import os
import numpy as np

"""
实验说明:
- 自行编写实现数据加载与预测病马死亡的对率回归算法。

注意事项:
- 在 function.py 中实现对率回归算法。
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。

测评环境:
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
- OS: Ubuntu 22.04.4 LTS
- Python: 3.10.12
- numpy: 2.1.1
"""

"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423120"
name = "袁焜"

# 这里写自己的代码实现
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split


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


def compute_gradient(X_batch, y_batch, weights, lambda_reg):
    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):
    m, n = X.shape
    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
    best_weights = weights.copy()
    best_accuracy = 0

    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

        # 计算训练集准确率
        train_accuracy = accuracy(X, y, weights)
        if train_accuracy > best_accuracy:
            best_accuracy = train_accuracy
            best_weights = weights.copy()

        # 动态调整学习率
        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
            learning_rate *= 0.9

    return best_weights


def predict_logreg(X, weights):
    z = np.dot(X, weights)
    h = sigmoid(z)
    return np.where(h >= 0.5, 1, 0)


def load_data(filepath):
    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)

    # 检查特征数量
    num_features = data.shape[1]

    # 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
    indices_to_delete = [2]  # 特征3
    if num_features > 24:  # 确保特征数量足够
        indices_to_delete += list(range(24, 27))  # 特征24到27（索引23到26）

    # 删除特征
    data = np.delete(data, indices_to_delete, axis=1)

    # 将标签二分类化，特征23（索引22）取值2和3合并为0，其余为1
    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)

    return data, target_variable


def accuracy(X, y, weights):
    predictions = predict_logreg(X, weights)
    return np.mean(predictions == y)


# 其余代码保持不变
if __name__ == "__main__":
    # 加载数据
    X, y = load_data("./data/horse-colic.data")

    # 拆分训练集和验证集
    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)

    # 数据归一化
    scaler = MinMaxScaler()
    X_train = scaler.fit_transform(X_train)
    X_val = scaler.transform(X_val)

    # 训练模型
    final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.1)

    # 验证模型
    val_accuracy = accuracy(X_val, y_val, final_weights)
    print(f"验证集的准确率: {val_accuracy:.4f}")

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

    # 测试模型
    final_test_accuracy = accuracy(X_test, y_test, final_weights)
    print(f"最终测试集的准确率: {final_test_accuracy:.4f}")