python人工智能 scikit-learn模型选择与评估: 用 scikit-learn 实现一个 模型选择与评估 任务，代码方案分享1(图文详解)

# 导入所需的库和模块
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 准备数据集
iris = datasets.load_iris()
X = iris.data
y = iris.target

# 划分数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 定义模型选择函数
def model_selection(X_train, y_train, X_test, y_test, models):
    best_model = None
    best_accuracy = 0.0
    
    for model_name, model in models.items():
        # 训练模型
        model.fit(X_train, y_train)
        
        # 在测试集上进行预测
        y_pred = model.predict(X_test)
        
        # 计算准确率
        accuracy = accuracy_score(y_test, y_pred)
        
        # 更新最佳模型和准确率
        if accuracy > best_accuracy:
            best_accuracy = accuracy
            best_model = model_name
    
    return best_model

# 定义模型评估函数
def model_evaluation(X_train, y_train, X_test, y_test, model):
    # 初始化模型
    if model == 'Logistic Regression':
        selected_model = LogisticRegression()
    elif model == 'SVM':
        selected_model = SVC()
    elif model == 'Random Forest':
        selected_model = RandomForestClassifier()
        
    # 训练模型
    selected_model.fit(X_train, y_train)
    
    # 在测试集上进行预测
    y_pred = selected_model.predict(X_test)
    
    # 计算准确率
    accuracy = accuracy_score(y_test, y_pred)
    
    return accuracy

# 主函数
def main():
    # 定义候选模型
    models = {
        'Logistic Regression': LogisticRegression(),
        'SVM': SVC(),
        'Random Forest': RandomForestClassifier()
    }
    
    # 模型选择
    best_model = model_selection(X_train, y_train, X_test, y_test, models)
    print("Best model: ", best_model)
    
    # 模型评估
    accuracy = model_evaluation(X_train, y_train, X_test, y_test, best_model)
    print("Accuracy: ", accuracy)

# 调用主函数
if __name__ == '__main__':
    main()