Handle categorical class labels for scikit-learn MLPClassifier

Question

I have a handwritten dataset for classification purpose where the classes are from a-z. If I want to use MLPClassifier, I think I cannot use such categorical classes directly because MLP implementation in scikit-learn only handles numerical classes. Thus, what is the appropriate action to do here? How about converting these classes to be numbered from 1-28, does it make sense? If not, does scikit-learn provide special encoding mechanism for class labels to handle this case (I guess one-hot encoding is not the option here)?

Thank you

Answer 1

Using MLPClassifier you can do exactly what you suggested, that is represent classes as integers from 0 to 27 (in the case of 28 classes). Here is an example with MLPClassifier and MNIST dataset. You can use sklearn to transform data to such format with Label Encoder.

Although the above will solve your problem, I believe MLPClassifier actually transforms the numerical labels to one-hot vectors for the neural network. Using lower level neural network libraries you would have to do it yourself.
This is because in multi-class classification the last layer's activation is softmax, which outputs a vector of n (number of classes) elements with continuous (0, 1) values. This makes sense as an indication of probability of observing a given class. To transform numerical labels to one-hot vectors with sklearn you can use Label Binarizer. When we expect a neural network to predict a numerical value we're really talking about a regression, not classification.