Pre 0.0.2 release work (#161)

* version bump for dependencies

* ignore revdeps in build

* predict_ no longer exported

* changes for sparklyr 1.0.0

* updated tests to avoid using the predict_* functions

* multi_predict no longer internal

* added an event time data set based on R CMD check times

* typp

Author: topepo

.Rbuildignore

@@ -9,4 +9,5 @@
 ^R/README\.md$
 derby.log
 ^logs$
-^tests/testthat/logs$
+^tests/testthat/logs$
+^revdep$

DESCRIPTION

@@ -17,11 +17,11 @@ VignetteBuilder: knitr
 Depends:
     R (>= 2.10)
 Imports: 
-    dplyr,
+    dplyr (>= 0.8.0.1),
     rlang (>= 0.3.1),
     purrr,
     utils,
-    tibble,
+    tibble (>= 2.1.1),
     generics,
     glue,
     magrittr,
@@ -39,7 +39,7 @@ Suggests:
     xgboost,
     covr,
     C50,
-    sparklyr,
+    sparklyr (>= 1.0.0),
     earth,
     glmnet,
     kernlab,

NEWS.md

@@ -21,6 +21,7 @@ that are actually varying).
 
 * The prediction modules (e.g. `predict_class`, `predict_numeric`, etc) were de-exported. These were internal functions that were not to be used by the users and the users were using them. 
 
+ * An event time data set (`check_times`) was included that is the time (in seconds) to run `R CMD check` using the "r-devel-windows-ix86+x86_64` flavor. Packages that errored are censored. 
 
 ## Bug Fixes
 

R/aaa_spark_helpers.R

@@ -4,9 +4,9 @@
 format_spark_probs <- function(results, object) {
   results <- dplyr::select(results, starts_with("probability_"))
   p <- ncol(results)
-  lvl <- paste0("probability_", 0:(p - 1))
-  names(lvl) <- paste0("pred_", object$fit$.index_labels)
-  results %>% rename(!!!syms(lvl))
+  lvl <- colnames(results)
+  names(lvl) <- paste0("pred_", object$fit$index_labels)
+  results %>% dplyr::rename(!!!syms(lvl))
 }
 
 format_spark_class <- function(results, object) {

R/data.R

@@ -44,3 +44,62 @@ NULL
 #' data(wa_churn)
 #' str(wa_churn)
 NULL
+
+#' Execution Time Data
+#'
+#' These data were collected from the CRAN web page for 13,626 R
+#' packages. The time to complete the standard package checking
+#' routine was collected In some cases, the package checking
+#' process is stopped due to errors and these data are treated as
+#' censored. It is less than 1 percent.
+#'
+#' As predictors, the associated package source code were
+#' downloaded and parsed to create predictors, including
+#'
+#' * `authors`: The number of authors in the author field.
+#' * `imports`: The number of imported packages.
+#' * `suggests`: The number of packages suggested.
+#' * `depends`: The number of hard dependencies.
+#' * `Roxygen`: a binary indicator for whether Roxygen was used
+#'   for documentation.
+#' * `gh`: a binary indicator for whether the URL field contained
+#'   a GitHub link.
+#' * `rforge`: a binary indicator for whether the URL field
+#'   contained a link to R-forge.
+#' * `descr`: The number of characters (or, in some cases, bytes)
+#'   in the description field.
+#' * `r_count`: The number of R files in the R directory.
+#' * `r_size`: The total disk size of the R files.
+#' * `ns_import`: Estimated number of imported functions or methods.
+#' * `ns_export`: Estimated number of exported functions or methods.
+#' * `s3_methods`: Estimated number of S3 methods.
+#' * `s4_methods`: Estimated number of S4 methods.
+#' * `doc_count`: How many Rmd or Rnw files in the vignettes
+#'   directory.
+#' * `doc_size`: The disk size of the Rmd or Rnw files.
+#' * `src_count`: The number of files in the `src` directory.
+#' * `src_size`: The size on disk of files in the `src` directory.
+#' * `data_count`  The number of files in the `data` directory.
+#' * `data_size`: The size on disk of files in the `data` directory.
+#' * `testthat_count`: The number of files in the `testthat`
+#'   directory.
+#' * `testthat_size`: The size on disk of files in the `testthat`
+#'   directory.
+#' * `check_time`: The time (in seconds) to run `R CMD check`
+#'   using the "r-devel-windows-ix86+x86_64` flavor.
+#' * `status`: An indicator for whether the tests completed.
+#'
+#' Data were collected on 2019-01-20.
+#' @name check_times
+#' @aliases check_times
+#' @docType data
+#' @return \item{check_times}{a data frame}
+#'
+#' @source CRAN
+#'
+#' @keywords datasets
+#' @examples
+#' data(check_times)
+#' str(check_times)
+NULL
+

R/predict.R

@@ -245,7 +245,6 @@ prepare_data <- function(object, new_data) {
 #' @return A tibble with the same number of rows as the data being predicted.
 #'  Mostly likely, there is a list-column named `.pred` that is a tibble with
 #'  multiple rows per sub-model.
-#' @keywords internal
 #' @export
 multi_predict <- function(object, ...) {
   if (inherits(object$fit, "try-error")) {
@@ -255,7 +254,6 @@ multi_predict <- function(object, ...) {
   UseMethod("multi_predict")
 }
 
-#' @keywords internal
 #' @export
 #' @rdname multi_predict
 multi_predict.default <- function(object, ...)

data/check_times.rda

@@ -1,2 +1,3 @@
 lending_club: lending_club
 wa_churn: wa_churn
+check_times: check_times