2

我需要为facetfacet_grid 中的每个（3 行和 3 列）手动指定 x 轴和 y 轴的限制。

我有 2 个分类因子和一个连续的 y 值（所以我catch_ema_thousands在y轴上绘制 ，数据由redlistCategory（3 个级别）和TaxonGroup（3 个级别）分面，然后根据VARIABLE（也是 3 个级别）对点进行着色。

具有非常不均匀的facet_grid数据点数量和 y 值范围（0 - 1,700，大多数点聚集在 0 附近，一些刻面有 20 个点，而另一些刻面有 0 或 1）。

我必须scale_y_sqrt转换 y 轴，这会有所帮助，但仍然很难看到繁忙面上的点。

我在 中使用了scales = "free"andspace="free"参数facet_grid()，它调整了 facet 的大小以适应数据点，但不考虑拟合geom_text_repel()标签。

我必须在 内调整刻面大小ggrepel吗？

library(scales)
library(ggrepel)
library(forcats)
library(RColorBrewer)
library(tidyverse)

ylimits <- c(2,NA) #keep the labels above the cluster of points at the bottom of the facets

我要标注的~25种物种清单：

special.points <- special.points <- rownames(subset(plotdat, 
                         SpeciesOrTaxon %in% c("Gadus morhua","Melanogrammus aeglefinus","Thunnus obesus",
                                            "Trachurus trachurus","Sardinella maderensis","Thunnus thynnus",
                                            "Thunnus maccoyii","Hippoglossus hippoglossus","Squalus acanthias",
                                            "Merluccius senegalensis","Epinephelus striatus","Apostichopus japonicus",
                                            "Mobula mobular","Isurus oxyrinchus","Mustelus schmitti",
                                            "Pseudotolithus senegalensis","Sebastolobus alascanus",
                                            "Leucoraja circularis","Argyrosomus hololepidotus","Raja undulata",
                                            "Isurus paucus","Sphyrna lewini","Squatina argentina","Dipturus batis",
                                            "Squatina squatina","Carcharhinus falciformis","Squalus acanthias",
                                            "Makaira nigricans","Thunnus orientalis","Carcharhinus longimanus",
                                            "Lamna nasus","Sphyrna zygaena","Alopias vulpinus","Cetorhinus maximus",
                                            "Alopias superciliosus","Carcharodon carcharias","Palinurus elephas")))

我真的很烦人的情节：

p <- ggplot(data = plotdat, aes(x= -totRank, y = catch_ema_thousands, label = Name_abbrev)) + 
  geom_point(data=plotdat,aes(color = VARIABLE), size = 1.2, shape = 1, stroke = 0.8) +
  scale_color_manual(values=c("black","orange","darkgrey"), labels = c("CITES","Intl trade","No intl trade")) +
  facet_grid(redlistCategory~TaxonGroup, scales = "free", space = "free") + 
  scale_y_sqrt() +
  geom_text_repel(data = plotdat, 
                  aes(x=-totRank, y = catch_ema_thousands, label = Name_abbrev), 
# used the abbreviated species name to try and fit them better
                  segment.color = "black", segment.size = 0.2, segment.alpha = 0.5, 
                  direction = "both",
                  min.segment.length = 0.5,
                  force = 10, size = 2, color = "black",
                  ylim = ylimits) + 
  ylab("Average catch (thousand tonnes)") +
  theme(axis.text.x = element_blank(),
        axis.ticks.x=element_blank(),
        axis.title.x=element_blank(),
        axis.title.y = element_blank(),
        legend.position = "top", 
        legend.title = element_blank(),
        panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(), axis.line = element_line(colour = "black")) 
#dev.off()

我尝试了一个新包，但出现错误：

devtools::install_github("zeehio/facetscales")
library(facetscales)
scales_y <- list(
  CR = scale_y_sqrt(limits = c(0,50), breaks = c(0,50,10)),
  EN = scale_y_continuous(limits = c(0,50), breaks = c(0,50,10)),
  VU = scale_y_continuous(labels = scientific_format())
)

scales_x <- list(
  'Invertebrates' = scale_x_discrete(limits = c(-50,-40)), # plotting in reverse rank (-59 to 0)
  'Cartilaginous fish' =  scale_x_discrete(limits = c(-59,0)),
  'Bony fish' =  scale_x_discrete(limits = c(-59,0))
)

然后，

facet_grid(redlistCategory~TaxonGroup, scales = list(y=scales_y, x = scales_x))

覆盖 facet_grid() 中的“自由”比例有些不对劲，我收到此错误：

Error in match.arg(scales, c("fixed", "free_x", "free_y",
 "free")) :    'arg' must be NULL or a character vector

样地数据：

plotdat <- dput(structure(list(SpeciesOrTaxon = c("Squatina argentina", "Dipturus batis", 
"Squatina squatina", "Thunnus maccoyii", "Epinephelus striatus", 
"Sphyrna lewini", "Mobula mobular", "Isurus oxyrinchus", "Mustelus schmitti", 
"Pseudotolithus senegalensis", "Sebastolobus alascanus", "Leucoraja circularis", 
"Argyrosomus hololepidotus", "Raja undulata", "Isurus paucus", 
"Thunnus thynnus", "Hippoglossus hippoglossus", "Merluccius senegalensis", 
"Apostichopus japonicus", "Carcharhinus falciformis", "Carcharhinus longimanus", 
"Lamna nasus", "Sphyrna zygaena", "Alopias vulpinus", "Cetorhinus maximus", 
"Alopias superciliosus", "Carcharodon carcharias", "Sardinella maderensis", 
"Galeorhinus galeus", "Pomatomus saltatrix", "Pentanemus quinquarius", 
"Pseudupeneus prayensis", "Nemipterus virgatus", "Pseudotolithus senegallus", 
"Dalatias licha", "Lutjanus campechanus", "Megalops atlanticus", 
"Mola mola", "Mustelus mustelus", "Centrophorus squamosus", "Balistes capriscus", 
"Centrophorus lusitanicus", "Leucoraja fullonica", "Rhomboplites aurorubens", 
"Dentex dentex", "Epinephelus marginatus", "Palinurus elephas", 
"Alosa immaculata", "Carcharhinus plumbeus", "Oxynotus centrina", 
"Gymnura altavela", "Carcharias taurus", "Gadus morhua", "Melanogrammus aeglefinus", 
"Thunnus obesus", "Trachurus trachurus", "Squalus acanthias", 
"Makaira nigricans", "Thunnus orientalis"), Name_abbrev = c("S. argentina", 
"D. batis", "S. squatina", "T. maccoyii", "E. striatus", "S. lewini", 
"M. mobular", "I. oxyrinchus", "M. schmitti", "P. senegalensis", 
"S. alascanus", "L. circularis", "A. hololepidotus", "R. undulata", 
"I. paucus", "T. thynnus", "H. hippoglossus", "M. senegalensis", 
"A. japonicus", "C. falciformis", "C. longimanus", "L. nasus", 
"S. zygaena", "A. vulpinus", "C. maximus", "A. superciliosus", 
"C.carcharias", "S. maderensis", "G. galeus", "P. saltatrix", 
"P. quinquarius", "P. prayensis", "N. virgatus", "P. senegallus", 
"D. licha", "L. campechanus", "M. atlanticus", "M. mola", "M. mustelus", 
"C. squamosus", "B. capriscus", "C. lusitanicus", "L. fullonica", 
"R. aurorubens", "D. dentex", "E. marginatus", "P. elephas", 
"A. immaculata", "C. plumbeus", "O. centrina", "G. altavela", 
"C. taurus", "G. morhua", "M. aeglefinus", "T. obesus", "T. trachurus", 
"S. acanthias", "M. nigricans", "T. orientalis"), redlistCategory = structure(c(1L, 
1L, 1L, 1L, 1L, 2L, 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, 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, 3L), .Label = c("CR", "EN", 
"VU"), class = "factor"), TaxonGroup = structure(c(2L, 2L, 2L, 
3L, 3L, 2L, 2L, 2L, 2L, 3L, 3L, 2L, 3L, 2L, 2L, 3L, 3L, 3L, 1L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 2L, 
3L, 3L, 3L, 2L, 2L, 3L, 2L, 2L, 3L, 3L, 3L, 1L, 3L, 2L, 2L, 2L, 
2L, 3L, 3L, 3L, 3L, 2L, 3L, 3L), .Label = c("Invertebrates", 
"Cartilaginous fish", "Bony fish"), class = "factor"), totRank = c(12, 
39, 55, 7, 38, 56, 57, 8, 11, 17, 33, 36, 37, 50, 58, 6, 9, 16, 
51, 15, 27, 30, 43, 45, 49, 52, 53, 5, 13, 14, 19, 20, 22, 23, 
24, 25, 26, 28, 29, 31, 32, 34, 35, 40, 41, 42, 44, 46, 47, 48, 
54, 59, 1, 2, 3, 4, 10, 18, 21), VARIABLE = structure(c(3L, 3L, 
3L, 2L, 2L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 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, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("CITES", "YES", 
"NO"), class = "factor"), catch_ema_thousands = c(3.886654422, 
0.1724791016, 0.00911430205, 10.54412869, 0.174470439, 0.00807692997, 
0.001640665002, 9.424452066, 6.583041893, 2.659608617, 0.2663195953, 
0.2329239555, 0.2219422872, 0.01671489332, 0.0014159872, 13.44830652, 
7.585155675, 2.774650025, 0.01599999, 3.024126379, 0.4539170316, 
0.3113769576, 0.1163730191, 0.1011488649, 0.01681304105, 0.01561369792, 
0.01416268544, 108.778465, 3.822553738, 3.251341729, 2.440669803, 
1.688880545, 1.358903072, 1.100693581, 1.06694699, 0.8025907339, 
0.5465603847, 0.4392502858, 0.3591757093, 0.2919081194, 0.2671983104, 
0.2478545144, 0.2435067011, 0.15794176, 0.1539382418, 0.1226202735, 
0.1079683714, 0.06792588753, 0.03801280875, 0.02357907878, 0.009323075655, 
0.000514006594, 1652.737638, 484.1897672, 397.4311939, 153.0306153, 
7.422144444, 2.459107988, 1.545317165)), row.names = c(NA, -59L
), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame")))
4

2 回答 2

0

编辑：添加替代使用scale_y_sqrt(expand = expand_scale)以在每个方面增加更多边界空间。

如果sqrt转换在这里更有意义，您可以考虑使用expand_scale. ggplot 中的默认值是在数据范围之外添加 5%，但增加这将为所有方面的标签创建更多空间。

可能还值得调整或删除该ylim = ylimits部分，因为当我第一次打开示例时，这会创建一些重叠的成束标签。

scale_y_sqrt(expand = expand_scale(0.2)) +
geom_text_repel(data = plotdat, 
                aes(x=-totRank, y = catch_ema_thousands, label = Name_abbrev), 
                # used the abbreviated species name to try and fit them better
                segment.color = "black", segment.size = 0.2, segment.alpha = 0.5, 
                direction = "both", nudge_y = 0,
                min.segment.length = 0.5, max.iter = 5000,
                force = 10, size = 2, color = "black") + # w/o ylim part

在此处输入图像描述

第一个答案：

我认为 log10 在这里可能是一个合适的缩放选项，因为幅度范围很广：

p <- ggplot(data = plotdat, aes(x= -totRank, y = catch_ema_thousands, label = Name_abbrev)) + 
  geom_point(data=plotdat,aes(color = VARIABLE), size = 1.2, shape = 1, stroke = 0.8) +
  scale_color_manual(values=c("black","orange","darkgrey"), labels = c("CITES","Intl trade","No intl trade")) +
  facet_grid(redlistCategory~TaxonGroup, scales = "free", space = "free") + 
    scale_y_log10(
      breaks = 10^(-10:10),
      labels = scales::trans_format("log10", scales::math_format(10^.x))
    ) +
    # annotation_logticks(side = "l") +

  geom_text_repel(data = plotdat, 
                  aes(x=-totRank, y = catch_ema_thousands, label = Name_abbrev), 
                  # used the abbreviated species name to try and fit them better
                  segment.color = "black", segment.size = 0.2, segment.alpha = 0.5, 
                  direction = "both", nudge_y = 0,
                  min.segment.length = 0.5, max.iter = 5000,
                  force = 10, size = 2, color = "black") + #, ylim = ylimits) + 
  ylab("Average catch (thousand tonnes)") +
  theme(axis.text.x = element_blank(),
        axis.ticks.x=element_blank(),
        axis.title.x=element_blank(),
        axis.title.y = element_blank(),
        legend.position = "top", 
        legend.title = element_blank(),
        panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(), axis.line = element_line(colour = "black")) 

  p

在此处输入图像描述

于 2019-06-02T03:10:22.687 回答
0 
blank_data <- read_csv("blankdata.csv")  
# must have all the columns that you call in ggplot. 
# Make a row for the minimum and maximum x and y values you want for each facet
p <- ggplot(data = plotdat, aes(x= xvar, y = yvar, label = labelvar)) + 
  geom_jitter(data=plotdat,
              aes(color = colorvar), size = 1.2, shape = 1, stroke = 0.8, width = 
                0.25, height = 0.25) +
  geom_blank(data=blankdata, aes(x =xvar, y = yvar, label = labelvar)) +
  facet_grid(ycategory ~ xcategory, scales = "free", space = "free") + 
  geom_text_repel(data = labelvar, # can subset and only label certain points
                  aes(x=xvar, y = yvar, label = labelvar),
                  segment.color = "black", segment.size = 0.2, segment.alpha = 
                    0.5, 
                  direction = "both", 
                  min.segment.length = 0.5,
                  force = 10, size = 2, color = "black") +
  scale_y_sqrt(expand = expand_scale(mult=c(0.1,0))) + 
  # added extra space (10%) at the bottom of each axis because all the labels were clustered there 
  scale_x_continuous(expand = expand_scale(mult=c(0.1,0.1))) +
  theme_bw()
于 2019-06-05T01:57:45.400 回答