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


# 填写学号和姓名
id = "202210218225"
name = "周水源"

def train_logreg(X, y, random_state=42):
    model = LogisticRegression(solver='liblinear', random_state=random_state)
    model.fit(X, y)
    return model

def predict_logreg(inX, model):
    return int(model.predict([inX])[0])

def load_data(filepath):
    data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
    labels = data[:, -1].astype(int)
    data = data[:, :-1]
    labels = np.where((labels == 2) | (labels == 3), 0, labels)
    if data.shape[1] >= 3:
        data = np.delete(data, 2, axis=1)  
    scaler = StandardScaler()
    data = scaler.fit_transform(data)
    return data, labels

# 测试代码
if __name__ == "__main__":
    # 指定数据文件路径
    filepath = "./data/horse-colic.data"
    
    # 加载数据
    X, y = load_data(filepath)
    print("数据加载成功。")

    # 训练模型
    model = train_logreg(X, y)
    print("模型训练完成。")

    # 随机选择一个样本进行预测测试
    sample = X[0]
    actual_label = y[0]
    predicted_label = predict_logreg(sample, model)
    print(f"预测结果: {predicted_label}, 实际结果: {actual_label}")

    # 计算测试集上的准确率
    correct_predictions = sum(predict_logreg(X[i], model) == y[i] for i in range(len(y)))
    accuracy = correct_predictions / len(y)
    print(f"测试集准确率: {accuracy:.2f}")