Report of Titanic: 2nd degree families and majority voting

Data From https://www.kaggle.com/erikbruin/titanic-2nd-degree-families-and-majority-voting/data

TestData = read.csv('./DATA/all/test.csv')

使用 split & apply 去分割出姓名與稱謂

心得…

Names = TestData$Name
splitTitle <- function(x){
  strsplit(x, split='[,.]')[[1]]
}
Temp = sapply(as.character(Names), splitTitle)

TestData$Surname <- Temp[1,]
TestData$Title <- Temp[2,]

library(knitr)

## Warning: package 'knitr' was built under R version 3.5.1

kable(table(TestData$Sex, TestData$Title))

	Col	Dona	Dr	Master	Miss	Mr	Mrs	Ms	Rev
female	0	1	0	0	78	0	72	1	0
male	2	0	1	21	0	240	0	0	2

all$Title[all$Title %in% c("Mlle", "Ms")] <- "Miss"
all$Title[all$Title== "Mme"] <- "Mrs"
all$Title[!(all$Title %in% c('Master', 'Miss', 'Mr', 'Mrs'))] <- "Rare Title"
all$Title <- as.factor(all$Title)
kable(table(all$Sex, all$Title))