ggstatsplot绘图|统计+可视化，学术科研神器

作者: 生信补给站 | 来源:发表于2019-10-29 23:21 被阅读0次

本文首发于“生信补给站”公众号，https://mp.weixin.qq.com/s/zdSit97SOEpbnR18ARzixw

更多关于R语言，ggplot2绘图，生信分析的内容，敬请关注小号。

ggstatsplot是ggplot2包的扩展包，可以同时输出美观的图片和统计分析结果，对于经常做统计分析或者生信人来说非常有用。

一准备数据

gapminder 数据集包含1952到2007年间(5年间隔)的142个国家的life expectancy, GDP per capita, 和 population信息

#载入绘图R包
library(ggstatsplot)
#载入gapminder 数据集

library(gapminder)
head(gapminder)

image.png

ggstatsplot-R包含有很多绘图函数（文末会给出），本文仅展示ggbetweenstats函数使用方法。

二 ggbetweenstats 绘图

1 基本绘图展示

显示2007年每个continent的预期寿命分布情况，并统计一下不同大陆之间平均预期寿命的是否有差异？差异是否显著？

#设置种子方便复现
set.seed(123)
# Oceania数据太少，去掉后分析
ggstatsplot::ggbetweenstats(
  data = dplyr::filter(
    .data = gapminder::gapminder,
    year == 2007, continent != "Oceania"
  ),
  x = continent,
  y = lifeExp,
  nboot = 10,
  messages = FALSE
)

img

可以看到图中展示出了2007年每个continent的预期寿命分布的箱线图，点图和小提琴图，均值，样本数；并且图形最上方给出了模型的一些统计量信息（整体）。

统计信息意义如下图所示：

img

注：该函数根据分组变量中的个数自动决定是选择独立样本t检验(2组)还是单因素方差分析(3组或更多组)

2 添加统计值

上方给出了整体的检验P值，下面两两之间比较，并添加检验统计量

set.seed(123)
ggstatsplot::ggbetweenstats(
  data = dplyr::filter(
    .data = gapminder::gapminder,year == 2007, continent != "Oceania"),
  x = continent,y = lifeExp,
  nboot = 10,
  messages = FALSE,
  effsize.type = "unbiased", # type of effect size (unbiased = omega)
  partial = FALSE, # partial omega or omega?
  pairwise.comparisons = TRUE, # display results from pairwise comparisons
  pairwise.display = "significant", # display only significant pairwise comparisons
  pairwise.annotation = "p.value", # annotate the pairwise comparisons using p-values
  p.adjust.method = "fdr", # adjust p-values for multiple tests using this method
)

img

3 图形美化

添加标题和说明，x轴和y轴标签，标记，离群值，更改主题以及调色板。

set.seed(123)
# plot
gapminder %>% # dataframe to use
  ggstatsplot::ggbetweenstats(
    data = dplyr::filter(.data = ., year == 2007, continent != "Oceania"),
    x = continent, # grouping/independent variable
    y = lifeExp, # dependent variables
    xlab = "Continent", # label for the x-axis
    ylab = "Life expectancy", # label for the y-axis
    plot.type = "boxviolin", # type of plot ,"box", "violin", or "boxviolin"
    type = "parametric", # type of statistical test , p (parametric), np ( nonparametric), r(robust), bf (Bayes Factor).
    effsize.type = "biased", # type of effect size
    nboot = 10, # number of bootstrap samples used
    bf.message = TRUE, # display bayes factor in favor of null hypothesis
    outlier.tagging = TRUE, # whether outliers should be flagged
    outlier.coef = 1.5, # coefficient for Tukey's rule
    outlier.label = country, # label to attach to outlier values
    outlier.label.color = "red", # outlier point label color
    mean.plotting = TRUE, # whether the mean is to be displayed
    mean.color = "darkblue", # color for mean
    messages = FALSE, # turn off messages
    ggtheme = ggplot2::theme_gray(), # a different theme
    package = "yarrr", # package from which color palette is to be taken
    palette = "info2", # choosing a different color palette
    title = "Comparison of life expectancy across continents (Year: 2007)",
    caption = "Source: Gapminder Foundation"
  ) + # modifying the plot further
  ggplot2::scale_y_continuous(
    limits = c(35, 85),
    breaks = seq(from = 35, to = 85, by = 5)
  )

img

三其他绘图函数

Function	Plot	Description
`ggbetweenstats`	violin plots	for comparisons between groups/conditions
`ggwithinstats`	violin plots	for comparisons within groups/conditions
`gghistostats`	histograms	for distribution about numeric variable
`ggdotplotstats`	dot plots/charts	for distribution about labeled numeric variable
`ggpiestats`	pie charts	for categorical data
`ggbarstats`	bar charts	for categorical data
`ggscatterstats`	scatterplots	for correlations between two variables
`ggcorrmat`	correlation matrices	for correlations between multiple variables
`ggcoefstats`	dot-and-whisker plots	for regression models