Version: 0.3.6 Date: 2025-05-06 Text: DESCRIPTION file: use Authors@R Version: 0.3.6 Date: 2025-05-06 Text: doc: - remove description-like items - add link missing packages - limmaTwoGroups: update link article to DOI - data: add data() in usage Version: 0.3.6 Date: 2025-05-06 Text: class -> inherits Version: 0.3.5 Date: 2018-06-29 Text: nlcv: add seed parameter, return testScores in case method not glm or nlda Version: 0.3.5 Date: 2018-06-29 Text: nlcv: use only training samples for feature selection with random forest Version: 0.3.4 Date: 2018-05-18 Text: add RUnit and ALL in Suggests Version: 0.3.3 Date: 2018-05-04 Text: remove ASCII characters in bib file vignette Version: 0.3.1 Text: more extensive package description Version: 0.3.0 Text: roxygen2 documentation, check imports for submission to CRAN Version: 0.2-2 Text: fix startup message Version: 0.2-2 Text: better data compression Version: 0.2-1 Text: fix storing of results in classify_bioc_2.3 Version: 0.2-0 Text: fix nlcv issue with limma feature selection Version: 0.1-99 Text: small documentation and namespace fixes Version: 0.1-98 Text: fix ordering by geneID in nlcv with limma feature selection Version: 0.1-97 Text: small fixes related to removal of nlcv as a4 dependency, a.o. introduction of dependency on a4Core Version: 0.1-96 Text: add y axis label to scores plot and improve main title Version: 0.1-95 Text: further fix of layout in mcrPlot Version: 0.1-94 Text: fix layout in mcrPlot Version: 0.1-93 Text: fix layout in scoresPlot Version: 0.1-92 Text: add randomForest explicitly to dependencies Version: 0.1-92 Text: 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 Version: 0.1-91 Text: rename topFeatures into topTable and turn the topFeatures function into a method (for 'nlcv' objects) Version: 0.1-91 Text: make use of sample names as x-axis labels of scoresPlot Version: 0.1-90 Text: document nldaI Version: 0.1-89 Text: confusionMatrix name space fix Version: 0.1-88 Text: replace MLearn interface for randomForest feature selection by plain use of the randomForest function Version: 0.1-87 Text: add geneID argument to nlcv to allow for different gene ID names in the fData of the expression set Version: 0.1-86 Text: small fix for topTable in limma2Groups (which is introduced as alias for limmaTwoGroups) Version: 0.1-85 Text: turned confusionMatrix into a generic function Version: 0.1-84 Text: added sampling strategy for unbalanced class distributions; argument 'distclass' of functions inTrainingSample and nlcv Version: 0.1-83 Text: fix too protective check in nlcv (randomForest feature selection) Version: 0.1-82 Text: fix to prevent pamr to mess up error handling Version: 0.1-81 Text: add fsMethod = "none" Version: 0.1-81 Text: add AUC for models with continuous outputs (nlda, glm) Version: 0.1-81 Text: store ROC curves (ROCR package) Version: 0.1-81 Text: add nldaI interface allowing to store testScores (for lda models) Version: 0.1-81 Text: add customization of ntree and mtry for feature selection using randomForest Version: 0.1-81 Text: check that mtry <= maximum of nFeatures Version: 0.1-80 Text: regenerate example data sets Version: 0.1-80 Text: add check on tech in scoresPlot Version: 0.1-79 Text: small tweak to scoresPlot Version: 0.1-79 Text: add qda (quadratic discriminant analysis) and glm (logistic regression) interfaces Version: 0.1-78 Text: add rescale argument to mcrPlot function Version: 0.1-78 Text: add plain lda and ksvm classifiers Version: 0.1-77 Text: quick extension of pamrML and predict.pamrML for ExpressionSet objects Version: 0.1-77 Text: added method argument to topFeatures; can be one of "percentage", "meanrank" or "medianrank" Version: 0.1-77 Text: fix limma feature selection (use training set, not full set) Version: 0.1-77 Text: added inst/generateData.R, a script used to generate the data in data/ Version: 0.1-76 Text: integrate pamr as an MLearn interface Version: 0.1-75 Text: remove featureSelectionRF wrapper and move code into nlcv function Version: 0.1-75 Text: fix randomForest feature selection code Version: 0.1-74 Text: add check on feature selection methods Version: 0.1-74 Text: add check on fact that it should be a two-class problem Version: 0.1-74 Text: new argument classifMethods to select the appropriate classification methods Version: 0.1-74 Text: updates related to BioC 2.3 release (testPredictions instead of predLabels) Version: 0.1-73 Text: nlcv again separate package (after temporary merge with a4) Version: 0.1-72 Text: added feature selection by limma (implying an additional dependency on a4) Version: 0.1-72 Text: improved passing of further parameters to the feature selection method (argument fsPar) Version: 0.1-71 Text: integration of final package vignette Version: 0.1-71 Text: xtable method for summary.mcrPlot objects added Version: 0.1-70 Text: another rewrite of simulateData Version: 0.1-70 Text: artificial datasets changed accordingly Version: 0.1-69 Text: artificial datasets updated (using updated nlcv) Version: 0.1-69 Text: fixed buglet in simulateData Version: 0.1-68 Text: fixed bug in nlcv (testPredictions returned factor, whereas predLabels returned a character vector) Version: 0.1-68 Text: small fix in simulateData Version: 0.1-68 Text: added run-time tests directory Version: 0.1-67 Text: added simulated datasets: nlcvRF, nlcvTT_SS, nlcvRF_WS, nlcvTT_WS, nlcvRF_WHS, nlcvTT_WHS, nlcvRF_R and nlcvTT_R Version: 0.1-67 Text: scoresPlot: added layout argument (in order to allow multiple plots on one panel) Version: 0.1-67 Text: rankDistributionPlot added Version: 0.1-66 Text: 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) Version: 0.1-66 Text: topFeatures: the percentages now represent presence in the top n, instead of presence in the top 2*n Version: 0.1-65 Text: fixed simulateData (for nNoEffectCols == 0) Version: 0.1-65 Text: added layout argument to mcrPlot function (in order to allow multiple plots on one panel) Version: 0.1-64 Text: added xtable method for confusionMatrix objects Version: 0.1-64 Text: added explicit dependencies to sma, ipred, pamr and xtable Version: 0.1-63 Text: featureSelectionRF added to name space Version: 0.1-63 Text: fixed naming issue in nlcv (featureSelectionRF instead of variableSelectionRF) Version: 0.1-62 Text: license information formatted according to rules: GPL (>=2) Version: 0.1-62 Text: recursiveRandomForestFS removed and replaced by featureSelectionRF; the nFeaturesFinal argument of the former function has been dropped accordingly in the latter function Version: 0.1-62 Text: simulateData gained additional arguments betweenClassDifference and withinClassSd Version: 0.1-61 Text: added function simulateData Version: 0.1-60 Text: added print method for confusionMatrix objects Version: 0.1-59 Text: confusionMatrix function added Version: 0.1-58 Text: mcrPlot and scoresPlot gain an argument plot (defaults to TRUE) to allow use of the functions for computational purposes Version: 0.1-57 Text: export topFeatures in NAMESPACE Version: 0.1-56 Text: scoresPlot: added supplementary legend for plot characters used Version: 0.1-56 Text: scoresPlot: added explicit main and sub arguments Version: 0.1-55 Text: scoresPlot: draw grid first, then add dots Version: 0.1-54 Text: scoresPlot: vectorize drawing of class membership strip Version: 0.1-53 Text: scoresPlot: fix drawing of class membership strip Version: 0.1-52 Text: added dependency on RColorBrewer for class membership display on scoresPlot Version: 0.1-51 Text: added topFeatures function and help page Version: 0.1-50 Text: put legend for scoresPlot in comment Version: 0.1-49 Text: make use of testPredictions instead of predLabels (new version of MLInterfaces) Version: 0.1-47 Text: remove remnant "type"s and replace with the appropriate variable passed as arguments to the functions (classVar argument) Version: 0.1-46 Text: replace randomForestB by MLearn and the appropriate method Version: 0.1-45 Text: removed warnings from generateData (by making a real ExpressionSet)