Should Incremental.partial_fit be concrete when handed numpy arrays?

What should happen here?

```python
sgd = skleran.SGDClassifier()
inc = Incremental(sgd)

X = np.array(...)
y = np.array(...)
inc.partial_fit(X, y)
```

Everything is concrete. Should we build things up lazily or should we execute directly using `inc.estimator.partial_fit(X, y)`?