R 야구 데이터 분석

library(readxl)
data <- read.csv("주요선수별성적-2013년.csv")
head(data)

bp <- barplot(data$연봉대비출루율,
              main=paste("야구 선수별 연봉 대비 출루율 분석","\n","(밥값여부계산)"),
              col = rainbow(25),
              cex.names=0.7, las =2,
              names.arg=data$선수명, ylim=c(0,50))
title(ylab="연봉대비출루율", col.lab = "red")

aver <- 0

for(i in 1:length(data$연봉대비출루율)){
  aver <- aver + data$연봉대비출루율[i]
}

aver

aver <- aver/length(data$연봉대비출루율)
aver

abline(h=aver, col="blue")
text(x=aver-11, y=14.5, col="black", cex=0.8, labels=paste(round(aver,1),"%","(평균출류율)"))

text(x=bp*1.01, y=data$연봉대비출루율*1.05, col="black", cex=0.7,
     labels=paste(data$연봉대비출루율,"%"))

data <- read.csv("주요선수별성적-2013년.csv")
head(data)

row.names(data) <- data$선수명
head(data)

# 득점, 안타, 홈런
data2 <- data[,c(7, 8, 11, 12, 13, 14, 17, 19)]
head(data2,3)

stars(data2,
      flip.labels = FALSE, draw.segments = TRUE,
      frame.plot = TRUE, full=TRUE,
      main="야구 선수별 주요 성적 분석-2013년")

label <- names(data2)

val <- table(label)
val

color <- c("black","red","green","blue","cyan","violet","yellow","grey")

pie(val,labels=label, col = color, radius = 0.1, cex=0.6)

# 선수명 연봉대비출루율 연봉대비타점율만 추출
data4 <- data[,c(2,21,22)]
head(data4,3)

# par() 함수를 이용하여 마진(margin)을 설정
par(mar=c(5,4,4,4)+0.1)


line1 <- data$연봉대비출루율
line2 <- data$연봉대비타점율

# 연봉대비타점율 시각화
plot(line1, type="o", axes=F,
     ylab="", xlab="", ylim=c(0,50),
     lty=2, lwd=2, col="blue",
     main="한국프로야구선수별 기록분석-2013년년")

# x축 설정
axis(1, at=1:25, lab=data4$선수명, las=2)

# y축 설정
axis(2,las=1)

# 연봉대비 출루율을 추가로 더 그리기 위해 par() 함수를 이용
par(new=T)

# 연봉대비출루율 시각화
plot(line2, type="o", axes=F,
     ylab="", xlab="", ylim=c(0,50),
     lty=2, lwd=2, col="red")


# y축 설정(오른쪽)
axis(4,las=1)
# y축 레이블 설정(오른쪽)
mtext(side=4,line=2.5,"연봉대비 타점율")
# y축 레이블 설정(왼쪽)
mtext(side=2,line=2.5,"연봉대비 출루율")

# 배경에 가이드라인을 격자 모양으로 추가
abline(h=seq(0,50,5),v=seq(1,25,1),col="gray",lty=2)

# 범례 추가
legend(18, 50, names(data[21:22]), cex=0.8, col=c("red","blue"),lty=1,lwd=2,bg="white")