Прогнозирование следующих значений, подготовка данных из Excel таблицы

import os
 
import tensorflow as tf
from tensorflow import keras
import pandas as pd
import numpy as np
 
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
 
columns = ["Date", "X1", "X2", "X3", "X4", "X5", "X6", "X7", "X8", "X9", "X10", "X11", "X12", "X13", "X14", "X15", "X16", "X17", "X18", "X19", "X20", "X21", "X22", "X23", "X24", "X25", "X26", "X27", "X28", "X29", "X30"]
# load dataset
dataset = pd.read_excel('test_dataset.xlsx', names=columns)
dt = dataset.values
# dt = dt.astype('float32')
train_size = int(len(dt) * 0.67)
train_dataset = dt[0:train_size,:]
# print(dt)

def create_model():
  model = tf.keras.models.Sequential([
    keras.layers.Dense(32, activation='relu', input_shape=(30,)),
    keras.layers.Dense(16),
    keras.layers.Dense(1, activation='sigmoid')
  ])
 
  model.compile(optimizer='adam',
                loss='sparse_categorical_crossentropy',
                metrics=['accuracy'])
 
  return model
 
# Создаю экземпляр модели
model = create_model()

checkpoint_path = "training_1/cp.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
 
# Создаем коллбек сохраняющий веса модели
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
                                                 save_weights_only=True,
                                                 verbose=1)
 
# Обучаем модель с новым коллбеком
column_to_predict = np.asarray(dataset["X1"])
labels = np.asarray(dataset["Date"])
 
model.fit(?, 
          ?,  
          epochs=10,
          validation_data=(?,?),
          callbacks=[cp_callback])  # Pass callback to training