adding static type checking with mypy

[jreback]

http://blog.zulip.org/2016/10/13/static-types-in-python-oh-mypy/

might be interesting if someone is looking for a project :>

[max-sixty]

#12412

[jorisvandenbossche]

See also wesm/pandas2#18 (a advantage for targetting this for 2.0 is we can directly use the python 3 syntax)

[brmc]

continuing the conversation from wesm/pandas2#18

I agree with @shoyer. type hints should be implemented as early as possible. I've taken a couple days off work, so I can get started on annotations for py2 tomorrow. Do you have any preference on how large pull requests should be? if it were up to me, given the relative safety of this sort of modification, I would probably do a PR per sub-module. Let me know if you'd like me to do it differently. After that i can move on to stubs

[jreback]

@brmc sounds great!

I think main things to add are support for Series, DataFrame, Index methods (Timestamp, Timedelta, Period would be nice to).

you are wanting to add .pyi files where the module live? (.e.g. pandas/core/)

will need to add a build with mypy as well for validation.

are there other projects that do this (just for seeing examples), if so how are they adding it?

[jreback]

A concern of mine is this:

essentially you are taking a file, say pandas/core/series.py and stripping out the impl, leaving the signatures. Then we validate that this works with mypy. I really really want to be sure this stays in sync with the actual signature / impl files. So we need tests that compares these directly (in py3 this is actually not that hard, you can iterate over the definitions and simply compare the signatures). I think if we only compare this in py3 would be ok actually as our definitions should be py2/3 compat anyways. (or do we want / need differing signatures, e.g. a 2 and 3 impl)?

Have others done this?

[TomAugspurger]

We'll want to push these upstream to https://github.com/python/typeshed/ once we have reasonable coverage.

[TomAugspurger]

Oh, and I hadn't heard of this, but https://github.com/python/mypy/blob/master/mypy/stubgen.py may be a good starting place? I guess it operates one module at a time so

mkdir out
stubgen pandas.core.series
stubgen pandas.core.frame
stubgen pandas.core.index

[brmc]

@jreback, to be honest, i've never used stubs as a core part of a project I was working on. I've only used them to supplement underlying dependencies or to workaround bugs in my IDE, so i've never thought too deeply about what consequences they might have

[brmc]

ok, I'm about to get started. To be clear, I'm going to only concentrate on method signatures and return types (for now). I'm not going to annotate local variables unless I have some justifiable reason.

Regarding the relevant parts of the contributing docs:

• style: for short signatures i'll do the annotations on a single line, for longer ones, i'll annotate each parameter individually
• committing: I should use the "CLN" prefix since this issue has the clean label, correct?
• docs: Does this change warrant an entry in whatsnew/v0.20.0.txt? if so, where? under Other Enhancements?

I've never contributed to pandas so please let me know if there's anything I'm overlooking