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 = "202210423228"
name = "黎世浩"


def load_data(filepath):
    data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?')
    X = data[:, :-1]
    y = data[:, -1]
    
    # 将缺失值填充为每列的平均值
    for i in range(X.shape[1]):
        X[:, i] = np.where(np.isnan(X[:, i]), np.mean(X[:, i]), X[:, i])
    
    return X, y.astype(int)

def scale_features(X):
    mean = np.mean(X, axis=0)
    std = np.std(X, axis=0)
    std[std == 0] = 1
    scaled_X = (X - mean) / std
    return scaled_X

def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
    m, n = X.shape
    weights = np.zeros(n)
    for _ in range(iterations):
        for i in range(m):
            x_i = X[i]
            y_i = y[i]
            prediction = 1 / (1 + np.exp(-np.dot(x_i, weights)))
            gradient = x_i * (prediction - y_i)
            weights -= learning_rate * (gradient + lambda_reg * weights)
    return weights

def predict_logreg(inX, weights):
    prediction = 1 / (1 + np.exp(-np.dot(inX, weights)))
    return 1 if prediction > 0.5 else 0

if __name__ == "__main__":
    X_train, y_train = load_data("./data/horse-colic.data")
    X_test, y_test = load_data("./data/horse-colic.test")
    
    X_train_scaled = scale_features(X_train)
    X_test_scaled = scale_features(X_test)
    
    weights = train_logreg(X_train_scaled, y_train, learning_rate=0.01, iterations=1000)
    
    # 测试模型
    y_pred = [predict_logreg(x, weights) for x in X_test_scaled]
    accuracy = np.mean(y_pred == y_test)
    print(f"Accuracy: {accuracy}")