Hi,
One problem you have is with the command:
regr<-randomForest(y~x1+x2, data=X_train, proximity=TRUE)
What you need is something like this:
X2 <- cbind(X,y)
regr<-randomForest(y~x1+x2, data=X2, proximity=TRUE)
HTH,
Eric
On Mon, May 8, 2023 at 11:11?PM varin sacha via R-help
<r-help at r-project.org> wrote:>
> Dear R-experts,
>
> Here below a toy example with some error messages, especially at the end of
the code (Tuning the parameters). Your help to correct my R code would be highly
appreciated.
>
>
> #######################################
> #libraries
> library(lattice)
> library(ggplot2)
> library(caret)
> library(randomForest)
>
> #Data
>
y=c(23,34,32,12,24,35,45,56,76,87,54,34,23,45,41,13,16,98,35,65,56,67,78,89,87,64,53,31,14,34,45,46,57,69,90,80,70,65,50,45,60,56,87,79,64,34,25,47,61,24,10,13,12,15,46,58,76,89,90,98)
>
x1=c(4,5,6,7,1,10,19,20,21,14,23,6,5,32,15,12,16,14,2,3,4,5,3,2,1,2,6,7,5,4,3,2,1,3,4,6,7,9,5,4,3,7,10,11,12,13,10,3,2,5,6,9,8,7,4,12,15,16,2,3)
>
x2=c(0,0,0,1,1,0,1,1,0,1,1,0,0,1,0,0,0,0,0,1,1,1,1,1,0,0,0,1,0,0,1,0,0,0,1,1,0,1,0,0,0,1,1,1,1,0,1,0,1,0,0,1,1,0,0,1,0,0,1,1)
>
> y=as.numeric(y)
> x1=as.numeric(x1)
> x2=as.factor(x2)
>
> X=data.frame(x1,x2)
> y=y
>
> #Split data into training and test sets
> index=createDataPartition(y, p=0.75, list=FALSE)
> X_train = X[index, ]
> X_test = X[-index, ]
> y_train= y[index ]
> y_test = y[-index ]
>
> #Train de model
> regr=randomForest (x=X_train, y=y_train, maxnodes=10, ntree=10)
>
> regr<-randomForest(y~x1+x2, data=X_train, proximity=TRUE)
> regr
>
> #Make prediction
> predictions= predict(regr, X_test)
>
> result= X_test
> result['y'] = y_test
> result['prediction'] = predictions
> result
>
> # Import library for Metrics
> library(Metrics)
>
> print(paste0('MAE: ' , mae(y_test,predictions) ))
> print(paste0('MSE: ' ,caret::postResample(predictions ,
y_test)['RMSE']^2 ))
> print(paste0('R2: ' ,caret::postResample(predictions ,
y_test)['Rsquared'] ))
>
>
> #Tuning the parameters
> N=500 #length(X_train)
> X_train_ = X_train[1:N , ]
> y_train_ = y_train[1:N]
>
> seed <-7
> metric<-'RMSE'
>
> customRF <- list(type = "Regression", library =
"randomForest", loop = NULL)
>
> customRF$parameters <- data.frame(parameter = c("maxnodes",
"ntree"), class = rep("numeric", 2), label =
c("maxnodes", "ntree"))
>
> customRF$grid <- function(x, y, len = NULL, search = "grid")
{}
>
> customRF$fit <- function(x, y, wts, param, lev, last, weights,
classProbs, ...) {
>
> randomForest(x, y, maxnodes = param$maxnodes, ntree=param$ntree, ...)
>
> }
>
> customRF$predict <- function(modelFit, newdata, preProc = NULL,
submodels = NULL)
>
> predict(modelFit, newdata)
>
> customRF$prob <- function(modelFit, newdata, preProc = NULL, submodels =
NULL)
>
> predict(modelFit, newdata, type = "prob")
>
> customRF$sort <- function(x) x[order(x[,1]),]
>
> customRF$levels <- function(x) x$classes
>
>
> # Set grid search parameters
> control <- trainControl(method="repeatedcv", number=10,
repeats=3, search='grid')
>
> # Outline the grid of parameters
> tunegrid <- expand.grid(.maxnodes=c(10,20,30,50), .ntree=c(100, 200,
300))
> set.seed(seed)
>
> # Train the model
> rf_gridsearch <- train(x=X_train_, y=y_train_, method=customRF,
metric=metric, tuneGrid=tunegrid, trControl=control)
>
> plot(rf_gridsearch)
>
> rf_gridsearch$bestTune
>
> #################################################
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.