Author : tmlab / Date : 2016. 10. 4. 01:22 / Category : Lecture/R 프로그래밍
seg.df <- read.csv("http://goo.gl/qw303p")
head(seg.df)
summary(seg.df)
str(seg.df)
attach(seg.df)
attach(seg.df)
mean(income[Segment == "Moving up"])
mean(income[Segment == "Moving up" & subscribe == "subNo"])
apply(seg.df[,c(1,3,4)], MARGIN=2, FUN=mean)
apply(seg.df[Segment == 'Moving up', c(1,3,4)], MARGIN=2, FUN=mean)
table(ownHome,subscribe)
table(kids)
table(Segment,kids, subscribe)
by(income, Segment, mean)
by(income, list(Segment, subscribe), mean)
aggregate(income, list(Segment), mean)
aggregate(income ~ Segment, data=seg.df, mean)
aggregate(income ~ Segment + ownHome, data = seg.df, mean)
aggregate(income ~ Segment + ownHome + subscribe, data = seg.df, mean)
cut.data = aggregate(income ~ Segment + ownHome + subscribe, data = seg.df, mean)
cut.data$income2 = cut(agr.data$income,
breaks = c(0,20000,30000,40000,50000,60000,70000),
labels = c('2만이하', '2만~3만', '3만~4만', '4만~5만','5만~6만', '6만이상'))
cut.data
grep("ap", c("apple", "Apple", "apple2", "bbapple")) #ap를 포함하는 원소들의 위치
grepl("ap", c("apple", "Apple", "apple2", "bbapple")) #ap를 포함하는 원소들의 위치
grep("ap", c("apple", "Apple", "apple2", "bbapple"), value=TRUE) #ap를 포함하는 원소
grep("[1-3]", c("apple1", "apple2", "apple3", "apple4", "Apple1")) #1,2,3을 포함하는 원소위치
seg.df$ownHome = as.character(seg.df$ownHome)
grep('Yes', seg.df$ownHome)
seg.df$Segment = gsub(" ", "", seg.df$Segment)
head(seg.df)