![> contacts.train[1,]
Pred Young Myope Astimatic Tear
1 P Y Y Y N
> contacts.train[,2]
[1] Y Y N N Y Y N N N N
Levels: N Y
> contacts.train[,"Pred"]
[1] P P P P N N N N N N
Levels: N P
> contacts.train$Pred
[1] P P P P N N N N N N
Levels: N P
> contacts.train[c(-1,-3,-5,-7,-9),]
Pred Young Myope Astimatic Tear
2 P Y Y N N
4 P N Y Y N
6 N Y Y N Y
8 N N N N N
10 N N N N N](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-4-320.jpg)
![> class(contacts.train)
[1] "data.frame"
> forecast <- data.frame(date=c("10/1","10/2","10/3"),
weather=c("sunny","sunny","rain"))
> forecast
date weather
1 10/1 sunny
2 10/2 sunny
3 10/3 rain
> forecast$weather
[1] sunny sunny rain
Levels: rain sunny
> forecast$date
[1] 10/1 10/2 10/3](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-5-320.jpg)
![> nrow(contacts.train)
[1] 10
> ncol(contacts.train)
[1] 5
> rownames(contacts.train)
[1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10"
> colnames(contacts.train)
[1] "Pred" "Young" "Myope" "Astimatic" "Tear"
> colnames(contacts.train)[2]
[1] "Young"
> colnames(contacts.train)[2] <- "Old"
> colnames(contacts.train)
[1] "Pred" "Old" "Myope" "Astimatic" "Tear"
> colnames(contacts.train)[2] <- "Young"](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-6-320.jpg)
![> contacts.train$Young
[1] Y Y N N Y Y N N N N
Levels: N Y
> order(contacts.train$Young)
[1] 3 4 7 8 9 10 1 2 5 6
> contacts.train[order(contacts.train$Young),]
Pred Young Myope Astimatic Tear
3 P N Y Y N
4 P N Y Y N
7 N N N N Y
8 N N N N N
9 N N N N Y
10 N N N N N
1 P Y Y Y N
2 P Y Y N N
5 N Y Y Y Y
6 N Y Y N Y](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-7-320.jpg)
![IRIS
• http://archive.ics.uci.edu/ml/machine-learning-databases/iris/ iris.data
• iris.name
• (setosa, versicolor, virginia)
• http://togodb.sel.is.ocha.ac.jp/
> iris.train <- read.table("iris_train.csv", sep=",", header=T)
> length(rownames(iris.train))
[1] 120
> length(colnames(iris.train))
[1] 5
> hist(iris.train$Sepal.length)
> hist(iris.train$Petal.length)](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-9-320.jpg)
![> plot(iris.train$Petal.length, iris.train$Petal.width, pch =
c(1,2,3)[unclass(iris.train$Class)])](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-12-320.jpg)
![> iris.test <- read.table("iris_test.csv", sep=",", header=T)
> iris.predict <- predict(iris.dtree, iris.test[1:4], type="class")
> iris.predict
2 4 18 34
Iris-setosa Iris-setosa Iris-setosa Iris-setosa
...
> iris.predict == iris.test$Class
[1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[11] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[21] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
> sum(iris.predict == iris.test$Class) / length(iris.test$Class)
[1] 0.9666667
> sum(iris.predict != iris.test$Class) / length(iris.test$Class)
[1] 0.03333333](https://image.slidesharecdn.com/dataminingr2nd-091029060855-phpapp01/85/Datamining-R-2nd-13-320.jpg)
Datamining R 2nd
- 1. R: sesejun@is.ocha.ac.jp 2009/10/29( )
- 2. • contacts_train.csv • • (setwd > > ) "Pred","Young","Myope","Astimatic","Tear" "P","Y","Y","Y","N" "P","Y","Y","N","N" "P","N","Y","Y","N" "P","N","Y","Y","N" "N","Y","Y","Y","Y" "N","Y","Y","N","Y" "N","N","N","N","Y" "N","N","N","N","N" "N","N","N","N","Y" "N","N","N","N","N" contacts.csv
- 3. > contacts.train<-read.table("contacts_train.csv", header=T, sep=",") > contacts.train Pred Young Myope Astimatic Tear 1 P Y Y Y N 2 P Y Y N N 3 P N Y Y N 4 P N Y Y N 5 N Y Y Y Y 6 N Y Y N Y 7 N N N N Y 8 N N N N N 9 N N N N Y 10 N N N N N
- 4. > contacts.train[1,] Pred Young Myope Astimatic Tear 1 P Y Y Y N > contacts.train[,2] [1] Y Y N N Y Y N N N N Levels: N Y > contacts.train[,"Pred"] [1] P P P P N N N N N N Levels: N P > contacts.train$Pred [1] P P P P N N N N N N Levels: N P > contacts.train[c(-1,-3,-5,-7,-9),] Pred Young Myope Astimatic Tear 2 P Y Y N N 4 P N Y Y N 6 N Y Y N Y 8 N N N N N 10 N N N N N
- 5. > class(contacts.train) [1] "data.frame" > forecast <- data.frame(date=c("10/1","10/2","10/3"), weather=c("sunny","sunny","rain")) > forecast date weather 1 10/1 sunny 2 10/2 sunny 3 10/3 rain > forecast$weather [1] sunny sunny rain Levels: rain sunny > forecast$date [1] 10/1 10/2 10/3
- 6. > nrow(contacts.train) [1] 10 > ncol(contacts.train) [1] 5 > rownames(contacts.train) [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" > colnames(contacts.train) [1] "Pred" "Young" "Myope" "Astimatic" "Tear" > colnames(contacts.train)[2] [1] "Young" > colnames(contacts.train)[2] <- "Old" > colnames(contacts.train) [1] "Pred" "Old" "Myope" "Astimatic" "Tear" > colnames(contacts.train)[2] <- "Young"
- 7. > contacts.train$Young [1] Y Y N N Y Y N N N N Levels: N Y > order(contacts.train$Young) [1] 3 4 7 8 9 10 1 2 5 6 > contacts.train[order(contacts.train$Young),] Pred Young Myope Astimatic Tear 3 P N Y Y N 4 P N Y Y N 7 N N N N Y 8 N N N N N 9 N N N N Y 10 N N N N N 1 P Y Y Y N 2 P Y Y N N 5 N Y Y Y Y 6 N Y Y N Y
- 8. > library("mvpart") > rpart(Young~., data=contacts.train, method="class") n= 10 node), split, n, loss, yval, (yprob) * denotes terminal node 1) root 10 4 N (0.6000000 0.4000000) 2) Myope=N 4 0 N (1.0000000 0.0000000) * 3) Myope=Y 6 2 Y (0.3333333 0.6666667) * > rpart(Young~., data=contacts.train, method="class", control=rpart.control(cp=-1)) n= 10 node), split, n, loss, yval, (yprob) * denotes terminal node 1) root 10 4 N (0.6000000 0.4000000) 2) Myope=N 4 0 N (1.0000000 0.0000000) * 3) Myope=Y 6 2 Y (0.3333333 0.6666667) 6) Pred=P 4 2 N (0.5000000 0.5000000) * 7) Pred=N 2 0 Y (0.0000000 1.0000000) *
- 9. IRIS • http://archive.ics.uci.edu/ml/machine-learning-databases/iris/ iris.data • iris.name • (setosa, versicolor, virginia) • http://togodb.sel.is.ocha.ac.jp/ > iris.train <- read.table("iris_train.csv", sep=",", header=T) > length(rownames(iris.train)) [1] 120 > length(colnames(iris.train)) [1] 5 > hist(iris.train$Sepal.length) > hist(iris.train$Petal.length)
- 10. > library(“mvpart”) > rpart(Class~., data=iris.train, method="class", control=rpart.control(cp=.1)) n= 120 node), split, n, loss, yval, (yprob) * denotes terminal node 1) root 120 77 Iris-setosa (0.35833333 0.34166667 0.30000000) 2) Petal.length< 2.45 43 0 Iris-setosa (1.00000000 0.00000000 0.00000000) * 3) Petal.length>=2.45 77 36 Iris-versicolor (0.00000000 0.53246753 0.46753247) 6) Petal.length< 4.75 37 1 Iris-versicolor (0.00000000 0.97297297 0.02702703) * 7) Petal.length>=4.75 40 5 Iris-virginica (0.00000000 0.12500000 0.87500000) *
- 11. > iris.dtree<-rpart(Class~., data=iris.train, method="class", control=rpart.control(cp=.1)) > plot.new() > plot(iris.dtree,uniform=T,margin=0.5) > text(iris.dtree,use.n=T,all.leaves=F)
- 12. > plot(iris.train$Petal.length, iris.train$Petal.width, pch = c(1,2,3)[unclass(iris.train$Class)])
- 13. > iris.test <- read.table("iris_test.csv", sep=",", header=T) > iris.predict <- predict(iris.dtree, iris.test[1:4], type="class") > iris.predict 2 4 18 34 Iris-setosa Iris-setosa Iris-setosa Iris-setosa ... > iris.predict == iris.test$Class [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE [11] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE [21] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE > sum(iris.predict == iris.test$Class) / length(iris.test$Class) [1] 0.9666667 > sum(iris.predict != iris.test$Class) / length(iris.test$Class) [1] 0.03333333
- 14. • • • • • rpart control=rpart.control(cp=.1) .1 • 10 • 3 2 3