Previously I was subverting the natural order of operations by
subclassing from `ndarray`, but it turns out that you can tell just
numpy to call your operator instead of its by setting the
`__array_priority__` attribute on your class. This is much simpler, and
it turns out the be a little more robust, too.
- Avoid importing numpy unless necessary.
- Mention numpy arrays and dictionaries in the docs.
- Add numpy to the list of tox dependencies.
- Don't unnecessarily copy arrays or allocate empty space for them.
- Use code from compat.py rather than writing py2/3 versions of things
myself.
- Avoid reimplementing __repr__ for built-in types.
- Add an option to consider NaN == NaN, because sometimes people use NaN
to mean "missing data".
Kale Kundert
Bruno Oliveira
Ronny Pfannschmidt