Closed markhwhiteii closed 4 years ago
it failed because I normalized and then adjusted for co-appearances; this does not lead to rows that all equal to 1 when one item always wins/always loses. so, I flipped the order. it first adjusts for co-appearances (doesn't matter of its a BIBD, since lambda is the same for all), and then normalizes so that everything is equal to one.
Merging #36 into master will increase coverage by
1.59%
. The diff coverage is100.00%
.
@@ Coverage Diff @@
## master #36 +/- ##
===========================================
+ Coverage 98.40% 100.00% +1.59%
===========================================
Files 17 17
Lines 251 271 +20
===========================================
+ Hits 247 271 +24
+ Misses 4 0 -4
Impacted Files | Coverage Δ | |
---|---|---|
R/eloscoring.R | 100.00% <100.00%> (ø) |
|
R/get_M.R | 100.00% <100.00%> (ø) |
|
R/get_checks.R | 100.00% <100.00%> (+13.33%) |
:arrow_up: |
R/prscoring.R | 100.00% <100.00%> (ø) |
|
R/walkscoring.R | 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 b7b457b...9a62b4e. Read the comment docs.
d224509 should also not fail any tests, because all test data so far have been bibd
get_checks testing goes way down; need another commit with more testing to get it back up
509626e should bring codecov back up
closes #35
opening to see if it fails checks—it shouldn't, since all examples so far have BIBD with lambda of 1