Hello to all
I have different train functions for NN, SVM and GBM and when I combine the
results using bwplot, it gives me the error " Different number of resamples
in each model". It gives me the results (MAE values) but using the boxplot,
it gives the error. The code is as follows:
set.seed(30218)
nnet1 <- train(results~ ., data = tr,
method = "nnet",
metric = "MAE",
trControl = ctrl,
preProc = c("center", "scale",
"zv"),
tuneGrid = data.frame(decay = (1),
size = (1.3801517)))
nnet1$results
///For SVM
set.seed(30218)
svm1 <- train(results ~ ., data = tr,
method = "svmRadial",
metric = "MAE",
preProc = c("center", "scale",
"zv"),
trControl = ctrl,
tuneGrid=expand.grid(sigma = (0.5),
C = c(1.348657)))
getTrainPerf(svm1)
svm1$results
//For GBM
set.seed(30218)
gbm <- train(results ~ ., data = tr,
method = "gbm",
preProc = c("center", "scale", "zv"),
metric = "MAE",
tuneGrid = data.frame(n.trees = (200.09633523),
interaction.depth = (1),
shrinkage=(0.1), n.minobsinnode=(10)))
gbm$results
//Then the boxplot
rvalues=resamples(list(nnet=nnet1, svm=svm1, GBM=gbm))
bwplot(rvalues, metric="MAE")
[[alternative HTML version deleted]]
?? Isn't is resample() not resamples()?>From what package?What package is bwplot from? lattice:::bwplot has no "metric" argument. Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it." -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) On Thu, Feb 20, 2020 at 12:55 PM javed khan <javedbtk111 at gmail.com> wrote:> Hello to all > > I have different train functions for NN, SVM and GBM and when I combine the > results using bwplot, it gives me the error " Different number of resamples > in each model". It gives me the results (MAE values) but using the boxplot, > it gives the error. The code is as follows: > > set.seed(30218) > nnet1 <- train(results~ ., data = tr, > method = "nnet", > > metric = "MAE", > trControl = ctrl, > > preProc = c("center", "scale", "zv"), > tuneGrid = data.frame(decay = (1), > size = (1.3801517))) > nnet1$results > > ///For SVM > > set.seed(30218) > svm1 <- train(results ~ ., data = tr, > method = "svmRadial", > > metric = "MAE", > preProc = c("center", "scale", "zv"), > trControl = ctrl, > tuneGrid=expand.grid(sigma = (0.5), > C = c(1.348657))) > getTrainPerf(svm1) > svm1$results > > //For GBM > > set.seed(30218) > gbm <- train(results ~ ., data = tr, > method = "gbm", > preProc = c("center", "scale", "zv"), > metric = "MAE", > > > tuneGrid = data.frame(n.trees = (200.09633523), > interaction.depth = (1), > shrinkage=(0.1), n.minobsinnode=(10))) > gbm$results > > //Then the boxplot > > rvalues=resamples(list(nnet=nnet1, svm=svm1, GBM=gbm)) > > bwplot(rvalues, metric="MAE") > > [[alternative HTML version deleted]] > > ______________________________________________ > 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. >[[alternative HTML version deleted]]
cc the list! (which I have done here) Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it." -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) On Thu, Feb 20, 2020 at 1:20 PM javed khan <javedbtk111 at gmail.com> wrote:> Thanks for your reply. > > I am not using any specific package for bwplot. I just used caret, nnet > and gbm packages. > > When I use resample (instead of resamples), it give me error message. > > metric=MAE gives the MAE values at x-axis when I used simple plots in the > recent past. > > Best regards > > On Thu, Feb 20, 2020 at 10:15 PM Bert Gunter <bgunter.4567 at gmail.com> > wrote: > >> ?? >> Isn't is resample() not resamples()? >> From what package? >> What package is bwplot from? lattice:::bwplot has no "metric" argument. >> >> >> >> Bert Gunter >> >> "The trouble with having an open mind is that people keep coming along >> and sticking things into it." >> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) >> >> >> On Thu, Feb 20, 2020 at 12:55 PM javed khan <javedbtk111 at gmail.com> >> wrote: >> >>> Hello to all >>> >>> I have different train functions for NN, SVM and GBM and when I combine >>> the >>> results using bwplot, it gives me the error " Different number of >>> resamples >>> in each model". It gives me the results (MAE values) but using the >>> boxplot, >>> it gives the error. The code is as follows: >>> >>> set.seed(30218) >>> nnet1 <- train(results~ ., data = tr, >>> method = "nnet", >>> >>> metric = "MAE", >>> trControl = ctrl, >>> >>> preProc = c("center", "scale", "zv"), >>> tuneGrid = data.frame(decay = (1), >>> size = (1.3801517))) >>> nnet1$results >>> >>> ///For SVM >>> >>> set.seed(30218) >>> svm1 <- train(results ~ ., data = tr, >>> method = "svmRadial", >>> >>> metric = "MAE", >>> preProc = c("center", "scale", "zv"), >>> trControl = ctrl, >>> tuneGrid=expand.grid(sigma = (0.5), >>> C = c(1.348657))) >>> getTrainPerf(svm1) >>> svm1$results >>> >>> //For GBM >>> >>> set.seed(30218) >>> gbm <- train(results ~ ., data = tr, >>> method = "gbm", >>> preProc = c("center", "scale", "zv"), >>> metric = "MAE", >>> >>> >>> tuneGrid = data.frame(n.trees = (200.09633523), >>> interaction.depth = (1), >>> shrinkage=(0.1), n.minobsinnode=(10))) >>> gbm$results >>> >>> //Then the boxplot >>> >>> rvalues=resamples(list(nnet=nnet1, svm=svm1, GBM=gbm)) >>> >>> bwplot(rvalues, metric="MAE") >>> >>> [[alternative HTML version deleted]] >>> >>> ______________________________________________ >>> 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. >>> >>[[alternative HTML version deleted]]
Thanks for your reply. I am not using any specific package for bwplot. I just used caret, nnet and gbm packages. When I use resample (instead of resamples), it give me error message. metric=MAE gives the MAE values at x-axis when I used simple plots in the recent past. Best regards On Thu, Feb 20, 2020 at 10:29 PM Bert Gunter <bgunter.4567 at gmail.com> wrote:> cc the list! > (which I have done here) > > Bert Gunter > > "The trouble with having an open mind is that people keep coming along and > sticking things into it." > -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) > > > On Thu, Feb 20, 2020 at 1:20 PM javed khan <javedbtk111 at gmail.com> wrote: > >> Thanks for your reply. >> >> I am not using any specific package for bwplot. I just used caret, nnet >> and gbm packages. >> >> When I use resample (instead of resamples), it give me error message. >> >> metric=MAE gives the MAE values at x-axis when I used simple plots in the >> recent past. >> >> Best regards >> >> On Thu, Feb 20, 2020 at 10:15 PM Bert Gunter <bgunter.4567 at gmail.com> >> wrote: >> >>> ?? >>> Isn't is resample() not resamples()? >>> From what package? >>> What package is bwplot from? lattice:::bwplot has no "metric" argument. >>> >>> >>> >>> Bert Gunter >>> >>> "The trouble with having an open mind is that people keep coming along >>> and sticking things into it." >>> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) >>> >>> >>> On Thu, Feb 20, 2020 at 12:55 PM javed khan <javedbtk111 at gmail.com> >>> wrote: >>> >>>> Hello to all >>>> >>>> I have different train functions for NN, SVM and GBM and when I combine >>>> the >>>> results using bwplot, it gives me the error " Different number of >>>> resamples >>>> in each model". It gives me the results (MAE values) but using the >>>> boxplot, >>>> it gives the error. The code is as follows: >>>> >>>> set.seed(30218) >>>> nnet1 <- train(results~ ., data = tr, >>>> method = "nnet", >>>> >>>> metric = "MAE", >>>> trControl = ctrl, >>>> >>>> preProc = c("center", "scale", "zv"), >>>> tuneGrid = data.frame(decay = (1), >>>> size = (1.3801517))) >>>> nnet1$results >>>> >>>> ///For SVM >>>> >>>> set.seed(30218) >>>> svm1 <- train(results ~ ., data = tr, >>>> method = "svmRadial", >>>> >>>> metric = "MAE", >>>> preProc = c("center", "scale", "zv"), >>>> trControl = ctrl, >>>> tuneGrid=expand.grid(sigma = (0.5), >>>> C = c(1.348657))) >>>> getTrainPerf(svm1) >>>> svm1$results >>>> >>>> //For GBM >>>> >>>> set.seed(30218) >>>> gbm <- train(results ~ ., data = tr, >>>> method = "gbm", >>>> preProc = c("center", "scale", "zv"), >>>> metric = "MAE", >>>> >>>> >>>> tuneGrid = data.frame(n.trees = (200.09633523), >>>> interaction.depth = (1), >>>> shrinkage=(0.1), >>>> n.minobsinnode=(10))) >>>> gbm$results >>>> >>>> //Then the boxplot >>>> >>>> rvalues=resamples(list(nnet=nnet1, svm=svm1, GBM=gbm)) >>>> >>>> bwplot(rvalues, metric="MAE") >>>> >>>> [[alternative HTML version deleted]] >>>> >>>> ______________________________________________ >>>> 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. >>>> >>>[[alternative HTML version deleted]]