geom_bar 中的条在使用 facet_wrap 时有不需要的不同宽度
Bars in geom_bar have unwanted different widths when using facet_wrap
我找不到解决以下问题的方法。非常感谢您的帮助！
以下代码使用 facet 生成条形图。然而，由于 "extra space" ggplot2 在某些组中有它使条形更宽，即使我指定宽度为 0.1 或类似的宽度。我觉得这很烦人，因为它看起来很不专业。我希望所有条形看起来都一样（填充除外）。我希望有人能告诉我如何解决这个问题。
其次，我如何重新排序方面 windows 中的不同 类，以便顺序始终为 C1、C2 ... C5、M、F，所有适用的地方。我尝试对因子的水平进行排序，但由于并非所有 类 都出现在每个图形部分中，因此它不起作用，或者至少我认为这是原因。
第三，如何减少条形之间的 space？从而使整个图更加压缩。即使我将图像缩小以便导出，R 也会将条形缩放得更小，但条形之间的 spaces 仍然很大。
对于任何这些答案，我将不胜感激！
我的数据：
http://pastebin.com/embed_iframe.php?i=kNVnmcR1
我的代码：
library(dplyr)
library(gdata)
library(ggplot2)
library(directlabels)
library(scales)
all<-read.xls('all_auto_visual_c.xls')
all$station<-as.factor(all$station)
#all$group.new<-factor(all$group, levels=c('C. hyperboreus','C. glacialis','Special Calanus','M. longa','Pseudocalanus sp.','Copepoda'))
allp <- ggplot(data = all, aes(x=shortname2, y=perc_correct, group=group,fill=sample_size)) +
geom_bar(aes(fill=sample_size),stat="identity", position="dodge", width=0.1, colour="NA") + scale_fill_gradient("Sample size (n)",low="lightblue",high="navyblue")+
facet_wrap(group~station,ncol=2,scales="free_x")+
xlab("Species and stages") + ylab("Automatic identification and visual validation concur (%)") +
ggtitle("Visual validation of predictions") +
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1), axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"), axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"), axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"), axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),legend.position="none", strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0), strip.text.y = element_text(size = 12, face="bold", colour = "black"))
allp
#ggsave(allp, file="auto_visual_stackover.jpeg", height= 11, width= 8.5, dpi= 400,)
当前需要修正的图表：
非常感谢！
这是我根据 Gregor 的建议所做的。如我所想，使用 geom_segment 和 geom_point 可以制作出漂亮的图表。
library(ggplot2)
all<-read.xls('all_auto_visual_c.xls')
all$station<-as.factor(all$station)
all$group.new<-factor(all$group, levels=c('C. hyperboreus','C. glacialis','Combined','M. longa','Pseudocalanus sp.','Copepoda'))
all$shortname2.new<-factor(all$shortname2, levels=c('All','F','M','C5','C4','C3','C2','C1','Micro', 'Oith','Tric','Cegg','Cnaup','C3&2','C2&1'))
allp<-ggplot(all, aes(x=perc_correct, y=shortname2.new)) +
geom_segment(aes(yend=shortname2.new), xend=0, colour="grey50") +
geom_point(size=4, aes(colour=sample_size)) +
scale_colour_gradient("Sample size (n)",low="lightblue",high="navyblue") +
geom_text(aes(label = perc_correct, hjust = -0.5)) +
theme_bw() +
theme(panel.grid.major.y = element_blank()) +
facet_grid(group.new~station,scales="free_y",space="free") +
xlab("Automatic identification and visual validation concur (%)") + ylab("Species and stages")+
ggtitle("Visual validation of predictions")+
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1), axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"), axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"), axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"), axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),legend.position="none", strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0), strip.text.y = element_text(size = 8, face="bold", colour = "black"))
allp
ggsave(allp, file="auto_visual_no_label.jpeg", height= 11, width= 8.5, dpi= 400,)
这就是它产生的结果！
假设条形宽度与 x-breaks 的数量成反比，可以输入适当的比例因子作为 width 美学来控制条形宽度。但首先，计算每个面板中的 x-breaks 数量，计算比例因子，并将它们放回 "all" 数据框。
更新到 ggplot2 2.0.0 facet_wrap 中提到的每一列在条带中都有自己的行。在编辑中，在数据框中设置了一个新的标签变量，以便条带标签保持在一行上。
library(ggplot2)
library(plyr)
all = structure(list(station = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Station 101",
"Station 126"), class = "factor"), shortname2 = structure(c(2L,
7L, 8L, 11L, 1L, 5L, 7L, 8L, 11L, 1L, 2L, 3L, 5L, 7L, 8L, 12L,
11L, 1L, 6L, 8L, 15L, 14L, 9L, 10L, 4L, 6L, 2L, 7L, 8L, 11L,
1L, 5L, 7L, 8L, 11L, 1L, 2L, 3L, 5L, 7L, 8L, 12L, 11L, 1L, 8L,
11L, 1L, 15L, 14L, 13L, 9L, 10L), .Label = c("All", "C1", "C2",
"C2&1", "C3", "C3&2", "C4", "C5", "Cegg", "Cnaup", "F", "M",
"Micro", "Oith", "Tric"), class = "factor"), color = c(1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
18L, 19L, 21L, 26L, 30L, 31L, 33L, 34L, 20L, 21L, 1L, 2L, 3L,
4L, 5L, 6L, 7L, 8L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L,
19L, 26L, 28L, 29L, 30L, 31L, 32L, 33L, 34L), group = structure(c(1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 6L, 5L, 3L, 3L, 3L, 3L, 6L, 6L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 3L, 3L,
3L, 3L, 3L), .Label = c("cgla", "Chyp", "Cope", "mlong", "pseudo",
"specC"), class = "factor"), sample_size = c(11L, 37L, 55L, 16L,
119L, 21L, 55L, 42L, 40L, 158L, 24L, 16L, 17L, 27L, 14L, 45L,
98L, 241L, 30L, 34L, 51L, 22L, 14L, 47L, 13L, 41L, 24L, 41L,
74L, 20L, 159L, 18L, 100L, 32L, 29L, 184L, 31L, 17L, 27L, 23L,
21L, 17L, 49L, 185L, 30L, 16L, 46L, 57L, 16L, 12L, 30L, 42L),
perc_correct = c(91L, 78L, 89L, 81L, 85L, 90L, 91L, 93L,
80L, 89L, 75L, 75L, 76L, 81L, 86L, 76L, 79L, 78L, 90L, 97L,
75L, 86L, 93L, 74L, 85L, 88L, 88L, 90L, 92L, 90L, 91L, 89L,
89L, 91L, 90L, 89L, 81L, 88L, 74L, 78L, 90L, 82L, 84L, 82L,
90L, 94L, 91L, 81L, 69L, 83L, 90L, 81L)), class = "data.frame", row.names = c(NA,
-52L))
all$station <- as.factor(all$station)
# Calculate scaling factor and insert into data frame
library(plyr)
N = ddply(all, .(station, group), function(x) length(row.names(x)))
N$Fac = N$V1 / max(N$V1)
all = merge(all, N[,-3], by = c("station", "group"))
all$label = paste(all$group, all$station, sep = ", ")
allp <- ggplot(data = all, aes(x=shortname2, y=perc_correct, group=group, fill=sample_size, width = .5*Fac)) +
geom_bar(stat="identity", position="dodge", colour="NA") +
scale_fill_gradient("Sample size (n)",low="lightblue",high="navyblue")+
facet_wrap(~label,ncol=2,scales="free_x") +
xlab("Species and stages") + ylab("Automatic identification and visual validation concur (%)") +
ggtitle("Visual validation of predictions") +
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1),
axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"),
axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"),
axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"),
axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),
legend.position="none",
strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0),
strip.text.y = element_text(size = 12, face="bold", colour = "black"))
allp
我找不到解决以下问题的方法。非常感谢您的帮助！
以下代码使用 facet 生成条形图。然而，由于 "extra space" ggplot2 在某些组中有它使条形更宽，即使我指定宽度为 0.1 或类似的宽度。我觉得这很烦人，因为它看起来很不专业。我希望所有条形看起来都一样（填充除外）。我希望有人能告诉我如何解决这个问题。
其次，我如何重新排序方面 windows 中的不同 类，以便顺序始终为 C1、C2 ... C5、M、F，所有适用的地方。我尝试对因子的水平进行排序，但由于并非所有 类 都出现在每个图形部分中，因此它不起作用，或者至少我认为这是原因。
第三，如何减少条形之间的 space？从而使整个图更加压缩。即使我将图像缩小以便导出，R 也会将条形缩放得更小，但条形之间的 spaces 仍然很大。
对于任何这些答案，我将不胜感激！
我的数据： http://pastebin.com/embed_iframe.php?i=kNVnmcR1
我的代码：
library(dplyr)
library(gdata)
library(ggplot2)
library(directlabels)
library(scales)
all<-read.xls('all_auto_visual_c.xls')
all$station<-as.factor(all$station)
#all$group.new<-factor(all$group, levels=c('C. hyperboreus','C. glacialis','Special Calanus','M. longa','Pseudocalanus sp.','Copepoda'))
allp <- ggplot(data = all, aes(x=shortname2, y=perc_correct, group=group,fill=sample_size)) +
geom_bar(aes(fill=sample_size),stat="identity", position="dodge", width=0.1, colour="NA") + scale_fill_gradient("Sample size (n)",low="lightblue",high="navyblue")+
facet_wrap(group~station,ncol=2,scales="free_x")+
xlab("Species and stages") + ylab("Automatic identification and visual validation concur (%)") +
ggtitle("Visual validation of predictions") +
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1), axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"), axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"), axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"), axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),legend.position="none", strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0), strip.text.y = element_text(size = 12, face="bold", colour = "black"))
allp
#ggsave(allp, file="auto_visual_stackover.jpeg", height= 11, width= 8.5, dpi= 400,)
当前需要修正的图表：
非常感谢！
这是我根据 Gregor 的建议所做的。如我所想，使用 geom_segment 和 geom_point 可以制作出漂亮的图表。
library(ggplot2)
all<-read.xls('all_auto_visual_c.xls')
all$station<-as.factor(all$station)
all$group.new<-factor(all$group, levels=c('C. hyperboreus','C. glacialis','Combined','M. longa','Pseudocalanus sp.','Copepoda'))
all$shortname2.new<-factor(all$shortname2, levels=c('All','F','M','C5','C4','C3','C2','C1','Micro', 'Oith','Tric','Cegg','Cnaup','C3&2','C2&1'))
allp<-ggplot(all, aes(x=perc_correct, y=shortname2.new)) +
geom_segment(aes(yend=shortname2.new), xend=0, colour="grey50") +
geom_point(size=4, aes(colour=sample_size)) +
scale_colour_gradient("Sample size (n)",low="lightblue",high="navyblue") +
geom_text(aes(label = perc_correct, hjust = -0.5)) +
theme_bw() +
theme(panel.grid.major.y = element_blank()) +
facet_grid(group.new~station,scales="free_y",space="free") +
xlab("Automatic identification and visual validation concur (%)") + ylab("Species and stages")+
ggtitle("Visual validation of predictions")+
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1), axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"), axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"), axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"), axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),legend.position="none", strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0), strip.text.y = element_text(size = 8, face="bold", colour = "black"))
allp
ggsave(allp, file="auto_visual_no_label.jpeg", height= 11, width= 8.5, dpi= 400,)
这就是它产生的结果！
假设条形宽度与 x-breaks 的数量成反比，可以输入适当的比例因子作为 width 美学来控制条形宽度。但首先，计算每个面板中的 x-breaks 数量，计算比例因子，并将它们放回 "all" 数据框。
更新到 ggplot2 2.0.0 facet_wrap 中提到的每一列在条带中都有自己的行。在编辑中，在数据框中设置了一个新的标签变量，以便条带标签保持在一行上。
library(ggplot2)
library(plyr)
all = structure(list(station = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Station 101",
"Station 126"), class = "factor"), shortname2 = structure(c(2L,
7L, 8L, 11L, 1L, 5L, 7L, 8L, 11L, 1L, 2L, 3L, 5L, 7L, 8L, 12L,
11L, 1L, 6L, 8L, 15L, 14L, 9L, 10L, 4L, 6L, 2L, 7L, 8L, 11L,
1L, 5L, 7L, 8L, 11L, 1L, 2L, 3L, 5L, 7L, 8L, 12L, 11L, 1L, 8L,
11L, 1L, 15L, 14L, 13L, 9L, 10L), .Label = c("All", "C1", "C2",
"C2&1", "C3", "C3&2", "C4", "C5", "Cegg", "Cnaup", "F", "M",
"Micro", "Oith", "Tric"), class = "factor"), color = c(1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
18L, 19L, 21L, 26L, 30L, 31L, 33L, 34L, 20L, 21L, 1L, 2L, 3L,
4L, 5L, 6L, 7L, 8L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L,
19L, 26L, 28L, 29L, 30L, 31L, 32L, 33L, 34L), group = structure(c(1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 6L, 5L, 3L, 3L, 3L, 3L, 6L, 6L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 3L, 3L,
3L, 3L, 3L), .Label = c("cgla", "Chyp", "Cope", "mlong", "pseudo",
"specC"), class = "factor"), sample_size = c(11L, 37L, 55L, 16L,
119L, 21L, 55L, 42L, 40L, 158L, 24L, 16L, 17L, 27L, 14L, 45L,
98L, 241L, 30L, 34L, 51L, 22L, 14L, 47L, 13L, 41L, 24L, 41L,
74L, 20L, 159L, 18L, 100L, 32L, 29L, 184L, 31L, 17L, 27L, 23L,
21L, 17L, 49L, 185L, 30L, 16L, 46L, 57L, 16L, 12L, 30L, 42L),
perc_correct = c(91L, 78L, 89L, 81L, 85L, 90L, 91L, 93L,
80L, 89L, 75L, 75L, 76L, 81L, 86L, 76L, 79L, 78L, 90L, 97L,
75L, 86L, 93L, 74L, 85L, 88L, 88L, 90L, 92L, 90L, 91L, 89L,
89L, 91L, 90L, 89L, 81L, 88L, 74L, 78L, 90L, 82L, 84L, 82L,
90L, 94L, 91L, 81L, 69L, 83L, 90L, 81L)), class = "data.frame", row.names = c(NA,
-52L))
all$station <- as.factor(all$station)
# Calculate scaling factor and insert into data frame
library(plyr)
N = ddply(all, .(station, group), function(x) length(row.names(x)))
N$Fac = N$V1 / max(N$V1)
all = merge(all, N[,-3], by = c("station", "group"))
all$label = paste(all$group, all$station, sep = ", ")
allp <- ggplot(data = all, aes(x=shortname2, y=perc_correct, group=group, fill=sample_size, width = .5*Fac)) +
geom_bar(stat="identity", position="dodge", colour="NA") +
scale_fill_gradient("Sample size (n)",low="lightblue",high="navyblue")+
facet_wrap(~label,ncol=2,scales="free_x") +
xlab("Species and stages") + ylab("Automatic identification and visual validation concur (%)") +
ggtitle("Visual validation of predictions") +
theme_bw() +
theme(plot.title = element_text(lineheight=.8, face="bold", size=20,vjust=1),
axis.text.x = element_text(colour="grey20",size=12,angle=0,hjust=.5,vjust=.5,face="bold"),
axis.text.y = element_text(colour="grey20",size=12,angle=0,hjust=1,vjust=0,face="bold"),
axis.title.x = element_text(colour="grey20",size=15,angle=0,hjust=.5,vjust=0,face="bold"),
axis.title.y = element_text(colour="grey20",size=15,angle=90,hjust=.5,vjust=1,face="bold"),
legend.position="none",
strip.text.x = element_text(size = 12, face="bold", colour = "black", angle = 0),
strip.text.y = element_text(size = 12, face="bold", colour = "black"))
allp