rebuild and recheck

WinVector · Jan 16, 2020 · fa2bd14 · fa2bd14
1 parent 6a591bc
commit fa2bd14
Show file tree

Hide file tree

Showing 29 changed files with 227 additions and 222 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,7 +2,7 @@ Package: vtreat
 Type: Package
 Title: A Statistically Sound 'data.frame' Processor/Conditioner
 Version: 1.5.1
-Date: 2020-01-14
+Date: 2020-01-16
 Authors@R: c(
     person("John", "Mount", email = "jmount@win-vector.com", role = c("aut", "cre")),
     person("Nina", "Zumel", email = "nzumel@win-vector.com", role = c("aut")),

diff --git a/NEWS.md b/NEWS.md
@@ -1,5 +1,5 @@
 
-# vtreat 1.5.1 2020/01/14
+# vtreat 1.5.1 2020/01/16
 
  * Check for same-frame on prepare paths.
  * Pipe into ft.

diff --git a/R/utils.R b/R/utils.R
@@ -385,8 +385,11 @@ vtreat_make_names <- function(nms_in,
 #' @importFrom digest digest
 NULL
 
-# approximate object identity check
+# approximate object identity check, can return NULL
 id_f <- function(d) { 
+  if(!isTRUE(getOption('vtreat.check_for_nested_model_bias', TRUE))) {
+    return(NULL)
+  }
   return(digest::digest(d))
 }
 
diff --git a/R/zzz.R b/R/zzz.R
@@ -4,7 +4,8 @@
   vtreat_default_options <- list(
     vtreat.use_data.table_binding = TRUE,
     vtreat.use_clean_suffix = FALSE,
-    vtreat.allow_parallel = TRUE
+    vtreat.allow_parallel = TRUE,
+    vtreat.check_for_nested_model_bias = TRUE
   )
   op <- options()
   toset <- setdiff(names(vtreat_default_options), names(op))

diff --git a/README.md b/README.md
@@ -336,14 +336,14 @@ dTestC <- data.frame(x=c('a', 'b', 'c', NA), z=c(10, 20, 30, NA))
 treatmentsC <- designTreatmentsC(dTrainC, colnames(dTrainC), 'y', TRUE,
                                  verbose=FALSE)
 print(treatmentsC$scoreFrame[, c('origName', 'varName', 'code', 'rsq', 'sig', 'extraModelDegrees')])
- #    origName   varName  code         rsq        sig extraModelDegrees
- #  1        x    x_catP  catP 0.059315943 0.45141252                 2
- #  2        x    x_catB  catB 0.029824903 0.59334713                 2
- #  3        z         z clean 0.237601767 0.13176020                 0
- #  4        z   z_isBAD isBAD 0.296065432 0.09248399                 0
- #  5        x  x_lev_NA   lev 0.296065432 0.09248399                 0
- #  6        x x_lev_x_a   lev 0.130005705 0.26490379                 0
- #  7        x x_lev_x_b   lev 0.006067337 0.80967242                 0
+ #    origName   varName  code          rsq        sig extraModelDegrees
+ #  1        x    x_catP  catP 1.559780e-01 0.22202097                 2
+ #  2        x    x_catB  catB 1.142159e-05 0.99166241                 2
+ #  3        z         z clean 2.376018e-01 0.13176020                 0
+ #  4        z   z_isBAD isBAD 2.960654e-01 0.09248399                 0
+ #  5        x  x_lev_NA   lev 2.960654e-01 0.09248399                 0
+ #  6        x x_lev_x_a   lev 1.300057e-01 0.26490379                 0
+ #  7        x x_lev_x_b   lev 6.067337e-03 0.80967242                 0
 
 # help("prepare")
 
@@ -383,9 +383,9 @@ treatmentsN = designTreatmentsN(dTrainN, colnames(dTrainN), 'y',
                                 verbose=FALSE)
 print(treatmentsN$scoreFrame[, c('origName', 'varName', 'code', 'rsq', 'sig', 'extraModelDegrees')])
  #    origName   varName  code          rsq       sig extraModelDegrees
- #  1        x    x_catP  catP 1.348315e-01 0.3708945                 2
- #  2        x    x_catN  catN 4.582430e-02 0.6107193                 2
- #  3        x    x_catD  catD 2.549856e-01 0.2018336                 2
+ #  1        x    x_catP  catP 7.174888e-02 0.5212691                 2
+ #  2        x    x_catN  catN 1.950163e-03 0.9173064                 2
+ #  3        x    x_catD  catD 3.743113e-01 0.1069707                 2
  #  4        z         z clean 2.880952e-01 0.1701892                 0
  #  5        z   z_isBAD isBAD 3.333333e-01 0.1339746                 0
  #  6        x  x_lev_NA   lev 3.333333e-01 0.1339746                 0

diff --git a/cran-comments.md b/cran-comments.md
@@ -3,46 +3,45 @@
 
 ### OSX
 
-    R CMD check --as-cran vtreat_1.5.0.tar.gz 
+    R CMD check --as-cran vtreat_1.5.1.tar.gz 
     * using R version 3.6.0 (2019-04-26)
     * using platform: x86_64-apple-darwin15.6.0 (64-bit)
     * using session charset: UTF-8
     * using option ‘--as-cran’
     * checking for file ‘vtreat/DESCRIPTION’ ... OK
     * checking extension type ... Package
-    * this is package ‘vtreat’ version ‘1.5.0’
+    * this is package ‘vtreat’ version ‘1.5.1’
     * checking CRAN incoming feasibility ... Note_to_CRAN_maintainers
     Maintainer: ‘John Mount <jmount@win-vector.com>’
     Status: OK
 
 ### Windows
 
      rhub::check_for_cran()
-     595#> setting _R_CHECK_FORCE_SUGGESTS_ to false
-     596#> setting R_COMPILE_AND_INSTALL_PACKAGES to never
-     597#> setting R_REMOTES_STANDALONE to true
-     598#> setting R_REMOTES_NO_ERRORS_FROM_WARNINGS to true
-     599#> setting _R_CHECK_FORCE_SUGGESTS_ to true
-     600#> setting _R_CHECK_CRAN_INCOMING_USE_ASPELL_ to true
-     601#> * using log directory 'C:/Users/USERHcCdOFfKjh/vtreat.Rcheck'
-     602#> * using R Under development (unstable) (2019-11-08 r77393)
-     603#> * using platform: x86_64-w64-mingw32 (64-bit)
-     604#> * using session charset: ISO8859-1
-     605#> * using option '--as-cran'
-     606#> * checking for file 'vtreat/DESCRIPTION' ... OK
-     607#> * checking extension type ... Package
-     608#> * this is package 'vtreat' version '1.5.0'
-     609#> * checking CRAN incoming feasibility ... Note_to_CRAN_maintainers
-     610#> Maintainer: 'John Mount '
-     652#> * checking sizes of PDF files under 'inst/doc' ... NOTE
-     653#> Unable to find GhostScript executable to run checks on size reduction
-     668#> Status: 1 NOTE
+     677#> setting _R_CHECK_FORCE_SUGGESTS_ to false
+     678#> setting R_COMPILE_AND_INSTALL_PACKAGES to never
+     679#> setting R_REMOTES_STANDALONE to true
+     680#> setting R_REMOTES_NO_ERRORS_FROM_WARNINGS to true
+     681#> setting _R_CHECK_FORCE_SUGGESTS_ to true
+     682#> setting _R_CHECK_CRAN_INCOMING_USE_ASPELL_ to true
+     683#> * using log directory 'C:/Users/USERDzGwBgVLWk/vtreat.Rcheck'
+     684#> * using R Under development (unstable) (2020-01-07 r77637)
+     685#> * using platform: x86_64-w64-mingw32 (64-bit)
+     686#> * using session charset: ISO8859-1
+     687#> * using option '--as-cran'
+     688#> * checking for file 'vtreat/DESCRIPTION' ... OK
+     689#> * checking extension type ... Package
+     690#> * this is package 'vtreat' version '1.5.1'
+     691#> * checking CRAN incoming feasibility ... Note_to_CRAN_maintainers
+     692#> Maintainer: 'John Mount '
+     734#> * checking sizes of PDF files under 'inst/doc' ... NOTE
+     735#> Unable to find GhostScript executable to run checks on size reduction
+     750#> Status: 1 NOTE
      GhostScript NOTE is a property of the test environment, not of the package.
 
 ## Downstream dependencies
 
 No declared reverse dependencies ( https://github.com/WinVector/vtreat/blob/master/extras/check_reverse_dependencies.md ).
-
 
 Mount and Zumel are not mis-spellings.
 
diff --git a/docs/articles/MultiClassVtreat.html b/docs/articles/MultiClassVtreat.html
diff --git a/docs/articles/SavingTreamentPlans.html b/docs/articles/SavingTreamentPlans.html
diff --git a/docs/articles/VariableImportance.html b/docs/articles/VariableImportance.html
diff --git a/docs/articles/vtreat.html b/docs/articles/vtreat.html