In sungcheolkim78/FiDEL: Fermi-Dirac based Ensemble Learning

knitr::opts_chunk$set(echo = TRUE)

library(FiDEL)

Bank data

Bank <- read.csv('data/bank.csv', sep=';')

inTraining0 <- createDataPartition(Bank$y, p = .75, list = FALSE)
training <- Bank[ inTraining0,]
testing  <- Bank[-inTraining0,]
testingY <- as_label(Bank[-inTraining0, ncol(Bank)])

table(Bank$y)

t1 <- mtrainer(c('nnet', 'rda', 'svmLinear', 'svmRadial', 'pls', 'earth', 'avNNet', 'mlp', 'nb', 'rf', 'rpart', 'xgbTree', 'ctree', 'C5.0', 'gbm', 'bayesglm', 'earth', 'glm', 'avNNet', 'glmnet', 'simpls', 'xgbLinear','ctree', 'C5.0', 'gbm')) %>%
  train(y~., training, update=F)

t1 <- t1 %>%
  addmodel.mtrainer(c('ctree', 'C5.0', 'gbm')) %>%
  train(y~., training, update=F)

check parameter fitting

t1 <- t1 %>%
  addmodel.mtrainer(c('svmLinear', 'svmRadial', 'pls', 'earth', 'avNNet', 'mlp', 'nb', 'rf', 'rpart', 'xgbTree', 'ctree', 'C5.0', 'gbm', 'bayesglm', 'earth', 'glm', 'avNNet', 'glmnet', 'simpls', 'xgbLinear','ctree', 'C5.0', 'gbm' )) %>%
  train(y~., training, update=F)

Select best parameters

plot(t1)

Calculate Rank

t1 <- predict(t1, newdata=testing)
auclist <- apply(t1$predictions, 2, auc.rank, testingY)

fde1 <- fde(t1$predictions)
fde1 <- predict_performance(fde1, auclist, attr(testingY, 'rho'))

Rank class probability

plot_cor(fde1, legend_flag = T)

fde1 <- fde(t1$predictions, testingY)

plot_single(fde1, 'score')

store.mtrainer(t1, 'bank_m8_pre.RData')
saveRDS(testingY, 'bank_m8_y.RData')

saveRDS(t1, 'bank_all.RData')

sungcheolkim78/FiDEL documentation built on Nov. 13, 2024, 7:58 a.m.