1. Using the models, prediction, deciding
Peter Fox
Data Analytics – ITWS-4963/ITWS-6965
Week 7b, March 7, 2014

2. scatterplotMatrix

3. Hierarchical clustering
> dswiss <- dist(as.matrix(swiss)) > hs <- hclust(dswiss) > plot(hs)

4. ctree
require(party) swiss_ctree <- ctree(Fertility ~ Agriculture + Education + Catholic, data = swiss) plot(swiss_ctree)

6. pairs(iris[1:4], main = "Anderson's Iris Data -- 3 species”, pch = 21, bg = c("red", "green3", "blue")[unclass(iris$Species)])

7. splom extra!
require(lattice) super.sym <- trellis.par.get("superpose.symbol") splom(~iris[1:4], groups = Species, data = iris, panel = panel.superpose, key = list(title = "Three Varieties of Iris", columns = 3, points = list(pch = super.sym$pch[1:3], col = super.sym$col[1:3]), text = list(c("Setosa", "Versicolor", "Virginica")))) splom(~iris[1:3]|Species, data = iris, layout=c(2,2), pscales = 0, varnames = c("Sepal\nLength", "Sepal\nWidth", "Petal\nLength"), page = function(...) { ltext(x = seq(.6, .8, length.out = 4), y = seq(.9, .6, length.out = 4), labels = c("Three", "Varieties", "of", "Iris"), cex = 2) })

8. parallelplot(~iris[1:4] | Species, iris)

9. parallelplot(~iris[1:4], iris, groups = Species,
horizontal.axis = FALSE, scales = list(x = list(rot = 90)))

10. hclust for iris

11. plot(iris_ctree)

12. Ctree
> iris_ctree <- ctree(Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data=iris)
> print(iris_ctree)
Conditional inference tree with 4 terminal nodes
Response: Species
Inputs: Sepal.Length, Sepal.Width, Petal.Length, Petal.Width
Number of observations: 150
1) Petal.Length <= 1.9; criterion = 1, statistic =
2)* weights = 50
1) Petal.Length > 1.9
3) Petal.Width <= 1.7; criterion = 1, statistic =
4) Petal.Length <= 4.8; criterion = 0.999, statistic =
5)* weights = 46
4) Petal.Length > 4.8
6)* weights = 8
3) Petal.Width > 1.7
7)* weights = 46

13. > plot(iris_ctree, type="simple”)

14. New dataset to work with trees
fitK <- rpart(Kyphosis ~ Age + Number + Start, method="class", data=kyphosis) printcp(fitK) # display the results plotcp(fitK) # visualize cross-validation results summary(fitK) # detailed summary of splits # plot tree plot(fitK, uniform=TRUE, main="Classification Tree for Kyphosis") text(fitK, use.n=TRUE, all=TRUE, cex=.8) # create attractive postscript plot of tree post(fitK, file = “kyphosistree.ps", title = "Classification Tree for Kyphosis") # might need to convert to PDF (distill)

16. > pfitK<- prune(fitK, cp= fitK$cptable[which
> pfitK<- prune(fitK, cp= fitK$cptable[which.min(fitK$cptable[,"xerror"]),"CP"])
> plot(pfitK, uniform=TRUE, main="Pruned Classification Tree for Kyphosis")
> text(pfitK, use.n=TRUE, all=TRUE, cex=.8)
> post(pfitK, file = “ptree.ps", title = "Pruned Classification Tree for Kyphosis”)

17. > fitK <- ctree(Kyphosis ~ Age + Number + Start, data=kyphosis)
> plot(fitK, main="Conditional Inference Tree for Kyphosis”)

18. > plot(fitK, main="Conditional Inference Tree for Kyphosis",type="simple")

19. randomForest
> require(randomForest) > fitKF <- randomForest(Kyphosis ~ Age + Number + Start, data=kyphosis) > print(fitKF) # view results Call: randomForest(formula = Kyphosis ~ Age + Number + Start, data = kyphosis) Type of random forest: classification Number of trees: 500 No. of variables tried at each split: 1 OOB estimate of error rate: 20.99% Confusion matrix: absent present class.error absent present > importance(fitKF) # importance of each predictor MeanDecreaseGini Age Number Start
Random forests improve predictive accuracy by generating a large number of bootstrapped trees (based on random samples of variables), classifying a case using each tree in this new "forest", and deciding a final predicted outcome by combining the results across all of the trees (an average in regression, a majority vote in classification).

20. More on another dataset.
# Regression Tree Example
library(rpart)
# build the tree
fitM <- rpart(Mileage~Price + Country + Reliability + Type, method="anova", data=cu.summary)
printcp(fitM) # display the results ….
Root node error: /60 =
n=60 (57 observations deleted due to missingness)
CP nsplit rel error xerror xstd

21. Mileage…
plotcp(fitM) # visualize cross-validation results summary(fitM) # detailed summary of splits <we will leave this for Friday to look at>

22. par(mfrow=c(1,2))
rsq.rpart(fitM) # visualize cross-validation results

23. # plot tree plot(fitM, uniform=TRUE, main="Regression Tree for Mileage ") text(fitM, use.n=TRUE, all=TRUE, cex=.8) # prune the tree pfitM<- prune(fitM, cp= ) # from cptable # plot the pruned tree plot(pfitM, uniform=TRUE, main="Pruned Regression Tree for Mileage") text(pfitM, use.n=TRUE, all=TRUE, cex=.8) post(pfitM, file = ”ptree2.ps", title = "Pruned Regression Tree for Mileage”)

25. # Conditional Inference Tree for Mileage fit2M <- ctree(Mileage~Price + Country + Reliability + Type, data=na.omit(cu.summary))

26. Enough of trees!

27. Bayes
> cl <- kmeans(iris[,1:4], 3) > table(cl$cluster, iris[,5]) setosa versicolor virginica # > m <- naiveBayes(iris[,1:4], iris[,5]) > table(predict(m, iris[,1:4]), iris[,5]) setosa versicolor virginica
pairs(iris[1:4],main="Iris Data (red=setosa,green=versicolor,blue=virginica)", pch=21, bg=c("red","green3","blue")[unclass(iris$Species)])

28. Digging into iris
classifier<-naiveBayes(iris[,1:4], iris[,5]) table(predict(classifier, iris[,-5]), iris[,5], dnn=list('predicted','actual')) actual predicted setosa versicolor virginica setosa versicolor virginica

29. Digging into iris
> classifier$apriori iris[, 5] setosa versicolor virginica > classifier$tables$Petal.Length Petal.Length iris[, 5] [,1] [,2] setosa versicolor virginica

30. Digging into iris
plot(function(x) dnorm(x, 1.462, ), 0, 8, col="red", main="Petal length distribution for the 3 different species") curve(dnorm(x, 4.260, ), add=TRUE, col="blue") curve(dnorm(x, 5.552, ), add=TRUE, col = "green")

31. http://www. ugrad. stat. ubc. ca/R/library/mlbench/html/HouseVotes84
> require(mlbench) > data(HouseVotes84) > model <- naiveBayes(Class ~ ., data = HouseVotes84) > predict(model, HouseVotes84[1:10,-1]) [1] republican republican republican democrat democrat democrat republican republican republican [10] democrat Levels: democrat republican

32. House Votes 1984
> predict(model, HouseVotes84[1:10,-1], type = "raw") democrat republican [1,] e e-01 [2,] e e-01 [3,] e e-01 [4,] e e-03 [5,] e e-02 [6,] e e-01 [7,] e e-01 [8,] e e-01 [9,] e e-01 [10,] e e-11

33. House Votes 1984
> pred <- predict(model, HouseVotes84[,-1]) > table(pred, HouseVotes84$Class) pred democrat republican democrat republican

34. So now you could complete this:
> data(HairEyeColor) > mosaicplot(HairEyeColor) > margin.table(HairEyeColor,3) Sex Male Female > margin.table(HairEyeColor,c(1,3)) Hair Male Female Black Brown Red Blond Construct a naïve Bayes classifier and test.

35. Assignments to come…
Term project (A6). Due ~ week % (25% written, 5% oral; individual).
Assignment 7: Predictive and Prescriptive Analytics. Due ~ week 9/10. 20% (15% written and 5% oral; individual);

36. Coming weeks I will be out of town Friday March 21 and 28
On March 21 you will have a lab – attendance will be taken – to work on assignments (term (6) and assignment 7). Your project proposals (Assignment 5) are on March 18.
On March 28 you will have a lecture on SVM, thus the Tuesday March 25 will be a lab.
Back to regular schedule in April (except 18th)

37. Admin info (keep/ print this slide)
Class: ITWS-4963/ITWS 6965
Hours: 12:00pm-1:50pm Tuesday/ Friday
Location: SAGE 3101
Instructor: Peter Fox
Instructor contact: (do not leave a msg)
Contact hours: Monday** 3:00-4:00pm (or by appt)
Contact location: Winslow 2120 (sometimes Lally 207A announced by )
TA: Lakshmi Chenicheri
Web site:
Schedule, lectures, syllabus, reading, assignments, etc.