UTS

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

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

data1 <- data.frame(Titanic)  
freq_data <- data1$Freq
Q1 <- quantile(freq_data, 0.25)     
Q3 <- quantile(freq_data, 0.75)     
IQR <- Q3 - Q1                     
lower_bound <- Q1 - 1.5 * IQR      
upper_bound <- Q3 + 1.5 * IQR      

outliers <- freq_data[freq_data < lower_bound | freq_data > 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)
rata_rata <- mean(nilai)
median <- median(nilai)
standar_deviasi <- sd(nilai)

cat("Rata-rata:", rata_rata, "\nMedian:", median, "\nStandar Deviasi:", standar_deviasi)

## Rata-rata: 80.4 
## Median: 80 
## Standar Deviasi: 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

set.seed(110)
split=sample.split(BreastCancer, SplitRatio = 0.8)
training_set=subset(BreastCancer,split==TRUE)
test_set=subset(BreastCancer,split==FALSE)

dim(training_set)

## [1] 509  11

dim(test_set)

## [1] 190  11

library(mlbench)
data("BreastCancer")
library(caTools)
set.seed(110)
split=sample.split(BreastCancer, SplitRatio = 0.2)
test_set=subset(BreastCancer,split==FALSE)
training_set=subset(BreastCancer,split==TRUE)

dim(training_set)

## [1] 128  11

dim(test_set)

## [1] 571  11