feat: add support for creating a Matrix Factorization model

[rey-esp]

Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Make sure to open an issue as a bug/issue before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea
• Ensure the tests and linter pass
• Code coverage does not decrease (if any source code was changed)
• Appropriate docs were updated (if necessary)

Fixes #<issue_number_goes_here> 🦕

[sycai]

Does it make sense to add some system/unit tests for this change?

[tswast]

@GarrettWu @shuoweil I see in #1282 you ended up passing in "id_col" as a separate argument to fit() instead of the class constructor. Is this a pattern you would recommend here?

Note: MatrixFactorization differs somewhat from that application in that normally in scikit-learn one would have a "sparse matrix" data type (e.g. https://docs.scipy.org/doc/scipy/reference/sparse.html) where rows/cols/values would all be bundled up in one object, similar to how we are using the bigframes DataFrame for this purpose.