当前位置： 文江博客话题详情

ggplot2 将表格绘制为线条

发布于 2024-11-28 15:09:19 字数 5164 浏览 0 评论 0原文

我想绘制以下数据集

structure(list(X = structure(c(3L, 12L, 11L, 7L, 13L, 2L, 1L, 
10L, 5L, 4L, 8L, 14L, 9L, 6L), .Label = c("BUM", "DDR", "ETB", 
"EXP", "HED", "HEDOS", "KON", "LEIT", "MAIN", "MAT", "PER", "PMA", 
"TRA", "TRADITION"), class = "factor"), Geschaeft = c(0.0468431771894094, 
0.0916666666666667, 0.0654761904761905, 0.0905432595573441, 0.0761904761904762, 
0.0672097759674134, 0.0869565217391304, 0.0650887573964497, 0.0762250453720508, 
0.0518234165067179, 0.0561330561330561, 0.060077519379845, 0.0865384615384615, 
0.0628683693516699), Gaststaette = c(0.0855397148676171, 0.0604166666666667, 
0.0555555555555556, 0.0764587525150905, 0.0895238095238095, 0.0712830957230143, 
0.075098814229249, 0.0631163708086785, 0.0780399274047187, 0.0383877159309021, 
0.0561330561330561, 0.0581395348837209, 0.0596153846153846, 0.0648330058939096
), Bank = c(0.065173116089613, 0.0854166666666667, 0.0972222222222222, 
0.0824949698189135, 0.060952380952381, 0.0529531568228106, 0.0731225296442688, 
0.0828402366863905, 0.0725952813067151, 0.0806142034548944, 0.0686070686070686, 
0.0503875968992248, 0.0807692307692308, 0.0550098231827112), 
    Hausarzt = c(0.0712830957230143, 0.0833333333333333, 0.0912698412698413, 
    0.0704225352112676, 0.0628571428571429, 0.0672097759674134, 
    0.106719367588933, 0.0710059171597633, 0.108892921960073, 
    0.0940499040307102, 0.0852390852390852, 0.0794573643410853, 
    0.0826923076923077, 0.110019646365422), Einr..F..Aeltere = c(0.10183299389002, 
    0.104166666666667, 0.107142857142857, 0.100603621730382, 
    0.12, 0.116089613034623, 0.112648221343874, 0.112426035502959, 
    0.121597096188748, 0.0998080614203455, 0.118503118503119, 
    0.131782945736434, 0.121153846153846, 0.104125736738703), 
    Park = c(0.0855397148676171, 0.0666666666666667, 0.0912698412698413, 
    0.0804828973843058, 0.0704761904761905, 0.0672097759674134, 
    0.0731225296442688, 0.0670611439842209, 0.0834845735027223, 
    0.0806142034548944, 0.0686070686070686, 0.0658914728682171, 
    0.0884615384615385, 0.0609037328094303), Sportstaette = c(0.0855397148676171, 
    0.0791666666666667, 0.0952380952380952, 0.0824949698189135, 
    0.0933333333333333, 0.114052953156823, 0.0810276679841897, 
    0.0788954635108481, 0.0780399274047187, 0.0825335892514395, 
    0.0831600831600832, 0.0852713178294574, 0.0884615384615385, 
    0.1237721021611), OEPNV = c(0.0529531568228106, 0.05625, 
    0.0456349206349206, 0.0583501006036217, 0.0666666666666667, 
    0.0366598778004073, 0.0434782608695652, 0.0571992110453649, 
    0.0344827586206897, 0.0633397312859885, 0.0478170478170478, 
    0.062015503875969, 0.0519230769230769, 0.0235756385068762
    ), Mangel.an.Gruenflaechen = c(0.0692464358452139, 0.0645833333333333, 
    0.0694444444444444, 0.0422535211267606, 0.0666666666666667, 
    0.0692464358452139, 0.0711462450592885, 0.0749506903353057, 
    0.0598911070780399, 0.0959692898272553, 0.0623700623700624, 
    0.0717054263565891, 0.0653846153846154, 0.0746561886051081
    ), Kriminalitaet = c(0.0672097759674134, 0.0541666666666667, 
    0.0476190476190476, 0.0422535211267606, 0.0628571428571429, 
    0.0509164969450102, 0.0454545454545455, 0.0532544378698225, 
    0.058076225045372, 0.072936660268714, 0.0602910602910603, 
    0.063953488372093, 0.0461538461538462, 0.0648330058939096
    ), Auslaender = c(0.0244399185336049, 0.04375, 0.0416666666666667, 
    0.0663983903420523, 0.0228571428571429, 0.0509164969450102, 
    0.0237154150197628, 0.0236686390532544, 0.0217785843920145, 
    0.0441458733205374, 0.024948024948025, 0.0232558139534884, 
    0.0230769230769231, 0.0451866404715128), Umweltbelastung = c(0.0468431771894094, 
    0.0479166666666667, 0.0476190476190476, 0.0402414486921529, 
    0.0438095238095238, 0.0468431771894094, 0.0454545454545455, 
    0.0512820512820513, 0.0417422867513612, 0.0518234165067179, 
    0.0478170478170478, 0.0445736434108527, 0.0442307692307692, 
    0.0451866404715128), Einr..f..Kinder = c(0.0753564154786151, 
    0.075, 0.0555555555555556, 0.0724346076458753, 0.0533333333333333, 
    0.0794297352342159, 0.075098814229249, 0.0788954635108481, 
    0.0598911070780399, 0.0460652591170825, 0.0977130977130977, 
    0.0930232558139535, 0.0634615384615385, 0.0451866404715128
    ), Einr..f..Jugendliche = c(0.122199592668024, 0.0875, 0.0892857142857143, 
    0.0945674044265594, 0.11047619047619, 0.109979633401222, 
    0.0869565217391304, 0.120315581854043, 0.105263157894737, 
    0.0978886756238004, 0.122661122661123, 0.11046511627907, 
    0.0980769230769231, 0.119842829076621)), .Names = c("X", 
"Geschaeft", "Gaststaette", "Bank", "Hausarzt", "Einr..F..Aeltere", 
"Park", "Sportstaette", "OEPNV", "Mangel.an.Gruenflaechen", "Kriminalitaet", 
"Auslaender", "Umweltbelastung", "Einr..f..Kinder", "Einr..f..Jugendliche"
), row.names = c(NA, -14L), class = "data.frame")

，使其看起来像我用 Excel 创建的这张图片（或者在单独的图中每行更好）。

使用 Excel 创建的图像

但我不知道如何...

非常感谢您的帮助。 Dominik

更新：这只是组（BUM、DDR、ETB 等）含义的地图。 环境地图

原文

I would like to plot the following dataset

structure(list(X = structure(c(3L, 12L, 11L, 7L, 13L, 2L, 1L, 
10L, 5L, 4L, 8L, 14L, 9L, 6L), .Label = c("BUM", "DDR", "ETB", 
"EXP", "HED", "HEDOS", "KON", "LEIT", "MAIN", "MAT", "PER", "PMA", 
"TRA", "TRADITION"), class = "factor"), Geschaeft = c(0.0468431771894094, 
0.0916666666666667, 0.0654761904761905, 0.0905432595573441, 0.0761904761904762, 
0.0672097759674134, 0.0869565217391304, 0.0650887573964497, 0.0762250453720508, 
0.0518234165067179, 0.0561330561330561, 0.060077519379845, 0.0865384615384615, 
0.0628683693516699), Gaststaette = c(0.0855397148676171, 0.0604166666666667, 
0.0555555555555556, 0.0764587525150905, 0.0895238095238095, 0.0712830957230143, 
0.075098814229249, 0.0631163708086785, 0.0780399274047187, 0.0383877159309021, 
0.0561330561330561, 0.0581395348837209, 0.0596153846153846, 0.0648330058939096
), Bank = c(0.065173116089613, 0.0854166666666667, 0.0972222222222222, 
0.0824949698189135, 0.060952380952381, 0.0529531568228106, 0.0731225296442688, 
0.0828402366863905, 0.0725952813067151, 0.0806142034548944, 0.0686070686070686, 
0.0503875968992248, 0.0807692307692308, 0.0550098231827112), 
    Hausarzt = c(0.0712830957230143, 0.0833333333333333, 0.0912698412698413, 
    0.0704225352112676, 0.0628571428571429, 0.0672097759674134, 
    0.106719367588933, 0.0710059171597633, 0.108892921960073, 
    0.0940499040307102, 0.0852390852390852, 0.0794573643410853, 
    0.0826923076923077, 0.110019646365422), Einr..F..Aeltere = c(0.10183299389002, 
    0.104166666666667, 0.107142857142857, 0.100603621730382, 
    0.12, 0.116089613034623, 0.112648221343874, 0.112426035502959, 
    0.121597096188748, 0.0998080614203455, 0.118503118503119, 
    0.131782945736434, 0.121153846153846, 0.104125736738703), 
    Park = c(0.0855397148676171, 0.0666666666666667, 0.0912698412698413, 
    0.0804828973843058, 0.0704761904761905, 0.0672097759674134, 
    0.0731225296442688, 0.0670611439842209, 0.0834845735027223, 
    0.0806142034548944, 0.0686070686070686, 0.0658914728682171, 
    0.0884615384615385, 0.0609037328094303), Sportstaette = c(0.0855397148676171, 
    0.0791666666666667, 0.0952380952380952, 0.0824949698189135, 
    0.0933333333333333, 0.114052953156823, 0.0810276679841897, 
    0.0788954635108481, 0.0780399274047187, 0.0825335892514395, 
    0.0831600831600832, 0.0852713178294574, 0.0884615384615385, 
    0.1237721021611), OEPNV = c(0.0529531568228106, 0.05625, 
    0.0456349206349206, 0.0583501006036217, 0.0666666666666667, 
    0.0366598778004073, 0.0434782608695652, 0.0571992110453649, 
    0.0344827586206897, 0.0633397312859885, 0.0478170478170478, 
    0.062015503875969, 0.0519230769230769, 0.0235756385068762
    ), Mangel.an.Gruenflaechen = c(0.0692464358452139, 0.0645833333333333, 
    0.0694444444444444, 0.0422535211267606, 0.0666666666666667, 
    0.0692464358452139, 0.0711462450592885, 0.0749506903353057, 
    0.0598911070780399, 0.0959692898272553, 0.0623700623700624, 
    0.0717054263565891, 0.0653846153846154, 0.0746561886051081
    ), Kriminalitaet = c(0.0672097759674134, 0.0541666666666667, 
    0.0476190476190476, 0.0422535211267606, 0.0628571428571429, 
    0.0509164969450102, 0.0454545454545455, 0.0532544378698225, 
    0.058076225045372, 0.072936660268714, 0.0602910602910603, 
    0.063953488372093, 0.0461538461538462, 0.0648330058939096
    ), Auslaender = c(0.0244399185336049, 0.04375, 0.0416666666666667, 
    0.0663983903420523, 0.0228571428571429, 0.0509164969450102, 
    0.0237154150197628, 0.0236686390532544, 0.0217785843920145, 
    0.0441458733205374, 0.024948024948025, 0.0232558139534884, 
    0.0230769230769231, 0.0451866404715128), Umweltbelastung = c(0.0468431771894094, 
    0.0479166666666667, 0.0476190476190476, 0.0402414486921529, 
    0.0438095238095238, 0.0468431771894094, 0.0454545454545455, 
    0.0512820512820513, 0.0417422867513612, 0.0518234165067179, 
    0.0478170478170478, 0.0445736434108527, 0.0442307692307692, 
    0.0451866404715128), Einr..f..Kinder = c(0.0753564154786151, 
    0.075, 0.0555555555555556, 0.0724346076458753, 0.0533333333333333, 
    0.0794297352342159, 0.075098814229249, 0.0788954635108481, 
    0.0598911070780399, 0.0460652591170825, 0.0977130977130977, 
    0.0930232558139535, 0.0634615384615385, 0.0451866404715128
    ), Einr..f..Jugendliche = c(0.122199592668024, 0.0875, 0.0892857142857143, 
    0.0945674044265594, 0.11047619047619, 0.109979633401222, 
    0.0869565217391304, 0.120315581854043, 0.105263157894737, 
    0.0978886756238004, 0.122661122661123, 0.11046511627907, 
    0.0980769230769231, 0.119842829076621)), .Names = c("X", 
"Geschaeft", "Gaststaette", "Bank", "Hausarzt", "Einr..F..Aeltere", 
"Park", "Sportstaette", "OEPNV", "Mangel.an.Gruenflaechen", "Kriminalitaet", 
"Auslaender", "Umweltbelastung", "Einr..f..Kinder", "Einr..f..Jugendliche"
), row.names = c(NA, -14L), class = "data.frame")

So that it look like this picture (or better with each line in a seperate plot) that I created with Excel.

Image created with Excel

But I can't figure out how...

Thanks a lot for your help.
Dominik

UPDATE: Here is just a map of what the groups (BUM,DDR,ETB etc.) mean.
Milieu map

如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论， 你可以免费 注册 一个本站的账号。

评论（3）

爱的十字路口 2024-12-05 15:09:19

这是@Andrie 解决方案的扩展。它将分面思想与过度绘图相结合（从 学习者博客，我发现它产生了很酷的可视化结果。这是代码和结果输出。欢迎评论

mdf <- melt(df, id.vars="X")
mdf = transform(mdf, variable = reorder(variable, value, mean), Y = X)

ggplot(mdf, aes(x = variable, y = value)) + 
  geom_line(data = transform(mdf, X = NULL), aes(group = Y), colour = "grey80") +
  geom_line(aes(group = X)) +
  facet_wrap(~X) +
  opts(axis.text.x = theme_text(angle=90, hjust=1))

在此处输入图像描述

编辑：如果您有不同的环境分组，那么更好的呈现方式可能是以下

mycols = c(brewer.pal(4, 'Oranges'), brewer.pal(4, 'Greens'), 
           brewer.pal(3, 'Blues'), brewer.pal(3, 'PuRd'))
mdf2 = read.table(textConnection("
  V1,  V2
  ETB, LEIT
  PMA, LEIT
  PER, LEIT
  LEIT, LEIT
  KON, TRADITION
  TRA, TRADITION
  DDR, TRADITION
  TRADITION, TRADITION
  BUM, MAIN
  MAT, MAIN
  MAIN, MAIN
  EXP, HEDOS
  HED, HEDOS
  HEDOS, HEDOS"), sep = ",", header = T, stringsAsFactors = F)

mdf2 = data.frame(mdf2, mycols = mycols)
mdf3 = merge(mdf, mdf2, by.x = 'X', by.y = "V1")

p1 = ggplot(mdf3, aes(x = variable, y = value, group = X, colour = mycols)) + 
  geom_line(subset = .(nchar(as.character(X)) == 3)) +
  geom_line(subset = .(nchar(as.character(X)) != 3), size = 1.5) +
  facet_wrap(~ V2) +
  scale_color_identity(name = 'Milieus', breaks = mdf2$mycols, labels = mdf2$V1) +
  theme_bw() + 
  opts(axis.text.x = theme_text(angle=90, hjust=1))

在此处输入图像描述

This is an extension to @Andrie's solution. It combines the faceting idea with that of overplotting (stolen liberally from the learnr blog, which I find results in a cool visualization. Here is the code and the resulting output. Comments are welcome

mdf <- melt(df, id.vars="X")
mdf = transform(mdf, variable = reorder(variable, value, mean), Y = X)

ggplot(mdf, aes(x = variable, y = value)) + 
  geom_line(data = transform(mdf, X = NULL), aes(group = Y), colour = "grey80") +
  geom_line(aes(group = X)) +
  facet_wrap(~X) +
  opts(axis.text.x = theme_text(angle=90, hjust=1))

enter image description here

EDIT: If you have groupings of milieus, then a better way to present might be the following

mycols = c(brewer.pal(4, 'Oranges'), brewer.pal(4, 'Greens'), 
           brewer.pal(3, 'Blues'), brewer.pal(3, 'PuRd'))
mdf2 = read.table(textConnection("
  V1,  V2
  ETB, LEIT
  PMA, LEIT
  PER, LEIT
  LEIT, LEIT
  KON, TRADITION
  TRA, TRADITION
  DDR, TRADITION
  TRADITION, TRADITION
  BUM, MAIN
  MAT, MAIN
  MAIN, MAIN
  EXP, HEDOS
  HED, HEDOS
  HEDOS, HEDOS"), sep = ",", header = T, stringsAsFactors = F)

mdf2 = data.frame(mdf2, mycols = mycols)
mdf3 = merge(mdf, mdf2, by.x = 'X', by.y = "V1")

p1 = ggplot(mdf3, aes(x = variable, y = value, group = X, colour = mycols)) + 
  geom_line(subset = .(nchar(as.character(X)) == 3)) +
  geom_line(subset = .(nchar(as.character(X)) != 3), size = 1.5) +
  facet_wrap(~ V2) +
  scale_color_identity(name = 'Milieus', breaks = mdf2$mycols, labels = mdf2$V1) +
  theme_bw() + 
  opts(axis.text.x = theme_text(angle=90, hjust=1))

enter image description here

回复 原文
奶茶白久 2024-12-05 15:09:19

诀窍是在将数据传递给 ggplot 之前将其重新调整为高格式。使用 reshape2 包中的 melt 函数时，这很容易：

假设您的数据是一个名为 df 的变量：

library(reshape2)
library(ggplot2)

mdf <- melt(df, id.vars="X")
str(mdf)
ggplot(mdf, aes(x=variable, y=value, colour=X, group=X)) + geom_line() +
    opts(axis.text.x = theme_text(angle=90, hjust=1))

在此处输入图像描述

编辑 正如@Chase建议的那样，您可以使用分面来使绘图更具可读性:

ggplot(mdf, aes(x=X, y=value)) + geom_point() +
    opts(axis.text.x = theme_text(angle=90, hjust=1)) + facet_wrap(~variable)

在此处输入图像描述

The trick is to reshape your data into tall format before you pass it to ggplot. This is easy when using the melt function in package reshape2:

Assuming your data is a variable called df:

library(reshape2)
library(ggplot2)

mdf <- melt(df, id.vars="X")
str(mdf)
ggplot(mdf, aes(x=variable, y=value, colour=X, group=X)) + geom_line() +
    opts(axis.text.x = theme_text(angle=90, hjust=1))

enter image description here

Edit As @Chase suggests, you can use facetting to make the plot more readable:

ggplot(mdf, aes(x=X, y=value)) + geom_point() +
    opts(axis.text.x = theme_text(angle=90, hjust=1)) + facet_wrap(~variable)

enter image description here

回复 原文
会发光的星星闪亮亮i 2024-12-05 15:09:19

首先，融合数据以将其转换为长格式。

melted_data <- melt(the_data, id.vars = "X")

现在用数字 x 轴绘制绘图，并修复标签。

p <- ggplot(melted_data, aes(as.numeric(variable), value, colour = X)) + 
  geom_line() + 
  scale_x_continuous(
    breaks = seq_len(nlevels(melted_data$variable)), 
    labels = levels(melted_data$variable)
  ) +
  opts(axis.text.x = theme_text(angle = 90))
p

回答完这个问题后，我不确定情节告诉你什么&ndahs;对我来说这只是一堆混乱的线条。您可能最好将大部分线条变灰，并突出显示一两个有趣的线条。

添加一个列来挑选，例如 EXP。

melted_data$is_EXP <- with(melted_data, X == "EXP")

忽略我之前的回答；安德里的更好。使用手动颜色和尺寸比例来突出显示您的新列。

p <- ggplot(melted_data, aes(variable, value, colour = is_EXP, size = is_EXP, group = X)) + 
  geom_line() + 
  scale_colour_manual(values = c("grey80", "black")) + 
  scale_size_manual(values = c(0.5, 1.5)) +
  opts(axis.text.x = theme_text(angle = 90, hjust=1))
p

增强图

First, melt the data to put it in a long format.

melted_data <- melt(the_data, id.vars = "X")

Now draw the plot with a numeric x axis, and fix up the labels.

p <- ggplot(melted_data, aes(as.numeric(variable), value, colour = X)) + 
  geom_line() + 
  scale_x_continuous(
    breaks = seq_len(nlevels(melted_data$variable)), 
    labels = levels(melted_data$variable)
  ) +
  opts(axis.text.x = theme_text(angle = 90))
p

Having answered this, I'm not sure what the plot tells you &ndahs; it's just a jumble of lines to me. You might be better greying out most of the lines, and highlighting one or two interesting ones.

Add a column that picks out, e.g., EXP.

melted_data$is_EXP <- with(melted_data, X == "EXP")

Ignore my previous anser; Andrie's is better. Use manual colour and size scales to highlight your new column.

p <- ggplot(melted_data, aes(variable, value, colour = is_EXP, size = is_EXP, group = X)) + 
  geom_line() + 
  scale_colour_manual(values = c("grey80", "black")) + 
  scale_size_manual(values = c(0.5, 1.5)) +
  opts(axis.text.x = theme_text(angle = 90, hjust=1))
p

enhanced plot

回复 原文
~没有更多了~

关于作者

遮了一弯

暂无简介

0 文章
0 评论
23 人气
发私信

相关话题

更多

热门标签

操作系统 程序设计 IT运维 Linux系统管理 JavaScript 服务器应用 solaris C/C++ PHP Shell BSD Vue.js aix Oracle Python HTML 系统管理 HTML5 CSS 前端
更多

推荐作者

胡图图

文章 0 评论 0

zt006

文章 0 评论 0

z祗昰~

文章 0 评论 0

冰葑

文章 0 评论 0

野の

文章 0 评论 0

天空

文章 0 评论 0

更多

友情链接

文江博客
    我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站，即表示您同意使用 Cookies 和您的相关数据。
    原文