R Plot Options
# main = "" 제목
# sub = "" 부제목
# xlab = "", ylab = "" x, y 축 제목 문자열
# xlim = , ylim = x, y 축 한계값
# ann = F x, y 축 제목 표시하지 않음
# axes = F x, y 축 표시하지 않음
# tmag = 2 제목 등에 사용되는 문자의 확대배율
#
# axis(...) 사용자지정 x, y 축
# title 메인, x, y 축 제목 지정
#
# <그래프 타입>
# type = "p" 점 (기본값)
# type = "l" 꺾은 선
# type = "b" 점과 선
# type = "c" "b"에서 점 생략
# type = "o" 점과 선 중첩
# type = "h" 각 점에서 x축까지 수직선 그래프
# type = "s" 왼쪽 값을 기초로 계단 모양으로 연결
# type = "S" 오른쪽 값을 기초로 계단 모양으로 연결
# type = "n" 축만 그리고 그래프는 그리지 않음
#
# <선>
# lty = 0, lty = "blank"
# lty = 1, lty = "solid"
# lty = 2, lty = "dashed"
# lty = 3, lty = "dotted"
# lty = 4, lty = "dotdash"
# lty = 5, lty = "longdash"
# lty = 6, lty = "twodash"
#
# <색, 기호>
# col = 1, col = "blue" 색상 1 ~ 8
# pch = 0, pch = "문자" 점 모양 지정
# bg = "blue" 그래프 배경색
# lwd = "숫자" 선 굵기
# cex = "숫자" 점 또는 문자 굵기
#
# par(mfrow = c(행수, 열수)) : 한 페이지에 여러 그래프 배치
# par(new = T) : 그래프 중첩
#
# lines : 그래프 위에 새로운 그래프 그리기
#
# legend : 범례
apple <- c(260, 400, 250, 200, 310)
peach <- c(180, 200, 210, 190, 170)
orange <- c(210, 250, 260, 330, 300)
fruits <- c(apple, peach, orange)
stem(fruits, scale = 0.5) # stem-leaf plot
##
## The decimal point is 2 digit(s) to the right of the |
##
## 1 | 789
## 2 | 00115566
## 3 | 013
## 4 | 0
# plot
# plot(y data, option)
# plot(x data, y data, option)
x <- c(1:20)
y <- sample(1:20)
plot(x, y, xlim = c(0,20), ylim = c(0,25), main = "sample", type = "o", lty = 2, col = 2)
# 사용자지정 x, y 축 --- 01_fruits_line.png
plot(apple, type="o", col="red", ylim=c(0,400), axes = F, ann=F)
axis(1, at=1:5, labels = c("Mon","Tue","Wed","Thu","Fri"))
axis(2, ylim=c(0,400))
title(main="Fruits", col.main="red", font.main=4)
title(xlab="Day", col.lab="black")
title(ylab="Qty", col.lab="blue")
par(new=T)
lines(peach, type="o", pch=21, col="green", lty=2)
lines(orange, type="o", pch=22, col="blue", lty=2)
legend(4, 130, c("apple","peach","orange"), col=c("red","green","blue"),
cex=0.8, pch=21, lty=1:3)
# multi graph on 1 window
par(mfrow = c(1,3))
plot(apple, type="o", col="red", ylim=c(0,400))
plot(peach, type="o", col="red", ylim=c(0,400))
plot(orange, type="o", col="red", ylim=c(0,400))
par(mfrow = c(1,1))
# barplot
# angle, density, col : 막대를 칠하는 선의 각도, 밀도, 색상
# lengent : 범례
# names : 각 막대의 라벨
# width : 각 막대의 상대적인 폭
# space : 각 막대 사이의 간격
# beside : True 일 경우 각 값마다 막대를 그린다.
# horiz : True 일 경우 가로막대 출력
# 요일별 apple 판매량
# density --- 02_apple_bar_density
barplot(apple, main="Apple", xlab="Day", ylab="Qty", border="blue",
names.arg = c("Mon","Tue","Wed","Thu","Fri"),
density = c(10,30,50,70,90))
# condition color 특정 조건을 만족하는 경우에 색깔 표시
# --- 03_apple_bar_conditionColor
colors <- c()
for (i in 1:length(apple)) {
if (apple[i] >= 300) {
colors <- c(colors, "red")
}
else {
colors <- c(colors, "grey")
}
}
barplot(apple, main="Apple", xlab="Day", ylab="Qty", border="blue", col=colors,
names.arg = c("Mon","Tue","Wed","Thu","Fri"))
# 과일별/요일별 판매랑 --- 04_fruits_bar_multi
fruits10 <- cbind(apple, peach, orange)
fruits10
## apple peach orange
## [1,] 260 180 210
## [2,] 400 200 250
## [3,] 250 210 260
## [4,] 200 190 330
## [5,] 310 170 300
barplot(as.matrix(fruits10), main="Fruits", ylab="Qty", ylim = c(0,450),
beside = T, col=rainbow(5))
legend(10, 450, c("Mon","Tue","Wed","Thu","Fri"), cex=0.8, fill=rainbow(5))
# 요일별/과일별 판매량 --- 05_fruits_bar_multisection
fruits11 <- t(fruits10)
colnames(fruits11) <- c(1,2,3,4,5)
fruits11
## 1 2 3 4 5
## apple 260 400 250 200 310
## peach 180 200 210 190 170
## orange 210 250 260 330 300
barplot(fruits11, main="Fruits", ylab="Qty", ylim = c(0,1100), col=rainbow(3), space=0.1,
cex=0.8, cex.axis=0.8, las=1, names.arg=c("Mon","Tue","Wed","Thu","Fri"))
legend(4, 1100, rownames(fruits11), cex=0.8, fill=rainbow(3))
# Pie Chart
# angle, density, col : 각도, 밀도, 색상
# labels : 각 부분의 이름 지정
# radius : 원형의 크기
# clockwise : 회전 방향. 기본 = 반시계방향
# init.angle : 시작되는 지점의 각도
apple <- c(260, 400, 250, 200, 310)
pie(apple)
# 1.
pie(apple, init.angle = 90, col=rainbow(length(apple)), radius = 1,
labels = c("Mon","Tue","Wed","Thu","Fri"))
# 2. 비율 --- 06_apple_pie
f_ratio <- round(apple/sum(apple)*100, 1)
f_labels <- paste(f_ratio, "%", sep = "")
pie(apple, main="Apple", init.angle = 90, col=rainbow(length(apple)), radius = 0.8,
cex=0.8, labels=f_labels)
legend(1,1, c("Mon","Tue","Wed","Thu","Fri"), cex=0.8, fill=rainbow(length(apple)))
# 3. --- 06_apple_pie_label
f_ratio <- round(apple/sum(apple)*100, 1)
f_days <- c("Mon","Tue","Wed","Thu","Fri")
f_labels <- paste(f_days, "\n", f_ratio, "%")
pie(apple, main="Apple", init.angle = 90, col=rainbow(length(apple)), radius = 1,
cex=1.0, labels=f_labels)
# 3D Pie Chart
# explode : 각 조각의 간격 --- 07_apple_3Dpie
library(plotrix)
f_ratio <- round(apple/sum(apple)*100, 1)
f_days <- c("Mon","Tue","Wed","Thu","Fri")
f_labels <- paste(f_days, "\n", f_ratio, "%")
pie3D(apple, main="Apple", col=rainbow(length(apple)), cex=0.8,
labels=f_labels, explode=0.05)
# boxplot
# col : 박스 색상
# names : 막대 라벨
# range : 박스 끝에서 수염까지의 길이. default = 1.5
# width : 박스 폭
# notch : True일 경우 상자의 허리부분 가늘게 표시
# horizontal : 가로 상자
boxplot(apple, peach, orange,
col=c("red","yellow","green"),
names=c("apple","peach","orange"),
horizontal = T)
# treemap
# vSize : 그룹핑 기준
# index : 화면 표시 기준
library(treemap)
data <- read.csv("data/all_student_score.csv")
data
## rank name team score score100 rankrate
## 1 1 Lesley 1 48 100.0 1.00
## 2 2 Kate 2 46 95.8 0.96
## 3 3 Hannah 1 45 93.8 0.94
## 4 4 Heather 3 43 89.6 0.90
## 5 5 Jennet 1 41 85.4 0.85
## 6 6 Laura 1 41 85.4 0.85
## 7 7 Paige 4 41 85.4 0.85
## 8 8 Sunny 3 40 83.3 0.83
## 9 9 Melissa 1 39 81.3 0.81
## 10 10 Vitoria 1 39 81.3 0.81
## 11 11 Katriana 2 39 81.3 0.81
## 12 12 Gloria 2 39 81.3 0.81
## 13 13 Lina 3 39 81.3 0.81
## 14 14 Scarlet 1 38 79.2 0.79
## 15 15 Serena 4 37 77.1 0.77
## 16 16 Diana 4 37 77.1 0.77
## 17 17 Kelly 2 36 75.0 0.75
## 18 18 Sally 2 34 70.8 0.71
## 19 19 Rachel 3 34 70.8 0.71
## 20 20 Emma 4 33 68.8 0.69
## 21 21 Emily 2 31 64.6 0.65
## 22 22 Julia 2 30 62.5 0.63
## 23 23 Juana 4 30 62.5 0.63
## 24 24 Yesica 4 27 56.3 0.56
## 25 25 Erica 3 24 50.0 0.50
## 26 26 Marcia 3 23 47.9 0.48
## 27 27 Zoe 4 23 47.9 0.48
## 28 28 Chloe 3 13 27.1 0.27
# --- 08_score_treemap
treemap(data, vSize="score", index="score")
treemap(data, vSize="team", index=c("score","name"))
treemap(data, vSize="score", index=c("team","score"))
# stars
# draw.segments = T : 부채꼴로 색상 표시
# full : T 원형 / F 반원형
data <- read.csv("data/all_subject_score.csv")
data
## name Korean English Math History Chemistry Physics
## 1 Sunny 90 85 55 88 91 79
## 2 Melissa 70 65 80 75 76 89
## 3 Vitoria 92 95 76 65 89 91
## 4 Katriana 76 89 88 98 100 91
## 5 Gloria 97 87 83 91 86 91
## 6 Lina 80 86 97 85 69 77
## 7 Scarlet 20 30 40 50 70 90
## 8 Serena 50 52 54 56 58 60
## 9 Diana 60 70 80 75 65 55
nrow(data)
## [1] 9
# 1번 이름 컬럼을 rowname으로 설정하고 삭제함
row.names(data) <- data$name
rownames(data)
## [1] "Sunny" "Melissa" "Vitoria" "Katriana" "Gloria" "Lina"
## [7] "Scarlet" "Serena" "Diana"
data <- data[2:7]
# star chart
# 1. --- 09_stardiagram_line
stars(data, flip.labels = F, draw.segments = F, frame.plot = T, full = T,
main = "Score Diagram of subject/student")
label <- names(data)
value <- table(label)
piechart <- pie(value, labels = label, radius = 0.2, cex = 0.6, col = NA)
# 2. --- 09_stardiagram_color
stars(data, flip.labels = T, draw.segments = T, frame.plot = T, full = T,
main = "Score Diagram of subject/student")
label <- names(data)
value <- table(label)
color <- c("black","red","green","blue","cyan","violet")
pie(value, labels = label, radius = 0.1, cex = 0.6, col = color)
# 3. --- 09_stardiagram_color_half
stars(data, flip.labels = T, draw.segments = T, frame.plot = T, full = F,
main = "Score Diagram of subject/student")
# star --> bar : --- 10_bar_multi
data2 <- t(data)
data2
## Sunny Melissa Vitoria Katriana Gloria Lina Scarlet Serena Diana
## Korean 90 70 92 76 97 80 20 50 60
## English 85 65 95 89 87 86 30 52 70
## Math 55 80 76 88 83 97 40 54 80
## History 88 75 65 98 91 85 50 56 75
## Chemistry 91 76 89 100 86 69 70 58 65
## Physics 79 89 91 91 91 77 90 60 55
label <- rownames(data2)
label
## [1] "Korean" "English" "Math" "History" "Chemistry" "Physics"
barplot(as.matrix(data2), main = "Test", ylab = "score", beside = T,
col = rainbow(5), ylim = c(0,150))
abline(h=60, col = "red", lwd=2)
legend(50,140, label, cex=0.8, fill = rainbow(5))
# ggplot2
# ggplot(data, aes(x=x axis data, y=y axis data)) + geom 함수
library(ggplot2)
data <- read.table("data/korean_score.txt", header=T, sep="")
data
## name subject score
## 1 Sunny Korean 90
## 2 Diana Korean 70
## 3 Serena Korean 92
## 4 Lina Korean 76
## 5 Gloria Korean 97
## 6 Victoria Korean 80
## 7 Scarlet Korean 20
## 8 Melisa Korean 50
## 9 Kate Korean 60
# geom_point() : 11_ggplot_point
ggplot(data, aes(x=name, y=score)) + geom_point()
# geom_bar()
# -- stat : 주어진 데이터에서 geom에 필요한 데이터를 생성.
ggplot(data, aes(x=name, y=score)) + geom_bar(stat = "identity")
gpbar <- ggplot(data, aes(x=name, y=score)) + geom_bar(stat = "identity", fill="cyan", colour="red")
gpbar + theme(axis.text.x=element_text(angle=45, hjust=1, vjust=1, color="blue", size=10))
# geom_bar + geom_text
library(plyr) # split-apply-combine paradigm !!!
data <- read.csv("data/student_score_3.csv", header=T, sep=",")
head(data)
## name subject score
## 1 Lesley Math 90
## 2 Kate Math 70
## 3 Hannah Math 92
## 4 Heather Math 76
## 5 Jennet Math 97
## 6 Laura Math 80
transData <- arrange(data, name, subject) # plyr : sort
# total 컬럼 추가
transData <- ddply(transData, "name", transform, total=cumsum(score)) # plyr : 누적합계
# label 컬럼 추가
transData <- ddply(transData, "name", transform, label=cumsum(score)-score*0.5) # 라벨 위치
head(transData)
## name subject score total label
## 1 Hannah English 95 95 47.5
## 2 Hannah Math 92 187 141.0
## 3 Hannah Physics 76 263 225.0
## 4 Heather English 89 89 44.5
## 5 Heather Math 76 165 127.0
## 6 Heather Physics 88 253 209.0
# --- 12_ggplot_bar_multisection
ggplot(transData, aes(x=name, y=score, fill=subject)) +
geom_bar(stat="identity") +
geom_text(aes(y=label, label=paste(score,"p")), color="black", size=4) +
theme(axis.text.x=element_text(angle=45, hjust=1, vjust=1, color="blue", size=10))
# geom_segment
data <- read.csv("data/all_subject_score.csv")
kdata <- data[, 1:2]
kdata
## name Korean
## 1 Sunny 90
## 2 Melissa 70
## 3 Vitoria 92
## 4 Katriana 76
## 5 Gloria 97
## 6 Lina 80
## 7 Scarlet 20
## 8 Serena 50
## 9 Diana 60
# theme_bw() : 배경 흑백
# panel.grid.major.y = element_line : 가로 선 그리기
# --- 13_ggplot_point_grid
ggplot(data[,1:2],aes(x=Korean, y=reorder(name,Korean))) + geom_point(size=5) +
theme_bw() +
theme(panel.grid.major.x = element_blank(),
panel.grid.minor.x = element_blank(),
panel.grid.major.y = element_line(color="red", linetype="dashed"))
# --- 13_ggplot_point_grid2
ggplot(data[,1:2], aes(x=Korean, y=reorder(name,Korean))) +
geom_segment(aes(yend=name, xend=0, color="red")) +
geom_point(size=5) +
theme_bw() +
theme(panel.grid.major.x = element_blank(),
panel.grid.minor.x = element_blank(),
panel.grid.major.y = element_blank())
# geom_line --- 14_ggplot_line
data <- read.csv("data/student_subject_score_3.csv")
data2 <- arrange(data, name, subject) # plyr : sort
data2
## name subject score
## 1 Jane Chemistry 76
## 2 Jane English 65
## 3 Jane History 89
## 4 Jane Korean 70
## 5 Jane Math 80
## 6 Jane Physics 75
## 7 Kate Chemistry 91
## 8 Kate English 85
## 9 Kate History 79
## 10 Kate Korean 90
## 11 Kate Math 55
## 12 Kate Physics 88
## 13 Sunny Chemistry 89
## 14 Sunny English 95
## 15 Sunny HIstory 91
## 16 Sunny Korean 92
## 17 Sunny Math 76
## 18 Sunny Physics 65
ggplot(data2, aes(x=subject, y=score, color=name, group=name)) + geom_line()
ggplot(data2, aes(x=subject, y=score, color=name, group=name, fill=name)) + geom_line() +
geom_point(size=3, shape=22)
