library(caret)
DataFolder = "/Users/ml/Library/Mobile Documents/com~apple~CloudDocs/PhD/Non Thesis/Research Papers/VovelMetric(ExtensionOfStrengthMetric)/Resources/EditableStuff/Experiment/SelectedProjects"
file_list <- list.files(path = DataFolder)
for (i in 1:length(file_list)) {
  fileName = paste(DataFolder,"/", file_list[i], sep = "")
  thedata <-
    read.csv(fileName)[, c(
      'StrengthOut',
      'StrengthIn',
      'RFC',
      'FanIn',
      'FanOut',
      'CBO',
      'Bug'
    )]

  pData <- thedata[ which(thedata$Bug==1),]
  nData <- thedata[ which(thedata$Bug==0),]
  
  tInstances = nrow(thedata)
  pInstances = nrow(pData)
  nInstances = nrow(nData)
  
  CBOs = paste(min(thedata$CBO), max(thedata$CBO), mean(thedata$CBO), median(thedata$CBO), sd(thedata$CBO), var(thedata$CBO))
  
  FanIns = paste(min(thedata$FanIn), max(thedata$FanIn), mean(thedata$FanIn), median(thedata$FanIn), sd(thedata$FanIn), var(thedata$FanIn))
  
  
  FanOuts = paste(min(thedata$FanOut), max(thedata$FanOut), mean(thedata$FanOut), median(thedata$FanOut), sd(thedata$FanOut), var(thedata$FanOut))
  
  RFCs = paste(min(thedata$RFC), max(thedata$RFC), mean(thedata$RFC), median(thedata$RFC), sd(thedata$RFC), var(thedata$RFC))
  
  StrengthIns = paste(min(thedata$StrengthIn), max(thedata$StrengthIn), mean(thedata$StrengthIn), median(thedata$StrengthIn), sd(thedata$StrengthIn), var(thedata$StrengthIn))

  StrengthOuts = paste(min(thedata$StrengthOut), max(thedata$StrengthOut), mean(thedata$StrengthOut), median(thedata$StrengthOut), sd(thedata$StrengthOut), var(thedata$StrengthOut))



  fname = sub(' ','',file_list[i])
  
 # print(paste(fname,tInstances, pInstances, nInstances, CBOs,FanIns, FanOuts, RFCs, StrengthIns, StrengthOuts))
  print(paste(fname,tInstances, pInstances, nInstances))
        
  }

getmode <- function(v) {
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}






library(philentropy)



library(caret)
DataFolder = "/Users/ml/Library/Mobile Documents/com~apple~CloudDocs/PhD/FinalThesisWriteup/Resources/EditableStuff/FirstExperiment/StatisOfDatasets.csv"
kc1<-c(145,60,85,0,24,8.317241379,8,0,6.376719211,40.66254789,3,24,12.3,13,14,5.600544768,31.36610169,0,18,5.505882353,4,0,5.324300825,28.34817927,0,61,11.8311961,8.666667,0,12.11931364,146.8777632,0,55.954546,17.36453212,14.8376625,33.521739,11.60535236,134.6842034,0,61,7.925311859,3.208333,0,10.94912872,119.8834196,0,100,17.42068966,12,8,17.44900067,304.4676245,5,99,21.53333333,15.5,7,18.97408283,360.0158192,0,100,14.51764706,10,5,15.76283435,248.4669468,0,222,34.37931034,28,38,36.20295203,1310.653736,5,198,41.43333333,34.5,38,37.77245282,1426.758192,0,222,29.4,24,8,34.41040817,1184.07619)
thedata <-read.csv(DataFolder, header = FALSE)


normalize <- function(x)
{
  return((x- min(x)) /(max(x)-min(x)))
}

for (i in 2:length(thedata)){
  thedata[i] = normalize(thedata[i])
}
write.csv(thedata, file = "/Users/ml/Library/Mobile Documents/com~apple~CloudDocs/PhD/FinalThesisWriteup/Resources/EditableStuff/FirstExperiment/Normalized.csv")

DataFolder = "/Users/ml/Library/Mobile Documents/com~apple~CloudDocs/PhD/FinalThesisWriteup/Resources/EditableStuff/FirstExperiment/Normalized.csv"
thedata<- read.csv(DataFolder, header = TRUE)

kc1<-c(0.063829787,0.268817204,0.037426901,0,0.024242424,0.426473709,1,0,0.14053563,0.042608632,0.125,0.024242424,0.040840259,0.0625,0.078431373,0.03854331,0.00339044,0,0.044728435,0.362054355,0.5,0,0.196229745,0.05746579,0,0,0,0,0,0,0,0,0,0,0,0.02001581,0,0,0,0,0,0,0,0,0,0,0.221621622,0.860453185,1,1,0.413408847,0.21270013,0.076923077,0.218918919,0.060257407,0.037549407,0.018382353,0.183605452,0.042478355,0,0.71875,1,1,1,0.75928633,0.609520558,0,0.510152284,0.978574907,1,1,0.858947844,0.762486647,0.035714286,0.449238579,0.128577083,0.100790514,0.121323529,0.392350694,0.179955527,0,1,1,1,1,1,1)
for (i in 1:nrow(thedata)){
  others<-as.double(unlist(thedata[i,2:length(thedata)]))
  x = rbind(kc1,others)
  d = distance(x, method = "euclidean")
  print(paste(thedata[i,1], d))
}



# define a probability density function P
P <- 1:10/sum(1:10)
# define a probability density function Q
Q <- 20:29/sum(20:29)

# combine P and Q as matrix object
x <- rbind(P,Q)