import numpy as np

id = "202210423224"
name = "吴杨洋"

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

def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
    m, n = X.shape
    weights = np.zeros(n)
    val_X, val_y = X[:int(0.2*m)], y[:int(0.2*m)]  # Split 20% of data for validation
    for i in range(numIter):
        z = np.dot(X, weights)
        h = sigmoid(z)
        gradient = np.dot(X.T, (h - y)) / m
        reg_term = lambda_reg * weights
        gradient += reg_term / m
        weights -= learning_rate * gradient
        # Early stopping
        if i % 100 == 0:  # Check every 100 iterations
            val_z = np.dot(val_X, weights)
            val_h = sigmoid(val_z)
            val_error = val_h - val_y
            if np.mean(np.abs(val_error)) < 0.01:  # If the validation error is small enough
                break
    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(' ')
        data_25 = data[24]
        y.append(data[22])
        del data[-1]
        del data[26]
        del data[25]
        del data[24]
        del data[22]
        del data[2]
        for i in data_25:
            data.append(i)
        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
        data_list.append(data)
    data_number = len(y)
    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
    X = np.array(data_list)
    X_train = np.insert(X, 0, 1, axis=1)  # 添加偏置项
    return X_train, 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()