## ---- echo = FALSE, results = "asis"--------------------------------------------------------------------------------------------
options(width = 130)

## ---- echo = FALSE--------------------------------------------------------------------------------------------------------------
htmltools::img(src = knitr::image_uri("ClassifyRprocedure.png"), 
               style = 'margin-left: auto;margin-right: auto')

## ---- message = FALSE-----------------------------------------------------------------------------------------------------------
library(ClassifyR)

## ---- message = FALSE-----------------------------------------------------------------------------------------------------------
data(asthma) # Contains measurements and classes variables.
measurements[1:5, 1:5]
head(classes)

## -------------------------------------------------------------------------------------------------------------------------------
result <- crossValidate(measurements, classes, classifier = "SVM",
                        nFeatures = 20, nFolds = 5, nRepeats = 2, nCores = 1)
performancePlot(result)

## -------------------------------------------------------------------------------------------------------------------------------
measurementsDF <- DataFrame(measurements)
mcols(measurementsDF) <- data.frame(
  dataset = rep(c("dataset_1", "dataset_2"), times = c(10, 1990)),
  feature = colnames(measurementsDF)
)

result <- crossValidate(measurementsDF, classes, classifier = "SVM", nFolds = 5,
                        nRepeats = 2, multiViewMethod = "merge")

performancePlot(result)

## ---- eval = FALSE--------------------------------------------------------------------------------------------------------------
#  # Assigns first 10 variables to dataset_1, and the rest to dataset_2
#  measurementsList <- list(
#    (measurements |> as.data.frame())[1:10],
#    (measurements |> as.data.frame())[11:2000]
#  )
#  names(measurementsList) <- c("dataset_1", "dataset_2")
#  
#  result <- crossValidate(measurementsList, classes, classifier = "SVM", nFolds = 5,
#                          nRepeats = 2, multiViewMethod = "merge")
#  
#  performancePlot(result)

## ---- eval = FALSE--------------------------------------------------------------------------------------------------------------
#  CVparams <- CrossValParams(parallelParams = SnowParam(16, RNGseed = 123))
#  CVparams

## -------------------------------------------------------------------------------------------------------------------------------
ModellingParams()

## ---- tidy = FALSE--------------------------------------------------------------------------------------------------------------
crossValParams <- CrossValParams(permutations = 5)
DMresults <- runTests(measurements, classes, crossValParams, verbose = 1)
DMresults

## ---- fig.height = 8, fig.width = 8, results = "hold", message = FALSE----------------------------------------------------------
selectionPercentages <- distribution(DMresults, plot = FALSE)
head(selectionPercentages)
sortedPercentages <- sort(selectionPercentages, decreasing = TRUE)
head(sortedPercentages)
mostChosen <- names(sortedPercentages)[1]
bestGenePlot <- plotFeatureClasses(measurements, classes, mostChosen, dotBinWidth = 0.1,
                                   xAxisLabel = "Normalised Expression")

## -------------------------------------------------------------------------------------------------------------------------------
DMresults <- calcCVperformance(DMresults, "Balanced Error")
DMresults
performance(DMresults)

## ---- tidy = FALSE--------------------------------------------------------------------------------------------------------------
modellingParamsDD <- ModellingParams(selectParams = SelectParams(KullbackLeiblerRanking),
                                     trainParams = TrainParams(naiveBayesKernel),
                                     predictParams = NULL)
DDresults <- runTests(measurements, classes, crossValParams, modellingParamsDD, verbose = 1)
DDresults

## ---- fig.width = 10, fig.height = 7--------------------------------------------------------------------------------------------
library(grid)
DMresults <- calcCVperformance(DMresults, "Sample Error")
DDresults <- calcCVperformance(DDresults, "Sample Error")
resultsList <- list(Abundance = DMresults, Distribution = DDresults)
errorPlot <- samplesMetricMap(resultsList, metric = "Sample Error", xAxisLabel = "Sample",
                              showXtickLabels = FALSE, plot = FALSE)
grid.newpage()
grid.draw(errorPlot)

## -------------------------------------------------------------------------------------------------------------------------------
performancePlot(list(DMresults, DDresults))

## -------------------------------------------------------------------------------------------------------------------------------
rankOverlaps <- rankingPlot(list(DDresults), topRanked = 1:100,
                            xLabelPositions = c(1, seq(10, 100, 10)),
                            plot = FALSE)
rankOverlaps

## ---- fig.height = 5, fig.width = 6---------------------------------------------------------------------------------------------
ROCcurves <- ROCplot(list(DMresults, DDresults), fontSizes = c(24, 12, 12, 12, 12))

## -------------------------------------------------------------------------------------------------------------------------------
tuneList <- list(cost = c(0.01, 0.1, 1, 10))
SVMparams <- ModellingParams(trainParams = TrainParams(SVMtrainInterface, kernel = "linear", tuneParams = tuneList),
                             predictParams = PredictParams(SVMpredictInterface))
SVMresults <- runTests(measurements, classes, crossValParams, SVMparams)

## -------------------------------------------------------------------------------------------------------------------------------
length(tunedParameters(SVMresults))
tunedParameters(SVMresults)[1:5]