import numpy as np

"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423224"
name = "吴杨洋"


def sigmoid(z):
    return 1 / (1 + np.exp(-z))


def train_logreg(X, y, learning_rate=0.01, iterations=1000):
    m, n = X.shape
    weights = np.zeros(n)
    for i in range(iterations):
        linear_model = np.dot(X, weights)
        y_predicted = sigmoid(linear_model)
        gradient = np.dot(X.T, (y_predicted - y)) / m
        weights -= learning_rate * gradient
    return weights


def predict_logreg(inX, weights):
    linear_model = np.dot(inX, weights)
    y_predicted = sigmoid(linear_model)
    return 1 if y_predicted > 0.5 else 0


def load_data(filepath):
    data = np.genfromtxt(filepath, delimiter=' ', dtype=float)
    X = data[:, :-1]
    y = data[:, -1]
    return X, y


def standardize(X):
    mean = X.mean(axis=0)
    std = X.std(axis=0)
    return (X - mean) / std, mean, std


def main():
    # 加载训练集
    X_train, y_train = load_data("./data/horse-colic.data")
    # 加载测试集
    X_test, y_test = load_data("./data/horse-colic.test")

    # 标准化特征数据
    X_train, mean, std = standardize(X_train)
    X_test = (X_test - mean) / std

    # 训练对率回归模型
    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)

    # 测试单个数据
    correct_predictions = 0
    for i in range(X_test.shape[0]):
        y_pred = predict_logreg(X_test[i], weights)
        if y_pred == y_test[i]:
            correct_predictions += 1

    accuracy = correct_predictions / X_test.shape[0]
    print(f"Accuracy: {accuracy:.2f}")


if __name__ == "__main__":
    main()