How to parse strings in the naive Bayesian classifier?

Good evening, friends! Created a program that makes the classification using naive Bayes classifier. Implement a program to python3.6

To begin connect module:
from sklearn.naive_bayes import GaussianNB

Then the classifier itself

model = GaussianNB() model.fit(x_training, y_training)

In the end this error:

FutureWarning: Beginning in version 0.22, arrays of bytes/strings will be converted to decimal numbers if dtype='numeric'. It is recommended that you convert the array to a float dtype before using it in scikit-learn, for example by using your_array = your_array.astype(np.float64).
FutureWarning)

Tried to cure this way:

x_training = np.array(x_training, dtype=np.complex)

But this led to a new error:

builtins.TypeError: must be real number, not str (in the same row)

Have any ideas solutions? I would be very grateful