dat <- dna_sj_n
dat$X1 <- as.numeric(dat$X1)

# Make split index
train_index <- sample(1:nrow(dat), nrow(dat)*0.75)

# Full data set
data_variables <- as.matrix(dat[,-1])
data_label <- dat[,"X1"]

data = as.matrix(dat)
data_matrix <- xgb.DMatrix(data, label = dat$X1)


# split train data and make xgb.DMatrix

train_data   <- data_variables[train_index,]
train_label <- data_label[train_index,]
train_label$X1 <- as.numeric(train_label$X1)

train_dat <- dat[train_index,]
test_dat <- dat[-train_index,]

train_matrix <- xgb.DMatrix(matrix(as.numeric(train_data),dim(train_data)), label = train_label$X1)

# split test data and make xgb.DMatrix
test_data  <- data_variables[-train_index,]
test_label <- data_label[-train_index,]
test_label$X1 <- as.numeric(test_label$X1)

test_matrix <- xgb.DMatrix(matrix(as.numeric(test_data),dim(test_data)), label = test_label$X1)



numberOfClasses <- length(unique(dat$X1))

accuracies <-c()
train_label$X1 <- as.character(train_label$X1)
train_label$X1 <- as.factor(train_label$X1)
######RANDOM FOREST
#modelFit <- randomForest(train_label$X1 ~., data = train_data,ntree=100,mtry=3,importance = TRUE)

modelFit <- randomForest(train_label$X1 ~., data = train_data)
prediction <- predict(modelFit, newdata = test_data)

t<-table(prediction, test_label$X1)
print(t)

mymat <- matrix(nrow=25, ncol=2)
g = 3
h = 30
# For each row and for each column, assign values based on position: product of two indexes
for(i in 1:dim(mymat)[1]) {
  
  
  for(j in 1:dim(mymat)[2]) {
    
    if (j == 1) {
      mymat[i,j] = g
    }else {
      h = h + 5
      mymat[i,j] = h
      if (h > 1200 ) {
        g = g + 2
        h = 450
      }
    }
    
  }
}
for(i in 1:dim(mymat)[1]) {
  
  ptm <- proc.time()
  mf  <- randomForest(train_label$X1 ~., data = train_data,ntree= mymat[i,2] ,mtry= mymat[i,1] ,importance = TRUE) 
  tr_time <- proc.time() - ptm
  ptm <- proc.time()
  pred <- predict(mf      , newdata = test_data)
  ts_time <- proc.time() - ptm
  t<-table(pred, test_label$X1)
  cm<-confusionMatrix(t)
  ss = paste("mtry:",mymat[i,1] ,"ntree:", mymat[i,2],"akurasi", cm$overall[1],"train_time",tr_time,"test_time", ts_time,sep=" ") 
  lapply(ss, write, file="rf_30-13.txt", sep="\t", append=TRUE, ncolumns=1000)
  
}

plot(mf)

ggplot(mf)
mf