Skip to content

Commit

Permalink
Merge pull request #142 from koalaverse/devel
Browse files Browse the repository at this point in the history
tweak headers
  • Loading branch information
bgreenwell committed Jul 16, 2023
2 parents d268866 + 4eae99f commit addabe6
Show file tree
Hide file tree
Showing 679 changed files with 216,364 additions and 1,055 deletions.
2 changes: 2 additions & 0 deletions .Rbuildignore
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,10 @@
^codecov\.yml$
^data-raw$
^docs$
^lightgbm\.model$
^README\.Rmd$
^README_cache
^revdep
^rjournal$
^slowtests
^tools$
Expand Down
45 changes: 19 additions & 26 deletions DESCRIPTION
Original file line number Diff line number Diff line change
Expand Up @@ -10,11 +10,7 @@ Authors@R: c(
person("Brad", "Boehmke",
email = "bradleyboehmke@gmail.com",
role = c("aut"),
comment = c(ORCID = "0000-0002-3611-8516")),
person("Bernie", "Gray",
email = "bfgray3@gmail.com",
role = c("aut"),
comment = c(ORCID = "0000-0001-9190-6032"))
comment = c(ORCID = "0000-0002-3611-8516"))
)
Description: A general framework for constructing variable importance plots from
various types of machine learning models in R. Aside from some standard model-
Expand All @@ -32,57 +28,54 @@ URL: https://github.com/koalaverse/vip/,
BugReports: https://github.com/koalaverse/vip/issues
Encoding: UTF-8
VignetteBuilder: knitr
Depends: R (>= 2.10)
Depends: R (>= 4.1.0)
Imports:
foreach,
ggplot2 (>= 0.9.0),
magrittr,
stats,
tibble,
yardstick,
utils
utils,
yardstick
Suggests:
bookdown,
DT,
C50,
caret,
Ckmeans.1d.dp,
covr,
Cubist,
doParallel,
dplyr,
fastshap (>= 0.1.0),
knitr,
lattice,
mlbench,
modeldata,
NeuralNetTools,
pdp,
rmarkdown,
tinytest (>= 1.4.1),
varImp
Enhances:
C50,
caret,
Cubist,
earth,
fastshap,
gbm,
glmnet,
h2o,
htmlwidgets,
keras,
knitr,
lattice,
lightgbm,
mixOmics,
mlbench,
mlr,
mlr3,
modeldata,
neuralnet,
NeuralNetTools,
nnet,
parsnip (>= 0.1.7),
party,
partykit,
pdp,
pls,
randomForest,
ranger,
rmarkdown,
rpart,
RSNNS,
sparkline,
sparklyr (>= 0.8.0),
tidymodels,
tinytest (>= 1.4.1),
varImp,
workflows (>= 0.2.3),
xgboost
LazyData: true
Expand Down
7 changes: 1 addition & 6 deletions NAMESPACE
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
# Generated by roxygen2: do not edit by hand

S3method(add_sparklines,vi)
S3method(vi,default)
S3method(vi_firm,default)
S3method(vi_model,C5.0)
Expand All @@ -18,6 +17,7 @@ S3method(vi_model,default)
S3method(vi_model,earth)
S3method(vi_model,gbm)
S3method(vi_model,glmnet)
S3method(vi_model,lgb.Booster)
S3method(vi_model,lm)
S3method(vi_model,mixo_pls)
S3method(vi_model,mixo_spls)
Expand Down Expand Up @@ -47,9 +47,6 @@ S3method(vip,WrappedModel)
S3method(vip,default)
S3method(vip,model_fit)
S3method(vip,workflow)
export("%>%")
export("%T>%")
export(add_sparklines)
export(gen_friedman)
export(list_metrics)
export(vi)
Expand All @@ -61,5 +58,3 @@ export(vip)
importFrom(foreach,"%do%")
importFrom(foreach,"%dopar%")
importFrom(foreach,foreach)
importFrom(magrittr,"%>%")
importFrom(magrittr,"%T>%")
44 changes: 29 additions & 15 deletions NEWS.md
Original file line number Diff line number Diff line change
@@ -1,24 +1,18 @@
# vip 0.3.3
# vip 0.4.0

## Breaking changes

* The `var_fun` argument in `vi_firm()` has been deprecated; use the new `var_continuous` and `var_categorical` instead.

* The explicit `ice` argument in `vi_firm()` has been removed; it was not really needed since it can be passed via the `...` argument.

## Enhancements
## Changed

* The permutation importance method (i.e., function `vi_permute()`) now integrates with and uses [yardstick](https://cran.r-project.org/package=yardstick) performance metrics.
* This NEWS file now follows the [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.

* `list_metrics()` gained an additional `smaller_is_better` column indicating whether or not the corresponding metric should be minimized (`smaller_is_better = TRUE`) or maximized (`smaller_is_better = FALSE`); thanks to @topedo. Additionally, all the column names are now in lower case.
* Raised R version dependency to >= 4.1.0 (the introduction of the native piper operator `|>`).

* Added support for partial least squares via the [mixOmics](https://bioconductor.org/packages/mixOmics/) package [(PR #129)](https://github.com/koalaverse/vip/pull/129); thanks to @topedo.
* The `vi_permute` function now uses [yardstick](https://cran.r-project.org/package=yardstick); consequently, metric functions now conform to [yardstick](https://cran.r-project.org/package=yardstick) metric argument names.

* Added support for the [workflows](https://cran.r-project.org/package=workflows) and [parsnip](https://cran.r-project.org/package=parsnip) packages from the [tidymodels](https://www.tidymodels.org/) ecosystem [(PR #128)](https://github.com/koalaverse/vip/pull/128); thanks to @topedo.
* The `var_fun` argument in `vi_firm()` has been deprecated; use the new `var_continuous` and `var_categorical` instead.

* New [pkgdown](https://cran.r-project.org/package=pkgdown) site and vignette based on our original R Journal article.
* The explicit `ice` argument in `vi_firm()` has been removed; it was not really needed since it can be passed via the `...` argument.

## Miscellaneous
* Removed [magrittr](https://cran.r-project.org/package=magrittr) from imports; it's easy enough to just laod the package if you need it or use R's newer internal pipe operator.

* Tweaked examples.

Expand All @@ -34,7 +28,27 @@

* Switched to using markdown syntax in `roxygen2` comments.

## Bug fixes
## Added

* `vi_model()` now supports [lightgbm](https://cran.r-project.org/package=lightgbm) models. Thanks to @nipnipj for the suggestion [(#146)](https://github.com/koalaverse/vip/issues/146).

* The permutation importance method (i.e., function `vi_permute()`) now integrates with and uses [yardstick](https://cran.r-project.org/package=yardstick) performance metrics.

* `list_metrics()` gained an additional `smaller_is_better` column indicating whether or not the corresponding metric should be minimized (`smaller_is_better = TRUE`) or maximized (`smaller_is_better = FALSE`); thanks to @topedo. Additionally, all the column names are now in lower case.

* Added support for partial least squares via the [mixOmics](https://bioconductor.org/packages/mixOmics/) package [(PR #129)](https://github.com/koalaverse/vip/pull/129); thanks to @topedo.

* Added support for the [workflows](https://cran.r-project.org/package=workflows) and [parsnip](https://cran.r-project.org/package=parsnip) packages from the [tidymodels](https://www.tidymodels.org/) ecosystem [(PR #128)](https://github.com/koalaverse/vip/pull/128); thanks to @topedo.

* New [pkgdown](https://cran.r-project.org/package=pkgdown) site and vignette based on our original R Journal article.

## Removed

* Function `add_sparklines()` seems out of scope and has been removed.
* Function `vint()` also seems out of scope and is too slow to implement for most practical problems; for now, the function will likely live on in the [moreparty](https://cran.r-project.org/package=moreparty) package.


## Fixed

* Fix model-based VI support for [mlr](https://cran.r-project.org/package=mlr), [mlr3](https://cran.r-project.org/package=mlr3), [parsnip](https://cran.r-project.org/package=parsnip), and [workflows](https://cran.r-project.org/package=workflows) model fits.

Expand Down
184 changes: 0 additions & 184 deletions R/add_sparklines.R

This file was deleted.

Loading

0 comments on commit addabe6

Please sign in to comment.