Add BinaryClassifierPrecisionEfficacy metric
#714
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #714 +/- ##
==========================================
+ Coverage 94.88% 95.11% +0.22%
==========================================
Files 106 110 +4
Lines 4126 4275 +149
==========================================
+ Hits 3915 4066 +151
+ Misses 211 209 -2
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
| return scores | ||
|
|
||
| @classmethod | ||
| def compute_breakdown( |
There was a problem hiding this comment.
why is this a class method?
There was a problem hiding this comment.
It's a class method by definition:
SDMetrics/sdmetrics/single_table/base.py
Line 168 in 280a93e
|
|
||
| self._fit_preprocess(data, metadata) | ||
|
|
||
| def _transform_preprocess(self, tables): |
There was a problem hiding this comment.
minor: we could just call transform
There was a problem hiding this comment.
Since it follows _fit_preprocess and I wanted it to differ from fit to prevent confusion with the ML model fix, I think we can keep it this way.
There was a problem hiding this comment.
The ML model was separated out though. I think _fit_preprocess confuses me as it makes me wonder if we are fitting on preprocessed data or fitting as part of the preprocess step
|
Thanks for the review @amontanez24. I addressed the comments in 791c7d5 and aafdd1e with some refactoring as you recommended |
| @@ -32,7 +32,7 @@ def wrapper(*args, **kwargs): | |||
| ipython_interpreter = str(get_ipython()) | |||
| if 'ZMQInteractiveShell' in ipython_interpreter and 'iframe' in renderers: | |||
| # This means we are using jupyter notebook | |||
| pio.renderers.default = 'vscode' | |||
| pio.renderers.default = 'iframe' | |||
There was a problem hiding this comment.
I found that this change was accidentally added in a previous PR, so I reverted it.
CU-86b3m9u4d
Resolve #711