Hello Rescuers,
I have a problem with retrieving the Accuracy Standard Deviation for a
"nnet" model trained by "train" in the "caret" package.
Below is my code. I checked several examples online whose published output
shows Accuracy SD but I could not get to finding a difference between these
codes and mine. I hope someone can help with identifying where my problem
is.
*set.seed(42)*
*control <- trainControl(method="repeatedcv", number=10, repeats=5)*
*rfFit <- train(Label ~., data = Train_2.4.16,*
* method = "rf",*
* preProc = c("center", "scale"),*
* tuneLength = 10,*
* metric = "Accuracy",*
* trControl=control,*
* allowParallel=TRUE)*
*print(rfFit) *
Below is the output I get:
*Random Forest *
*3141 samples*
* 110 predictor*
* 5 classes: '(2.81,3.19]', '(3.19,3.48]', '(3.48,3.74]', '(3.74,4]',
'[0.43,2.81]' *
*No pre-processing*
*Resampling: Cross-Validated (10 fold, repeated 5 times) *
*Summary of sample sizes: 2827, 2827, 2828, 2827, 2828, 2827, ... *
*Resampling results:*
* Accuracy Kappa *
* 0.7520328 0.6900293*
*Tuning parameter 'mtry' was held constant at a value of 10.48809*
If relevant, I am using Windows 10, RStudio and the Caret package updated
as of today version 6.0-71
Thank you,
Heba.
--
*Heba AtteyaResearch Analyst Data Analytics and Institutional Researchtel.
20.2.2615. 2230"Information is the oil of the 21st century, and analytics
is the combustion engine" ~Senior VP, Gartner Research*
[[alternative HTML version deleted]]
______________________________________________
R-help@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.
