Closed paulstey closed 5 years ago
Merging #36 into master will decrease coverage by
1.12%
. The diff coverage is100%
.
@@ Coverage Diff @@
## master #36 +/- ##
==========================================
- Coverage 97.81% 96.68% -1.13%
==========================================
Files 10 11 +1
Lines 183 181 -2
==========================================
- Hits 179 175 -4
- Misses 4 6 +2
Impacted Files | Coverage Δ | |
---|---|---|
src/Impute.jl | 87.5% <ø> (-2.5%) |
:arrow_down: |
src/imputors.jl | 93.75% <ø> (-6.25%) |
:arrow_down: |
src/imputors/hotdeck.jl | 100% <100%> (ø) |
|
src/context.jl | 96.87% <0%> (-3.13%) |
:arrow_down: |
src/imputors/interp.jl | 100% <0%> (ø) |
:arrow_up: |
src/deprecated.jl | 100% <0%> (ø) |
: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 b436833...ba08ad0. Read the comment docs.
@rofinn, I think this should be all set now. Thanks for the comments!
@paulstey Do you mind if I just fix up you branch and merge it?
@rofinn Sorry for the delay, I've been traveling. And yes, that would be perfect!
Also, I like the idea of renaming to SRS!
This is all set; thank you!
I've added the ability to use hot-deck imputation. This allows for the imputation of missing values while preserving the univariate-distributional properties of the variables being imputed.
I've written it to behave like the existing imputation methods. I've also written a few test, all of which are passing.
I'd also be interested in working on multiple imputation using chained equations—assuming there would be interest in that.