Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- ### question 4 hint ####
- library(MASS)
- library(class)
- Boston$medv01 <- ifelse(Boston$medv > median(Boston$medv),1,0)
- names(Boston)
- # Choice of subsets
- plot(Boston)
- #subset 1: "lstat","rm"
- #subset 2: "lstat", "rm","age","rad"
- #subset 3: all predictors
- Boston$medv <- NULL
- names(Boston)
- ### try three values of K #######
- ##### K=1 #######
- x.train <- Boston[,c("lstat","rm")]
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(x.train, y.train, k=1) !=y.train)
- test.err
- x.train <- Boston[,c("lstat", "rm","age","rad")]
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=1) !=y.train)
- test.err
- x.train <- Boston[,-14]### using all the predictors
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=1) !=y.train)
- test.err
- x.train <- Boston[,c("lstat","rm")]
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(x.train, y.train, k=3) !=y.train)
- test.err
- x.train <- Boston[,c("lstat", "rm","age","rad")]
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=3) !=y.train)
- test.err
- x.train <- Boston[,-14]### using all the predictors
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=3) !=y.train)
- test.err
- x.train <- Boston[,c("lstat","rm")]
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(x.train, y.train, k=10) !=y.train)
- test.err
- x.train <- Boston[,c("lstat", "rm","age","rad")]
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=10) !=y.train)
- test.err
- x.train <- Boston[,-14]### using all the predictors
- y.train <- Boston[,14]
- test.err <- mean(knn.cv(x.train, y.train, k=10) !=y.train)
- test.err
- ###SCALED DATA####
- X.train <- Boston[,c("lstat","rm")]
- X.train.scaled <- scale(X.train)
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=1) !=y.train)
- test.err
- X.train <- Boston[,c("lstat", "rm","age","rad")]
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=1) !=y.train.scaled)
- test.err
- X.train <- Boston[,-14]### using all the predictors
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=1) !=y.train)
- test.err
- X.train <- Boston[,c("lstat","rm")]
- X.train.scaled <- scale(X.train)
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=3) !=y.train)
- test.err
- X.train <- Boston[,c("lstat", "rm","age","rad")]
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=3) !=y.train.scaled)
- test.err
- X.train <- Boston[,-14]### using all the predictors
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=3) !=y.train)
- test.err
- X.train <- Boston[,c("lstat","rm")]
- X.train.scaled <- scale(X.train)
- y.train <- Boston[,"medv01"]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=10) !=y.train)
- test.err
- X.train <- Boston[,c("lstat", "rm","age","rad")]
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=10) !=y.train.scaled)
- test.err
- X.train <- Boston[,-14]### using all the predictors
- X.train.scaled <- scale(X.train)
- y.train.scaled <- Boston[,14]
- test.err <- mean(knn.cv(X.train.scaled, y.train, k=10) !=y.train)
- test.err
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement