Lesson 2.Answer
Sung Won Kang
2016년 11월 5일
- 자료 준비(교재 pp. 37-48)
#data=read.csv("C:/work_2016/Rstat/Lesson 2/data/ch02.csv",header=F,na.strings=c("."))
data=read.csv(file="../data/ch02.csv",header=F,na.strings=c("."))
str(data)## 'data.frame': 468284 obs. of 5 variables:
## $ V1: int 1 1 1 1 1 1 1 1 1 1 ...
## $ V2: int 0 0 0 0 0 0 0 0 0 0 ...
## $ V3: int 3 3 3 3 3 3 3 3 3 3 ...
## $ V4: int 1 1 1 1 1 1 1 1 1 1 ...
## $ V5: int NA NA NA NA NA NA NA NA NA NA ...data$V1=factor(data$V1,levels=c(1,2),labels=c("남자","여자"))
data$V3=factor(data$V3,levels=(1:14),
labels=c("가구주","가구주의 배우자","자녀","자녀의배우자","가구주의 부모",
"배우자의 부모","손자녀및배우자","증손자녀및배우자","조부모","형제자매및배우자","형제자매의자녀및배우자",
"부모의형제자매및배우자","기타친인척","동거인"))
data$V4=factor(data$V4,levels=1:8,
labels=c("안받음","초등학교","중학교","고등학교","대학4년제미만","대학4년제이상","석사과정","박사과정"))
str(data)## 'data.frame': 468284 obs. of 5 variables:
## $ V1: Factor w/ 2 levels "남자","여자": 1 1 1 1 1 1 1 1 1 1 ...
## $ V2: int 0 0 0 0 0 0 0 0 0 0 ...
## $ V3: Factor w/ 14 levels "가구주","가구주의 배우자",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ V4: Factor w/ 8 levels "안받음","초등학교",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ V5: int NA NA NA NA NA NA NA NA NA NA ...save.image("data.rda")- graph
- 산점도 1.(Scatterplot)
str(cars)## 'data.frame': 50 obs. of 2 variables:
## $ speed: num 4 4 7 7 8 9 10 10 10 11 ...
## $ dist : num 2 10 4 22 16 10 18 26 34 17 ...summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00#그냥 보는 그래프
plot(cars$speed,cars$dist)
plot(cars)
#남에게 보여주는 그래프
plot(cars$speed,cars$dist, main="속도와 제동거리", xlab="속도(mph)",ylab="제동거리(km)",pch=1,col="red")
# pch =1 : 동그라미로 표시
# col ="red": 표시 색깔은 빨간색 - 산점도 2.(Scatterplot): 시계열(time series)
str(Nile)## Time-Series [1:100] from 1871 to 1970: 1120 1160 963 1210 1160 1160 813 1230 1370 1140 ...summary(Nile)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 456.0 798.5 893.5 919.4 1032.0 1370.0#그냥 보는 그래프
plot(Nile)
plot((1871:1970),Nile, xlab="Time",type="l")
plot((start(Nile)[1]:end(Nile)[1]),Nile, xlab="Time",type="l")
#남에게 보여주는 그래프
plot(Nile, main="나일강의 연도별 유량변화", xlab="연도",ylab="유량")#선그래프
plot(Nile, type="p",main="나일강의 연도별 유량변화", xlab="연도",ylab="유량")#점그래프
- 막대그래프와 히스토그램: barplot(), hist()
load("data.rda")
str(data)## 'data.frame': 468284 obs. of 5 variables:
## $ V1: Factor w/ 2 levels "남자","여자": 1 1 1 1 1 1 1 1 1 1 ...
## $ V2: int 0 0 0 0 0 0 0 0 0 0 ...
## $ V3: Factor w/ 14 levels "가구주","가구주의 배우자",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ V4: Factor w/ 8 levels "안받음","초등학교",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ V5: int NA NA NA NA NA NA NA NA NA NA ...summary(data)## V1 V2 V3
## 남자:226965 Min. : 0.00 가구주 :179293
## 여자:241319 1st Qu.:22.00 자녀 :145533
## Median :40.00 가구주의 배우자 :106311
## Mean :39.34 가구주의 부모 : 12069
## 3rd Qu.:55.00 손자녀및배우자 : 7832
## Max. :85.00 형제자매및배우자: 5332
## (Other) : 11914
## V4 V5
## 고등학교 :134246 Min. : 0.00
## 대학4년제이상: 81110 1st Qu.: 1.00
## 초등학교 : 80710 Median : 1.00
## 중학교 : 55704 Mean : 1.32
## 안받음 : 51085 3rd Qu.: 2.00
## 대학4년제미만: 50753 Max. :12.00
## (Other) : 14676 NA's :310308table(data$V5)##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 30788 69624 41010 11165 3667 1228 346 104 21 8 4 10
## 12
## 1table.V5=table(data$V5)# 자녀 수의 분포
barplot(table.V5)
barplot(table.V5, main="출생아별 빈도", xlab="출생아수",ylab="빈도")
table(data$V1,data$V4)#남녀-교육수준 분포##
## 안받음 초등학교 중학교 고등학교 대학4년제미만 대학4년제이상
## 남자 19161 34214 26588 66548 25673 45530
## 여자 31924 46496 29116 67698 25080 35580
##
## 석사과정 박사과정
## 남자 7107 2144
## 여자 4634 791tableV1.V4=table(data$V1,data$V4)
barplot(tableV1.V4)# 내가 보기용. 어? 뭔가 부족하네?
barplot(tableV1.V4, legend.text=T)#내가 보기용
barplot(tableV1.V4, legend.text=T,beside=T)#나란히 보기
barplot(tableV1.V4, legend.text=T,horiz=T)#옆으로 뻗는 막대그래프
barplot(tableV1.V4, legend.text=T,horiz=T,beside=T)#옆으로 뻗는 막대그래프
#남에게 보여주기용
barplot(tableV1.V4, legend.text=T, col=c("orange","green"), main="학력에따른 성별인원수",xlab="학력",ylab="빈도")
hist(data$V2)#나이의 분포
hist(data$V2, breaks=c(seq(0,90,10)))#나이의 분포
#보고용
hist(data$V2, breaks=c(seq(0,90,10)), right=F,main="연령별분포",xlab="연령", ylab="빈도")
- 파이그래프: pie()
table(data$V4)##
## 안받음 초등학교 중학교 고등학교 대학4년제미만
## 51085 80710 55704 134246 50753
## 대학4년제이상 석사과정 박사과정
## 81110 11741 2935table.V4=table(data$V4)
pie(table.V4)#내가 보가
pie(table.V4, main="학력수준별 비중")
jpeg(filename="pie.jpg")
pie(table.V4, main="학력수준별 비중")
dev.off()## quartz_off_screen
## 22.모수와 통계량(parameter, statistics) - rara의 Cafe 자료
#ranicafe=read.csv("C:/work_2016/Rstat/Lesson 2/data/cafedata.csv",header=T,na.strings=c("na"))
ranicafe=read.csv("../data/cafedata.csv",header=T,na.strings=c("na"))
str(ranicafe)## 'data.frame': 48 obs. of 22 variables:
## $ t : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Date : Factor w/ 48 levels "2010-01-19","2010-01-20",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ Day.Code : int 2 3 4 5 1 2 3 4 5 1 ...
## $ Day.of.Week : Factor w/ 5 levels "Fri","Mon","Thu",..: 4 5 3 1 2 4 5 3 1 2 ...
## $ Bread.Sand.Sold : int 5 6 8 4 3 7 6 0 3 2 ...
## $ Bread.Sand.Waste : int 3 8 2 2 0 1 6 0 4 6 ...
## $ Wraps.Sold : int 25 7 14 5 10 5 19 7 4 13 ...
## $ Wraps.Waste : int 5 17 0 7 0 3 3 0 9 3 ...
## $ Muffins.Sold : int 5 3 4 5 8 1 6 6 0 3 ...
## $ Muffins.Waste : int 1 5 0 0 0 0 0 1 4 0 ...
## $ Cookies.Sold : int 5 1 1 3 3 5 10 0 3 6 ...
## $ Cookies.Waste : int 3 6 0 1 0 0 0 0 2 0 ...
## $ Fruit.Cup.Sold : int 1 0 0 3 2 2 2 0 1 2 ...
## $ Fruit.Cup.Waste : int 4 3 3 0 0 0 0 0 1 0 ...
## $ Chips : int 12 0 0 20 0 4 2 20 3 16 ...
## $ Juices : int 8 0 13 0 5 4 5 6 4 7 ...
## $ Sodas : int 20 13 23 13 13 33 15 27 12 19 ...
## $ Coffees : int 41 33 34 27 20 23 32 31 30 27 ...
## $ Total.Soda.and.Coffee : int 61 46 57 40 33 56 47 58 42 46 ...
## $ Sales : num 200 196 103 163 102 ...
## $ Max.Daily.Temperature..F.: int 36 34 39 40 36 26 34 33 20 37 ...
## $ Total.Items.Wasted : int 16 39 5 10 0 4 9 1 20 9 ...summary(ranicafe)## t Date Day.Code Day.of.Week Bread.Sand.Sold
## Min. : 1.00 2010-01-19: 1 Min. :1 Fri: 9 Min. :0.000
## 1st Qu.:12.75 2010-01-20: 1 1st Qu.:2 Mon: 9 1st Qu.:3.000
## Median :24.50 2010-01-21: 1 Median :3 Thu:10 Median :4.000
## Mean :24.50 2010-01-22: 1 Mean :3 Tue:10 Mean :4.702
## 3rd Qu.:36.25 2010-01-25: 1 3rd Qu.:4 Wed:10 3rd Qu.:6.000
## Max. :48.00 2010-01-26: 1 Max. :5 Max. :9.000
## (Other) :42 NA's :1
## Bread.Sand.Waste Wraps.Sold Wraps.Waste Muffins.Sold
## Min. :0.000 Min. : 4.00 Min. : 0.00 Min. : 0.000
## 1st Qu.:0.000 1st Qu.: 9.00 1st Qu.: 0.00 1st Qu.: 3.000
## Median :0.000 Median :13.00 Median : 0.00 Median : 5.000
## Mean :1.574 Mean :13.15 Mean : 1.66 Mean : 5.851
## 3rd Qu.:3.000 3rd Qu.:16.50 3rd Qu.: 2.00 3rd Qu.: 8.000
## Max. :8.000 Max. :25.00 Max. :17.00 Max. :28.000
## NA's :1 NA's :1 NA's :1 NA's :1
## Muffins.Waste Cookies.Sold Cookies.Waste Fruit.Cup.Sold
## Min. :0.000 Min. : 0.000 Min. :0.000 Min. :0.000
## 1st Qu.:0.000 1st Qu.: 3.000 1st Qu.:0.000 1st Qu.:1.000
## Median :0.000 Median : 5.000 Median :0.000 Median :2.000
## Mean :0.617 Mean : 5.787 Mean :1.043 Mean :1.702
## 3rd Qu.:1.000 3rd Qu.: 8.000 3rd Qu.:1.500 3rd Qu.:2.000
## Max. :5.000 Max. :13.000 Max. :6.000 Max. :4.000
## NA's :1 NA's :1 NA's :1 NA's :1
## Fruit.Cup.Waste Chips Juices Sodas
## Min. :0.0000 Min. : 0.000 Min. : 0.000 Min. :11.00
## 1st Qu.:0.0000 1st Qu.: 6.500 1st Qu.: 3.000 1st Qu.:21.00
## Median :0.0000 Median : 9.000 Median : 4.000 Median :29.00
## Mean :0.3617 Mean : 9.149 Mean : 4.936 Mean :29.57
## 3rd Qu.:0.0000 3rd Qu.:11.000 3rd Qu.: 6.000 3rd Qu.:36.00
## Max. :4.0000 Max. :25.000 Max. :21.000 Max. :55.00
## NA's :1 NA's :1 NA's :1 NA's :1
## Coffees Total.Soda.and.Coffee Sales
## Min. : 3.00 Min. :27.00 Min. : 61.94
## 1st Qu.:12.00 1st Qu.:41.00 1st Qu.:119.88
## Median :23.00 Median :52.00 Median :150.51
## Mean :21.51 Mean :51.09 Mean :148.22
## 3rd Qu.:30.00 3rd Qu.:60.00 3rd Qu.:179.02
## Max. :48.00 Max. :74.00 Max. :240.87
## NA's :1 NA's :1 NA's :1
## Max.Daily.Temperature..F. Total.Items.Wasted
## Min. :20.00 Min. : 0.000
## 1st Qu.:33.00 1st Qu.: 1.000
## Median :37.50 Median : 4.000
## Mean :41.92 Mean : 5.255
## 3rd Qu.:48.25 3rd Qu.: 7.000
## Max. :80.00 Max. :39.000
## NA's :1table.coffee=table(ranicafe$Coffees)
coffe.ext=rep(0,50)
coffe.ext[as.numeric(names(table.coffee))]=table.coffee
names(coffe.ext)=(1:50)
barplot(coffe.ext)
- 표본통계량1: 자료의 범위(max min)
ranicafe$Coffee## [1] 41 33 34 27 20 23 32 31 30 27 30 27 26 24 18 22 21 28 23 31 29 48 25
## [24] 31 25 35 33 35 16 24 20 11 21 NA 8 8 4 4 3 5 6 4 13 4 16 14
## [47] 10 11#max
sort(ranicafe$Coffee)## [1] 3 4 4 4 4 5 6 8 8 10 11 11 13 14 16 16 18 20 20 21 21 22 23
## [24] 23 24 24 25 25 26 27 27 27 28 29 30 30 31 31 31 32 33 33 34 35 35 41
## [47] 48sort(ranicafe$Coffee)[1]## [1] 3min(ranicafe$Coffee,na.rm=T)## [1] 3#min
sort(ranicafe$Coffee,decreasing=T)## [1] 48 41 35 35 34 33 33 32 31 31 31 30 30 29 28 27 27 27 26 25 25 24 24
## [24] 23 23 22 21 21 20 20 18 16 16 14 13 11 11 10 8 8 6 5 4 4 4 4
## [47] 3sort(ranicafe$Coffee,decreasing=T)[1]## [1] 48max(ranicafe$Coffee,na.rm=T)## [1] 48range(ranicafe$Coffee,na.rm=T)## [1] 3 48- 표본통계량2: 대표값(최빈값,평균,중앙값)
#최빈값(mode)
rc=ranicafe$Coffees
stem(rc)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 34444
## 0 | 5688
## 1 | 01134
## 1 | 668
## 2 | 001123344
## 2 | 55677789
## 3 | 001112334
## 3 | 55
## 4 | 1
## 4 | 8sort(table(ranicafe$Coffees),decreasing=T)[1]## 4
## 4names(sort(table(ranicafe$Coffees),decreasing=T)[1])## [1] "4"as.numeric(names(sort(table(ranicafe$Coffees),decreasing=T)[1]))## [1] 4#평균
## 평균 가중치
weight=1/length(rc)
sum(rc*weight,na.rm=T)## [1] 21.0625weight2=1/length(rc[!is.na(rc)]) # Size without mission obs
sum(rc*weight2,na.rm=T)## [1] 21.51064## 평균
mean(rc)## [1] NAmean(rc,na.rm=T)## [1] 21.51064rc=c(rc,NA)
tail(rc,n=5)## [1] 16 14 10 11 NAmean(rc)## [1] NAmean(rc,na.rm=T)## [1] 21.51064## 평균은 자주 보이지 않을 수 있다.
rc[(rc==21)|(rc==22)] # cannot determine, then we include ## [1] 22 21 21 NA NArc[which(rc==21|rc==22)] # we include wha we can determine. Things cannot be determined our out.## [1] 22 21 21ranicafe[(rc==21)|(rc==22),]## t Date Day.Code Day.of.Week Bread.Sand.Sold Bread.Sand.Waste
## 16 16 2010-02-09 2 Tue 8 0
## 17 17 2010-02-10 3 Wed 7 0
## 33 33 2010-03-04 4 Thu 4 0
## NA NA <NA> NA <NA> NA NA
## NA.1 NA <NA> NA <NA> NA NA
## Wraps.Sold Wraps.Waste Muffins.Sold Muffins.Waste Cookies.Sold
## 16 16 0 11 0 9
## 17 12 0 5 0 7
## 33 14 0 6 0 8
## NA NA NA NA NA NA
## NA.1 NA NA NA NA NA
## Cookies.Waste Fruit.Cup.Sold Fruit.Cup.Waste Chips Juices Sodas
## 16 1 2 0 11 8 31
## 17 3 1 0 14 3 24
## 33 0 2 0 8 5 43
## NA NA NA NA NA NA NA
## NA.1 NA NA NA NA NA NA
## Coffees Total.Soda.and.Coffee Sales Max.Daily.Temperature..F.
## 16 22 53 181.43 29
## 17 21 45 125.57 26
## 33 21 64 168.08 45
## NA NA NA NA NA
## NA.1 NA NA NA NA
## Total.Items.Wasted
## 16 1
## 17 3
## 33 0
## NA NA
## NA.1 NAranicafe[which((rc==21)|(rc==22)),]## t Date Day.Code Day.of.Week Bread.Sand.Sold Bread.Sand.Waste
## 16 16 2010-02-09 2 Tue 8 0
## 17 17 2010-02-10 3 Wed 7 0
## 33 33 2010-03-04 4 Thu 4 0
## Wraps.Sold Wraps.Waste Muffins.Sold Muffins.Waste Cookies.Sold
## 16 16 0 11 0 9
## 17 12 0 5 0 7
## 33 14 0 6 0 8
## Cookies.Waste Fruit.Cup.Sold Fruit.Cup.Waste Chips Juices Sodas Coffees
## 16 1 2 0 11 8 31 22
## 17 3 1 0 14 3 24 21
## 33 0 2 0 8 5 43 21
## Total.Soda.and.Coffee Sales Max.Daily.Temperature..F.
## 16 53 181.43 29
## 17 45 125.57 26
## 33 64 168.08 45
## Total.Items.Wasted
## 16 1
## 17 3
## 33 0## 평균은 outlier에 민감하다.
rc[which.max(rc)]=480
mean(rc,na.rm=T)## [1] 30.70213## 중위수
rc_m=rc[!is.na(rc)]
median.idx=(length(rc_m)+1)/2
rc.s=sort(rc_m)
rc.s[median.idx]## [1] 23median(rc,na.rm=T)## [1] 23## 중위수는 outlier에 덜 민감하다.
rc[which.max(rc)]=48
median(rc,na.rm=T)## [1] 23- 표본통계량 3: 펴저있는 정도(표준편차 사분위수 범위)
- 표준편차 (Standard deviation)
## 편차
height=c(164, 166, 168, 170,172,174,176)
height.m=mean(height)
height.dev=height-mean(height)
sum(height.dev)## [1] 0# (더하면 0이더라)
## 분산
var(height.dev)## [1] 18.66667#? var
mean(height.dev^2) # 확률 1/6로 키가 가지는 값이 6개 밖에 없는 경우## [1] 16var(height.dev)*(length(height)-1)/length(height)## [1] 16##표준편차
sd(height)## [1] 4.320494##?sd
sqrt(mean(height.dev^2)) # 확률 1/6로 키가 가지는 값이 6개 밖에 없는 경우## [1] 4sd(height)*sqrt((length(height)-1)/length(height))## [1] 4## 커피 판매 평균, 표준편차
rc.m=mean(rc,na.rm=T)
rc.sd=sd(rc,na.rm=T)
cat("Coffee sales=", round(rc.m,1),"+/-",round(rc.sd,2))## Coffee sales= 21.5 +/- 11.08## 변동계수
rj=ranicafe$Juices
rj.m=mean(rj,na.rm=T)
rj.sd=sd(rj,na.rm=T)
rc.cv=rc.sd/rc.m
rj.cv=rj.sd/rj.m
rc.cv## [1] 0.5151163rj.cv## [1] 0.7502046# 쥬스 판매가 커피 판매보다 더 변화가 심하다.b. 4분위수# 최소갑, 4분위수, 최대값
qs=quantile(rc,na.rm=T)
qs## 0% 25% 50% 75% 100%
## 3 12 23 30 48# 3분위수 -1분위수: 분위 간 범위
IQR(rc,na.rm=T)## [1] 18qs[4]-qs[2]## 75%
## 18bp.rc=boxplot(rc,na.rm=T)
bp.rc## $stats
## [,1]
## [1,] 3
## [2,] 12
## [3,] 23
## [4,] 30
## [5,] 48
##
## $n
## [1] 47
##
## $conf
## [,1]
## [1,] 18.8516
## [2,] 27.1484
##
## $out
## numeric(0)
##
## $group
## numeric(0)
##
## $names
## [1] ""## 자동차 제동거리 outlier
is.na(cars$dist)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [12] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [23] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [34] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [45] FALSE FALSE FALSE FALSE FALSE FALSEqscar=quantile(cars$dist)
qscar## 0% 25% 50% 75% 100%
## 2 26 36 56 120bp.dist=boxplot(cars$dist)
bp.dist## $stats
## [,1]
## [1,] 2
## [2,] 26
## [3,] 36
## [4,] 56
## [5,] 93
##
## $n
## [1] 50
##
## $conf
## [,1]
## [1,] 29.29663
## [2,] 42.70337
##
## $out
## [1] 120
##
## $group
## [1] 1
##
## $names
## [1] "1"# outlier 판별 기준: 하한값/상한값
ll.dist=qscar[2]-1.5*IQR(cars$dist,na.rm=T)
ul.dist=qscar[4]+1.5*IQR(cars$dist,na.rm=T)
dist.out=cars$dist[(cars$dist>ul.dist|cars$dist<ll.dist)&!is.na(cars$dist)]
dist.in=cars$dist[(cars$dist<=ul.dist)&(cars$dist>=ll.dist)&!is.na(cars$dist)]
whisker.dist=range(dist.in)
range(bp.dist$stats)## [1] 2 93dist.out## [1] 120ll.rc=qs[2]-1.5*IQR(rc,na.rm=T)
ul.rc=qs[4]+1.5*IQR(rc,na.rm=T)
rc.out=rc[(rc>ul.rc|rc<ll.rc)&!is.na(rc)]
rc.in=rc[(rc<=ul.rc)&(rc>=ll.rc)&!is.na(rc)]
whisker.rc=range(rc.in)
range(bp.rc$stats)## [1] 3 48rc.out## numeric(0)## quantile. extended
quantile(rc,seq(0,1,0.1),na.rm=T)## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 3.0 4.6 10.2 15.6 20.4 23.0 25.6 28.2 31.0 33.4 48.0#install.packages("statar")
library(statar)
xtile(rc,n=4)## [1] 4 4 4 3 2 2 4 4 3 3 3 3 3 3 2 2 2 3 2 4 3 4 3
## [24] 4 3 4 4 4 2 3 2 1 2 NA 1 1 1 1 1 1 1 1 2 1 2 2
## [47] 1 1 NAxtile(rc,prob=seq(0.25,1,0.25))## [1] 4 4 4 3 2 2 4 4 3 3 3 3 3 3 2 2 2 3 2 4 3 4 3
## [24] 4 3 4 4 4 2 3 2 1 2 NA 1 1 1 1 1 1 1 1 2 1 2 2
## [47] 1 1 NA- 다음 시간 준비
save.image("Lesson2.RData")
#install.packages("prob")
library("prob")
tosscoin(1)## toss1
## 1 H
## 2 T