rm(list=ls())

source('dataPartitionUtil.R')
source('GAUtil.R')

load("top_univariate_features.RData")

library(GA)
library(reshape2)
library(ggplot2)
library(e1071)
library(foreach)
library(doMC)
library(parallel)
library(cvTools)

registerDoMC(cores = detectCores())

predict.SVM <- function(){

    fitness <- function(string){

        print(paste("Executando função de ajuste...", i))
        i <<- i + 1

        predict.with.SVM <- function(fs.train, fs.test){

            inc <- which(string == 1)

            features.subset <- top.features.vector[inc]

            train.fs.data <- fs.data[fs.train, features.subset]
            train.fs.data <- transform(train.fs.data,
                                       Label = fs.data$Label[fs.train])

            test.fs.data <- fs.data[fs.test, features.subset]
            test.fs.data <- transform(test.fs.data ,
                                      Label = fs.data$Label[fs.test])

            model <- svm(Label ~.,
                         data = train.fs.data)

            result <- predict(model, newdata = test.fs.data)

            mean(result == test.fs.data$Label)
        }

        folds <- cvFolds(nrow(fs.data), K = 10)

        prediction <- foreach(i = 1:10,
                               .combine = 'cbind',
                               .packages = 'e1071',
                               .export = c('top.features.vector',
                                           'fs.data', 'down.sample')) %dopar% {

            predict.with.SVM(folds$subsets[folds$which != i],
                             folds$subsets[folds$which == i])
        }

        mean(prediction)
    }

    train <- down.sample(breast.cancer.data,
                         breast.cancer.data$Label,
                         30)

    fs.data <- breast.cancer.data[train,]

    remaining.data <- breast.cancer.data[-train,]

    test <- down.sample(remaining.data,
                        remaining.data$Label,
                        10)

    test.data <- remaining.data[test,]

    i <- 0

    GA <- ga("binary",
             fitness = fitness,
             nBits = length(top.features.vector),
             names = top.features.vector,
             monitor = plot,
             maxiter = 300,
             population = best.first,
             popSize = 100
    )

    plot(GA)

    solution.SVM <- top.features.vector[GA@solution[1, ] == 1]#[1:64]

    predict.breast.cancer <- function(){

        train.data <- fs.data[, solution.SVM]
        train.data <- transform(train.data,
                                Label = fs.data$Label)

        vld.data <- test.data[, solution.SVM]
        vld.data <- transform(test.data ,
                              Label = test.data$Label)

        model <- svm(Label ~.,
                     data = train.data)

        result <- predict(model, newdata = vld.data)

        c1.test.indexes <- vld.data$Label == 1
        c2.test.indexes <- vld.data$Label == 0

        c2.acc <- mean(result[c2.test.indexes] == vld.data$Label[c2.test.indexes])
        c1.acc <- mean(result[c1.test.indexes] == vld.data$Label[c1.test.indexes])
        total.acc <- mean(result == vld.data$Label)

        c(c1.acc, c2.acc, total.acc)
    }

    predictions <- predict.breast.cancer()

    names(predictions) <- c("Classe 1 (y = 1)", "Classe 2 (y = 0)", "Total")

    list(top.features = solution.SVM,
         predictions = predictions)

}

final.result <- lapply(1:10,
                       function(i){
                           predict.SVM()
                       })

acc <- matrix(nrow = 0, ncol = 3)
for(i in 1:length(final.result)){
  acc <- as.matrix(rbind(acc, final.result[[i]]$predictions))
}

melted <- melt(acc)
boxplot <- ggplot(melted, aes(x = Var2, y = value)) +
  facet_wrap(~Var2, scale="free_x") +
  geom_boxplot() +
  ggtitle("Performance using SVM applied to best subset of features according to GA with SVM") +
  xlab("Classes") +
  ylab("Accuracy") +
  theme(title =  element_text(size = 20))

print(boxplot)

ggsave(plot = boxplot,
       filename = "GA_SVM_rene_no_pls.pdf",
       height = 10,
       width = 20)

save.image("SVM_rene.RData")