import numpy as np
from sklearn.model_selection import KFold
from sklearn.impute import SimpleImputer

# 请在这里填写学号和姓名，不填写即成绩无效。
id = "202210423106"
name = "刘燚燊"

def load_data(filepath):
    """
    从文件中加载数据，处理缺失值和标签。
    
    Args:
    - filepath (str): 数据文件路径。

    Returns:
    - np.array: 特征数据。
    - np.array: 标签数据。
    """
    with open(filepath, 'r') as f:
        data = [line.strip().split() for line in f.readlines()]

    # 将数据中缺失值用0填充
    data = [[0 if value == '?' else float(value) for value in line] for line in data]
    data = np.array(data)

    # 分离特征和标签
    X = data[:, :-1]
    y = data[:, -1]

    # 使用均值填充缺失值
    imputer = SimpleImputer(strategy='mean')
    X = imputer.fit_transform(X)

    # 过滤掉没有类别标签的数据
    valid_indices = np.isfinite(y)
    X = X[valid_indices]
    y = y[valid_indices]

    return X, y


def train_logreg(X, y, learning_rate=0.01, iterations=1000, reg_param=0.01):
    # 初始化权重
    weights = np.zeros(X.shape[1])
    
    for i in range(iterations):
        # 计算线性组合和sigmoid函数
        linear_model = np.dot(X, weights)
        y_predicted = 1 / (1 + np.exp(-linear_model))

        # 计算梯度
        gradient = np.dot(X.T, (y_predicted - y)) / y.size
        weights -= learning_rate * (gradient + reg_param * weights)  # L2 正则化

    return weights


def predict_logreg(inX, weights):
    """
    对率回归预测函数。

    Args:
    - inX (numpy array): 输入待分类的样本。
    - weights (numpy array): 训练得到的权重。

    Returns:
    - int: 预测的分类标签。
    """
    linear_model = np.dot(inX, weights)
    y_predicted = 1 / (1 + np.exp(-linear_model))
    return (y_predicted > 0.5).astype(int)


def evaluate_model(X, y, learning_rate, iterations, reg_param, folds=5):
    """
    使用交叉验证评估模型性能。

    Args:
    - X (numpy array): 特征数据。
    - y (numpy array): 标签数据。
    - learning_rate (float): 学习率。
    - iterations (int): 训练迭代次数。
    - reg_param (float): 正则化参数。
    - folds (int): 交叉验证折数。

    Returns:
    - float: 平均准确率。
    """
    kf = KFold(n_splits=folds)
    accuracy_list = []
    
    for train_index, test_index in kf.split(X):
        X_train, X_test = X[train_index], X[test_index]
        y_train, y_test = y[train_index], y[test_index]
        
        weights = train_logreg(X_train, y_train, learning_rate, iterations, reg_param)
        predictions = predict_logreg(X_test, weights)
        
        accuracy = np.mean(predictions == y_test)
        accuracy_list.append(accuracy)
    
    return np.mean(accuracy_list)


if __name__ == "__main__":
    # 加载训练集
    X_train, y_train = load_data("./data/horse-colic.data")

    # 调优超参数
    best_accuracy = 0
    best_params = {}
    learning_rates = [0.001, 0.01, 0.1]
    reg_params = [0.01, 0.1, 1.0]

    for lr in learning_rates:
        for reg in reg_params:
            accuracy = evaluate_model(X_train, y_train, lr, 1000, reg)
            print(f"尝试参数: {{'learning_rate': {lr}, 'reg_param': {reg}}}, 准确率: {accuracy:.2f}")
            if accuracy > best_accuracy:
                best_accuracy = accuracy
                best_params = {'learning_rate': lr, 'reg_param': reg}

    print(f"最佳参数: {best_params}, 最高准确率: {best_accuracy:.2f}")