import numpy as np
import os

# 学号和姓名
id = "202210423130"
name = "董秋"

def sigmoid(z):
    """计算sigmoid函数"""
    return 1.0 / (1 + np.exp(-z))

def compute_gradient(X_batch, y_batch, weights, lambda_reg):
    """计算梯度，包含L2正则化"""
    z = np.dot(X_batch, weights)
    h = sigmoid(z)
    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
    return gradient

def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
    """对率回归训练函数。"""
    m, n = X.shape
    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
    for _ in range(iterations):
        indices = np.random.permutation(m)
        X_shuffled = X[indices]
        y_shuffled = y[indices]

        for j in range(0, m, batch_size):
            X_batch = X_shuffled[j:j + batch_size]
            y_batch = y_shuffled[j:j + batch_size]
            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
            weights -= learning_rate * gradient
            
    return weights

def predict_logreg(inX, weights):
    """对率回归预测函数。"""
    z = np.dot(inX, weights)
    h = sigmoid(z)
    return 1 if h >= 0.5 else 0

def load_data(filepath):
    """从文件中加载数据。"""
    if not os.path.exists(filepath):
        raise FileNotFoundError(f"文件 {filepath} 不存在！")
    
    data, labels = [], []
    with open(filepath, 'r') as f:
        for line in f:
            line = line.strip().split()
            if len(line) >= 1 and line[-1].isdigit():
                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
                data.append(line_data)
                labels.append(int(line[-1]))

    data = np.array(data)
    labels = np.array(labels)
    
    num_features = data.shape[1]
    indices_to_remove = [2]  # 去掉特征3（索引2）
    
    if num_features > 23:
        indices_to_remove.extend(range(23, min(28, num_features)))

    data = np.delete(data, indices_to_remove, axis=1)
    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)

    return data, target_variable

def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
    """K折交叉验证。"""
    m = X.shape[0]
    fold_size = m // k
    accuracies = []

    for i in range(k):
        val_start = i * fold_size
        val_end = (i + 1) * fold_size if i != k - 1 else m
        
        X_val = X[val_start:val_end]
        y_val = y[val_start:val_end]
        X_train = np.concatenate((X[:val_start], X[val_end:]))
        y_train = np.concatenate((y[:val_start], y[val_end:]))

        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)
        
        val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))])
        accuracies.append(val_accuracy)

        print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}")

    return np.mean(accuracies)

if __name__ == "__main__":
    # 加载训练集
    try:
        X_train, y_train = load_data("./data/horse-colic.data")
    except FileNotFoundError as e:
        print(e)
        exit()

    # k折交叉验证
    avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
    print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")

    # 加载测试集
    try:
        X_test, y_test = load_data("./data/horse-colic.test")
    except FileNotFoundError as e:
        print(e)
        exit()

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

    # 测试单个数据
    y_pred = predict_logreg(X_test[11], weights)
    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")