R ggplot2 网格标签
R ggplot2 grid labeling
有人要求我根据污染数据制作条形图。可以找到示例数据 here。数据结构如下
str(datos) 'data.frame': 55 obs. of 10 variables:
$ PROVINCIA : int 46 46 46 46 46 46 46 46 46 46 ...
$ ESTACION : Factor w/ 55 levels "Alacant-El_Pla",..: 5 1 2 3 8 23 24 21 31 22 ...
$ MAXIMO_HORARIO : num 99.5 88.5 88.5 90 97.5 87.3 96 92.5 88 20 ...
$ PROMEDIO_DIARIO : num NA NA NA NA NA NA NA NA NA NA ...
$ MAXIMO_OCTOHORARIO : num 103.9 83.1 80.9 75.7 95.1 ...
$ VARIACION_MAX_HOR : num -25.2 -6.5 -6.7 -1.2 -13.2 -15.4 -12.7
-29.5 -16.3 NA ...
$ VARIACION_PRM_DIA : num NA NA NA NA NA NA NA NA NA NA ...
$ OSCILACION_DIARIO : num 16.5 63.7 53.3 62 26.8 31.3 29.2 15 52 20 ...
$ ESTACIONALIDAD_MAX : num -38.2 -39.6 -36.8 -38.8 -37.6 -51.8 -35.6 -40.3 -42.9 -86.5 ...
$ ESTACIONALIDAD_MAX-1: num NA NA NA NA NA NA NA NA NA NA ...
我已经尝试使用 ggplot2 geom_bar 几何和以下代码的分面
datos=read.csv("data.csv",header=T,sep=",", na.strings="-99.9")
ggplot(datos, aes(ESTACION,MAXIMO_HORARIO, fill = factor(MAXIMO_HORARIO))) +
geom_bar(stat="identity") +
theme(axis.text.x = element_text(angle=90, size=10)) +
facet_grid(PROVINCIA ~ .)
获取此输出
这是正确的方式，但我希望每个方面（组）都显示自己的值而不是空 space 对应于另一个方面的数据，并且每个网格中都有正确的标签.我可以将数据分成三部分并生成三个不同的图，但我只想构建一个包含三个图的文件。
期望的输出看起来像
编辑：dput(datos) 的输出
**>
dput(datos)
structure(list(PROVINCIA = c(46L, 46L, 46L, 46L, 46L, 46L, 46L,
46L, 46L, 46L, 46L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L), ESTACION = structure(c(5L, 1L, 2L, 3L,
8L, 23L, 24L, 21L, 31L, 22L, 41L, 27L, 12L, 13L, 14L, 15L, 16L,
18L, 28L, 29L, 19L, 37L, 39L, 26L, 49L, 52L, 53L, 54L, 55L, 4L,
7L, 6L, 9L, 10L, 11L, 17L, 20L, 33L, 25L, 30L, 32L, 36L, 35L,
34L, 38L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 50L, 51L, 40L), .Label = c("Alacant-El_Pla",
"Alacant-Florida_Babel", "Alacant-Rabassa", "Albalat_dels_Tarongers",
"Alcoi-Verge_dels_Lliris", "Algar_de_Pal", "Alzira", "Benidorm",
"Benig", "Bull", "Burjassot-Facultats", "Burriana", "Castell1",
"Castell2", "Castell3", "Castell4", "Caudete_de_las_Fuentes",
"Cirat", "Coratxar", "Cortes_de_Pall", "Elda-Lacy", "El_Pin",
"Elx-Agroalimentari", "Elx-Parc_de_Bombers", "Gandia", "La_Vall_d",
"Lluce", "Morella", "Onda", "Ontinyent", "Orihuela", "Paterna-CEAM",
"Quart_de_Poblet", "Sagunt-CEA", "Sagunt-Nord", "Sagunt-Port",
"Sant_Jordi", "Torrebaja", "Torre_Endom", "Torrent-El_Vedat",
"Torrevieja", "Val1", "Val2", "Val3", "Val4", "Val5", "Val6",
"Val7", "Vilafranca", "Vilamarxant", "Villar_del_Arzobispo",
"Vinaros", "VinarosP", "Viver", "Zorita"), class = "factor"),
MAXIMO_HORARIO = c(99.5, 88.5, 88.5, 90, 97.5, 87.3, 96,
92.5, 88, 20, 20, 81.5, 99, 91.7, 93.5, 81.5, 90.5, 84.5,
100.3, 96.3, 41.7, 91.5, 57.3, NA, 93, 111.5, 86.8, NA, 100.3,
21.9, 80.5, 111, 98.7, 87.3, 89.7, 87.5, 41.7, 81.7, NA,
20, 84.8, 92, 88.7, NA, 74, NA, 95, 20.5, 85.7, 80, 82.3,
76, 20, 90.8, NA), PROMEDIO_DIARIO = c(NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 21.9, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA), MAXIMO_OCTOHORARIO = c(103.9, 83.1,
80.9, 75.7, 95.1, 82.9, 90.2, 83.5, 85, NA, NA, 77.1, 76.7,
91.4, 73.1, 65.1, 96.6, 81.1, 110.5, 91.1, NA, 87.8, 54.8,
NA, 95.1, 116.8, 79.9, NA, 107.2, 73.9, 70.5, 102.8, 100.5,
77.5, 80.9, 86.9, NA, 70.5, NA, NA, 73.5, 86.9, 86, NA, 83.5,
NA, 84.5, 20.5, 90.8, 71.5, 67.5, 64.5, NA, 91.4, NA), VARIACION_MAX_HOR = c(-25.2,
-6.5, -6.7, -1.2, -13.2, -15.4, -12.7, -29.5, -16.3, NA,
NA, -32.5, -11.5, -22.3, -19.5, -22.3, -25.3, -24.7, -14.7,
-18, NA, -12.8, -36, NA, -27.3, -11.4, -15.7, NA, -21.4,
-103.6, -26, -24.5, -33.1, -30, -31, -17.8, NA, -15.1, NA,
NA, -23.5, -32.5, -16.1, NA, -32.3, NA, -28.2, 0.3, -30.5,
-17.3, -18.4, -19.7, NA, -31.2, NA), VARIACION_PRM_DIA = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 0, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA), OSCILACION_DIARIO = c(16.5,
63.7, 53.3, 62, 26.8, 31.3, 29.2, 15, 52, 20, 20, 51.8, 85.7,
27.5, 80, 74.8, 45, 48.3, 12.5, 21.6, 41.7, 41.8, 35.3, NA,
26.5, 27.1, 64.2, NA, 58.6, 3.9, 39.2, 39.3, 32.9, 22.6,
43.4, 17.3, 41.7, 46.9, NA, 20, 50.8, 58.2, 64.5, NA, 2.7,
NA, 40.2, 1.5, 25.9, 30.5, 58.6, 31, 20, 15.8, NA), ESTACIONALIDAD_MAX = c(-38.2,
-39.6, -36.8, -38.8, -37.6, -51.8, -35.6, -40.3, -42.9, -86.5,
-83.6, -50.6, -35, -46.8, -45, -57.1, -31.4, -49.7, -35.5,
-45.7, -75.2, -44.1, -62.6, NA, -48.4, -10.8, -39.3, NA,
-38.1, -86.4, -53.7, -16.5, -42.3, -42.2, -38.1, -48.7, -68.2,
-45.4, NA, -87.6, -43.8, -44.2, -43.1, NA, -55.5, NA, -33.1,
-86.1, -38.3, -44.4, -41.6, -38.2, -85.5, -50.1, NA), ESTACIONALIDAD_MAX.1 = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, -71.11,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("PROVINCIA",
"ESTACION", "MAXIMO_HORARIO", "PROMEDIO_DIARIO", "MAXIMO_OCTOHORARIO",
"VARIACION_MAX_HOR", "VARIACION_PRM_DIA", "OSCILACION_DIARIO",
"ESTACIONALIDAD_MAX", "ESTACIONALIDAD_MAX.1"), class = "data.frame", row.names = c(NA,
-55L))
**
facet_grid() 不是为你想要的而设计的。分别制作三个地块是正确的做法。但是使用 gridExtra 包可以很容易地将这些绘图元素（gridExtra 包称它们为 "grobs"）组合成单个图或单个文件。
require(ggplot2)
require(gridExtra)
#toy data
dat <- data.frame(x=1:20, y=sample(1:20, size=20, replace=T), group=sample(1:3, size=20, replace=T))
#making each "grob"
p1 <- ggplot(subset(dat, group==1), aes(factor(x), y)) +
geom_bar(stat='identity')
p2 <- ggplot(subset(dat, group==2), aes(factor(x), y)) +
geom_bar(stat='identity')
p3 <- ggplot(subset(dat, group==3), aes(factor(x), y)) +
geom_bar(stat='identity')
#combine them into a single stack of plots
pAll <- grid.arrange(p1, p2, p3, ncol=1)
pAll
请注意，要使此方法起作用，父项 data.frame 中的 x 变量必须是字符串或数字，而不是因子。 （对于数字，您必须在子集化后将其作为一个因子：这是 ggplot2 知道您 不想 显示每个子集没有的间隙的唯一方法数据。对于字符串，这不是问题，而且 x 轴在任何时候都不需要成为一个因素。）
听起来您想要 facet_wrap 而不是 facet_grid。尝试
ggplot(datos, aes(ESTACION,MAXIMO_HORARIO, fill = factor(MAXIMO_HORARIO))) +
geom_bar(stat="identity") +
theme(axis.text.x = element_text(angle=90, size=10)) +
facet_wrap(~PROVINCIA , scales="free", ncol=1)
得到
有人要求我根据污染数据制作条形图。可以找到示例数据 here。数据结构如下
str(datos) 'data.frame': 55 obs. of 10 variables:
$ PROVINCIA : int 46 46 46 46 46 46 46 46 46 46 ...
$ ESTACION : Factor w/ 55 levels "Alacant-El_Pla",..: 5 1 2 3 8 23 24 21 31 22 ...
$ MAXIMO_HORARIO : num 99.5 88.5 88.5 90 97.5 87.3 96 92.5 88 20 ...
$ PROMEDIO_DIARIO : num NA NA NA NA NA NA NA NA NA NA ...
$ MAXIMO_OCTOHORARIO : num 103.9 83.1 80.9 75.7 95.1 ...
$ VARIACION_MAX_HOR : num -25.2 -6.5 -6.7 -1.2 -13.2 -15.4 -12.7
-29.5 -16.3 NA ...
$ VARIACION_PRM_DIA : num NA NA NA NA NA NA NA NA NA NA ...
$ OSCILACION_DIARIO : num 16.5 63.7 53.3 62 26.8 31.3 29.2 15 52 20 ...
$ ESTACIONALIDAD_MAX : num -38.2 -39.6 -36.8 -38.8 -37.6 -51.8 -35.6 -40.3 -42.9 -86.5 ...
$ ESTACIONALIDAD_MAX-1: num NA NA NA NA NA NA NA NA NA NA ...
我已经尝试使用 ggplot2 geom_bar 几何和以下代码的分面
datos=read.csv("data.csv",header=T,sep=",", na.strings="-99.9")
ggplot(datos, aes(ESTACION,MAXIMO_HORARIO, fill = factor(MAXIMO_HORARIO))) +
geom_bar(stat="identity") +
theme(axis.text.x = element_text(angle=90, size=10)) +
facet_grid(PROVINCIA ~ .)
获取此输出
这是正确的方式，但我希望每个方面（组）都显示自己的值而不是空 space 对应于另一个方面的数据，并且每个网格中都有正确的标签.我可以将数据分成三部分并生成三个不同的图，但我只想构建一个包含三个图的文件。
期望的输出看起来像
编辑：dput(datos) 的输出 **>
dput(datos)
structure(list(PROVINCIA = c(46L, 46L, 46L, 46L, 46L, 46L, 46L,
46L, 46L, 46L, 46L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L), ESTACION = structure(c(5L, 1L, 2L, 3L,
8L, 23L, 24L, 21L, 31L, 22L, 41L, 27L, 12L, 13L, 14L, 15L, 16L,
18L, 28L, 29L, 19L, 37L, 39L, 26L, 49L, 52L, 53L, 54L, 55L, 4L,
7L, 6L, 9L, 10L, 11L, 17L, 20L, 33L, 25L, 30L, 32L, 36L, 35L,
34L, 38L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 50L, 51L, 40L), .Label = c("Alacant-El_Pla",
"Alacant-Florida_Babel", "Alacant-Rabassa", "Albalat_dels_Tarongers",
"Alcoi-Verge_dels_Lliris", "Algar_de_Pal", "Alzira", "Benidorm",
"Benig", "Bull", "Burjassot-Facultats", "Burriana", "Castell1",
"Castell2", "Castell3", "Castell4", "Caudete_de_las_Fuentes",
"Cirat", "Coratxar", "Cortes_de_Pall", "Elda-Lacy", "El_Pin",
"Elx-Agroalimentari", "Elx-Parc_de_Bombers", "Gandia", "La_Vall_d",
"Lluce", "Morella", "Onda", "Ontinyent", "Orihuela", "Paterna-CEAM",
"Quart_de_Poblet", "Sagunt-CEA", "Sagunt-Nord", "Sagunt-Port",
"Sant_Jordi", "Torrebaja", "Torre_Endom", "Torrent-El_Vedat",
"Torrevieja", "Val1", "Val2", "Val3", "Val4", "Val5", "Val6",
"Val7", "Vilafranca", "Vilamarxant", "Villar_del_Arzobispo",
"Vinaros", "VinarosP", "Viver", "Zorita"), class = "factor"),
MAXIMO_HORARIO = c(99.5, 88.5, 88.5, 90, 97.5, 87.3, 96,
92.5, 88, 20, 20, 81.5, 99, 91.7, 93.5, 81.5, 90.5, 84.5,
100.3, 96.3, 41.7, 91.5, 57.3, NA, 93, 111.5, 86.8, NA, 100.3,
21.9, 80.5, 111, 98.7, 87.3, 89.7, 87.5, 41.7, 81.7, NA,
20, 84.8, 92, 88.7, NA, 74, NA, 95, 20.5, 85.7, 80, 82.3,
76, 20, 90.8, NA), PROMEDIO_DIARIO = c(NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 21.9, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA), MAXIMO_OCTOHORARIO = c(103.9, 83.1,
80.9, 75.7, 95.1, 82.9, 90.2, 83.5, 85, NA, NA, 77.1, 76.7,
91.4, 73.1, 65.1, 96.6, 81.1, 110.5, 91.1, NA, 87.8, 54.8,
NA, 95.1, 116.8, 79.9, NA, 107.2, 73.9, 70.5, 102.8, 100.5,
77.5, 80.9, 86.9, NA, 70.5, NA, NA, 73.5, 86.9, 86, NA, 83.5,
NA, 84.5, 20.5, 90.8, 71.5, 67.5, 64.5, NA, 91.4, NA), VARIACION_MAX_HOR = c(-25.2,
-6.5, -6.7, -1.2, -13.2, -15.4, -12.7, -29.5, -16.3, NA,
NA, -32.5, -11.5, -22.3, -19.5, -22.3, -25.3, -24.7, -14.7,
-18, NA, -12.8, -36, NA, -27.3, -11.4, -15.7, NA, -21.4,
-103.6, -26, -24.5, -33.1, -30, -31, -17.8, NA, -15.1, NA,
NA, -23.5, -32.5, -16.1, NA, -32.3, NA, -28.2, 0.3, -30.5,
-17.3, -18.4, -19.7, NA, -31.2, NA), VARIACION_PRM_DIA = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 0, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA), OSCILACION_DIARIO = c(16.5,
63.7, 53.3, 62, 26.8, 31.3, 29.2, 15, 52, 20, 20, 51.8, 85.7,
27.5, 80, 74.8, 45, 48.3, 12.5, 21.6, 41.7, 41.8, 35.3, NA,
26.5, 27.1, 64.2, NA, 58.6, 3.9, 39.2, 39.3, 32.9, 22.6,
43.4, 17.3, 41.7, 46.9, NA, 20, 50.8, 58.2, 64.5, NA, 2.7,
NA, 40.2, 1.5, 25.9, 30.5, 58.6, 31, 20, 15.8, NA), ESTACIONALIDAD_MAX = c(-38.2,
-39.6, -36.8, -38.8, -37.6, -51.8, -35.6, -40.3, -42.9, -86.5,
-83.6, -50.6, -35, -46.8, -45, -57.1, -31.4, -49.7, -35.5,
-45.7, -75.2, -44.1, -62.6, NA, -48.4, -10.8, -39.3, NA,
-38.1, -86.4, -53.7, -16.5, -42.3, -42.2, -38.1, -48.7, -68.2,
-45.4, NA, -87.6, -43.8, -44.2, -43.1, NA, -55.5, NA, -33.1,
-86.1, -38.3, -44.4, -41.6, -38.2, -85.5, -50.1, NA), ESTACIONALIDAD_MAX.1 = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, -71.11,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("PROVINCIA",
"ESTACION", "MAXIMO_HORARIO", "PROMEDIO_DIARIO", "MAXIMO_OCTOHORARIO",
"VARIACION_MAX_HOR", "VARIACION_PRM_DIA", "OSCILACION_DIARIO",
"ESTACIONALIDAD_MAX", "ESTACIONALIDAD_MAX.1"), class = "data.frame", row.names = c(NA,
-55L))
**
facet_grid() 不是为你想要的而设计的。分别制作三个地块是正确的做法。但是使用 gridExtra 包可以很容易地将这些绘图元素（gridExtra 包称它们为 "grobs"）组合成单个图或单个文件。
require(ggplot2)
require(gridExtra)
#toy data
dat <- data.frame(x=1:20, y=sample(1:20, size=20, replace=T), group=sample(1:3, size=20, replace=T))
#making each "grob"
p1 <- ggplot(subset(dat, group==1), aes(factor(x), y)) +
geom_bar(stat='identity')
p2 <- ggplot(subset(dat, group==2), aes(factor(x), y)) +
geom_bar(stat='identity')
p3 <- ggplot(subset(dat, group==3), aes(factor(x), y)) +
geom_bar(stat='identity')
#combine them into a single stack of plots
pAll <- grid.arrange(p1, p2, p3, ncol=1)
pAll
请注意，要使此方法起作用，父项 data.frame 中的 x 变量必须是字符串或数字，而不是因子。 （对于数字，您必须在子集化后将其作为一个因子：这是 ggplot2 知道您 不想 显示每个子集没有的间隙的唯一方法数据。对于字符串，这不是问题，而且 x 轴在任何时候都不需要成为一个因素。）
听起来您想要 facet_wrap 而不是 facet_grid。尝试
ggplot(datos, aes(ESTACION,MAXIMO_HORARIO, fill = factor(MAXIMO_HORARIO))) +
geom_bar(stat="identity") +
theme(axis.text.x = element_text(angle=90, size=10)) +
facet_wrap(~PROVINCIA , scales="free", ncol=1)
得到