Closed ablaom closed 3 years ago
@AttilaKovacs Any objection?
Merging #10 (25ef345) into master (325c22d) will increase coverage by
1.51%
. The diff coverage is100.00%
.
@@ Coverage Diff @@
## master #10 +/- ##
==========================================
+ Coverage 88.48% 90.00% +1.51%
==========================================
Files 1 1
Lines 139 160 +21
==========================================
+ Hits 123 144 +21
Misses 16 16
Impacted Files | Coverage Δ | |
---|---|---|
src/MLJXGBoostInterface.jl | 90.00% <100.00%> (+1.51%) |
:arrow_up: |
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 c565121...25ef345. Read the comment docs.
For the binary classifier, it appears behaviour of the underlying XGBoost model has changed slightly, causing a fail at
but which passes if relaxed to
which is what this PR does.
Since this is really just an integration test, and not a test of XGBoost itself, I expect this is fine.