每日总结46

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

 

# 加载 iris 数据集

iris = load_iris()

X, y = iris.data, iris.target

 

# 使用留出法留出 1/3 的样本作为测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=42)

 

from sklearn.linear_model import LogisticRegression

 

# 创建逻辑回归模型实例

logistic = LogisticRegression(max_iter=200)

 

# 训练模型

logistic.fit(X_train, y_train)

 

from sklearn.model_selection import cross_val_score

from sklearn.metrics import classification_report

 

# 使用五折交叉验证评估模型

scores = cross_val_score(logistic, X_train, y_train, cv=5, scoring='accuracy')

 

# 训练模型并预测

y_pred = logistic.predict(X_train)

 

# 输出模型性能报告

print("五折交叉验证准确度:", scores.mean())

print("分类报告：")

print(classification_report(y_train, y_pred))

 

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

 

# 使用测试集进行预测

y_test_pred = logistic.predict(X_test)

 

# 计算性能指标

accuracy = accuracy_score(y_test, y_test_pred)

precision = precision_score(y_test, y_test_pred, average='macro')

recall = recall_score(y_test, y_test_pred, average='macro')

f1 = f1_score(y_test, y_test_pred, average='macro')

 

# 输出性能指标

print(f"测试集准确度: {accuracy}")

print(f"测试集精度: {precision}")

print(f"测试集召回率: {recall}")

print(f"测试集F1值: {f1}")