gistfile1.txt

#Bayesian Regularization for Feed-Forward Neural Networks
training_comp<-training%>%na.omit()
neurons=2
p=length(names(training_comp))-1
n=dim(training_comp)[1]
npar=neurons*(1+1+p)+1
brnngrid<-initnw(neurons,p,n,npar)
brnn1 <- train(rochefant~. - consumer, data = training_comp,
               method = "brnn",
               trControl = tr)
               brnn1 <- train(rochefant~.-customer, data = training_comp,
               method = "brnn",
               trControl = tr)
testing_comp<-testing%>%na.omit()
testing_comp$pred<-predict(brnn1, testing)
ggplot(testing_comp, aes(rochefant,pred, 
                         colour=as.factor(slaughtermonth))) +
  geom_point(alpha=0.3, size=1) +
  geom_smooth(method=lm, se=FALSE, linetype="dashed", size=1)+
  geom_abline(slope=1, linetype="dashed") + theme_bw() +
  facet_wrap(~slaughteryear)+theme_bw()