We carried out comparisons between the bagging and random forest methods in the previous chapter. Using the gbm
function, we now add boosting accuracy to the earlier analyses:
> data("spam") > set.seed(12345) > Train_Test <- sample(c("Train","Test"),nrow(spam),replace = TRUE, + prob = c(0.7,0.3)) > head(Train_Test) [1] "Test" "Test" "Test" "Test" "Train" "Train" > spam_Train <- spam[Train_Test=="Train",] > spam_TestX <- within(spam[Train_Test=="Test",], + rm(type)) > spam_TestY <- spam[Train_Test=="Test","type"] > spam_Formula <- as.formula("type~.") > spam_rf <- randomForest(spam_Formula,data=spam_Train,coob=TRUE, + ntree=500,keepX=TRUE,mtry=5) > spam_rf_predict <- predict(spam_rf,newdata=spam_TestX,type="class") > rf_accuracy <- sum(spam_rf_predict==spam_TestY)/nrow(spam_TestX) > rf_accuracy [1] 0.9436117 > spam_bag <- randomForest...