Out of Time In space split is wrong on space_time_split_dataset function

[marcelogdeandrade]

Issue location

src/fklearn/preprocessing/splitting.py

Function: space_time_split_dataset

Problem description

space_time_split_dataset splits the input DataFrame into 4 parts:

• train_set
• intime_outspace_hdout
• outime_inspace_hdout
• outime_outspace_hdout

The outime_inspace_hdout split is defined wrongly on the function. It is only filtered by time, but not in space

outime_inspace_hdout = dataset[
        (dataset[time_column] >= train_end_date) & (dataset[time_column] < holdout_end_date)]

Expected behavior

The outime_inspace_hdout should split the DataFrame out of space and in time, not only out of space

Possible solutions

We should rename this variable to outime_hdout, and define the right split with the other 3.

E.g.

train_set = train_period[~train_period[space_column].isin(holdout_space)]
intime_outspace_hdout = train_period[train_period[space_column].isin(holdout_space)]
outime_outspace_hdout = outime_hdout[outime_hdout[space_column].isin(holdout_space)]
outime_inspace_hdout = outime_hdout[~outime_hdout[space_column].isin(holdout_space)]

[caique-lima]

Is a bit hard to understand this issue because I think we have some messed up stuff in the documentation.

First of all seems that we have an issue with the docstring:

intime_outspace_hdout : pandas.DataFrame
    The out of ID sample and in time hold out set.

Is equal to

outime_inspace_hdout : pandas.DataFrame
    The out of ID sample and in time hold out set.

This last one should be The in ID sample and out time hold out set

And just to clarify, the expected behaviour is that in this test:

https://github.com/nubank/fklearn/blob/master/tests/preprocessing/test_splitting.py#L62

This value should be:

'space': ['space2'],

Just like the training dataset

@marcelogdeandrade can you solve this bug? Your solution seems fine to me, but don't forget to update the docstring

[marcelogdeandrade]

@caique-lima Sure, I'll solve it

[caique-lima]

Related to #62