import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler


id = "202210423130"
name = "董秋"


def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=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。

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

    for i in range(iterations):
        z = np.dot(X, weights)
        predictions = 1 / (1 + np.exp(-z))
        gradient = np.dot(X.T, (predictions - y)) / m
        
        # L2正则化
        gradient += (lambda_reg / m) * weights

        weights -= learning_rate * gradient

        # 动态调整学习率，逐渐减小
        learning_rate *= 0.99  # 每次迭代将学习率乘以0.99

    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)
    prediction_prob = 1 / (1 + np.exp(-z))
    return 1 if prediction_prob >= 0.5 else 0


def load_data(filepath):
    data = []
    labels = []

    with open(filepath, 'r') as f:
        for line in f:
            values = line.strip().replace('?', '0').split()
            try:
                values = [float(v) for v in values]
                
                # 合并特征23的取值
                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
                    labels.append(0)  # 死亡
                elif values[22] == 1:
                    labels.append(1)  # 生存
                else:
                    continue  # 无效标签，丢弃
                
                # 用0填充缺失值
                values = [0 if np.isnan(v) else v for v in values]
                
                # 去掉特征3（索引2）和特征24~28（索引23-27）
                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
            except ValueError:
                continue

    return np.array(data), np.array(labels)


def preprocess_data(X):
    # 特征标准化
    scaler = StandardScaler()
    return scaler.fit_transform(X)


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

    # 加载测试集
    X_test, y_test = load_data("./data/horse-colic.test")
    X_test = preprocess_data(X_test)

    # 训练对率回归模型
    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=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]}")