如何使用ggplot获取箱线图中的所有点？

Question

我想为我的每个数据显示一个带点的箱线图。

这是我对数据的下采样：

    value   value1  value2  value3  value4  value5  value6  value7  value8  value9  value10 value11 value12 value13 value14 value15 value16 value17 value18 value19 value20 value21 value22 value23 value24 value25 value26 value27 value28 value29 value30 value31 value32 value33 value34 value35 value36 value37 value38 value39 value40 value41 value42 value43 value44 value45 value46 value47 value48 value49 value50 value51 value52 value53 value54 value55 value56 value57 value58 value59 value60 value61 value62 value63 value64 value65 value66 value67 value68 value69 value70 value71 value72 value73 value74 value75 value76 value77 value78 value79 value80 value81 value82 value83 value84 value85 value86 value87 value88 value89 value90 value91 value92 value93
1   DLBCL   1994.95631  2621.3410   753.2132    0.000000    11197.10111 0.000000    176.337991  2000.983371 862.402989  8491.35251  0.000000    0.000000    0.000000    0.000000    0.000000    1293.604484 431.201495  11022.058175    6899.22391  1557.191604 0.00000 0.0000000   491.33939   0.00000 935.4880    473.089640  117093.3704 267.06673   0.000000    1201.315893 546.473181  817.685797  5550.213652 5864.340327 0.000000    756.0793    1186.963254 0.000000    0.000000    182.35834   0.000000    0.000000    2.221214e+04    546.4731813 0.000000    22467.36115 25197.16560 4527.61569  47851.49797 0.0000000   809.029514  1780.444881 466.4264055 2854.851275 2178.702289 0.000000    1155.2188880    0.000000    0.000000    0.000000    0.0000000   325.947587  0.000000    0.000000    0.00000 0.000000    0.000000    0.000000    0.000000    0.000000    0.000000    0.0000000   0.000000    5219.72808  0.000000    1092.946363 1914.235537 0.00000 41395.343   5012.19294  0.0000  0.00000 0.000000    0.00000 211214.036  771.94114   5792.9344   155407.942  586.647915  904.81625   5221.03431  26527.2485  118750.28   103149.05
2   HL  2685.55082  3282.5779   4598.1600   4183.367213 1465.89302  0.000000    66.245848   0.000000    161.991801  61.34601    161.991801  0.000000    485.975403  404.979503  80.995901   80.995901   161.991801  6164.020846 4211.78683  17549.958130    2601.72383  1143.4715367    1292.08891  2101.51526  8785.9960   157.980575  25628.0113  2257.43413  426.060627  3572.830049 410.593080  11519.416962    23630.893343    47042.419019    2594.830952 5964.8488   3901.738003 0.000000    0.000000    376.79150   0.000000    833.100691  1.251683e+05    3797.9859885    4500.351000 231.24480   901.51959   8990.54496  21686.09505 0.0000000   50.655417   0.000000    5081.5230881    766.069601  8594.091339 4754.510950 578.6497823 0.000000    0.000000    540.128957  5906.6921396    1897.982677 0.000000    0.000000    0.00000 517.142472  0.000000    90.021493   0.000000    0.000000    395.929041  51.1553056  0.000000    5501.47987  569.641498  1180.455105 1258.479657 0.00000 31700.549   8406.06103  650.9810    198.52612   1888.006678 183.67574   130532.228  108.74974   3400.4110   58514.733   4600.624542 1019.75167  0.00000 20734.9505  163994.61   181005.92
3   HL  3937.68099  5174.0505   14309.5447  17201.448539    6027.55676  0.000000    1566.266081 246.848582  9575.025066 966.94533   5745.015039 5106.680035 5745.015039 8298.355057 5745.015039 8936.690061 3830.010026 2595.831304 0.00000 3842.016327 932.01765   0.0000000   0.00000 0.00000 12463.7614  2256.666225 105760.7753 165061.07726    2014.690206 296.397390  808.979015  0.000000    684.694530  0.000000    1120.551505 47009.4381  0.000000    0.000000    0.000000    809.86996   0.000000    6565.731474 1.992851e+03    2831.4265541    0.000000    911.22915   0.00000 0.00000 0.00000 0.0000000   0.000000    0.000000    345.2403404 1811.236269 0.000000    1561.277973 0.0000000   0.000000    736.098023  3192.598806 0.0000000   0.000000    0.000000    0.000000    0.00000 9897.983156 0.000000    3015.232206 0.000000    1210.472305 3120.347631 2015.7947507    0.000000    89720.16482 0.000000    0.000000    0.000000    984.42025   23569.292   794.98586   570.0480    0.00000 0.000000    482.52095   42461.843   571.37679   3573.1872   25446.846   1519.791401 0.00000 0.00000 57004.8004  153509.90   112514.3

这是我的代码：

data2=read.table("/../data.txt",sep="\t",header=TRUE )
data2 %>%
ggplot( aes(x=name, y=value, value1, value2, value3, value4, value5, value6, value7, value8, value9, value10, value11, value12, value13, value14, value15, value16, value17, value18, value19, value20, value21, value22, value23, value24, value25, value26, value27, value28, value29, value30, value31, value32, value33, value34, value35, value36, value37, value38, value39, value40, value41, value42, value43, value44, value45, value46, value47, value48, value49, value50, value51, value52, value53, value54, value55, value56, value57, value58, value59, value60, value61, value62, value63, value64, value65, value66, value67, value68, value69, value70, value71, value72, value73, value74, value75, value76, value77, value78, value79, value80, value81, value82, value83, value84, value85, value86, value87, value88, value89, value90, value91, value92, value93, fill=name)) +
geom_boxplot() +
  scale_fill_viridis(discrete = TRUE, alpha=0.6) +
  geom_jitter(color="black", size=0.4, alpha=0.9) +
  theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)
  ) +
  ggtitle("Distribution of ... ") +
  xlab("")

我得到了一个 plot 但不是我的所有数据都出现了。 我怀疑只考虑了第一列（值）。

我错过了什么？ 有谁知道得到我所有点的技巧吗？

非常感谢！

Answer 1

您可以尝试将数据整形为长：

library(ggplot2)
library(dplyr)
library(tidyr)
#Code
data2 %>%
  rename(key=value) %>%
  pivot_longer(-key) %>%
  ggplot(aes(x=key,y=value,fill=name))+
  geom_boxplot() +
  #scale_fill_viridis(discrete = TRUE, alpha=0.6) +
  geom_jitter(color="black", size=0.4, alpha=0.9) +
  #theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)
  ) +
  ggtitle("Distribution of total EBV gene expression for each PTCL subtype ") +
  xlab("")

Output：