CODEWITHSUNDEEP
rr-caret
user3740289
user3740289

Reputation: 265

Extract winning RMSE from optimal R Caret model

I create nnet models using the caret package and extract the predicted value using the following code:

nnet<-predict(my_model, newdata = my_new_data) 
nnet
[1] -0.1468207

I also create the following output whereby I can view the the optimal model parameters as below: 

Resampling results across tuning parameters:

  size  decay  RMSE        Rsquared   RMSE SD      Rsquared SD
  10    0.001  0.01867841  0.4789708  0.002538599  0.12778927 
  10    0.100  0.02349088  0.1233067  0.001859455  0.10188046 
  12    0.001  0.01826047  0.5059824  0.002630588  0.12962511 
  12    0.100  0.02348553  0.1238252  0.001890646  0.09851303 
  15    0.001  0.01795350  0.5289120  0.003021449  0.13908835 
  15    0.100  0.02318972  0.1429446  0.001932714  0.11156927 

RMSE was used to select the optimal model using  the smallest value.
The final values used for the model were size = 15 and decay = 0.001.

My question is how can I create a variable which just contains the optimal RMSE from the final model? (Instead of having to manually check the output.)

Eg. Something along these lines: 

Model_RMSE<-nnet$finalModelRMSE
Model_RMSE
[1] 0.01795350

Thank you

*Update Thanks @SamThomas that's it. I actually wanted just the RMSE from the 'winning/optimum' used model so I just wrapped your suggestion in a min() as below. 

>nnet$results["RMSE"]
        RMSE
1 0.01867841
2 0.02349088
3 0.01826047
4 0.02348553
5 0.01795350
6 0.02318972

>min(nnet$results["RMSE"])
[1] 0.0179535

Upvotes: 3

Views: 4885

Answers (2)

topepo
topepo

Reputation: 14316

There is already a function to do just this called getTrainPerf.

Max

Upvotes: 7

Whitebeard
Whitebeard

Reputation: 6193

Glad the comment helped. If you want the full row from the results, this might be useful.

nnet$results[which.min(nnet$results[, "RMSE"]), ]

Upvotes: 0

Related Questions