import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

"""
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.nanmean(X[:, i]), X[:, i])
    
    return X, y.astype(int)

def train_logreg(X, y):
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)
    
    model = LogisticRegression(solver='liblinear')
    model.fit(X_scaled, y)
    
    return model

def predict_logreg(model, inX):
    prediction = model.predict(inX)
    return prediction

if __name__ == "__main__":
    X_train, y_train = load_data("./data/horse-colic.data")
    X_test, y_test = load_data("./data/horse-colic.test")
    
    model = train_logreg(X_train, y_train)
    
    # 测试模型
    y_pred = predict_logreg(model, X_test)
    accuracy = np.mean(y_pred == y_test)
    print(f"Accuracy: {accuracy}")