UTS Data Mining

data1 <- data.frame(Titanic)
colSums(is.na(data1))

##    Class      Sex      Age Survived     Freq 
##        0        0        0        0        0

freq <- data1$Freq

Q1 <- quantile(freq, 0.25)
Q3 <- quantile(freq, 0.75)
IQR <- Q3 - Q1

lower_bound <- Q1 - 1.5 * IQR
upper_bound <- Q3 + 1.5 * IQR

outliers <- freq[freq < lower_bound | freq > upper_bound]
length(outliers)

## [1] 3

sum(duplicated(data1))

## [1] 0

nilai <- c(70, 75, 80, 85, 85, 90, 95, 100, 60, 75, 77, 85, 90, 98, 68, 92, 85, 66, 75, 80, 72, 84, 50, 69, 76, 80, 90, 95, 88, 77)

mean(nilai)    # rata-rata

## [1] 80.4

median(nilai)  # median

## [1] 80

sd(nilai)      # standar deviasi

## [1] 11.48792

library(mlbench)

## Warning: package 'mlbench' was built under R version 4.4.3

data("BreastCancer")
library(caTools)

## Warning: package 'caTools' was built under R version 4.4.3

# Bersihkan NA
bc <- na.omit(BreastCancer)

set.seed(110)
split <- sample.split(bc$Class, SplitRatio = 0.8)
train <- subset(bc, split == TRUE)
test <- subset(bc, split == FALSE)

nrow(train)  

## [1] 546

nrow(test)   

## [1] 137