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

# 创建自定义数据集

np.random.seed(42)

X, y = datasets.make_blobs(n_samples=100, centers=2, random_state=42)

# 可选：添加一些噪声

X = X + np.random.randn(100, 2) * 0.1

# 数据标准化

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)

# 使用 SVM 进行分类

svm = SVC(kernel='linear')

svm.fit(X_train, y_train)

# 预测测试集

y_pred = svm.predict(X_test)

# 可视化结果

plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap='viridis')

plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap='viridis', alpha=0.5)

plt.title('SVM 分类结果')

plt.xlabel('特征1')

plt.ylabel('特征2')

plt.show()