Closed ras44 closed 7 months ago
Let's merge this PR as is and open a new PR for adding an option for
skipna=False
. Thanks for the contribution.
Took a quick look at this and not sure how the skipna=False
argument should work:
.cumsum(skipna)
seems redundant since there never will be NaNsIs the idea for skipna to allow NaN's in the dataframe? So:
.cumsum(skipna)
Proposed changes
This is a minimal fix to resolve the issue described in #707. The fix contains assertions in the functions
get_cumlift
,get_qini
,get_tmlegain
, andget_tmleqini
that required columns in the dataframes do not contain null values. An example test forget_cumlift
is included.Types of changes
What types of changes does your code introduce to CausalML? Put an
x
in the boxes that applyChecklist
Put an
x
in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.Further comments
None