@@ -3,8 +3,8 @@ Type: Package

 Title: A framework for cross-validated classification problems, with

        applications to differential variability and differential

        distribution testing

-Version: 3.1.23

-Date: 2022-10-14

+Version: 3.1.24

+Date: 2022-10-17

 Author: Dario Strbenac, Ellis Patrick, John Ormerod, Graham Mann, Jean Yang

 Maintainer: Dario Strbenac <dario.strbenac@sydney.edu.au>

 VignetteBuilder: knitr

@@ -118,8 +118,6 @@ setMethod("crossValidate", "DataFrame",

               # Which data-types or data-views are present?

               assayIDs <- unique(mcols(measurements)$assay)

               if(is.null(assayIDs)) assayIDs <- 1

-              

-              checkData(measurements, outcome)

               # Check that other variables are in the right format and fix

               nFeatures <- cleanNFeatures(nFeatures = nFeatures,

@@ -184,17 +182,12 @@ Using an ordinary GLM instead.")

                                       characteristicsLabel = characteristicsLabel

                                   )

                               },

-

                               simplify = FALSE)

                           },

-

                           simplify = FALSE)

                       },

-

                       simplify = FALSE)

-

                   result <- unlist(unlist(resClassifier))

-

               }

               ################################

@@ -558,24 +551,6 @@ generateCrossValParams <- function(nRepeats, nFolds, nCores, selectionOptimisati

 }

 ######################################

-

-

-######################################

-######################################

-checkData <- function(measurements, outcome){

-    if(is.null(rownames(measurements)))

-        stop("'measurements' DataFrame must have sample identifiers as its row names.")

-    if(any(is.na(measurements)))

-        stop("Some data elements are missing and classifiers don't work with missing data. Consider imputation or filtering.")

-

-    # !!!  Need to check mcols has assay NUm

-

-}

-######################################

-

-

-

-######################################

 ######################################

 #' A function to generate a ModellingParams object

 #'

@@ -643,9 +618,10 @@ generateModellingParams <- function(assayIDs,

     knownClassifiers <- .ClassifyRenvir[["classifyKeywords"]][, "classifier Keyword"]

     if(!classifier %in% knownClassifiers)

         stop(paste("Classifier must exactly match of these (be careful of case):", paste(knownClassifiers, collapse = ", ")))

-    

+

     classifierParams <- .classifierKeywordToParams(classifier)

-    classifierParams$trainParams@tuneParams <- c(classifierParams$trainParams@tuneParams, performanceType = performanceType)

+    if(!is.null(classifierParams$trainParams@tuneParams))

+      classifierParams$trainParams@tuneParams <- c(classifierParams$trainParams@tuneParams, performanceType = performanceType)

     selectionMethod <- unlist(selectionMethod)

@@ -833,11 +809,6 @@ CV <- function(measurements = NULL,

                characteristicsLabel = NULL)

 {

-    # Check that data is in the right format

-    if(!is.null(measurements))

-      checkData(measurements, outcome)

-    else

-      checkData(x, x)

     # Check that other variables are in the right format and fix

     nFeatures <- cleanNFeatures(nFeatures = nFeatures,

                                 measurements = measurements)

@@ -11,6 +11,7 @@ GLMtrainInterface <- function(measurementsTrain, classesTrain, ..., verbose = 3)

     } else {fitData <- measurementsTrain}

   glm(class ~ . + 0, family = binomial, data = fitData, ...)

 }

+attr(GLMtrainInterface, "name") <- "GLMtrainInterface"

 # model is of class glm.

 GLMpredictInterface <- function(model, measurementsTest, returnType = c("both", "class", "score"),

@@ -51,11 +51,17 @@ setMethod("prepareData", "matrix",

 setMethod("prepareData", "DataFrame",

   function(measurements, outcome, useFeatures = "all", maxMissingProp = 0.0, topNvariance = NULL)

 {

+  if(is.null(rownames(measurements)))

+  {

+    warning("'measurements' DataFrame must have sample identifiers as its row names. Generating generic ones.")

+    rownames(measurements) <- paste("Sample", seq_len(nrow(measurements)))

+  }      

+            

   if(useFeatures != "all") # Subset to only the desired ones.

     measurements <- measurements[, useFeatures]

   # Won't ever be true if input data was MultiAssayExperiment because wideFormat already produces valid names.  

-  if(all.equal(colnames(measurements), make.names(colnames(measurements))) != TRUE)

+  if(!all(colnames(measurements) == make.names(colnames(measurements))))

   {

     warning("Unsafe feature names in input data. Converted into safe names.")

     mcols(measurements)$feature <- colnames(measurements) # Save the originals.

@@ -114,7 +120,7 @@ setMethod("prepareData", "DataFrame",

     else # Three columns. Therefore, counting process data.

       outcome <- survival::Surv(outcome[, 1], outcome[, 2], outcome[, 3])

   }

-  

+

   # Remove samples with indeterminate outcome.

   dropSamples <- which(is.na(outcome) | is.null(outcome))

   if(length(dropSamples) > 0)

@@ -125,8 +131,9 @@ setMethod("prepareData", "DataFrame",

   # Remove features with more missingness than allowed.

   nSamples <- nrow(measurements)

-  dropFeatures <- which(apply(measurements, 2, function(featureMeasurements) sum(is.na(featureMeasurements)))

-                        / nrow(measurements) > maxMissingProp)

+  measurementsMatrix <- as.matrix(measurements) # For speed of calculation.

+  dropFeatures <- which(apply(measurementsMatrix, 2, function(featureMeasurements) sum(is.na(featureMeasurements)))

+                        / nrow(measurementsMatrix) > maxMissingProp)

   if(length(dropFeatures) > 0)

     measurements <- measurements[, -dropFeatures]

@@ -139,6 +139,12 @@

         return(list(NULL, rankings[[1]], NULL))

     tuneParamsTrain <- list(topN = topNfeatures)

+    performanceIndex <- match("performanceType", names(modellingParams@trainParams@tuneParams))

+    if(!is.na(performanceIndex))

+    {

+      performanceType <- modellingParams@trainParams@tuneParams[["performanceType"]]

+      modellingParams@trainParams@tuneParams <- modellingParams@trainParams@tuneParams[-performanceIndex]

+    }

     tuneParamsTrain <- append(tuneParamsTrain, modellingParams@trainParams@tuneParams)

     tuneCombosTrain <- expand.grid(tuneParamsTrain, stringsAsFactors = FALSE)  

     modellingParams@trainParams@tuneParams <- NULL