机器学习实验如下import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import KFold
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
import requests
import os
1. 使用pandas从本地读取iris数据集
def read_with_pandas():
# 如果文件不存在则下载
if not os.path.exists('iris.csv'):
print("正在下载iris数据集...")
try:
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
response = requests.get(url)
with open('iris.csv', 'wb') as f:
f.write(response.content)
print("数据集下载完成！")
except:
print("下载失败，将直接使用sklearn数据集")
return None
# 读取数据
columns = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'class']
df = pd.read_csv('iris.csv', header=None, names=columns)print("\n【Pandas加载结果】")
print(f"数据集形状: {df.shape}")
print("前5行数据:")
print(df.head())
return df
2. 从scikit-learn直接加载iris数据集
def load_from_sklearn():
iris = load_iris()
X, y = iris.data, iris.target
print("\n【Sklearn加载结果】")
print(f"数据集形状: {X.shape}")
print(f"特征名称: {iris.feature_names}")
print(f"类别名称: {iris.target_names}")
return X, y, iris.target_names
3-4. 五折交叉验证和模型评估
def cross_validation_and_evaluation(X, y, target_names):
# 创建分类器
rf = RandomForestClassifier(n_estimators=100, random_state=42)
# 五折交叉验证
kf = KFold(n_splits=5, shuffle=True, random_state=42)# 存储评估指标
accuracies = []
precisions = []
recalls = []
f1_scores = []print("\n【五折交叉验证结果】")
for i, (train_idx, test_idx) in enumerate(kf.split(X)):X_train, X_test = X[train_idx], X[test_idx]y_train, y_test = y[train_idx], y[test_idx]# 训练模型rf.fit(X_train, y_train)# 预测y_pred = rf.predict(X_test)# 计算指标acc = accuracy_score(y_test, y_pred)precision = precision_score(y_test, y_pred, average='macro')recall = recall_score(y_test, y_pred, average='macro')f1 = f1_score(y_test, y_pred, average='macro')# 存储结果accuracies.append(acc)precisions.append(precision)recalls.append(recall)f1_scores.append(f1)print(f"\n折 {i+1}:")print(f" 准确度: {acc:.4f}")print(f" 精度: {precision:.4f}")print(f" 召回率: {recall:.4f}")print(f" F1值: {f1:.4f}")# 输出平均结果
print("\n【平均评估指标】")
print(f"平均准确度: {np.mean(accuracies):.4f}")
print(f"平均精度: {np.mean(precisions):.4f}")
print(f"平均召回率: {np.mean(recalls):.4f}")
print(f"平均F1值: {np.mean(f1_scores):.4f}")
主函数
def main():
print("========== Iris数据集实验 ==========")
# 步骤1: 用pandas读取
print("\n步骤1: 使用pandas读取iris数据集")
df = read_with_pandas()# 步骤2: 用sklearn读取
print("\n步骤2: 从scikit-learn加载iris数据集")
X, y, target_names = load_from_sklearn()# 步骤3-4: 交叉验证和评估
print("\n步骤3-4: 五折交叉验证和模型评估")
cross_validation_and_evaluation(X, y, target_names)print("\n========== 实验完成 ==========")
if name == "main":
main()