【AI知识】有监视学习分类使命之支持向量机 - IT评测·应用市场-qidao123.com

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
# 创建线性可分数据集
def generate_linear_data():
# 使用sklearn生成一个线性可分的数据集
X, y = datasets.make_classification(n_samples=200, n_features=2, n_informative=2,
n_redundant=0, n_clusters_per_class=1, class_sep=2)
return X, y
# 创建非线性可分数据集
def generate_nonlinear_data():
# 使用sklearn生成一个非线性可分的数据集
# 它生成的是一个包含两个类别的数据集，其中样本数据分布在两个同心圆形状的区域内
X, y = datasets.make_circles(n_samples=200, noise=0.1, factor=0.5)
return X, y
# 绘制SVM的决策边界
def plot_decision_boundary(X, y, clf):
h = 0.02 # 网格间距
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 = clf.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, alpha=0.3)
plt.scatter(X[:, 0], X[:, 1], c=y, marker='o', edgecolors='k', s=50)
plt.title("SVM Decision Boundary")
plt.show()
# 训练并可视化SVM模型
def train_and_visualize(X, y, kernel_type='linear'):
# 切分数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
# 数据标准化
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# 初始化SVM分类器
clf = SVC(kernel=kernel_type)
# 训练SVM
clf.fit(X_train, y_train)
# 打印支持向量信息
print(f"Number of support vectors: {len(clf.support_)}")
# 可视化决策边界
plot_decision_boundary(X_train, y_train, clf)
# 主函数
def main():
# 1. 线性可分数据
print("Training with linearly separable data...")
X_linear, y_linear = generate_linear_data()
train_and_visualize(X_linear, y_linear, kernel_type='linear')
# 2. 非线性可分数据
print("Training with non-linearly separable data...")
X_nonlinear, y_nonlinear = generate_nonlinear_data()
train_and_visualize(X_nonlinear, y_nonlinear, kernel_type='rbf')
if __name__ == "__main__":
main()

复制代码