UTS

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.4.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)

## Warning: package 'tidyr' was built under R version 4.4.2

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.4.2

data1<-data.frame(Titanic)
head(Titanic)

## , , Age = Child, Survived = No
## 
##       Sex
## Class  Male Female
##   1st     0      0
##   2nd     0      0
##   3rd    35     17
##   Crew    0      0
## 
## , , Age = Adult, Survived = No
## 
##       Sex
## Class  Male Female
##   1st   118      4
##   2nd   154     13
##   3rd   387     89
##   Crew  670      3
## 
## , , Age = Child, Survived = Yes
## 
##       Sex
## Class  Male Female
##   1st     5      1
##   2nd    11     13
##   3rd    13     14
##   Crew    0      0
## 
## , , Age = Adult, Survived = Yes
## 
##       Sex
## Class  Male Female
##   1st    57    140
##   2nd    14     80
##   3rd    75     76
##   Crew  192     20

colSums(is.na(data1))

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

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)
mean(nilai)

## [1] 80.4

median(nilai)

## [1] 80

sd(nilai)

## [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

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