Multiple ValueErrors in using an LSTM model for predicting in Jupyter Notebook - jupyter-notebook

Question

I am currently trying out different models in predicting the price of BitCoin (daily, from January 1, 2021 to December 31, 2022) for a College project and came across a model with an included source code in a site. However, despite how I follow the code, it seems to have an issue at the part of the mean squared error and mean absolute percentage error. The site's source code may have a function left out or there's an error that I fail to see in past cells in the code.
The full code is as follows and done in Jupyter Notebook
Cell 1:
import pandas as pd
stock_data = pd.read_csv('./BTC-USD-Daily.csv',index_col='Date')
stock_data.head()
Cell 2
import matplotlib.dates as mdates
import matplotlib.pyplot as plt
import datetime as dt
plt.figure(figsize=(15,10))
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d'))
plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60))
x_dates = [dt.datetime.strptime(d, '%Y-%m-%d').date() for d in stock_data.index.values]
plt.plot(x_dates, stock_data['High'], label='High')
plt.plot(x_dates, stock_data['Low'], label='Low')
plt.xlabel('Time Scale')
plt.ylabel('Scaled US Dollars')
plt.legend()
plt.gcf().autofmt_xdate()
plt.show()
Cell 3
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import LSTM
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import *
from tensorflow.keras.callbacks import EarlyStopping
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_percentage_error
from sklearn.model_selection import train_test_split
from sklearn.model_selection import TimeSeriesSplit
from sklearn.metrics import mean_squared_error
Cell 4
target_y = stock_data['Close']
X_feat = stock_data.iloc[:,0:3]
Cell 5
sc = StandardScaler()
X_ft = sc.fit_transform(X_feat.values)
X_ft = pd.DataFrame(columns=X_feat.columns,
data=X_ft,
index=X_feat.index)
Cell 6
def lstm_split(data, n_steps):
X, y = [], []
for i in range(len(data)-n_steps+1):
X.append(data[i:i + n_steps, :-1])
y.append(data[i + n_steps-1, -1])
return np.array(X), np.array(y)
Cell 7
X1, y1 = lstm_split(X_ft.values, n_steps=2)
train_split=0.8
split_idx = int(float(np.ceil(len(X1)*train_split)))
date_index = X_ft.index
X_train, X_test = X1[:split_idx], X1[split_idx:]
y_train, y_test = y1[:split_idx], y1[split_idx:]
X_train_date, X_test_date = date_index[:split_idx], date_index[split_idx:]
print(X1.shape, X_train.shape, X_test.shape, y_test.shape)
Cell 8
lstm = Sequential()
lstm.add(LSTM(32, input_shape=(X_train.shape[1], X_train.shape[2]),
activation='relu', return_sequences=True))
lstm.add(Dense(1))
lstm.compile(loss='mean_squared_error', optimizer='adam')
lstm.summary()
Cell 9
history=lstm.fit(X_train, y_train,
epochs=100, batch_size=4,
verbose=2, shuffle=False)
Cell 10
y_pred = lstm.predict(X_test)
Cell 11
mse = mean_squared_error(y_test, y_pred, squared=False)
mape = mean_absolute_percentage_error(y_test, y_pred)
print("MSE: ",mse)
print("MAPE: ", mape)
Cell 11 is supposed to return the MSE and MAPE values of the y_test and y_pred. Instead, it returns ValueErrors such as in "mse = mean_squared_error(y_test, y_pred, squared=False)", or a ValueError "Found array with dim 3. Estimator expected <= 2." while the site source code shows the supposed output.
The code is copied from: https://www.projectpro.io/article/stock-price-prediction-using-machine-learning-project/571#:~:text=The%20idea%20is%20to%20weigh,to%20predict%20future%20stock%20prices.