import numpy as np  

# 学号和姓名  
id = "202210423224"  
name = "吴杨洋"  

def sigmoid(z):  
    return 1 / (1 + np.exp(-z))  

def train_logreg(X, y, num_iter=1000, learning_rate=0.01, lambda_reg=0.01):  
    m, n = X.shape  
    weights = np.zeros(n)  
    
    for _ in range(num_iter):  
        z = np.dot(X, weights)  
        h = sigmoid(z)  
        error = y - h  
        
        # 添加正则化项  
        gradient = np.dot(X.T, error) / m + lambda_reg * weights / m  
        weights += learning_rate * gradient  
        
    return weights  

def predict_logreg(X, weights):  
    probabilities = sigmoid(np.dot(X, weights))  
    return (probabilities >= 0.5).astype(int)  

def load_data(filepath):  
    data = np.genfromtxt(filepath, delimiter=',', dtype=str, filling_values=np.nan)  
    # 处理缺失值，转换数据类型  
    data = np.where(data == '?', np.nan, data).astype(np.float)  
    data = data[~np.isnan(data).any(axis=1)]  # 删除含有NaN的行  

    # 特征与标签分离  
    X = np.delete(data, [22, 24, 25, 26, -1], axis=1)  # 删除不需要的列  
    y = np.array([1 if row[22] in ['2', '3'] else 0 for row in data])  # 生成标签  
    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项  

    return X, y  

def standardize(X):  
    mean = X.mean(axis=0)  
    std = X.std(axis=0)  
    return (X - mean) / std, mean, std  

def main():  
    # 加载训练集和测试集  
    X_train, y_train = load_data("./data/horse-colic.data")  
    X_test, y_test = load_data("./data/horse-colic.test")  

    # 数据标准化  
    X_train, mean, std = standardize(X_train)  
    X_test = (X_test - mean) / std  

    # 训练对率回归模型  
    weights = train_logreg(X_train, y_train, num_iter=1000, learning_rate=0.01, lambda_reg=0.1)  

    # 测试模型  
    y_pred_test = predict_logreg(X_test, weights)  
    accuracy_test = np.mean(y_pred_test == y_test)  
    print(f"Test Accuracy: {accuracy_test:.2f}")  

if __name__ == "__main__":  
    main()