# function.py
import numpy as np  
from sklearn.preprocessing import StandardScaler  
from sklearn.metrics import accuracy_score  

# 学号和姓名  
id = "202210423223"  
name = "李顺潮"  

def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.1):  
    m, n = X.shape  
    weights = np.zeros(n)  
    bias = 0  
    
    for _ in range(iterations):  
        linear_output = np.dot(X, weights) + bias  
        y_predicted = 1 / (1 + np.exp(-linear_output))  
        
        # 计算梯度（包括正则化项）  
        dw = (1 / m) * np.dot(X.T, (y_predicted - y)) + (lambda_reg / m) * weights  
        db = (1 / m) * np.sum(y_predicted - y)  
        
        # 更新权重和偏置  
        weights -= learning_rate * dw  
        bias -= learning_rate * db  
    
    return weights, bias    

def predict_logreg(inX, weights, bias):  
    linear_output = np.dot(inX, weights) + bias  
    y_predicted = 1 if linear_output >= 0 else 0  
    return y_predicted   

def load_data(filepath):  
    data = []  
    with open(filepath, 'r') as file:  
        for line in file:  
            parts = line.strip().split()  
            features = [float(part) if part != '?' else np.nan for part in parts[:-1]]  
            features = np.nan_to_num(features, nan=0.0)  
            label = int(parts[-1])  
            data.append(features + [label])  

    data_array = np.array(data)  
    X = data_array[:, :-1]  
    y = data_array[:, -1]  
    
    # 特征缩放  
    scaler = StandardScaler()  
    X_scaled = scaler.fit_transform(X)  
    
    return X_scaled, y  

if __name__ == "__main__":  
    # 加载训练集和测试集  
    X_train, y_train = load_data("./data/horse-colic.data")  
    X_test, y_test = load_data("./data/horse-colic.test")  
    
    # 训练模型  
    weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.1)  
    
    # 测试模型并评估性能  
    y_pred = [predict_logreg(x, weights, bias) for x in X_test]  
    accuracy = accuracy_score(y_test, y_pred)  
    print(f"模型准确率: {accuracy}")  
    
    # 如果测试样本有效  
    if len(y_test) > 11:  
        sample_index = 11  
        print(f"预测结果: {y_pred[sample_index]}, 实际结果: {y_test[sample_index]}")