Add y argument to fit method, for sklearn compatibility

[adodge]

The fit() method in sklearn has the signature fit(X,y) even if the class doesn't use the y value. This allows the object to be used in Pipelines, etc.

For example, note the fit() method for CountVectorizer: https://github.com/scikit-learn/scikit-learn/blob/bac89c2/sklearn/feature_extraction/text.py#L966

[gregversteeg]

Thanks adodge, that's very useful!