NNbenchmark3.0.0 in /NNbenchmark2020

As in NEWS
- added functions from CD's 2020 code for training and predicting in NN
- some small changes to NNSummary

NNbenchmark2019/DESCRIPTION

@@ -14,4 +14,4 @@ Author: Patrice Kiener [aut, cre],
 Encoding: UTF-8
 NeedsCompilation: no
 LazyData: true
-RoxygenNote: 6.1.1
+RoxygenNote: 7.1.0

NNbenchmark2020/DESCRIPTION

@@ -3,7 +3,7 @@ Title: Datasets and Functions to Benchmark Neural Network Packages
 Description: Datasets and functions to benchmark (convergence, speed, ease of use) R packages dedicated to regression with neural networks (no classification in this version). The templates for the tested packages are available in R, Rmd and html formats at <https://github.com/pkR-pkR/NNbenchmarkTemplates> and <https://akshajverma.com/NNbenchmarkWeb>.
 Imports: R6, pkgload
 Suggests: brnn, validann
-Version: 2.3.7
+Version: 3.0.0
 Date: 2020-06-19
 License: GPL-2
 Maintainer: Patrice Kiener <fattailsr@inmodelia.com>

NNbenchmark2020/NAMESPACE

@@ -18,10 +18,13 @@ export(lipoNN)
 export(plotNN)
 export(prepareZZ)
 export(timeR)
+export(train_predict_1data)
+export(train_predict_1mth_1data)
 import(R6)
 import(graphics)
 import(utils)
 importFrom(R6,R6Class)
 importFrom(pkgload,unload)
 importFrom(stats,formula)
+importFrom(stats,lm)
 importFrom(stats,sd)

NNbenchmark2020/NEWS

@@ -2,10 +2,14 @@
 - Akshaj Verma, Salabila Mahdi, Patrice Kiener
 - Christophe Dutang, John Nash 
 
+NNbenchmark 3.0.0 - 2020-06-21
+==============================
+- NNTrain_Predict.R for NEW 2020 code do.call() implementation to train and predict NNs
+
 NNbenchmark 2.3.7 - 2020-06-19
 ==============================
 - Added MSE and WAE to funRMSE.R
-- Made a new R file: NNSummary.R for 2020 code
+- Made a new R file: NNSummary.R for 2020 summary function
 
 NNbenchmark 2.3.6 - 2020-01-11
 ==============================

NNbenchmark2020/R/NNSummary.R

@@ -6,8 +6,8 @@
 #' Summarize measures of fit and time for a single training. Measures of fit 
 #' include the Root Mean Squared Error (RMSE), the Mean Squared Error (MSE), 
 #' the Mean Absolute Error (MAE), and the Worst Absolute Error (WAE) rounded
-#' by default to 4 digits and set to \code{na.rm = TRUE}. See more at \code{funRMSE}. 
-#' The summary can also include the results of time from \code{getTimer} in
+#' by default to 4 digits and set to \code{na.rm = TRUE}. See more at \code{\link{funRMSE}}. 
+#' The summary can also include the results of time from \code{\link{getTimer}} in
 #' NNbenchmark or results of time from other functions/packages
 #' 
 #' @param   y_pred  numeric vector of the predicted values