目录
代码:
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 导入鸢尾花数据集
iris = datasets.load_iris()
X = iris.data[:, :2] # 为了方便可视化,我们只使用前两个特征
y = iris.target
# 数据预处理
scaler = StandardScaler()
X = scaler.fit_transform(X)
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 定义绘制决策边界的函数
def plot_decision_boundary(model, X, y):
h = .02 # 步长
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.coolwarm, alpha=0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.coolwarm, edgecolors='k')
# 使用Hard Margin SVM进行分类
hard_svm = SVC(kernel='linear', C=1e6) # C设置为一个非常大的数,表示Hard Margin
hard_svm.fit(X_train, y_train)
# 绘制Hard Margin SVM的决策边界
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plot_decision_boundary(hard_svm, X_train, y_train)
plt.title('Hard Margin SVM')
# 使用Soft Margin SVM进行分类
soft_svm = SVC(kernel='linear', C=0.1) # C设置为一个较小的数,表示Soft Margin
soft_svm.fit(X_train, y_train)
# 绘制Soft Margin SVM的决策边界
plt.subplot(1, 2, 2)
plot_decision_boundary(soft_svm, X_train, y_train)
plt.title('Soft Margin SVM')
plt.show()