11.20

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import cross_val_score, StratifiedKFold
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

# 从scikit-learn加载Iris数据集
iris = load_iris()
X = iris.data  # 特征矩阵
y = iris.target  # 标签

# 定义随机森林分类器
rf_classifier = RandomForestClassifier(n_estimators=100)

# 定义五折交叉验证
cv = StratifiedKFold(n_splits=5)

# 使用交叉验证评估模型性能
accuracy = cross_val_score(rf_classifier, X, y, cv=cv, scoring='accuracy')
precision = cross_val_score(rf_classifier, X, y, cv=cv, scoring='precision_weighted')
recall = cross_val_score(rf_classifier, X, y, cv=cv, scoring='recall_weighted')
f1 = cross_val_score(rf_classifier, X, y, cv=cv, scoring='f1_weighted')

# 输出评估结果
print(f'Accuracy: {accuracy.mean()}')
print(f'Precision: {precision.mean()}')
print(f'Recall: {recall.mean()}')
print(f'F1 Score: {f1.mean()}')