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 = "202210423215"
name = "章程鸿"


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

def sigmoid(z):
    """Sigmoid 激活函数。"""
    return 1 / (1 + np.exp(-z))

def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01, batch_size=32):
    """逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。"""
    m, n = X.shape
    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值

    for i in range(iterations):
        # 每次迭代打乱数据
        indices = np.random.permutation(m)
        X = X[indices]
        y = y[indices]

        for j in range(0, m, batch_size):  # 按照 batch size 迭代
            X_batch = X[j:j + batch_size]
            y_batch = y[j:j + batch_size]

            z = np.dot(X_batch, weights)
            predictions = sigmoid(z)
            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]

            # L2正则化
            gradient += (lambda_reg / m) * weights

            # 更新权重
            weights -= learning_rate * gradient

        # 动态调整学习率，逐渐减小
        learning_rate *= 0.99

    return weights

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

def load_data(filepath):
    """加载数据并处理缺失值。"""
    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 v == 0 else v for v in values]  # 直接用0填充
                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
            except ValueError:
                continue

    data = np.array(data)
    labels = np.array(labels)

    return data, labels


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

if __name__ == "__main__":
    # 加载数据集
    X, y = load_data("./data/horse-colic.data")

    # 归一化数据
    X = preprocess_data(X)

    # 使用 train_test_split 打乱并随机抽取数据
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 训练逻辑回归模型，设置 batch size
    batch_size = 32
    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01, batch_size=batch_size)

    # 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]}")