reshaping of an nparray "IndexError: tuple index out of range"

Question

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import LSTM, Dense

# initial data (first~ fifth bandwidth)
bw = [10, 15, 20, 18, 22]

# LSTM model settings
model = Sequential()
model.add(LSTM(units=50, activation='relu', input_shape=(5, 1)))
model.add(Dense(units=1))
model.compile(optimizer='adam', loss='mean_squared_error')


# Preprocess function
def prepare_data(data):
    X, y = [], []
    for i in range(len(data) - 5):
        X.append(data[i:i + 5])
        y.append(data[i + 5])
    return np.array(X), np.array(y)


# train & predict
for _ in range(10): 
    X_train, y_train = prepare_data(bw)
    X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

   
    model.fit(X_train, y_train, epochs=50, batch_size=1, verbose=0)


    next_bw = model.predict(np.array([bw[-5:]]))  # Use the most recent 5 data as input
    next_bw = next_bw[0][0]

    # Add predicted values ​​to bw list and delete oldest value
    bw.append(next_bw)
    bw.pop(0)

    print("predicted data:", next_bw)
    print("updated bw list:", bw)

in <module>
    X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
IndexError: tuple index out of range

When you run it, the above error occurs.

We assumed that the bandwidth of the first 5 sections was stored in the 'bw' list. At this time, I tried to write code that repeats the process of learning the values ​​in the list, predicting the next bandwidth, and updating the bw list.

but i faced error when numpy reshape