doc fixes and then re-build and re-check

Author: JohnMount

.Rbuildignore

@@ -21,3 +21,4 @@
 ^paper.md$
 ^paper.bib$
 ^CONTRIBUTING.md$
+^Examples$

DESCRIPTION

@@ -2,7 +2,7 @@ Package: vtreat
 Type: Package
 Title: A Statistically Sound 'data.frame' Processor/Conditioner
 Version: 1.4.5
-Date: 2019-07-31
+Date: 2019-09-11
 Authors@R: c(
     person("John", "Mount", email = "[email protected]", role = c("aut", "cre")),
     person("Nina", "Zumel", email = "[email protected]", role = c("aut")),

NEWS.md

@@ -1,5 +1,5 @@
 
-# vtreat 1.4.5 2019/07/31
+# vtreat 1.4.5 2019/09/11
 
  * Some doc updates.
 

README.Rmd

@@ -349,7 +349,8 @@ dTrainN %.>%
 
 Related work:
 
-  * ["A Transformation for Simplifying the Interpretation of Coefficients of Binary Variables in Regression Analysis"](https://www.jstor.org/stable/2683780), Robert E. Sweeney and Edwin F. Ulveling; The American Statistician, vol. 26, no. 5, pp. 30-32, 1972.
+  * Cohen J, Cohen P (1983). Applied Multiple Regression/Correlation Analysis For The Behav-
+ioral Sciences. 2 edition. Lawrence Erlbaum Associates, Inc. ISBN 0-89859-268-2.
   * ["A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems"](http://dl.acm.org/citation.cfm?id=507538) Daniele Micci-Barreca; ACM SIGKDD Explorations, Volume 3 Issue 1, July 2001 Pages 27-32.
   * ["Modeling Trick: Impact Coding of Categorical Variables with Many Levels"](http://www.win-vector.com/blog/2012/07/modeling-trick-impact-coding-of-categorical-variables-with-many-levels/) Nina Zumel; Win-Vector blog, 2012.
   * "Big Learning Made Easy – with Counts!", Misha Bilenko, Cortana Intelligence and Machine Learning Blog, 2015.

README.md

@@ -304,14 +304,14 @@ 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 0.130498074 0.26400089                 2
- #  2        x    x_catB  catB 0.030345745 0.59013918                 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")
 
@@ -349,9 +349,9 @@ 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 3.700306e-01 0.1095637                 2
- #  2        x    x_catN  catN 2.606061e-01 0.1961166                 2
- #  3        x    x_catD  catD 6.666667e-02 0.5369633                 2
+ #  1        x    x_catP  catP 3.558824e-01 0.1184999                 2
+ #  2        x    x_catN  catN 2.663337e-02 0.6993947                 2
+ #  3        x    x_catD  catD 4.226472e-02 0.6252538                 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
@@ -407,11 +407,9 @@ dTrainN %.>%
 
 Related work:
 
-  - [“A Transformation for Simplifying the Interpretation of
-    Coefficients of Binary Variables in Regression
-    Analysis”](https://www.jstor.org/stable/2683780), Robert E.
-    Sweeney and Edwin F. Ulveling; The American Statistician, vol. 26,
-    no. 5, pp. 30-32, 1972.
+  - Cohen J, Cohen P (1983). Applied Multiple Regression/Correlation
+    Analysis For The Behav- ioral Sciences. 2 edition. Lawrence Erlbaum
+    Associates, Inc. ISBN 0-89859-268-2.
   - [“A preprocessing scheme for high-cardinality categorical attributes
     in classification and prediction
     problems”](http://dl.acm.org/citation.cfm?id=507538) Daniele

cran-comments.md

@@ -6,38 +6,35 @@
 
 ### OSX
 
-    R CMD check --as-cran vtreat_1.4.4.tar.gz
+    R CMD check --as-cran vtreat_1.4.5.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 ‘1.4.4’
-    * checking CRAN incoming feasibility ... NOTE
+    * this is package ‘vtreat’ version ‘1.4.5’
+    * checking CRAN incoming feasibility ... Note_to_CRAN_maintainers
     Maintainer: ‘John Mount <[email protected]>’
-    Found the following (possibly) invalid URLs:
-      URL: https://www.jstor.org/stable/2683780
-        From: inst/doc/vtreat.html
-        Status: 403
-        Message: Forbidden
-    * checking top-level files ... WARNING
-    Conversion of ‘README.md’ failed:
-    pandoc: Could not fetch https://www.r-pkg.org/badges/version/vtreat
-    TlsException (HandshakeFailed (Error_Protocol ("expecting server hello, got alert : [(AlertLevel_Fatal,HandshakeFailure)]",True,HandshakeFailure)))
-    Status: 1 WARNING, 1 NOTE
-    WARNING and NOTE are spurious, URLs https://www.jstor.org/stable/2683780 and https://www.jstor.org/stable/2683780 are correct and working.
+    Status: OK
 
 ### Windows
 
     rhub::check_for_cran()
-    Build ID:	vtreat_1.4.4.tar.gz-d878c7bb020e4c0abb135d9e32ceee14
-    Platform:	Windows Server 2008 R2 SP1, R-devel, 32/64 bit
-    NOTES:
-    * checking sizes of PDF files under 'inst/doc' ... NOTE
-    Unable to find GhostScript executable to run checks on size reduction
+    595#> * using R Under development (unstable) (2019-08-30 r77101)
+    596#> * using platform: x86_64-w64-mingw32 (64-bit)
+    597#> * using session charset: ISO8859-1
+    598#> * using option '--as-cran'
+    599#> * checking for file 'vtreat/DESCRIPTION' ... OK
+    600#> * checking extension type ... Package
+    601#> * this is package 'vtreat' version '1.4.5'
+    602#> * checking CRAN incoming feasibility ... Note_to_CRAN_maintainers
+    603#> Maintainer: 'John Mount '
+    645#> * checking sizes of PDF files under 'inst/doc' ... NOTE
+    646#> Unable to find GhostScript executable to run checks on size reduction
+    660#> * DONE
+    661#> Status: 1 NOTE
     GhostScript NOTE is a property of the test environment, not the package.
- 
 
 ## Downstream dependencies