I used arules package and generated a set of rules which have class values as consequent. My ultimate goal is to predict the class labels of unknown data using these rules.
Now I am trying to adopt these rules to generate a decision tree as predict method in arules doesnt suit for this scinario. How can I adopt a set of rules generated by association rules to create a decision tree and predict?
I am following the example in http://www.rdatamining.com/examples/association-rules
Desired output is to predict the class label i.e either Survived = yes or no for a given unseen record using rules generated from following code
rules <- apriori(titanic.raw,
+ parameter = list(minlen=2, supp=0.005, conf=0.8),
+ appearance = list(rhs=c("Survived=No", "Survived=Yes"),
+ default="lhs"),
+ control = list(verbose=F))
rules.sorted <- sort(rules, by="lift")