if (!require("devtools")) install.packages("devtools")
library(devtools)
install_github("insilico/npdro")
if (!require("npdro")) install.packages("npdro")
library(npdro)
if (!require("dplyr")) install.packages("dplyr")
library(dplyr)

create_data <- function(num.samples=300, num.variables=100,
                        pct.imbalance=0.5,pct.signals=0.2,
                        main.bias=0.5,interaction.bias=1,
                        hi.cor=0.95,lo.cor=0.2,
                        mix.type="main-interactionScalefree",
                        label="class",sim.type="mixed",
                        pct.mixed=0.5,pct.train=0.5,
                        pct.holdout=0.5,pct.validation=0,
                        plot.graph=F,graph.structure = NULL,
                        verbose=T){
  
  dataset <- npdro::createSimulation2(num.samples=num.samples,
                                      num.variables=num.variables,
                                      pct.imbalance=pct.imbalance,
                                      pct.signals=pct.signals,
                                      main.bias=main.bias,
                                      interaction.bias=interaction.bias,
                                      hi.cor=hi.cor,
                                      lo.cor=lo.cor,
                                      mix.type=mix.type,
                                      label=label,
                                      sim.type=sim.type,
                                      pct.mixed=pct.mixed,
                                      pct.train=pct.train,
                                      pct.holdout=pct.holdout,
                                      pct.validation=pct.validation,
                                      plot.graph=plot.graph,
                                      graph.structure = graph.structure,
                                      verbose=verbose)
  
  train <- dataset$train  #150x101
  test <- dataset$holdout 
  validation <- dataset$validation
  dataset$signal.names
  colnames(train)
  
  # separate the class vector from the predictor data matrix
  train.X <- train[, -which(colnames(train) == "class")]
  train.y <- train[, "class"]
  train.y.01 <- as.numeric(train.y)-1
  
  return(list(train=train, test=test, train.X=train.X, train.y=train.y,
           validation=validation, train.y.01=train.y.01))
}