UTS DatMin

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

## , , Survived = No
## 
##         Age
## Sex      Child Adult
##   Male       0     0
##   Female     0     0
## 
## , , Survived = Yes
## 
##         Age
## Sex      Child Adult
##   Male       0     0
##   Female     0     0

summary(Titanic)

## Number of cases in table: 2201 
## Number of factors: 4 
## Test for independence of all factors:
##  Chisq = 1637.4, df = 25, p-value = 0
##  Chi-squared approximation may be incorrect

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)
summary(nilai)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    50.0    75.0    80.0    80.4    89.5   100.0

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 = 0.2)
training_set=subset(BreastCancer,split==TRUE)
test_set=subset(BreastCancer,split==FALSE) 
dim(training_set)

## [1] 128  11

dim(test_set)

## [1] 571  11

topredict_set<-test_set[1:4]