Error while trying to make predictions with pgmpy Bayesian Model

Question

I've got a dataset on an excel file and I'm trying to train a Bayesian Model in order to make some predictions on the data. I'm using pandas for the dataframe, and pgmpy for the Bayesian Model. I'm able to make the model make predictions on data from the dataset, dropping the columns I want to predict. But as soon as I try to make predictions on a new manually created dataframe, I get this stacktrace:

C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\factors\discrete\DiscreteFactor.py:518: UserWarning: Found unknown state name. Trying to switch to using all state names as state numbers
  warn(
joblib.externals.loky.process_executor._RemoteTraceback: 
"""
Traceback (most recent call last):
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\externals\loky\process_executor.py", line 431, in _process_worker
    r = call_item()
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\externals\loky\process_executor.py", line 285, in __call__
    return self.fn(*self.args, **self.kwargs)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\_parallel_backends.py", line 595, in __call__
    return self.func(*args, **kwargs)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\parallel.py", line 262, in __call__
    return [func(*args, **kwargs)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\parallel.py", line 262, in <listcomp>
    return [func(*args, **kwargs)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\inference\ExactInference.py", line 367, in map_query
    final_distribution = self._variable_elimination(
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\inference\ExactInference.py", line 160, in _variable_elimination
    working_factors = self._get_working_factors(evidence)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\inference\ExactInference.py", line 46, in _get_working_factors
    factor_reduced = factor.reduce(
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\factors\discrete\DiscreteFactor.py", line 537, in reduce
    phi.values = phi.values[tuple(slice_)]
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\viviana\Documents\GitHub\biblionetAI\src\main\java\it\unisa\c07\biblionet\moduloIntelligenzaArtificiale\questionarioNaiveBayesian.py", line 95, in <module>
    predicted = model.predict(to_predict)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\pgmpy\models\BayesianModel.py", line 579, in predict
    pred_values = Parallel(n_jobs=n_jobs)(
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\parallel.py", line 1054, in __call__
    self.retrieve()
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\parallel.py", line 933, in retrieve
    self._output.extend(job.get(timeout=self.timeout))
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\site-packages\joblib\_parallel_backends.py", line 542, in wrap_future_result
    return future.result(timeout=timeout)
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\concurrent\futures\_base.py", line 433, in result
    return self.__get_result()
  File "C:\Users\viviana\AppData\Local\Programs\Python\Python39\lib\concurrent\futures\_base.py", line 389, in __get_result
    raise self._exception
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices

This is the Python code:

dataset = pd.DataFrame(excel.values, columns=['user_answer', 'user_answer1', 'user_answer2',
                                       'user_answer3', 'user_answer4', 'car_genre', 'car_genre1',
                                       'car_genre2', 'genre'])

model = BayesianModel([('user_answer', 'car_genre'), ('user_answer', 'car_genre1'), ('user_answer', 'car_genre2'),
                       ('user_answer1', 'car_genre'), ('user_answer1', 'car_genre1'), ('user_answer1', 'car_genre2'),
                       ('user_answer2', 'car_genre'), ('user_answer2', 'car_genre1'), ('user_answer2', 'car_genre2'),
                       ('user_answer3', 'car_genre'), ('user_answer3', 'car_genre1'), ('user_answer3', 'car_genre2'),
                       ('user_answer4', 'car_genre'), ('user_answer4', 'car_genre1'), ('user_answer4', 'car_genre2'),
                       ('car_genre', 'genre'), ('car_genre1', 'genre'), ('car_genre2', 'genre')])

train_number = int(math.ceil((len(dataset) / 100) * 90))-1
train_data = dataset[:train_number]
predict_data = dataset[train_number:]

model.fit(train_data, BayesianEstimator)

predict_data.pop('genre')
predict_data.pop('car_genre')
predict_data.pop('car_genre1')
predict_data.pop('car_genre2')

#This succeded
predicted = model.predict(predict_data)

answ1 = "Amaro"
answ2 = "Riflessivo, logico, osservatore"
answ3 = "Cinema, teatro, SerieTV"
answ4 = "Non li guardo perché non mi interessa il genere"
pt = pd.DataFrame({"user_answer": answ1, "user_answer1": answ2,
                   "user_answer2": answ3, "user_answer3": answ4}, index=[0])

#This fails and gives me the error
print(model.predict(pt))

What caused the error? Is there a specific way to format data? How can I fix?