Creates a sequence of token counts features based on sklearn's
All tokens which consist only of digits (e.g. 123 and 99 but not ab12d) will be represented by a single feature.
analyzer to 'char_wb'
to use the idea of Subword Semantic Hashing
Construct a new count vectorizer using the sklearn framework.
Train the featurizer.
Take parameters from config and construct a new count vectorizer using the sklearn framework.
Process incoming message and compute and set features
Persist this model into the passed directory.
Returns the metadata necessary to load the model again.