Closed bbengfort closed 2 years ago
Merging #1251 (941e793) into develop (233d9d1) will increase coverage by
0.00%
. The diff coverage is100.00%
.
@@ Coverage Diff @@
## develop #1251 +/- ##
========================================
Coverage 90.57% 90.58%
========================================
Files 92 92
Lines 5209 5213 +4
========================================
+ Hits 4718 4722 +4
Misses 491 491
Impacted Files | Coverage Δ | |
---|---|---|
yellowbrick/model_selection/dropping_curve.py | 92.18% <ø> (ø) |
|
yellowbrick/cluster/elbow.py | 97.81% <100.00%> (-0.04%) |
:arrow_down: |
yellowbrick/utils/wrapper.py | 100.00% <100.00%> (ø) |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update 233d9d1...941e793. Read the comment docs.
It was dropping curve...
@bbengfort You should open an issue to create get_params test.
I just checked DroppingCurve
- get_params
works fine, so I guess you fixed it.
@lwgray Issue #1252 opened at your request.
I also added a test for DroppingCurve.get_params
.
This PR fixes #1232 which reported a bug that caused a problem to occur when users call
KElbow.get_params()
, e.g. in a notebook when they want to render the scikit-learn rich visualization of the estimator.I have made the following changes:
KElbow
to ensure it stores all hyperparams and only creates learned params infit()
get_params
works forKElbow
Sample Code and Plot
The above code snippet should not produce an exception:
AttributeError: 'KMeans' object has no attribute 'k'
Questions for the @DistrictDataLabs/team-oz-maintainers:
get_params
for all our models to make sure this doesn't happen?CHECKLIST
pytest
?make html
?~