#Elena Giasi
Titanic<-read.csv("TitanicData.csv")
View(Titanic)
man=subset(Titanic,Titanic$Survived == 1)
View(man)
dim(Titanic)[1]
## [1] 889
nrow(Titanic)
## [1] 889
survived=subset(Titanic,Titanic$Survived==1)
dim(survived)[1]
## [1] 340
View(survived)
survived=subset(Titanic,Titanic$Survived==1)
dim(survived)
## [1] 340 8
Titanic$Survived<-factor(Titanic$Survived,levels = c(0,1),labels =c("No","Yes") )
library(vcd)
## Loading required package: grid
mytable<-with(Titanic,table(Survived))
mytable
## Survived
## No Yes
## 549 340
prop.table(mytable)*100
## Survived
## No Yes
## 61.75478 38.24522
mytable2<-xtabs(~Titanic$Pclass+Titanic$Survived,data=Titanic)
mytable2
## Titanic$Survived
## Titanic$Pclass No Yes
## 1 80 134
## 2 97 87
## 3 372 119
(addmargins(mytable2))
## Titanic$Survived
## Titanic$Pclass No Yes Sum
## 1 80 134 214
## 2 97 87 184
## 3 372 119 491
## Sum 549 340 889
barplot(mytable2,main = "Survival by Passenger Class", xlab="Passenger class", ylab = "Frequency", col = c("grey","black"),legend=rownames(mytable2),beside = TRUE)
View(Titanic)
qwe= subset(Titanic,Titanic$Survived=="Yes")
View(qwe)
nrow(qwe)
## [1] 340
survived1=subset(Titanic, Titanic$Survived=="Yes" & Titanic$Pclass==1)
View(survived1)
dim(survived1)[1]
## [1] 134
nrow(survived1)
## [1] 134
prop.table(mytable2)
## Titanic$Survived
## Titanic$Pclass No Yes
## 1 0.08998875 0.15073116
## 2 0.10911136 0.09786277
## 3 0.41844769 0.13385827
mytable3<-xtabs(~Survived+Pclass+Sex, data = Titanic)
mytable3
## , , Sex = female
##
## Pclass
## Survived 1 2 3
## No 3 6 72
## Yes 89 70 72
##
## , , Sex = male
##
## Pclass
## Survived 1 2 3
## No 77 91 300
## Yes 45 17 47
ftable(addmargins(mytable3))
## Sex female male Sum
## Survived Pclass
## No 1 3 77 80
## 2 6 91 97
## 3 72 300 372
## Sum 81 468 549
## Yes 1 89 45 134
## 2 70 17 87
## 3 72 47 119
## Sum 231 109 340
## Sum 1 92 122 214
## 2 76 108 184
## 3 144 347 491
## Sum 312 577 889
ftable(addmargins(prop.table(mytable3,c(1,2)),3)*100)
## Sex female male Sum
## Survived Pclass
## No 1 3.750000 96.250000 100.000000
## 2 6.185567 93.814433 100.000000
## 3 19.354839 80.645161 100.000000
## Yes 1 66.417910 33.582090 100.000000
## 2 80.459770 19.540230 100.000000
## 3 60.504202 39.495798 100.000000
par(mfrow=c(1,2))
mytable2<- xtabs(~Survived+Pclass,data=Titanic,Titanic$Sex=="male")
mytable2
## Pclass
## Survived 1 2 3
## No 77 91 300
## Yes 45 17 47
barplot(mytable2,main = "Males",
ylab = "Nr of passengers",
col = c("gray", "white"),legend=rownames(mytable2),beside = TRUE)
mytable4<- xtabs(~Survived+Pclass,data=Titanic,Titanic$Sex=="female")
mytable4
## Pclass
## Survived 1 2 3
## No 3 6 72
## Yes 89 70 72
barplot(mytable4,main = "Females",
ylab = "Nr of passengers",
col = c("gray", "white"),legend=rownames(mytable4),beside = TRUE)
mytable4
## Pclass
## Survived 1 2 3
## No 3 6 72
## Yes 89 70 72
View(mytable4)
survivors<-xtabs(~Titanic$Survived+Titanic$Sex,data = Titanic)
survivors
## Titanic$Sex
## Titanic$Survived female male
## No 81 468
## Yes 231 109
chisq.test(survivors)[3]
## $p.value
## [1] 3.77991e-58
sex<-factor(Titanic$Sex,levels = c("female","male"),
labels = c("F","M"))
tab<-xtabs(~Survived+Pclass+Sex, data = Titanic)
mosaicplot(tab, main = "Mosaic Plot Survors",color = c("green","white","red"))
dead<-subset(Titanic,Titanic$Survived==0)
averagedead<-mean((dead$Age))
averagealived<-mean(survived$Age)
matrix<-matrix(c(averagedead,averagealived))
colnames(matrix)<- "Average"
row.names(matrix)<-c("Dead","Alived")
matrix
## Average
## Dead NaN
## Alived 28.42382
boxplot(Titanic$Age~Titanic$Survived,data = Titanic,
main="Age of alived and dead",
xlab="age",
ylab="alive or dead")
