Update pipeline `save` / `load` to use pickle instead of cloudpickle

[angela97lin]

[dsherry]

This is fine with me. I think its preferable to use the python built-in pickle as our default serialization strategy.

I'd like this issue to track updating our pipeline and AutoMLSearch save and load methods to support both pickle and cloudpickle formats, via a format keyword arg.

Note that before we make pickle the new default serialization format, we should verify that this doesn't affect the serialization required for the dask-backed parallel engine (@chukarsten ). If pickle causes problems for the parallel engine, we'll need to update that code to continue to use cloudpickle.