技術標籤：R語言r語言資料分析視覺化

原始資料

程式碼

data = read.csv('原始資料.csv',header = T)

# 畫圖
attach(data)
par(mfrow=c(2,2))
plot(年份, 報名人數,  pch = 15, lty = 1, col = "red", xlab = "年份", ylab = "報名人數")
abline(lsfit(年份,報名人數))
plot(年份, 錄取人數, type = "b", pch = 16, lty = 2, col = "blue", xlab = "年份", ylab = "錄取人數")
plot(年份, 畢業生人數, type = "b", pch = 17, lty = 3, col = "orange", xlab = "年份", ylab = "畢業生人數")
plot(年份, 就業率, type = "b", pch = 15, lty = 1, col = "black", xlab = "年份", ylab = "就業率")
par(mfrow=c(1,1))
detach(data)

# 相關性分析
#library(psych)
#corr.test(data[,c(2,3,4,5)])  # 上面是相關係數，下面是檢測值
cov(data[,c(2,3,4,5)])  # 檢視相關係數
# 報名人數與錄取人數的相關性
cor.test(data[,2],data[,3])
# 報名人數與畢業生人數的相關性
cor.test(data[,2],data[,4])
# 報名人數與就業率的相關性
cor.test(data[,2],data[,5])

# 多元線性迴歸
fit = lm(報名人數~錄取人數+畢業生人數+就業率)
summary(fit)  # 檢視擬合效果
options(digits = 4)  # 保留四位數
coef(fit)  # 檢視係數
# 畫迴歸後對照圖形
plot(年份, 報名人數, type = "b", pch = 15, lty = 1, col = "black", xlab = "年份", ylab = "報名人數",ylim = c(140,300))
lines(年份,迴歸資料,type = "b",pch = 16,lty=2,col = "red")
legend("topleft",c('源資料','迴歸資料'), 
       lty = c(1,2), pch = c(15,16),col=c('black','red'))