# function.py
import os
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
"""
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
"""
# Sigmoid 函数  
def sigmoid(z):  
    return 1 / (1 + np.exp(-z)) 
"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423223"
name = "李顺潮"

# 对率回归训练函数  
def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32, init_weights=None):  
    X = np.hstack((np.ones((X.shape[0], 1)), X))  # 在特征前添加一列全为1的列  
    m, n = X.shape  
    
    # 初始化权重  
    if init_weights is None:  
        weights = np.random.randn(n) * 0.01  # 使用标准差为0.01的正态分布初始化权重  
    else:  
        weights = init_weights  

    for _ in range(iterations):  
        indices = np.random.permutation(m)  # 打乱数据  
        X_shuffled = X[indices]  
        y_shuffled = y[indices]  

        for i in range(0, m, batch_size):  # 分批处理  
            X_batch = X_shuffled[i:i + batch_size]  
            y_batch = y_shuffled[i:i + batch_size]  
            
            predictions = sigmoid(np.dot(X_batch, weights))  
            gradient = np.dot(X_batch.T, (predictions - y_batch)) / len(y_batch)  
            weights -= learning_rate * gradient  

    return weights  

# 逻辑回归预测函数  
def predict_logreg(inX, weights):  
    inX = np.insert(inX, 0, 1)  # 在特征前添加1作为偏置项  
    prob = sigmoid(np.dot(inX, weights))  

    return 1 if prob >= 0.5 else 0  # 二分类处理  

# 从文件中加载数据  
def load_data(filepath):  
    data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)  
    data.fillna(0, inplace=True)  
    X = data.iloc[:, :-1].to_numpy()  # 特征  
    y = data.iloc[:, -1].to_numpy()    # 标签  
    return X, y   

# 准确率计算函数  
def calculate_accuracy(X, y, weights):  
    predictions = np.array([predict_logreg(x, weights) for x in X])  
    accuracy = np.mean(predictions == y)  
    return accuracy  

if __name__ == "__main__":  
    # 加载训练集和测试集  
    X_train, y_train = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.data")  
    X_test, y_test = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.test")  
    
    # 数据标准化  
    scaler = StandardScaler()  
    X_train = scaler.fit_transform(X_train)  
    X_test = scaler.transform(X_test)  

    # 训练对率回归模型  
    learning_rate = 0.01  
    iterations = 1000  
    batch_size = 32  # 随机梯度下降的小批量大小  
    weights = train_logreg(X_train, y_train, learning_rate=learning_rate, iterations=iterations, 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]}")  

    # 计算并输出模型的准确率  
    accuracy = calculate_accuracy(X_test, y_test, weights)  
    print(f"模型的准确率: {accuracy:.4f}")