R C5.0: Error while including minCases in tunegrid (caret) - r

Question

i am trying to implement the minCases-argument into my tuning process of a c5.0 model.
As i am using the caret package i am trying to get that argument into the "tuneGrid".
For that purpose i found the following Tutorial.
https://www.euclidean.com/machine-learning-in-practice/2015/6/12/r-caret-and-parameter-tuning-c50
After implementing the code into my syntax i get the following error:
**Error: The tuning parameter grid should have columns NA, NA, NA, splits**
Anyone knows where there is a mistake?
The error occurs as soon as i am building my model "mdl" in the last line of the code.
With regard to the Tutorial mentionend above my current code is the following:
library(datasets)
data(iris)
library('gmodels')
library("RcppCNPy")
library("class")
library("C50")
library('caret')
library('mlbench')
####Customizing the C5.0
C5CustomSort <- function(x) {
x$model <- factor(as.character(x$model), levels = c("rules","tree"))
x[order(x$trials, x$model, x$splits, !x$winnow),]
}
C5CustomLoop <- function (grid)
{
loop <- ddply(grid, c("model", "winnow","splits"), function(x) c(trials = max(x$trials)))
submodels <- vector(mode = "list", length = nrow(loop))
for (i in seq(along = loop$trials)) {
index <- which(grid$model == loop$model[i] & grid$winnow == loop$winnow[i] & grid$splits == loop$splits[i])
trials <- grid[index, "trials"]
submodels[[i]] <- data.frame(trials = trials[trials != loop$trials[i]])
}
list(loop = loop, submodels = submodels)
}
C5CustomGrid <- function(x, y, len = NULL) {
c5seq <- if(len == 1) 1 else c(1, 10*((2:min(len, 11)) - 1))
expand.grid(trials = c5seq, splits = c(2,10,20,50), winnow = c(TRUE, FALSE), model = c("tree","rules"))
}
C5CustomFit <- function(x, y, wts, param, lev, last, classProbs, ...) {
# add the splits parameter to the fit function
# minCases is a function of splits
theDots <- list(...)
splits <- param$splits
minCases <- floor( length(y)/splits ) - 1
if(any(names(theDots) == "control"))
{
theDots$control$winnow <- param$winnow
theDots$control$minCases <- minCases
theDots$control$earlyStopping <- FALSE
}
else
theDots$control <- C5.0Control(winnow = param$winnow, minCases = minCases, earlyStopping=FALSE )
argList <- list(x = x, y = y, weights = wts, trials = param$trials, rules = param$model == "rules")
argList <- c(argList, theDots)
do.call("C5.0.default", argList)
}
GetC5Info <- function() {
# get the default C5.0 model functions
c5ModelInfo <- getModelInfo(model = "C5.0", regex = FALSE)[[1]]
# modify the parameters data frame so that it includes splits
c5ModelInfo$parameters$parameter <- factor(c5ModelInfo$parameters$parameter,levels=c(levels(c5ModelInfo$parameters$parameter),'splits'))
c5ModelInfo$parameters$label <- factor(c5ModelInfo$parameters$label,levels=c(levels(c5ModelInfo$parameters$label),'Splits'))
c5ModelInfo$parameters <- rbind(c5ModelInfo$parameters,c('splits','numeric','Splits'))
# replace the default c5.0 functions with ones that are aware of the splits parameter
c5ModelInfo$fit <- C5CustomFit
c5ModelInfo$loop <- C5CustomLoop
c5ModelInfo$grid <- C5CustomGrid
c5ModelInfo$sort <- C5CustomSort
return (c5ModelInfo)
}
c5info <- GetC5Info()
#Building the actual model
x_a <- iris[c("Sepal.Length","Sepal.Width","Petal.Length","Petal.Width")]
y_a <-as.factor(iris[,c("Species")])
fitControl <- trainControl(method = "cv", number = 10)
grida <- expand.grid( .winnow = "FALSE", .trials=c(1,5,10,15,20), .model="tree", .splits=c(2,5,10,15,20,25,50,100) )
mdl<- train(x=x_a,y=y_a,tuneGrid=grida,trControl=fitControl,method=c5info)

Answer 1

the problem seems to be in some of the Custom functions, i have this other version that works for me:
library(caret)
library(C50)
library(mlbench)
library(tidyverse)
library(plyr)
C5CustomSort <- function(x) {
x$model <- factor(as.character(x$model), levels = c("rules","tree"))
x[order(x$trials, x$model, x$splits, !x$winnow),]
}
C5CustomLoop <- function (grid)
{
loop <- ddply(grid, .(winnow,model, splits,trials), function(x) c(trials = max(x$trials)))
submodels <- vector(mode = "list", length = nrow(loop))
for (i in seq(along = loop$trials)) {
index <- which(grid$model == loop$model[i] & grid$winnow ==
loop$winnow[i] & grid$splits == loop$splits[i])
trials <- grid[index, "trials"]
submodels[[i]] <- data.frame(trials = trials[trials !=
loop$trials[i]],winnow = loop$winnow[i], model=loop$model[i],splits=loop$splits[i])
}
list(loop = loop, submodels = submodels)
}
C5CustomGrid <- function(x, y, len = NULL) {
c5seq <- if(len == 1) 1 else c(1, 10*((2:min(len, 11)) - 1))
expand.grid(trials = c5seq, splits = c(2,10,20,50), winnow = c(TRUE, FALSE), model = c("tree","rules"))
}
C5CustomFit <- function(x, y, wts, param, lev, last, classProbs, ...) {
theDots <- list(...)
splits <- loop$splits
minCases <- floor( length(y)/splits ) - 1
if(any(names(theDots) == "control"))
{
theDots$control$winnow <- param$winnow
theDots$control$minCases <- minCases
theDots$control$earlyStopping <- FALSE
}
else
theDots$control <- C5.0Control(winnow = param$winnow, minCases = minCases, earlyStopping=FALSE )
argList <- list(x = x, y = y, weights = wts, trials = param$trials, rules = param$model == "rules")
argList <- c(argList, theDots)
do.call("C5.0.default", argList)
}
GetC5Info <- function() {
c5ModelInfo <- getModelInfo(model = "C5.0", regex = FALSE)[[1]]
c5ModelInfo$parameters$parameter <- factor(c5ModelInfo$parameters$parameter,levels=c(c5ModelInfo$parameters$parameter,'splits'))
c5ModelInfo$parameters$label <- factor(c5ModelInfo$parameters$label,levels=c(c5ModelInfo$parameters$label,'Splits'))
c5ModelInfo$parameters <- rbind(c5ModelInfo$parameters,c('splits','numeric','Splits'))parameter
c5ModelInfo$fit <- C5CustomFit
c5ModelInfo$loop <- C5CustomLoop
c5ModelInfo$sort <- C5CustomSort
return (c5ModelInfo)
}
c5info <- GetC5Info()
fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 10)
splits<-c(5,25,100)
grid <- expand.grid( winnow = c(FALSE), trials=c(5,6), model=c("tree"), splits=c(5,25,100) )
data(PimaIndiansDiabetes2)
x <- PimaIndiansDiabetes2[c("age","glucose","insulin","mass","pedigree","pregnant","pressure","triceps")]
y <- PimaIndiansDiabetes2$diabetes
mdl<- train(x=x,y=y,tuneGrid=grid,trControl=fitControl,method=c5info,verbose=FALSE)