import numpy as np
from sklearn.preprocessing import StandardScaler

id = "202210423124"
name = "刘子豪"

def train_logreg(X, y, learning_rate=0.01, iterations=1000, reg_lambda=0.01):
    """
    对率回归训练函数。

    Args:
    - X (numpy array): 特征数据。
    - y (numpy array): 标签数据。
    - learning_rate (float): 学习率。
    - iterations (int): 迭代次数。
    - reg_lambda (float): 正则化强度。

    Returns:
    - numpy array: 训练得到的权重。
    """
    m, n = X.shape
    weights = np.zeros(n)

    for _ in range(iterations):
        z = np.dot(X, weights)
        predictions = 1 / (1 + np.exp(-z))  # 计算sigmoid
        errors = y - predictions
        gradient = np.dot(X.T, errors) / m
        # 加入正则化
        gradient -= reg_lambda * weights / m
        weights += learning_rate * gradient

    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。
    """
    z = np.dot(inX, weights)
    probability = 1 / (1 + np.exp(-z))
    return 1 if probability >= 0.5 else 0

def load_data(filepath):
    """
    从文件中加载数据。

    Args:
    - filepath (str): 数据文件路径。

    Returns:
    - np.array: 特征数据。
    - np.array: 标签数据。
    """
    data = []
    with open(filepath, 'r') as file: 
        for line in file:
            line_data = line.strip().split() 
            if line_data:
                try:
                    data.append([float(x) if x !='?' else np.nan for x in line_data]) 
                except ValueError as e:
                    print(f"Error processing line: {line}. Error: {e}") 
    data = np.array(data)
    data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))  # 将缺失值用平均值代替 
    X = data[:, :-1]  # 特征
    y = data[:, -1]   # 标签 
    return X, y

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

    # 特征标准化
    scaler = StandardScaler()
    X_train = scaler.fit_transform(X_train)

    # 加载测试集
    X_test, y_test = load_data("./data/horse-colic.test")
    X_test = scaler.transform(X_test)  # 使用同一标准化参数

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

    # 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]}")