NEWS

---

nlcv 0.3.6 (2025-05-06)

• DESCRIPTION file: use Authors@R
• doc: - remove description-like items - add link missing packages - limmaTwoGroups: update link article to DOI - data: add data() in usage
• class -> inherits

nlcv 0.3.5 (2018-06-29)

• nlcv: add seed parameter, return testScores in case method not glm or nlda
• nlcv: use only training samples for feature selection with random forest

nlcv 0.3.4 (2018-05-18)

• add RUnit and ALL in Suggests

nlcv 0.3.3 (2018-05-04)

• remove ASCII characters in bib file vignette

nlcv 0.3.1

• more extensive package description

nlcv 0.3.0

• roxygen2 documentation, check imports for submission to CRAN

nlcv 0.2-2

• fix startup message
• better data compression

nlcv 0.2-1

• fix storing of results in classify_bioc_2.3

nlcv 0.2-0

• fix nlcv issue with limma feature selection

nlcv 0.1-99

• small documentation and namespace fixes

nlcv 0.1-98

• fix ordering by geneID in nlcv with limma feature selection

nlcv 0.1-97

• small fixes related to removal of nlcv as a4 dependency, a.o. introduction of dependency on a4Core

nlcv 0.1-96

• add y axis label to scores plot and improve main title

nlcv 0.1-95

• further fix of layout in mcrPlot

nlcv 0.1-94

• fix layout in mcrPlot

nlcv 0.1-93

• fix layout in scoresPlot

nlcv 0.1-92

• add randomForest explicitly to dependencies
• fix bug in nlcv with limma feature selection, where incidentally the geneID column could be a factor and therefore cause erroneous extraction from an ExpressionSet

nlcv 0.1-91

• rename topFeatures into topTable and turn the topFeatures function into a method (for 'nlcv' objects)
• make use of sample names as x-axis labels of scoresPlot

nlcv 0.1-90

• document nldaI

nlcv 0.1-89

• confusionMatrix name space fix

nlcv 0.1-88

• replace MLearn interface for randomForest feature selection by plain use of the randomForest function

nlcv 0.1-87

• add geneID argument to nlcv to allow for different gene ID names in the fData of the expression set

nlcv 0.1-86

• small fix for topTable in limma2Groups (which is introduced as alias for limmaTwoGroups)

nlcv 0.1-85

• turned confusionMatrix into a generic function

nlcv 0.1-84

• added sampling strategy for unbalanced class distributions; argument 'distclass' of functions inTrainingSample and nlcv

nlcv 0.1-83

• fix too protective check in nlcv (randomForest feature selection)

nlcv 0.1-82

• fix to prevent pamr to mess up error handling

nlcv 0.1-81

• add fsMethod = "none"
• add AUC for models with continuous outputs (nlda, glm)
• store ROC curves (ROCR package)
• add nldaI interface allowing to store testScores (for lda models)
• add customization of ntree and mtry for feature selection using randomForest
• check that mtry <= maximum of nFeatures

nlcv 0.1-80

• regenerate example data sets
• add check on tech in scoresPlot

nlcv 0.1-79

• small tweak to scoresPlot
• add qda (quadratic discriminant analysis) and glm (logistic regression) interfaces

nlcv 0.1-78

• add rescale argument to mcrPlot function
• add plain lda and ksvm classifiers

nlcv 0.1-77

• quick extension of pamrML and predict.pamrML for ExpressionSet objects
• added method argument to topFeatures; can be one of "percentage", "meanrank" or "medianrank"
• fix limma feature selection (use training set, not full set)
• added inst/generateData.R, a script used to generate the data in data/

nlcv 0.1-76

• integrate pamr as an MLearn interface

nlcv 0.1-75

• remove featureSelectionRF wrapper and move code into nlcv function
• fix randomForest feature selection code

nlcv 0.1-74

• add check on feature selection methods
• add check on fact that it should be a two-class problem
• new argument classifMethods to select the appropriate classification methods
• updates related to BioC 2.3 release (testPredictions instead of predLabels)

nlcv 0.1-73

• nlcv again separate package (after temporary merge with a4)

nlcv 0.1-72

• added feature selection by limma (implying an additional dependency on a4)
• improved passing of further parameters to the feature selection method (argument fsPar)

nlcv 0.1-71

• integration of final package vignette
• xtable method for summary.mcrPlot objects added

nlcv 0.1-70

• another rewrite of simulateData
• artificial datasets changed accordingly

nlcv 0.1-69

• artificial datasets updated (using updated nlcv)
• fixed buglet in simulateData

nlcv 0.1-68

• fixed bug in nlcv (testPredictions returned factor, whereas predLabels returned a character vector)
• small fix in simulateData
• added run-time tests directory

nlcv 0.1-67

• added simulated datasets: nlcvRF, nlcvTT_SS, nlcvRF_WS, nlcvTT_WS, nlcvRF_WHS, nlcvTT_WHS, nlcvRF_R and nlcvTT_R
• scoresPlot: added layout argument (in order to allow multiple plots on one panel)
• rankDistributionPlot added

nlcv 0.1-66

• scoresPlot: put information on classification technique and number of features into main (instead of sub) in order to avoid overlap with the sample names (x axis labels)
• topFeatures: the percentages now represent presence in the top n, instead of presence in the top 2*n

nlcv 0.1-65

• fixed simulateData (for nNoEffectCols == 0)
• added layout argument to mcrPlot function (in order to allow multiple plots on one panel)

nlcv 0.1-64

• added xtable method for confusionMatrix objects
• added explicit dependencies to sma, ipred, pamr and xtable

nlcv 0.1-63

• featureSelectionRF added to name space
• fixed naming issue in nlcv (featureSelectionRF instead of variableSelectionRF)

nlcv 0.1-62

• license information formatted according to rules: GPL (>=2)
• recursiveRandomForestFS removed and replaced by featureSelectionRF; the nFeaturesFinal argument of the former function has been dropped accordingly in the latter function
• simulateData gained additional arguments betweenClassDifference and withinClassSd

nlcv 0.1-61

• added function simulateData

nlcv 0.1-60

• added print method for confusionMatrix objects

nlcv 0.1-59

• confusionMatrix function added

nlcv 0.1-58

• mcrPlot and scoresPlot gain an argument plot (defaults to TRUE) to allow use of the functions for computational purposes

nlcv 0.1-57

• export topFeatures in NAMESPACE

nlcv 0.1-56

• scoresPlot: added supplementary legend for plot characters used
• scoresPlot: added explicit main and sub arguments

nlcv 0.1-55

• scoresPlot: draw grid first, then add dots

nlcv 0.1-54

• scoresPlot: vectorize drawing of class membership strip

nlcv 0.1-53

• scoresPlot: fix drawing of class membership strip

nlcv 0.1-52

• added dependency on RColorBrewer for class membership display on scoresPlot

nlcv 0.1-51

• added topFeatures function and help page

nlcv 0.1-50

• put legend for scoresPlot in comment

nlcv 0.1-49

• make use of testPredictions instead of predLabels (new version of MLInterfaces)

nlcv 0.1-47

• remove remnant "type"s and replace with the appropriate variable passed as arguments to the functions (classVar argument)

nlcv 0.1-46

• replace randomForestB by MLearn and the appropriate method

nlcv 0.1-45

• removed warnings from generateData (by making a real ExpressionSet)