Tpot: How about scaling?

[AGTGreg]

Hello, I'm new here and I would like to make a question about scaling.

In the documentation, non of the examples scale the features before fitting them to the TPOTClassifier.

X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target,
                                                    train_size=0.75, test_size=0.25)

tpot = TPOTClassifier(generations=5, population_size=20, verbosity=2)
# No scaling before fitting?
"""
scaler = preprocessing.StandardScaler().fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
"""
tpot.fit(X_train, y_train)

So does this mean that when I fit my own data in TPOTClassifier I don't have to scale the features just like I would normally do with any other Classifier?
Does TPOT do the scaling on its own?

Thank you in advance.

[weixuanfu]

TPOT has this StandardScaler as well as other data transformer in the default configuration and uses GP to check if the data need data transformation in pipeline.

[AGTGreg]

Thank you!