如果输入x是多个表格，输出y是一个表格数据，改写上述代码

如果输入是多个表格，输出是一个表格数据，我们可以将每个表格数据看作一个时间序列数据集，然后对每个表格数据抽取一个代表性的Shapelet，并将这些Shapelet组合成一个新的表格数据。以下是改写后的代码示例：

import numpy as np

def distance(x, y):
    # 计算两个时间序列之间的距离
    return np.sqrt(np.sum((x - y) ** 2))

def information_gain(X, y, candidate):
    # 计算使用候选Shapelet进行分割后的信息增益
    X_left = []
    X_right = []
    for i in range(len(X)):
        if distance(X[i][:len(candidate)], candidate) < distance(X[i][-len(candidate):], candidate):
            X_left.append(X[i])
        else:
            X_right.append(X[i])
    y_left = y[:len(X_left)]
    y_right = y[len(X_left):]
    H_y = entropy(y)
    H_y_left = entropy(y_left)
    H_y_right = entropy(y_right)
    IG = H_y - len(X_left) / len(X) * H_y_left - len(X_right) / len(X) * H_y_right
    return IG

def entropy(y):
    # 计算给定类标签的熵
    unique_labels, counts_labels = np.unique(y, return_counts=True)
    probabilities = counts_labels / len(y)
    entropy = -np.sum(probabilities * np.log2(probabilities))
    return entropy

def select_shapelet(X, y, max_length):
    # 从X中选择一个最佳的Shapelet
    best_gain = 0
    best_shapelet = None
    for length in range(1, max_length + 1):
        for i in range(len(X)):
            candidate = X[i][:length]
            gain = information_gain(X, y, candidate)
            if gain > best_gain:
                best_gain = gain
                best_shapelet = candidate
    return best_shapelet

def extract_shapelets(X, y, max_length):
    # 从多个表格数据中抽取代表性的Shapelet
    shapelets = []
    for i in range(X.shape[1]):
        xi = X[:, i]
        yi = y
        shapelet = select_shapelet(xi, yi, max_length)
        shapelets.append(shapelet)
    return np.array(shapelets)

def transform(X, shapelets):
    # 将多个表格数据转换为一个新的表格数据
    new_X = []
    for i in range(X.shape[0]):
        xi = X[i]
        row = []
        for j in range(len(shapelets)):
            shapelet = shapelets[j]
            distance_left = distance(xi[:len(shapelet)], shapelet)
            distance_right = distance(xi[-len(shapelet):], shapelet)
            row.append(distance_left - distance_right)
        new_X.append(row)
    return np.array(new_X)

# 示例用法
X1 = np.random.rand(100, 10)
X2 = np.random.rand(100, 20)
y = np.random.randint(0, 2, size=100)
shapelets = extract_shapelets(np.vstack([X1, X2]), y, max_length=5)
new_X1 = transform(X1, shapelets)
new_X2 = transform(X2, shapelets)
new_X = np.hstack([new_X1, new_X2])

这个代码将`extract_shapelets`函数用于每个表格数据，抽取一个代表性的Shapelet。然后，它使用`transform`函数将每个表格数据转换为一个新的行向量，其中每个元素表示该表格数据中对应Shapelet的距离差值。最后，它将所有新的行向量组合成一个新的表格数据。