This is continuation of example 1. In this script, we want to implement few things to reduce “mean absolute error”

• Choosing the sample random and include all available features
• Using normalization instead of z-core standardization (used in example1)

Here is the function for normalization

normalize <- function(x) {
    norm <- ((x - min(x))/(max(x) - min(x)))
    return (norm)
}


marketSample <- function(smarkt, test_pct = 20) {
    train_pct = 100 - test_pct
    #Seeding for reproducibility
    set.seed(test_pct)
    test_indx <- sample(nrow(smarkt), nrow(smarkt) * test_pct/100, replace=FALSE)
    test.all <- smarkt[test_indx,]
    
    test.data <- test.all[,-9]
    test.direction <- test.all$Direction
    
    #Prep. training data  which is noting but remaing test data
    train.all <- smarkt[-test_indx,]
    train.data <- train.all[,-9]
    train.direction <- train.all$Direction
    
    rtrn_list <- list(testdata = test.data, testdir = test.direction, traindata = train.data, traindir = train.direction)
    
    return(rtrn_list)
    
}

Data prep using normalize function

library(ISLR)
input.norml <- as.data.frame(lapply(Smarket[,-9],normalize))
input.norml$Direction <- Smarket$Direction

temp_list <- marketSample(input.norml, 20)
train.data <- temp_list$traindata
train.dir <- temp_list$traindir

test.data <- temp_list$testdata
test.dir <- temp_list$testdir

rm(temp_list)

Quickly evaluating knn algorithm

library(class)
knn.pred <- knn(train = train.data,test = test.data,cl = train.dir,k = 3)
table(knn.pred,test.dir)

##         test.dir
## knn.pred Down  Up
##     Down  108  22
##     Up     14 106

mean(knn.pred == test.dir)

## [1] 0.856

Above 80% cases are correctly predicted which is much greater than example1.