![1
> m <- matrix((1:9)**2, nrow=3) > l <- list(a=1:3, b=4:6)
> m > l
[,1] [,2] [,3] $a
[1,] 1 16 49 [1] 1 2 3
[2,] 4 25 64
[3,] 9 36 81 $b
> apply(m, 1, sum) [1] 4 5 6
[1] 66 93 126
> apply(m, 2, sum) > lapply(l, sum)
[1] 14 77 194 $a
> apply(m, c(1,2), sqrt) [1] 6
[,1] [,2] [,3]
[1,] 1 4 7 $b
[2,] 2 5 8 [1] 15
[3,] 3 6 9
> sapply(l, sum)
a b
6 15
8](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-8-320.jpg)
![2
> m <- matrix((1:9)**2, nrow=3) > l <- list(a=1:3, b=4:6)
> m > l
[,1] [,2] [,3] $a
[1,] 1 16 49 [1] 1 2 3
[2,] 4 25 64
[3,] 9 36 81 $b
> apply(m, 1, sum) [1] 4 5 6
[1] 66 93 126
> apply(m, 2, sum) > lapply(l, sum)
[1] 14 77 194 $a
> apply(m, c(1,2), sqrt) [1] 6
[,1] [,2] [,3]
[1,] 1 4 7 $b
[2,] 2 5 8 [1] 15
[3,] 3 6 9
> sapply(l, sum)
a b
6 15
9](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-9-320.jpg)
![K-NN
•
> iris.train <- read.table("iris_train.csv", sep=",", header=T)
> iris.test <- read.table("iris_test.csv", sep=",", header=T)
> q <- iris.test[1,1:4]
> diff <- sweep(iris.train[1:4], 2, t(q))
> diff * diff
> distquery <- apply(diff * diff, 1, sum)
> sort(distquery)
> order(distquery)
10](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-10-320.jpg)
![1
> iris.train[order(distquery)[1:5],]
> iris.train[order(distquery)[1:5],]$Class
> knnclasses <- table(iris.train[order(distquery)[1:5],]$Class)
> as.factor(table(knnclasses)
> sortedtable <- sort(as.factor(table(knnclasses)), decreasing=T)
> labels(sortedtable)[1]
> predclass <- labels(sortedtable)[1]
> predclass == iris.test$Class[1]
11](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-11-320.jpg)
![> knnpredict <- function(train,class,query,k) {
+ diff <- sweep(train,2,query)
+ distquery <- apply(diff * diff, 1, sum)
+ knnclasses <- class[order(distquery)[1:k]]
+ sortedtable <- sort(as.factor(table(knnclasses)), decreasing=T)
+ labels(sortedtable)[1]
+ }
> knnpredict(iris.train[1:4], iris.train$Class, t(iris.test[1,1:4]),
5)
> knnpredict(iris.train[1:4], iris.train$Class, t(iris.test[10,1:4]),
1)
> for (i in 1:length(rownames(iris.test))) {
+ pred <- knnpredict(iris.train[1:4], iris.train$Class, t(iris.test
[i,1:4]),10)
+ result <- pred == iris.test[i,]$Class
+ cat(paste(pred, iris.test[i,]$Class, result, sep="t"))
+ cat("n")
+ } 12](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-12-320.jpg)
![> resvec <- c()
> for (i in 1:30) {
+ pred <- knnpredict(iris.train[1:4], iris.train$Class, t(iris.test
[i,1:4]),10)
+ resvec <- append(resvec, pred == iris.test[i,]$Class)
+ }
> sum(resvec)/length(resvec)
13](https://image.slidesharecdn.com/dataminingr4th-101226215415-phpapp02/85/Datamining-r-4th-13-320.jpg)
Datamining r 4th
- 1. R: k apply sesejun@is.ocha.ac.jp 2009/11/19
- 2. USPS
- 3. ImageName Class 0,0 0,1 0,2 0,3 0,4 img_2_00_02 1 0 0 0 0 0 img_2_00_03 1 0 38 22 0 0 img_2_00_05 1 13 0 64 13 42 ... img_0_00_09 -1 34 53 0 38 0 img_0_00_28 -1 0 64 0 98 93 img_0_01_08 -1 13 0 0 59 13 img_0_03_05 -1 34 34 0 0 0
- 5. img_3_29_25 img_5_03_31 img_3_06_30 img_3_17_08
- 6. k-NN
- 7. Apply Family • , , • for • apply(X, 1, ) apply(X, 2, ) apply(X, c(1,2), ) lapply(X, ) dataframe sapply(X, ) table sweep(X, M,V) X (M=1) (M=2) (M=c(1,2)) V 7
- 8. 1 > m <- matrix((1:9)**2, nrow=3) > l <- list(a=1:3, b=4:6) > m > l [,1] [,2] [,3] $a [1,] 1 16 49 [1] 1 2 3 [2,] 4 25 64 [3,] 9 36 81 $b > apply(m, 1, sum) [1] 4 5 6 [1] 66 93 126 > apply(m, 2, sum) > lapply(l, sum) [1] 14 77 194 $a > apply(m, c(1,2), sqrt) [1] 6 [,1] [,2] [,3] [1,] 1 4 7 $b [2,] 2 5 8 [1] 15 [3,] 3 6 9 > sapply(l, sum) a b 6 15 8
- 9. 2 > m <- matrix((1:9)**2, nrow=3) > l <- list(a=1:3, b=4:6) > m > l [,1] [,2] [,3] $a [1,] 1 16 49 [1] 1 2 3 [2,] 4 25 64 [3,] 9 36 81 $b > apply(m, 1, sum) [1] 4 5 6 [1] 66 93 126 > apply(m, 2, sum) > lapply(l, sum) [1] 14 77 194 $a > apply(m, c(1,2), sqrt) [1] 6 [,1] [,2] [,3] [1,] 1 4 7 $b [2,] 2 5 8 [1] 15 [3,] 3 6 9 > sapply(l, sum) a b 6 15 9
- 10. K-NN • > iris.train <- read.table("iris_train.csv", sep=",", header=T) > iris.test <- read.table("iris_test.csv", sep=",", header=T) > q <- iris.test[1,1:4] > diff <- sweep(iris.train[1:4], 2, t(q)) > diff * diff > distquery <- apply(diff * diff, 1, sum) > sort(distquery) > order(distquery) 10
- 11. 1 > iris.train[order(distquery)[1:5],] > iris.train[order(distquery)[1:5],]$Class > knnclasses <- table(iris.train[order(distquery)[1:5],]$Class) > as.factor(table(knnclasses) > sortedtable <- sort(as.factor(table(knnclasses)), decreasing=T) > labels(sortedtable)[1] > predclass <- labels(sortedtable)[1] > predclass == iris.test$Class[1] 11
- 12. > knnpredict <- function(train,class,query,k) { + diff <- sweep(train,2,query) + distquery <- apply(diff * diff, 1, sum) + knnclasses <- class[order(distquery)[1:k]] + sortedtable <- sort(as.factor(table(knnclasses)), decreasing=T) + labels(sortedtable)[1] + } > knnpredict(iris.train[1:4], iris.train$Class, t(iris.test[1,1:4]), 5) > knnpredict(iris.train[1:4], iris.train$Class, t(iris.test[10,1:4]), 1) > for (i in 1:length(rownames(iris.test))) { + pred <- knnpredict(iris.train[1:4], iris.train$Class, t(iris.test [i,1:4]),10) + result <- pred == iris.test[i,]$Class + cat(paste(pred, iris.test[i,]$Class, result, sep="t")) + cat("n") + } 12
- 13. > resvec <- c() > for (i in 1:30) { + pred <- knnpredict(iris.train[1:4], iris.train$Class, t(iris.test [i,1:4]),10) + resvec <- append(resvec, pred == iris.test[i,]$Class) + } > sum(resvec)/length(resvec) 13
- 14. 3 1. IRIS 1. IRIS 4 ("Sepal.length","Sepal.width", "Petal.length","Petal.width") 2. IRIS K-NN 2. USPS 1. USPS 5-NN (0-9) 2. K-NN K 3. USPS K-NN K-NN K 4. USPS 14