Lab weighted kNN, decision trees, random forest (“cross-validation” built in – more labs on it later in the course) Peter Fox and Greg Hughes Data Analytics – ITWS-4600/ITWS-6600 Group 2 Lab 3, February 23, 2017
Weighted KNN group2/lab3_kknn1.R Make sure you look carefully at the results Apply it to other datasets!
Rpart – recursive partitioning and Conditional Inference group2/lab3_rpart1.R group2/lab3_rpart2.R group2/lab3_rpart3.R group2/lab3_rpart4.R Try rpart for “Rings” on the Abalone dataset group2/lab3_ctree1.R group2/lab3_ctree2.R group2/lab3_ctree3.R
randomForest group2/lab3_randomforest1.R Do your own Random Forest , i.e. different implementations, cforest {party} on the other datasets
Trees for the Titanic data(Titanic) rpart, ctree, hclust, randomForest for Survived ~ .