.figure(figsize=(10, 5))

# Plot the decision boundaries
ax = plt.subplot(121)
disp = DecisionBoundaryDisplay.from_estimator(
    bdt,
    X,
    cmap=plt.cm.Paired,
    response_method="predict",
    ax=ax,
    xlabel="x",
    ylabel="y",
)
x_min, x_max = disp.xx0.min(), disp.xx0.max()
y_min, y_max = disp.xx1.min(), disp.xx1.max()
plt.axis("tight")

# Plot the training points
for i, n, c in zip(range(2), class_names, plot_colors):
    idx = np.where(y == i)
    plt.scatter(
        X[idx, 0],
        X[idx, 1],
        c=c,
        s=20,
        edgecolor="k",
        label="Class %s" % n,
    )
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.legend(loc="upper right")

plt.title("Decision Boundary")

# Plot the two-class decision scores
twoclass_output = bdt.decision_function(X)
plot_range = (twoclass_output.min(), twoclass_output.max())
plt.subplot(122)
for i, n, c in zip(range(2), class_names, plot_colors):
    plt.hist(
        twoclass_output[y == i],
        bins=10,
        range=plot_range,
        facecolor=c,
        label="Class %s" % n,
        alpha=0.5,
        edgecolor="k",
    )
x1, x2, y1, y2 = plt.axis()
plt.axis((x1, x2, y1, y2 * 1.2))
plt.legend(loc="upper right")
plt.ylabel("Samples")
plt.xlabel("Score")
plt.title("Decision Scores")

plt.tight_layout()
plt.subplots_adjust(wspace=0.35)
plt.show()

脚本总运行时间：（0 分钟 0.871 秒）