Data Manipulation
- Data Frame으로 정리하고, 다시 long format 으로 변환. height를 인치로 변환하면 어떻게 될까?
dimnames(crimtab.2)[[2]]<-as.numeric(dimnames(crimtab.2)[[2]])/2.54
crimtab.2
## 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
## 9.4 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9.5 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9.6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9.7 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9.8 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9.9 0 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 10 1 0 0 1 2 0 2 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 10.1 0 0 0 1 3 1 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0
## 10.2 0 0 2 2 2 1 0 2 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 10.3 0 1 1 3 2 2 3 5 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 10.4 0 0 1 1 2 3 3 4 3 3 0 0 0 0 0 0 0 0 0 0 0 0
## 10.5 0 0 0 1 3 7 6 4 3 1 3 1 0 1 0 0 0 0 0 0 0 0
## 10.6 0 0 0 1 4 5 9 14 6 3 1 0 0 1 0 0 0 0 0 0 0 0
## 10.7 0 0 1 2 4 9 14 16 15 7 3 1 2 0 0 0 0 0 0 0 0 0
## 10.8 0 0 0 2 5 6 14 27 10 7 1 2 1 0 0 0 0 0 0 0 0 0
## 10.9 0 0 0 0 2 6 14 24 27 14 10 4 1 0 0 0 0 0 0 0 0 0
## 11 0 0 0 2 6 12 15 31 37 27 17 10 6 0 0 0 0 0 0 0 0 0
## 11.1 0 0 0 3 3 12 22 26 24 26 24 7 4 1 0 0 0 0 0 0 0 0
## 11.2 0 0 0 3 2 7 21 30 38 29 27 20 4 1 0 0 0 0 0 0 0 1
## 11.3 0 0 0 1 0 5 10 24 26 39 26 24 7 2 0 0 0 0 0 0 0 0
## 11.4 0 0 0 0 3 4 9 29 56 58 26 22 10 11 0 0 0 0 0 0 0 0
## 11.5 0 0 0 0 0 5 11 17 33 57 38 34 25 11 2 0 0 0 0 0 0 0
## 11.6 0 0 0 0 2 1 4 13 37 39 48 38 27 12 2 2 0 1 0 0 0 0
## 11.7 0 0 0 0 0 2 9 17 30 37 48 45 24 9 9 2 0 0 0 0 0 0
## 11.8 0 0 0 0 1 0 2 11 15 35 41 34 29 10 5 1 0 0 0 0 0 0
## 11.9 0 0 0 0 1 1 2 12 10 27 32 35 19 10 9 3 1 0 0 0 0 0
## 12 0 0 0 0 0 0 1 4 8 19 42 39 22 16 8 2 2 0 0 0 0 0
## 12.1 0 0 0 0 0 0 0 2 4 13 22 28 15 27 10 4 1 0 0 0 0 0
## 12.2 0 0 0 0 0 0 1 2 5 6 23 17 16 11 8 1 1 0 0 0 0 0
## 12.3 0 0 0 0 0 0 0 0 4 8 10 13 20 23 6 5 0 0 0 0 0 0
## 12.4 0 0 0 0 0 0 1 1 1 2 7 12 4 7 7 1 0 0 1 0 0 0
## 12.5 0 0 0 0 0 0 0 1 0 1 3 12 11 8 6 8 0 2 0 0 0 0
## 12.6 0 0 0 0 0 0 0 0 0 1 0 3 5 7 8 6 3 1 1 0 0 0
## 12.7 0 0 0 0 0 0 0 0 0 1 1 7 5 5 8 2 2 0 0 0 0 0
## 12.8 0 0 0 0 0 0 0 0 0 0 1 2 3 1 8 5 3 1 1 0 0 0
## 12.9 0 0 0 0 0 0 0 0 0 0 0 1 2 2 0 1 1 0 0 0 0 0
## 13 0 0 0 0 0 0 0 0 0 0 3 0 1 0 1 0 2 1 0 0 0 0
## 13.1 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0
## 13.2 0 0 0 0 0 0 0 0 0 0 1 1 0 1 0 3 0 0 0 0 0 0
## 13.3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0
## 13.4 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 13.5 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
crimtab.3<-crimtab.2
crimtab.3.df<-as.data.frame(crimtab.3, stringsAsFactors = F)
head(crimtab.3.df)
## Var1 Var2 Freq
## 1 9.4 56 0
## 2 9.5 56 0
## 3 9.6 56 0
## 4 9.7 56 0
## 5 9.8 56 0
## 6 9.9 56 0
str(crimtab.3.df)
## 'data.frame': 924 obs. of 3 variables:
## $ Var1: chr "9.4" "9.5" "9.6" "9.7" ...
## $ Var2: chr "56" "56" "56" "56" ...
## $ Freq: int 0 0 0 0 0 0 1 0 0 0 ...
crimtab.3.df$finger<-as.numeric(crimtab.3.df$Var1)
crimtab.3.df$height<-as.numeric(crimtab.3.df$Var2)
str(crimtab.3.df)
## 'data.frame': 924 obs. of 5 variables:
## $ Var1 : chr "9.4" "9.5" "9.6" "9.7" ...
## $ Var2 : chr "56" "56" "56" "56" ...
## $ Freq : int 0 0 0 0 0 0 1 0 0 0 ...
## $ finger: num 9.4 9.5 9.6 9.7 9.8 9.9 10 10.1 10.2 10.3 ...
## $ height: num 56 56 56 56 56 56 56 56 56 56 ...
crimtab.3.long<-apply(crimtab.3.df[,4:5], 2, function(x) rep(x, crimtab.3.df[,3]))
str(crimtab.3.long)
## num [1:3000, 1:2] 10 10.3 9.9 10.2 10.2 10.3 10.4 10.7 10 10.1 ...
## - attr(*, "dimnames")=List of 2
## ..$ : NULL
## ..$ : chr [1:2] "finger" "height"
- 산점도를 제대로 그리기 위하여 필요한 패키지 설치
install.packages("hexbin")
library(hexbin)
crimtab.bin<-hexbin(crimtab.3.long[,"height"],crimtab.3.long[,"finger"], xbins=50)
par(mfrow=c(2,2))
plot(finger~height, data=crimtab.3.long)
plot(finger~height, data=crimtab.3.long, pch=20)
smoothScatter(crimtab.3.long[,"height"], crimtab.3.long[,"finger"], xlab="height", ylab="finger")
smoothScatter(crimtab.3.long[,"height"], crimtab.3.long[,"finger"], nbin=32, xlab="height", ylab="finger")
par(mfrow=c(1,1))
plot(crimtab.bin, xlab="height(inches)", ylab="finger length(cm)")
par(mar=c(4,4,1,1))
par(fig=c(0,0.8,0,0.8))
plot(finger~height, data=crimtab.3.long, pch=20)
par(fig=c(0,0.8,0.68,1), new=TRUE)
hist(crimtab.3.long[,"height"], axes=F, ann=F)
par(fig=c(0.68,1,0,0.8), new=TRUE)
barplot(table(cut(crimtab.3.long[,"finger"], breaks=10)), space=0, col="white", horiz=T, axes=F, axisnames=F)
par(fig=c(0,1,0,1))
par(mar=c(5,4,1,1)+0.1)
- persp()를 활용하면 다양한 각도에서 3차원 겨냥도를 그려볼 수 있음. \(x\) 축은 행, \(y\) 축은 열에 펼쳐진 격자를 0에서 1까지로 조정. theta와 phi는 박스를 돌려보는 각도이고, expand는 박스 높이의 상대적인 비율임. \(x\) 축과 \(y\) 축의 라벨 이외에는 디폴트값을 적용시킨 겨냥도와 적절히 조정한 겨냥도를 비교해 볼 것,
par(mfrow=c(2,2))
persp(crimtab.3, xlab="Finger Length", ylab="Height")
persp(crimtab.3, xlab="Finger Length", ylab="Height", theta=90, phi=30, expand=0.5, scale=TRUE)
persp(crimtab.3, xlab="Finger Length", ylab="Height", theta=135, phi=30, expand=0.5, scale=TRUE)
persp(crimtab.3, xlab="Finger Length", ylab="Height", theta=45, phi=45, expand=0.5, scale=TRUE)
par(mfrow=c(1,1))