Titanic = read.csv(“https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/Titanic.csv”, header = TRUE) titanic <- data.frame(Titanic) summary(titanic) X Name
Min. : 1 Carlsson, Mr Frans Olof : 2
1st Qu.: 329 Connolly, Miss Kate : 2
Median : 657 Kelly, Mr James : 2
Mean : 657 Abbing, Mr Anthony : 1
3rd Qu.: 985 Abbott, Master Eugene Joseph: 1
Max. :1313 Abbott, Mr Rossmore Edward : 1
(Other) :1304
PClass Age Sex Survived
* : 1 Min. : 0.17 female:462 Min. :0.0000
1st:322 1st Qu.:21.00 male :851 1st Qu.:0.0000
2nd:279 Median :28.00 Median :0.0000
3rd:711 Mean :30.40 Mean :0.3427
3rd Qu.:39.00 3rd Qu.:1.0000
Max. :71.00 Max. :1.0000
NA’s :557
SexCode
Min. :0.0000
1st Qu.:0.0000
Median :0.0000
Mean :0.3519
3rd Qu.:1.0000
Max. :1.0000
mean(titanic\(Age, na.rm=TRUE) [1] 30.39799 median(titanic\)Age, na.rm = TRUE) [1] 28 mean(titanic\(Survived, na.rm = TRUE) [1] 0.3427266 median(titanic\)Survived, na.rm = TRUE) [1] 0
newdata <- subset(titanic,Survived == 1, select= c(“Age”, “Sex”, “PClass”))
colnames(newdata) <- c(“age”, “gender”, “class”)
summary (newdata) age gender class
Min. : 0.17 female:308 * : 0
1st Qu.:19.00 male :142 1st:193
Median :28.00 2nd:119
Mean :29.36 3rd:138
3rd Qu.:39.00
Max. :69.00
NA’s :137
aggregate(age ~ class, newdata, mean) class age 1 1st 36.77640 2 2nd 24.22531 3 3rd 22.46154
mean(newdata$age, na.rm = TRUE) [1] 29.35958
levels(newdata\(class)[levels(newdata\)class)==“2nd”] <- “second” levels(newdata\(class)[levels(newdata\)class) == “3rd”] <- “third” levels(newdata\(class)[levels(newdata\)class) == “1st”] <- “first”
newdata[c(17, 200, 400), ] age gender class 28 30 female first 339 4 female second 979 NA female third
Titanic = read.csv(“https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/Titanic.csv”, header = TRUE)