SVM使用python和CPLEX，加载目标函数的二次部分

import cplex
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

# 加载数据集
iris = datasets.load_iris()
X = iris.data
y = iris.target

# 数据预处理
scaler = StandardScaler()
X_scaled = 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_scaled, y, test_size=0.3, random_state=42)

# 使用scikit-learn的SVC来获取二次规划问题的参数
svc = SVC(kernel='linear', C=1.0)
svc.fit(X_train, y_train)

# 获取支持向量和系数
support_vectors = svc.support_vectors_
coef = svc.coef_

# 创建CPLEX问题实例
prob = cplex.Cplex()

# 添加变量
num_vars = X_train.shape[1] * len(support_vectors)
prob.variables.add(obj=[0] * num_vars, lb=[-cplex.infinity] * num_vars, ub=[cplex.infinity] * num_vars)

# 添加约束
for i in range(len(support_vectors)):
    for j in range(X_train.shape[1]):
        prob.linear_constraints.add(lin_expr=[[list(range(i * X_train.shape[1], (i + 1) * X_train.shape[1])), coef[i]]], senses=["G"], rhs=[-1])

# 添加目标函数（二次部分）
for i in range(len(support_vectors)):
    for j in range(X_train.shape[1]):
        for k in range(j, X_train.shape[1]):
            prob.objective.set_quadratic_coefficients({(i * X_train.shape[1] + j, i * X_train.shape[1] + k): support_vectors[i][j] * support_vectors[i][k]})

# 求解问题
prob.solve()

# 获取解
solution = prob.solution.get_values()