根据数据大小可视化图表

Question

我正在使用不同的数据集制作一些图表，但是当我更改数据时，图表会失去形状并且看起来不太好。我不知道是否有办法在代码中编写一些东西，使图表根据数据呈现其形状或如何修复它。

acum <- structure(list(med_res_galan_2018 = c(57, 60, 52, 57, 56), med_res_galan_2019 = c(62, 
62, 57, 59, 60), med_res_galan_2020 = c(60, 61, 56, 58, 54), 
    med_res_galan_2021 = c(59, 58, 53, 56, 54), med_res_galan_2022 = c(60, 
    60, 55, 59, 57)), class = "data.frame", row.names = c("Lectura", 
"Matemáticas", "Sociales", "Naturales", "Inglés"))

id_year <- factor(2020:2024)

plot(id_year, acum[1,], type = "l", lwd=2, xlim = c(0,6),
     ylim = c(40,80), axes = F, xlab = "", ylab = "")

id_col <- c("black","red","blue","green","orange")

for(i in 1:4){
  lines(id_year,acum[i+1,],col=id_col[i+1],lwd=2)
}

id_col2 <- c("black","red","blue","green","orange")

for(i in 1:5){
  points(id_year,acum[i,], pch=15, col=id_col2[i])  
}

axis(1,pos = 40,lwd = 2,at=c(1:5),labels = c(id_year),font = 2)

axis(2,pos = 0,at=seq(40,55,by=5),lwd = 2,font = 2,las=2)

arrows(0,40,6,40,length = 0.15,angle = 15,lwd = 2)
arrows(0,40,0,60,length = 0.15,angle = 15,lwd = 2)

title(main = "Resultados Prueba Saber 11 Año 2018-2022")
title(main = "Instituto José Antonio Galán",line = 0.5)
title(xlab = "Años",font.lab=2)
title(ylab = "Puntajes",font.lab=2,line = 1)

legend("top",lty = 1,col = id_col2,lwd = 2,pch = 15,
       legend = c("Lectura",
                  "Matemáticas",
                  "Sociales",
                  "Naturales",
                  "Inglés"),
       horiz = T, 
       bty = "l",bg="lightblue",text.font = 2,
       text.col = id_col2)

text(id_year,acum[1,],pos = 3,font = 2,cex = 0.8,labels = acum[1,])
text(1,acum[2,1],pos = 3,font = 2,cex = 0.8,labels = acum[2,1],
     col="red")

text(2,acum[2,2],pos = 2,font = 2,cex = 0.8,labels = acum[2,2],
     col="red")

text(3,acum[2,3],pos = 3,font = 2,cex = 0.8,labels = acum[2,3],
     col="red")

text(4,acum[2,4],pos = 3,font = 2,cex = 0.8,labels = acum[2,4],
     col="red")

text(5,acum[2,5],pos = 4,font = 2,cex = 0.8,labels = acum[2,5],
     col="red")

text(id_year[-3],acum[3,-3],pos = 3,font = 2,cex = 0.8,labels = acum[3,-3],
     col="blue")

text(id_year[3],acum[3,3],pos = 1,font = 2,cex = 0.8,labels = acum[3,3],
     col="blue")

text(id_year[1],acum[4,1],pos = 2,font = 2,cex = 0.8,labels = acum[4,1],
     col="green")

text(id_year[5],acum[4,5],pos = 3,font = 2,cex = 0.8,labels = acum[4,5],
     col="green")

text(id_year[3],acum[4,3],pos = 1,font = 2,cex = 0.8,labels = acum[4,3],
     col="green")

text(id_year[4],acum[4,4],pos = 3,font = 2,cex = 0.8,labels = acum[4,4],
     col="green")

text(id_year,acum[5,],pos = 1,font = 2,cex = 0.8,labels = acum[5,],
     col="orange")

我尝试更改 X - Y 中的值，它有所改善，但并不完全。图表的线条仍然重叠。

Answer 1

使用

matplot

更容易。

type='o'

绘制线和点。动态编码

xlim/ylim

以允许它们适应新数据。在

text

中你可以输入矩阵。对于箭头，使用

par()$usr

给出绘图的边距位置。将代码放入函数中并使用

png

始终获得相同的大小。

plot_acum <- \(data, id_col=c("black", "red", "blue", "green", "orange")) {
  matplot(as.matrix(data), type='o', lty=1, lwd=2, pch=15, col=id_col, 
          xlim=c(.5, ncol(data) + .5), ylim=c(min(data)*.95, max(data)*1.075),
          ann=FALSE, axes=FALSE)
  title(main="Resultados Prueba Saber 11 Año 2018-2022")
  text(x=col(data), y=t(data)*1.005, pos=rep_len(1:3, ncol(data)), labels=t(data), 
       col=id_col, font=2)
  axis(1, axTicks(1), labels=gsub('.*_', '', colnames(data)), lwd=2, font=2)
  axis(2, las=1, lwd=2, font=2)
  mtext('Años', 1, 2.5, font=2); mtext('Puntajes', 2, 2.5, font=2)
  pu <- par()$usr
  arrows(pu[1], pu[3], pu[2], pu[3], length=0.15, angle=15, lwd=2.3, xpd=TRUE)
  arrows(pu[1], pu[3], pu[1], pu[4], length=0.15, angle=15, lwd=2.3, xpd=TRUE)
  legend("top", lty=1, col=id_col, lwd=2, pch=15, cex=.9, 
         legend=c("Lectura", "Matemáticas", "Sociales", "Naturales", "Inglés"), 
         horiz=TRUE, bg="#00808022", text.font=2, text.col=id_col)
}

使用随机测试

acum

:

acum <- array(round(runif(prod(dim(acum)), 50, 80)), dim(acum), dimnames(acum))

---

数据：

> dput(acum)
structure(list(med_res_galan_2018 = c(57, 60, 52, 57, 56), med_res_galan_2019 = c(62, 
62, 57, 59, 60), med_res_galan_2020 = c(60, 61, 56, 58, 54), 
    med_res_galan_2021 = c(59, 58, 53, 56, 54), med_res_galan_2022 = c(60, 
    60, 55, 59, 57)), class = "data.frame", row.names = c("Lectura", 
"Matemáticas", "Sociales", "Naturales", "Inglés"))