机器学习算法|支持向量机（Support Vector Machine，SVM）

# 导入必要的库
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import joblib  # 用于保存/加载模型

# 1. 加载数据集（以乳腺癌数据集为例）
data = datasets.load_breast_cancer()
X, y = data.data, data.target

# 2. 数据预处理
# 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)

# 标准化特征（SVM对特征尺度敏感）
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 3. 创建SVM模型
# 线性SVM
linear_svm = SVC(kernel='linear', C=1.0)  # C为惩罚参数
# 非线性SVM（使用高斯核RBF）
rbf_svm = SVC(kernel='rbf', gamma=0.1, C=1.0)  # gamma控制核函数的宽度

# 4. 训练模型
linear_svm.fit(X_train, y_train)
rbf_svm.fit(X_train, y_train)

# 5. 模型评估
def evaluate_model(model, X_test, y_test):
    y_pred = model.predict(X_test)
    print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
    print("\nClassification Report:")
    print(classification_report(y_test, y_pred))
    print("\nConfusion Matrix:")
    print(confusion_matrix(y_test, y_pred))

print("===== 线性SVM性能 =====")
evaluate_model(linear_svm, X_test, y_test)

print("\n===== 非线性SVM（RBF核）性能 =====")
evaluate_model(rbf_svm, X_test, y_test)

# 6. 保存模型（可选）
joblib.dump(linear_svm, 'linear_svm_model.pkl')
joblib.dump(rbf_svm, 'rbf_svm_model.pkl')

# 7. 加载模型并进行预测（示例）
loaded_model = joblib.load('linear_svm_model.pkl')
sample_data = scaler.transform([X_test[0]])  # 注意对新数据标准化
prediction = loaded_model.predict(sample_data)
print(f"\n预测结果: {prediction[0]}, 真实标签: {y_test[0]}")

from sklearn.model_selection import GridSearchCV
param_grid = {
    'C': [0.1, 1, 10],
    'gamma': [0.01, 0.1, 1]
}
grid_search = GridSearchCV(SVC(kernel='rbf'), param_grid, cv=5)
grid_search.fit(X_train, y_train)
print("最优参数:", grid_search.best_params_)

# 降维到2个特征（仅用于演示）
X_2d = X[:, :2]
X_train_2d, X_test_2d, y_train_2d, y_test_2d = train_test_split(X_2d, y, test_size=0.2)

model = SVC(kernel='rbf', C=1.0, gamma=0.5)
model.fit(X_train_2d, y_train_2d)

# 绘制决策边界
x_min, x_max = X_train_2d[:, 0].min()-1, X_train_2d[:, 0].max()+1
y_min, y_max = X_train_2d[:, 1].min()-1, X_train_2d[:, 1].max()+1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
                     np.arange(y_min, y_max, 0.02))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)

plt.contourf(xx, yy, Z, alpha=0.8)
plt.scatter(X_train_2d[:, 0], X_train_2d[:, 1], c=y_train_2d, edgecolors='k')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.title('SVM Decision Boundary (RBF Kernel)')
plt.show()