Merge pull request #76 from bgreenwell/devel

fix outdated URLs and rm old Rd file

.Rproj.user/shared/notebooks/paths

@@ -23,9 +23,14 @@
 /Users/bgreenwell/Dropbox/devel/fastshap/inst/tinytest/test-fastshap-vs-other-pkgs.R="F70E1DED"
 /Users/bgreenwell/Dropbox/devel/fastshap/inst/tinytest/test-genOMat.R="54612D12"
 /Users/bgreenwell/Dropbox/devel/fastshap/inst/tinytest/test-shapviz.R="29D8DEE8"
+/Users/bgreenwell/Dropbox/devel/fastshap/man/bin.Rd="869889FE"
+/Users/bgreenwell/Dropbox/devel/fastshap/revdep/cran.md="FA0CBEF5"
+/Users/bgreenwell/Dropbox/devel/fastshap/revdep/failures.md="54C2BBDB"
+/Users/bgreenwell/Dropbox/devel/fastshap/revdep/problems.md="EC41BDD2"
 /Users/bgreenwell/Dropbox/devel/fastshap/slowtests/fastshap-genOMat.cpp="99FEC81E"
 /Users/bgreenwell/Dropbox/devel/fastshap/slowtests/slowtest-benchmark.R="29ADFB84"
 /Users/bgreenwell/Dropbox/devel/fastshap/slowtests/slowtest-parallel.R="7B058F98"
+/Users/bgreenwell/Dropbox/devel/fastshap/src/Makevars="2B6CF773"
 /Users/bgreenwell/Dropbox/devel/fastshap/src/Makevars.win="0A0149DE"
 /Users/bgreenwell/Dropbox/devel/fastshap/src/RcppExports.cpp="394C142D"
 /Users/bgreenwell/Dropbox/devel/fastshap/vignettes/fastshap.Rmd="536A2979"

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: fastshap
 Type: Package
 Title: Fast Approximate Shapley Values
-Version: 0.1.0
+Version: 0.1.1
 Authors@R: person("Brandon", "Greenwell", email = "greenwell.brandon@gmail.com", role =
          c("aut", "cre"), comment = c(ORCID = "0000-0002-8120-0084"))
 Description: Computes fast (relative to other implementations) approximate 
@@ -23,6 +23,7 @@ Enhances:
 Suggests: 
     AmesHousing,
     covr,
+    earth,
     knitr,
     ranger,
     rmarkdown,

NEWS.md

@@ -1,3 +1,15 @@
+# fastshap 0.1.1
+
+## Changed
+
+* This NEWS file now follows the [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) format.
+
+## Fixed 
+
+* Removed an unnecessary `.Rd` file to satisfy CRAN policies.
+* Fixed a couple of outdated URLs.
+* Added [earth](https://CRAN.R-project.org/package=earth) to the list of suggested packages since it's referenced a couple of times in the package documentation.
+
 # fastshap 0.1.0
 
 ## Breaking changes
@@ -70,9 +82,9 @@ features.
 ## New features
 
 * The default method of `explain()` gained a new logical argument called `adjust`. When `adjust = TRUE` (and `nsim > 1`), the algorithm will adjust the sum of the estimated Shapley values to satisfy the *efficiency property*; that is, to equal the difference between the model's prediction for that sample and the average prediction over all the training data. This option is experimental and we follow the same approach as in
-[shap](https://github.com/slundberg/shap) [(#6)](https://github.com/bgreenwell/fastshap/issues/6).
+[shap](https://github.com/shap/shap) [(#6)](https://github.com/bgreenwell/fastshap/issues/6).
 
-* New (experimental) function for constructing [force plots](https://github.com/slundberg/shap) [(#7)](https://github.com/bgreenwell/fastshap/issues/7) to help visualize prediction explanations. The function is also a generic which means additional methods can be added.
+* New (experimental) function for constructing [force plots](https://github.com/shap/shap) [(#7)](https://github.com/bgreenwell/fastshap/issues/7) to help visualize prediction explanations. The function is also a generic which means additional methods can be added.
 
 * Function `explain()` became a generic and gained a new logical argument, `exact`, for computing exact Shapley contributions for linear models (Linear SHAP, which assumes independent features) and boosted decision trees (Tree SHAP). Currently, only `"lm"`, `"glm"`, and `"xgb.Booster"` objects are supported [(#2)](https://github.com/bgreenwell/fastshap/issues/2)[(#3)](https://github.com/bgreenwell/fastshap/issues/3).
 

R/explain.R

@@ -6,7 +6,7 @@
 #' @importFrom foreach foreach %do% %dopar%
 #' @importFrom stats var
 explain_column <- function(object, X, column, pred_wrapper, newdata = NULL) {
-  
+
   # Check types
   if (!is.null(newdata) && !identical(class(X), class(newdata))) {
     stop("Arguments `X` and `newdata` do not inherit from the same class: ",
@@ -191,7 +191,7 @@ explain_column <- function(object, X, column, pred_wrapper, newdata = NULL) {
 #' [stats::lm()] or [stats::glm()] object) assumes that the
 #' input features are independent. Also, setting `adjust = TRUE` is 
 #' experimental and we follow the same approach as in
-#' [shap](https://github.com/slundberg/shap).
+#' [shap](https://github.com/shap/shap).
 #' 
 #' @references 
 #' Strumbelj, E., and Igor K. (2014). Explaining prediction models and 

R/gen_friedman.R

@@ -7,6 +7,8 @@
 #' @param Integer specifying the number of bins to split `x` into.
 #'
 #' @keywords internal
+#'
+#' @noRd
 bin <- function(x, n_bins) {
   quantiles <- stats::quantile(x, probs = seq(from = 0, to = 1,
                                               length = n_bins + 1))

src/Makevars

@@ -1,4 +1,3 @@
-CXX_STD = CXX11
 ## PKG_CXXFLAGS = $(SHLIB_OPENMP_CXXFLAGS)
 ## PKG_LIBS = $(SHLIB_OPENMP_CXXFLAGS) $(LAPACK_LIBS) $(BLAS_LIBS) $(FLIBS)
 

vignettes/fastshap.Rmd

@@ -153,7 +153,7 @@ set.seed(2129)  # for reproducibility
 ## [1] "explain" "matrix"  "array"
 ```
 
-Note that the MC approach used by [fastshap](https://cran.r-project.org/package=fastshap) (and other packages) will not produce Shapley-based feature contributions that satisfy the [efficiency property](https://christophm.github.io/interpretable-ml-book/shapley.html#the-shapley-value-in-detail); that is, they won't add up to the difference between the corresponding prediction and baseline (i.e., average training prediction). However, borrowing a trick from the popular Python [shap](https://github.com/slundberg/shap) library, we can use a regression-based adjustment to correct the sum. To do this, simply set `adjust = TRUE` in the call to `explain()`^[Note that `nsim` has to be larger than one whenever setting `adjust = TRUE`.]:
+Note that the MC approach used by [fastshap](https://cran.r-project.org/package=fastshap) (and other packages) will not produce Shapley-based feature contributions that satisfy the [efficiency property](https://christophm.github.io/interpretable-ml-book/shapley.html#the-shapley-value-in-detail); that is, they won't add up to the difference between the corresponding prediction and baseline (i.e., average training prediction). However, borrowing a trick from the popular Python [shap](https://github.com/shap/shap) library, we can use a regression-based adjustment to correct the sum. To do this, simply set `adjust = TRUE` in the call to `explain()`^[Note that `nsim` has to be larger than one whenever setting `adjust = TRUE`.]:
 
 
 ```r

vignettes/fastshap.Rmd.orig

@@ -97,7 +97,7 @@ set.seed(2129)  # for reproducibility
                     nsim = 1000))
 ```
 
-Note that the MC approach used by [fastshap](https://cran.r-project.org/package=fastshap) (and other packages) will not produce Shapley-based feature contributions that satisfy the [efficiency property](https://christophm.github.io/interpretable-ml-book/shapley.html#the-shapley-value-in-detail); that is, they won't add up to the difference between the corresponding prediction and baseline (i.e., average training prediction). However, borrowing a trick from the popular Python [shap](https://github.com/slundberg/shap) library, we can use a regression-based adjustment to correct the sum. To do this, simply set `adjust = TRUE` in the call to `explain()`^[Note that `nsim` has to be larger than one whenever setting `adjust = TRUE`.]:
+Note that the MC approach used by [fastshap](https://cran.r-project.org/package=fastshap) (and other packages) will not produce Shapley-based feature contributions that satisfy the [efficiency property](https://christophm.github.io/interpretable-ml-book/shapley.html#the-shapley-value-in-detail); that is, they won't add up to the difference between the corresponding prediction and baseline (i.e., average training prediction). However, borrowing a trick from the popular Python [shap](https://github.com/shap/shap) library, we can use a regression-based adjustment to correct the sum. To do this, simply set `adjust = TRUE` in the call to `explain()`^[Note that `nsim` has to be larger than one whenever setting `adjust = TRUE`.]:
 
 ```{r titanic-explain-jack-adjust}
 set.seed(2133)  # for reproducibility