Question

我目前正在尝试在Hadley Wickham的大量资源（“面向数据科学家的资源”，“用于数据分析的ggplot2优雅图形”）的帮助下学习r。到目前为止，我已经能够找到那里所有问题的答案（非常感谢，哈德利！），但是这次却没有。

当前，我正在使用一种仪器的数据，该仪器通过粒子散射的光来估计粒径（DLS，Zetasizer Nano，Malvern Instruments）。从此设备提取的数据是一些摘要统计信息（例如，平均粒度）和直方图数据：x =尺寸（以箱为单位分割），y =强度[％]。这是我的一项测量的小标题：

   # A tibble: 70 x 3
   sample_name        intensities      bins
   <chr>                    <dbl>     <dbl>
 1 core formulation 1         0       0.4  
 2 core formulation 1         0       0.463
 3 core formulation 1         0       0.536
 4 core formulation 1         0       0.621
 5 core formulation 1         0       0.720
 6 core formulation 1         0       0.833
 7 core formulation 1         0       0.965
 8 core formulation 1         0       1.12 
 9 core formulation 1         0       1.29 
10 core formulation 1         0       1.50 
11 core formulation 1         0       1.74 
12 core formulation 1         0       2.01 
13 core formulation 1         0       2.33 
14 core formulation 1         0       2.70 
15 core formulation 1         0       3.12 
16 core formulation 1         0       3.62 
17 core formulation 1         0       4.19 
18 core formulation 1         0       4.85 
19 core formulation 1         0       5.62 
20 core formulation 1         0       6.50 
21 core formulation 1         0       7.53 
22 core formulation 1         0       8.72 
23 core formulation 1         0      10.1  
24 core formulation 1         0      11.7  
25 core formulation 1         0      13.5  
26 core formulation 1         0      15.7  
27 core formulation 1         0      18.2  
28 core formulation 1         0      21.0  
29 core formulation 1         0      24.4  
30 core formulation 1         0      28.2  
31 core formulation 1         0      32.7  
32 core formulation 1         0      37.8  
33 core formulation 1         0      43.8  
34 core formulation 1         0.2    50.8  
35 core formulation 1         1.4    58.8  
36 core formulation 1         3.7    68.1  
37 core formulation 1         6.9    78.8  
38 core formulation 1        10.2    91.3  
39 core formulation 1        12.9   106.   
40 core formulation 1        14.4   122.   
41 core formulation 1        14.4   142.   
42 core formulation 1        13     164.   
43 core formulation 1        10.3   190.   
44 core formulation 1         7.1   220.   
45 core formulation 1         3.9   255    
46 core formulation 1         1.5   295.   
47 core formulation 1         0.2   342    
48 core formulation 1         0     396.   
49 core formulation 1         0     459.   
50 core formulation 1         0     531.   
51 core formulation 1         0     615.   
52 core formulation 1         0     712.   
53 core formulation 1         0     825    
54 core formulation 1         0     955.   
55 core formulation 1         0    1106    
56 core formulation 1         0    1281    
57 core formulation 1         0    1484    
58 core formulation 1         0    1718    
59 core formulation 1         0    1990    
60 core formulation 1         0    2305    
61 core formulation 1         0    2669    
62 core formulation 1         0    3091    
63 core formulation 1         0    3580    
64 core formulation 1         0    4145    
65 core formulation 1         0    4801    
66 core formulation 1         0    5560    
67 core formulation 1         0    6439    
68 core formulation 1         0    7456    
69 core formulation 1         0    8635    
70 core formulation 1         0   10000

以下是使用dput()命令生成的数据：

structure(list(sample_name = c("core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1", "core formulation 1", 
"core formulation 1", "core formulation 1"), intensities = c(0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.2, 1.4, 3.7, 6.9, 10.2, 12.9, 
14.4, 14.4, 13, 10.3, 7.1, 3.9, 1.5, 0.2, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), bins = c(0.4, 
0.4632, 0.5365, 0.6213, 0.7195, 0.8332, 0.9649, 1.117, 1.294, 
1.499, 1.736, 2.01, 2.328, 2.696, 3.122, 3.615, 4.187, 4.849, 
5.615, 6.503, 7.531, 8.721, 10.1, 11.7, 13.54, 15.69, 18.17, 
21.04, 24.36, 28.21, 32.67, 37.84, 43.82, 50.75, 58.77, 68.06, 
78.82, 91.28, 105.7, 122.4, 141.8, 164.2, 190.1, 220.2, 255, 
295.3, 342, 396.1, 458.7, 531.2, 615.1, 712.4, 825, 955.4, 1106, 
1281, 1484, 1718, 1990, 2305, 2669, 3091, 3580, 4145, 4801, 5560, 
6439, 7456, 8635, 10000)), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -70L))

我可以从这些数据中毫无问题地生成直方图：

library(tidyverse)
ggplot (DLS_intensities_core, aes(bins,intensities) ) + 
  geom_line() + 
  scale_x_continuous(trans = 'log10')

line plot, intensities against bins

为了显示我的粒径的总体分布，我想将此数据转换为小提琴图，并在我的图的第二层中使用设备提供的汇总统计信息。

因此，我想对这些数据进行转换，以便能够从中创建一个小提琴图。

我已经尝试将其输入到小提琴图的stat_density（）参数，但到目前为止没有成功。

您知道如何根据这些数据创建小提琴图吗？

非常感谢您！

最佳，

多米尼克

Answer 1

在您回复第二条评论后，我将对此进行更新（如果需要）。您可以通过以下方式获得bins和intensities的小提琴图：

library(hrbrthemes)

gather(DLS_intensities_core, measure, value, -sample_name) %>% 
  ggplot(aes(measure, value)) +
  geom_violin(scale = "count") +
  scale_y_comma() +
  facet_wrap(~measure, scales="free") +
  labs(
    x = NULL, y = "A better label than this",
    title = "A better title than this",
    caption = "NOTE: Free Y scales"
  ) +
  theme_ipsum_rc(grid="Y") +
  theme(axis.text.x = element_blank())

我通常也喜欢在要点上分层：

gather(DLS_intensities_core, measure, value, -sample_name) %>% 
  ggplot(aes(measure, value)) +
  geom_violin(scale = "count") +
  ggbeeswarm::geom_quasirandom() +
  scale_y_comma() +
  facet_wrap(~measure, scales="free") +
  labs(
    x = NULL, y = "A better label than this",
    title = "A better title than this",
    caption = "NOTE: Free Y scales"
  ) +
  theme_ipsum_rc(grid="Y") +
  theme(axis.text.x = element_blank())

根据您的评论，也许这可能是显示bins分布以及与intensities的关系的更好方法：

library(hrbrthemes)
library(tidyverse)

ggplot(DLS_intensities_core, aes(x="", bins)) +
  geom_violin(scale = "count") +
  ggbeeswarm::geom_quasirandom(
    aes(size = intensities, fill = intensities), shape = 21
  ) +
  scale_y_comma(trans="log10") +
  viridis::scale_fill_viridis(direction = -1, trans = "log1p") +
  scale_size_continuous(trans = "log1p", range = c(2, 10)) +
  guides(fill = guide_legend()) +
  labs(
    x = NULL, y = "A better label than this",
    title = "A better title than this"
  ) +
  theme_ipsum_rc(grid="Y")

您必须进行一些其他的自定义转换，以尝试使小提琴的形状随强度而变化（并且实际上并不能反映该点的分布）。

Answer 2

我找到了解决问题的方法，它可能不是很优雅：

library (tidyverse)

DLS_intensities_core <- DLS_intensities_core %>% 
  mutate(counts = intensities * 10 )

vectors <- DLS_intensities_core %>%
  filter(counts > 0) 

bins_v <- vectors$bins
count_v <- vectors$counts

violin_DLSdata <- as.tibble(rep.int(bins_v, count_v))
violin_DLSdata$sample_name <- "core formulation 1"

ggplot (violin_DLSdata, aes(sample_name, value)) + 
  geom_violin() + 
  labs(
    x = NULL, y = "size"
  ) +
  scale_y_continuous(trans = 'log10', limits = c(1, 1000))

对于我的整个数据集，它看起来像这样：我已添加：摘要统计为带有错误栏的红点。

你怎么看？

用ggplot将直方图转换为r中的小提琴图

2 个答案: