Better use of preload data

Author: koenderks

R/commonMachineLearningClassification.R

@@ -42,10 +42,7 @@
 }
 
 .mlClassificationReadData <- function(dataset, options) {
-  dataset <- .readDataClassificationRegressionAnalyses(dataset, options)
-  if (length(unlist(options[["predictors"]])) > 0 && options[["scaleVariables"]]) {
-    dataset[, options[["predictors"]]] <- .scaleNumericData(dataset[, options[["predictors"]], drop = FALSE])
-  }
+  dataset <- .readDataClassificationRegressionAnalyses(dataset, options, include_weights = FALSE)
   if (options[["target"]] != "") {
     dataset[, options[["target"]]] <- factor(dataset[, options[["target"]]], ordered = FALSE)
   }

R/commonMachineLearningClustering.R

@@ -33,7 +33,7 @@
 .mlClusteringReadData <- function(dataset, options) {
   predictors <- unlist(options[["predictors"]])
   predictors <- predictors[predictors != ""]
-  dataset <- .readAndAddCompleteRowIndices(options, "predictors")
+  dataset <- jaspBase::excludeNaListwise(dataset, predictors)
   if (options[["scaleVariables"]] && length(unlist(options[["predictors"]])) > 0) {
     dataset <- .scaleNumericData(dataset)
   }

R/commonMachineLearningRegression.R

@@ -44,21 +44,39 @@
   return(opt)
 }
 
-.readDataRegressionAnalyses <- function(dataset, options, jaspResults) {
-  dataset <- .readDataClassificationRegressionAnalyses(dataset, options)
-  if (length(unlist(options[["predictors"]])) > 0 && options[["scaleVariables"]]) {
-    dataset[, options[["predictors"]]] <- .scaleNumericData(dataset[, options[["predictors"]], drop = FALSE])
-  }
+.readDataRegressionAnalyses <- function(dataset, options, jaspResults, include_weights = FALSE) {
+  dataset <- .readDataClassificationRegressionAnalyses(dataset, options, include_weights)
   return(dataset)
 }
 
-.readDataClassificationRegressionAnalyses <- function(dataset, options) {
+.readDataClassificationRegressionAnalyses <- function(dataset, options, include_weights) {
 
+  target <- NULL
+  weights <- NULL
   testSetIndicator <- NULL
-  if (options[["testSetIndicatorVariable"]] != "" && options[["holdoutData"]] == "testSetIndicator")
-    testSetIndicator <- "testSetIndicatorVariable"
+  if (options[["target"]] != "") {
+    target <- options[["target"]]
+  }
+  if (include_weights && options[["weights"]] != "") {
+    weights <- options[["weights"]]
+  }
+  if (options[["testSetIndicatorVariable"]] != "" && options[["holdoutData"]] == "testSetIndicator") {
+    testSetIndicator <- options[["testSetIndicatorVariable"]]
+  }
 
-  return(.readAndAddCompleteRowIndices(options, c("target", "predictors"), testSetIndicator))
+  predictors <- unlist(options["predictors"])
+  predictors <- predictors[predictors != ""]
+  dataset <- jaspBase::excludeNaListwise(dataset, c(target, predictors, weights, testSetIndicator))
+
+  # Scale numeric predictors
+  if (length(unlist(options[["predictors"]])) > 0 && options[["scaleVariables"]]) {
+    dataset[, options[["predictors"]]] <- .scaleNumericData(dataset[, options[["predictors"]], drop = FALSE])
+  }
+  # Make sure the test set indicator is numeric
+  if (options[["testSetIndicatorVariable"]] != "" && options[["holdoutData"]] == "testSetIndicator")
+    dataset[[options[["testSetIndicatorVariable"]]]] <- as.numeric(dataset[[options[["testSetIndicatorVariable"]]]])
+  
+  return(dataset)
 }
 
 .readAndAddCompleteRowIndices <- function(options, optionNames = NULL, optionNamesAsNumeric = NULL) {

R/mlRegressionRegularized.R

@@ -18,7 +18,7 @@
 mlRegressionRegularized <- function(jaspResults, dataset, options, ...) {
 
   # Preparatory work
-  dataset <- .mlRegressionRegularizedReadData(dataset, options)
+  dataset <- .readDataRegressionAnalyses(dataset, options, include_weights = TRUE)
   .mlRegressionErrorHandling(dataset, options, type = "regularized")
 
   # Check if analysis is ready to run
@@ -58,29 +58,6 @@ mlRegressionRegularized <- function(jaspResults, dataset, options, ...) {
   .mlRegressionRegularizedPlotLambda(options, jaspResults, ready, position = 10)
 }
 
-# Read dataset
-.mlRegressionRegularizedReadData <- function(dataset, options) {
-  target <- NULL
-  weights <- NULL
-  testSetIndicator <- NULL
-  if (options[["target"]] != "") {
-    target <- options[["target"]]
-  }
-  if (options[["weights"]] != "") {
-    weights <- options[["weights"]]
-  }
-  if (options[["testSetIndicatorVariable"]] != "" && options[["holdoutData"]] == "testSetIndicator")
-    testSetIndicator <- "testSetIndicatorVariable"
-
-  predictors <- unlist(options["predictors"])
-  predictors <- predictors[predictors != ""]
-  dataset <- .readAndAddCompleteRowIndices(options, c("target", "predictors", "weights"), testSetIndicator)
-  if (length(unlist(options[["predictors"]])) > 0 && options[["scaleVariables"]]) {
-    dataset[, options[["predictors"]]] <- .scaleNumericData(dataset[, options[["predictors"]], drop = FALSE])
-  }
-  return(dataset)
-}
-
 .regularizedRegression <- function(dataset, options, jaspResults) {
   # Set model-specific parameters
   alpha <- switch(options[["penalty"]],