我在避免图形中重叠标签方面遇到了问题。我看一下类似的问题,但没有一个能帮我解决问题。下面我提供了一个可重复的例子。另外,我不明白为什么direct.labels没有为每个标签选择合适的颜色。
mydf <- structure(list(ano = c(1970, 1975, 1980, 1985, 1990, 1995, 2000,
2004, 2005, 2006, 2007, 2008, 2009, 1970, 1975, 1980, 1985, 1990,
1995, 2000, 2004, 2005, 2006, 2007, 2008, 2009, 1970, 1975, 1980,
1985, 1990, 1995, 2000, 2004, 2005, 2006, 2007, 2008, 2009, 1970,
1975, 1980, 1985, 1990, 1995, 2000, 2004, 2005, 2006, 2007, 2008,
2009, 1970, 1975, 1980, 1985, 1990, 1995, 2000, 2004, 2005, 2006,
2007, 2008, 2009, 1970, 1975, 1980, 1985, 1990, 1995, 2000, 2004,
2005, 2006, 2007, 2008, 2009, 1970, 1975, 1980, 1985, 1990, 1995,
2000, 2004, 2005, 2006, 2007, 2008, 2009), field = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L), .Label = c("Humanites",
"Scial Sciences", "Natural Sciences", "Computer science and engineering",
"education", "business", "Other fields"), class = "factor"),
value = c(143549, 150736, 134139, 132891, 172485, 193404,
214107, 254847, 261696, 265808, 274535, 278387, 280993, 193511,
176674, 141581, 134468, 183762, 199895, 201681, 242506, 249619,
254222, 259950, 262771, 269996, 81916, 91596, 78092, 76228,
70209, 93443, 89772, 99370, 105899, 113077, 117200, 121009,
125809, 52570, 52328, 90476, 139459, 104910, 102503, 117011,
133655, 128886, 124024, 122084, 122408, 128318, 176307, 154437,
108074, 87147, 110807, 105384, 105458, 105451, 107238, 105641,
102582, 101708, 101265, 115396, 143171, 200521, 236700, 249165,
226623, 263515, 311574, 318042, 327531, 335254, 347985, 358293,
76481, 156804, 182257, 180930, 203200, 243540, 252627, 291861,
313862, 333789, 351464, 367100, 385340)), .Names = c("ano",
"field", "value"), row.names = c(NA, -91L), class = "data.frame")
require(ggplot2)
require(directlabels)
require(scales)
p <- ggplot(mydf, aes(y=value, x=ano, group=field)) + geom_line(aes(group=field, colour=field), show_guide = FALSE) +
ylab("Number of B.A. degrees awarded") + xlab("year") + theme_hyper() +
theme(legend.key = element_rect(colour = "white")) + scale_y_continuous(labels=comma)
p1 <- p + geom_dl(aes(label=field), list('last.points', cex = 1.3, hjust = 1))
p1
函数theme_hyper如下:
theme_hyper <- function(angle=0, fonte="arial", size=14) {
theme(panel.grid.major = element_blank()) +
theme(panel.background = element_blank())+
theme (panel.grid.minor = element_blank()) +
theme(legend.title = element_text(family=fonte, size = size, face = "bold")) +
theme(legend.text = element_text(family=fonte, size = size, face = "bold")) +
theme(plot.title = element_text(family=fonte, size = size, face = "bold")) +
theme(axis.text.x = element_text(family=fonte, size = size, face = "bold", angle = angle, vjust = .5)) +
theme(axis.text.y= element_text(family=fonte, size = size, face = "bold", hjust=.5)) +
theme(axis.title.x= element_text(family=fonte, size = size, face = "bold")) +
theme(axis.title.y= element_text(family=fonte, size = size, face = "bold"))
}
答案 0 :(得分:7)
使用"last.bumpup"
添加colour=field
为标签添加颜色。
geom_dl(aes(label=field, colour=field), list('last.bumpup', cex = 1.3, hjust = 1))
删除颜色图例/指南。
scale_colour_discrete(guide="none")
最后的电话:
p <- ggplot(mydf, aes(y=value, x=ano, group=field)) +
geom_line(aes(group=field, colour=field), show_guide = FALSE) +
ylab("Number of B.A. degrees awarded") + xlab("year") + theme_hyper() +
theme(legend.key = element_rect(colour = "white")) +
scale_y_continuous(labels=comma) +
geom_dl(aes(label=field, colour=field), list('last.bumpup', cex = 1.3, hjust = 1)) +
scale_colour_discrete(guide="none")
答案 1 :(得分:4)
您是否考虑过使用ggrepel定位文字标签而不重叠?
阅读数据:
library(ggrepel)
#> Loading required package: ggplot2
library(scales)
library(readr)
#>
#> Attaching package: 'readr'
#> The following object is masked from 'package:scales':
#>
#> col_factor
library(sitools)
library(tools)
mydf <- read_tsv("ano field value
1970 Humanities 143549
1975 Humanities 150736
1980 Humanities 134139
1985 Humanities 132891
1990 Humanities 172485
1995 Humanities 193404
2000 Humanities 214107
2004 Humanities 254847
2005 Humanities 261696
2006 Humanities 265808
2007 Humanities 274535
2008 Humanities 278387
2009 Humanities 280993
1970 Social Sciences 193511
1975 Social Sciences 176674
1980 Social Sciences 141581
1985 Social Sciences 134468
1990 Social Sciences 183762
1995 Social Sciences 199895
2000 Social Sciences 201681
2004 Social Sciences 242506
2005 Social Sciences 249619
2006 Social Sciences 254222
2007 Social Sciences 259950
2008 Social Sciences 262771
2009 Social Sciences 269996
1970 Natural Sciences 81916
1975 Natural Sciences 91596
1980 Natural Sciences 78092
1985 Natural Sciences 76228
1990 Natural Sciences 70209
1995 Natural Sciences 93443
2000 Natural Sciences 89772
2004 Natural Sciences 99370
2005 Natural Sciences 105899
2006 Natural Sciences 113077
2007 Natural Sciences 117200
2008 Natural Sciences 121009
2009 Natural Sciences 125809
1970 Computer science and engineering 52570
1975 Computer science and engineering 52328
1980 Computer science and engineering 90476
1985 Computer science and engineering 139459
1990 Computer science and engineering 104910
1995 Computer science and engineering 102503
2000 Computer science and engineering 117011
2004 Computer science and engineering 133655
2005 Computer science and engineering 128886
2006 Computer science and engineering 124024
2007 Computer science and engineering 122084
2008 Computer science and engineering 122408
2009 Computer science and engineering 128318
1970 education 176307
1975 education 154437
1980 education 108074
1985 education 87147
1990 education 110807
1995 education 105384
2000 education 105458
2004 education 105451
2005 education 107238
2006 education 105641
2007 education 102582
2008 education 101708
2009 education 101265
1970 business 115396
1975 business 143171
1980 business 200521
1985 business 236700
1990 business 249165
1995 business 226623
2000 business 263515
2004 business 311574
2005 business 318042
2006 business 327531
2007 business 335254
2008 business 347985
2009 business 358293
1970 Other fields 76481
1975 Other fields 156804
1980 Other fields 182257
1985 Other fields 180930
1990 Other fields 203200
1995 Other fields 243540
2000 Other fields 252627
2004 Other fields 291861
2005 Other fields 313862
2006 Other fields 333789
2007 Other fields 351464
2008 Other fields 367100
2009 Other fields 385340")
创建情节:
p <- ggplot(mydf, aes(x = ano, y = value, group = field)) +
geom_line(aes(group = field, color = field), size = 1.5, show.legend = FALSE) +
scale_x_continuous(
expand = c(0, 1),
limits = c(min(mydf$ano), max(mydf$ano) + 50),
breaks = seq(1970, 2010, by = 10)
) +
scale_y_continuous(labels = sitools::f2si) +
annotate(
geom = "rect", xmin = 2010.5, xmax = Inf, ymin = -Inf, ymax = Inf,
fill = "white"
) +
geom_point(
data = subset(mydf, ano == max(ano)),
aes(color = field),
size = 3,
show.legend = FALSE
) +
geom_text_repel(
data = subset(mydf, ano == max(ano)),
aes(label = sprintf("%s %s", comma(value), toTitleCase(field)), color = field),
size = 7,
hjust = 0,
direction = "y",
nudge_x = 2,
segment.color = NA,
show.legend = FALSE
) +
theme_minimal(base_size = 24) +
theme(panel.grid.minor.x = element_blank()) +
labs(
x = NULL,
y = NULL,
title = "B.A. degrees awarded per year"
)
ggsave(
plot = p,
filename = "stackoverflow-21004491.png",
width = 12.5,
height = 6
)
由reprex package创建于2018-12-29(v0.2.1)
答案 2 :(得分:2)