import numpy as np
from sklearn.model_selection import train_test_split, cross_val_score, StratifiedKFold
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.metrics import precision_score, recall_score, f1_score, accuracy_score
from sklearn.model_selection import cross_validate
# 1. 加载 Iris 数据集
iris = load_iris()
X = iris.data
y = iris.target
# 2. 使用留出法分割数据集（1/3 测试集，2/3 训练集）
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=42, stratify=y)
# 3. 训练支持向量机（SVM）分类算法
svm_model = SVC(kernel='linear', random_state=42)
svm_model.fit(X_train, y_train)
# 4. 使用五折交叉验证评估模型性能（准确度、精度、召回率、F1 值）
cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
scoring = ['accuracy', 'precision_weighted', 'recall_weighted', 'f1_weighted']
# 使用 cross_validate 计算交叉验证结果
cv_results = cross_validate(svm_model, X_train, y_train, cv=cv, scoring=scoring)
# 打印交叉验证结果
print(f"准确度（均值）: {cv_results['test_accuracy'].mean():.4f}")
print(f"精度（均值）: {cv_results['test_precision_weighted'].mean():.4f}")
print(f"召回率（均值）: {cv_results['test_recall_weighted'].mean():.4f}")
print(f"F1 分数（均值）: {cv_results['test_f1_weighted'].mean():.4f}")
# 5. 使用测试集评估模型性能
y_pred = svm_model.predict(X_test)
# 计算测试集上的性能指标
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')
# 打印测试集上的评估结果
print(f"\n测试集评估结果:")
print(f"准确度: {accuracy:.4f}")
print(f"精度: {precision:.4f}")
print(f"召回率: {recall:.4f}")
print(f"F1 分数: {f1:.4f}")
