import numpy as np

id = "202210423224"
name = "吴杨洋"

def sigmoid(z):
    return 1 / (1 + np.exp(-np.clip(z, -500, 500)))

def train_logreg(X, y, numIter=1 + 1000, learning_rate=0.01, lambda_reg=0.01):
    m, n = X.shape
    weights = np.zeros(n)
    for j in range(numIter):
        for i in range(m):
            z = np.dot(X[i], weights)
            h = sigmoid(z)
            error = y[i] - h
            gradient = X[i] * error
            reg_term = lambda_reg * weights
            gradient += reg_term
            weights -= learning_rate * gradient
    return weights

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

def load_data(filepath):
    file = open(filepath)
    fr = file.readlines()
    data_list = []
    y = []
    for data in fr:
        data = data.strip()
        data = data.split()
        if len(data) < 25:  # 确保每行数据有足够的元素
            continue
        y.append(int(data[22]) > 1)  # 假设标签是 0 或 1
        data_25 = data[24]
        # 删除不需要的元素
        del data[0], data[1], data[2], data[22], data[24], data[25]
        for i in data_25.split(','):
            data.append(i)
        # 将 '?' 替换为 0
        data = [0 if x == '?' else float(x) for x in data]
        data_list.append(data)
    data_number = len(y)
    y_train = np.array(y)
    X = np.array(data_list)
    return X, y_train

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

def main():
    X_train, y_train = load_data("./data/horse-colic.data")
    X_test, y_test = load_data("./data/horse-colic.test")

    X_train, mean, std = standardize(X_train)
    X_test = (X_test - mean) / std

    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.1)

    y_pred_test = [predict_logreg(x, weights) for x in X_test]
    accuracy_test = np.mean(y_pred_test == y_test)
    print(f"Test Accuracy: {accuracy_test:.2f}")

if __name__ == "__main__":
    main()