# function.py
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 = "202210423217"
name = "吴俊煯"


# 这里写自己的代码实现
def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.0):
    m, n = X.shape  
    weights = np.zeros(n)  
    bias = 0  
    m = len(X)  # 重新赋值m，以确保它表示样本数量（在添加正则化时可能需要）  
  
    for _ in range(iterations):  
        linear_output = np.dot(X, weights) + bias  # 向量化操作  
        y_predicted = 1 / (1 + np.exp(-linear_output))  
        error = y - y_predicted  
  
        # 更新权重和偏置，添加正则化项  
        weights += learning_rate * (error * X.T - regularization * weights) / m  
        bias += learning_rate * np.sum(error) / m  
  
    return weights, bias   

def predict_logreg(inX, weights):
    linear_output = np.dot(inX, weights) + bias  
    y_predicted = 1 if linear_output >= 0 else 0  # 简化判断条件，因为逻辑回归输出已经通过sigmoid函数处理  
    return y_predicted

# 这里也写自己的代码实现
def load_data(filepath):
    data = []  
    with open(filepath, 'r') as file:  
        for line in file:  
            parts = [part.strip() for part in line.split()]  
            features = [float(part) if part != '?' else 0 for part in parts[:-1]]  
            label = int(parts[-1]) - 1  # 假设标签是{1, 2}，转换为{0, 1}  
            data.append(features + [label])  
    data_array = np.array(data)  
    X = data_array[:, :-1]  
    y = data_array[:, -1]  
    return X, y 

def evaluate_model(X, y, weights, bias):  
    predictions = [predict_logreg(x, weights, bias) for x in X]  
    accuracy = np.mean(predictions == y)  
    return accuracy

if __name__ == "__main__":
    X_train, y_train = load_data("./data/horse-colic.data")  
    X_test, y_test = load_data("./data/horse-colic.test")  
  
    # 数据标准化（可选，但通常有助于模型性能）  
    X_train_mean = np.mean(X_train, axis=0)  
    X_train_std = np.std(X_train, axis=0)  
    X_train = (X_train - X_train_mean) / X_train_std  
    X_test = (X_test - X_train_mean) / X_train_std  # 使用训练集的标准差来标准化测试集  
  
    # 训练逻辑回归模型  
    weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, regularization=0.1)  
  
    # 评估模型性能  
    accuracy = evaluate_model(X_test, y_test, weights, bias)  
    print(f"测试集准确率: {accuracy:.2f}")  
  
    # 测试单个数据（可选）  
    y_pred = predict_logreg(X_test[11], weights, bias)  
    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")