Box / Violin Plot — BoxPlot • plotthis

Box plot or violin plot with optional jitter points, trend line, statistical test, background, line, and highlight.

Usage

BoxPlot(
  data,
  x,
  x_sep = "_",
  y = NULL,
  in_form = c("long", "wide"),
  split_by = NULL,
  split_by_sep = "_",
  sort_x = c("none", "mean_asc", "mean_desc", "mean", "median_asc", "median_desc",
    "median"),
  flip = FALSE,
  keep_empty = FALSE,
  group_by = NULL,
  group_by_sep = "_",
  group_name = NULL,
  x_text_angle = ifelse(isTRUE(flip) && isTRUE(stack), 90, 45),
  fill_mode = ifelse(!is.null(group_by), "dodge", "x"),
  fill_reverse = FALSE,
  theme = "theme_this",
  theme_args = list(),
  palette = "Paired",
  palcolor = NULL,
  alpha = 1,
  aspect.ratio = NULL,
  legend.position = "right",
  legend.direction = "vertical",
  add_point = FALSE,
  pt_color = "grey30",
  pt_size = NULL,
  pt_alpha = 1,
  jitter_width = 0.5,
  jitter_height = 0.1,
  stack = FALSE,
  y_max = NULL,
  y_min = NULL,
  add_trend = FALSE,
  trend_color = NULL,
  trend_linewidth = 1,
  trend_ptsize = 2,
  add_stat = NULL,
  stat_name = NULL,
  stat_color = "black",
  stat_size = 1,
  stat_stroke = 1,
  stat_shape = 25,
  add_bg = FALSE,
  bg_palette = "stripe",
  bg_palcolor = NULL,
  bg_alpha = 0.2,
  add_line = NULL,
  line_color = "red2",
  line_width = 0.6,
  line_type = 2,
  highlight = NULL,
  highlight_color = "red2",
  highlight_size = 1,
  highlight_alpha = 1,
  comparisons = NULL,
  ref_group = NULL,
  pairwise_method = "wilcox.test",
  multiplegroup_comparisons = FALSE,
  multiple_method = "kruskal.test",
  sig_label = c("p.signif", "p.format"),
  sig_labelsize = 3.5,
  facet_by = NULL,
  facet_scales = "fixed",
  facet_ncol = NULL,
  facet_nrow = NULL,
  facet_byrow = TRUE,
  title = NULL,
  subtitle = NULL,
  xlab = NULL,
  ylab = NULL,
  seed = 8525,
  combine = TRUE,
  nrow = NULL,
  ncol = NULL,
  byrow = TRUE,
  ...
)

ViolinPlot(
  data,
  x,
  x_sep = "_",
  y = NULL,
  in_form = c("long", "wide"),
  split_by = NULL,
  split_by_sep = "_",
  sort_x = c("none", "mean_asc", "mean_desc", "mean", "median_asc", "median_desc",
    "median"),
  flip = FALSE,
  keep_empty = FALSE,
  group_by = NULL,
  group_by_sep = "_",
  group_name = NULL,
  x_text_angle = ifelse(isTRUE(flip) && isTRUE(stack), 90, 45),
  fill_mode = ifelse(!is.null(group_by), "dodge", "x"),
  fill_reverse = FALSE,
  theme = "theme_this",
  theme_args = list(),
  palette = "Paired",
  palcolor = NULL,
  alpha = 1,
  aspect.ratio = NULL,
  legend.position = "right",
  legend.direction = "vertical",
  add_point = FALSE,
  pt_color = "grey30",
  pt_size = NULL,
  pt_alpha = 1,
  jitter_width = 0.5,
  jitter_height = 0.1,
  stack = FALSE,
  y_max = NULL,
  y_min = NULL,
  add_box = FALSE,
  box_color = "black",
  box_width = 0.1,
  box_ptsize = 2.5,
  add_trend = FALSE,
  trend_color = NULL,
  trend_linewidth = 1,
  trend_ptsize = 2,
  add_stat = NULL,
  stat_name = NULL,
  stat_color = "black",
  stat_size = 1,
  stat_stroke = 1,
  stat_shape = 25,
  add_bg = FALSE,
  bg_palette = "stripe",
  bg_palcolor = NULL,
  bg_alpha = 0.2,
  add_line = NULL,
  line_color = "red2",
  line_width = 0.6,
  line_type = 2,
  highlight = NULL,
  highlight_color = "red2",
  highlight_size = 1,
  highlight_alpha = 1,
  comparisons = NULL,
  ref_group = NULL,
  pairwise_method = "wilcox.test",
  multiplegroup_comparisons = FALSE,
  multiple_method = "kruskal.test",
  sig_label = c("p.signif", "p.format"),
  sig_labelsize = 3.5,
  facet_by = NULL,
  facet_scales = "fixed",
  facet_ncol = NULL,
  facet_nrow = NULL,
  facet_byrow = TRUE,
  title = NULL,
  subtitle = NULL,
  xlab = NULL,
  ylab = NULL,
  seed = 8525,
  combine = TRUE,
  nrow = NULL,
  ncol = NULL,
  byrow = TRUE,
  ...
)

Arguments

data: A data frame.
x: A character string specifying the column name of the data frame to plot for the x-axis.
x_sep: A character string to concatenate the columns in x, if multiple columns are provided. When in_form is "wide", x columns will not be concatenated.
y: A character string specifying the column name of the data frame to plot for the y-axis.
in_form: A character string to specify the input data type. Either "long" or "wide".
split_by: The column(s) to split data by and plot separately.
split_by_sep: The separator for multiple split_by columns. See split_by
sort_x: A character string to specify the sorting of x-axis. Either "none", "mean_asc", "mean_desc", "mean", "median_asc", "median_desc", "median".
flip: A logical value to flip the plot.
keep_empty: A logical value indicating whether to keep empty groups. If FALSE, empty groups will be removed.
group_by: Columns to group the data for plotting For those plotting functions that do not support multiple groups, They will be concatenated into one column, using group_by_sep as the separator
group_by_sep: The separator for multiple group_by columns. See group_by
group_name: A character string to name the legend of dodge.
x_text_angle: A numeric value specifying the angle of the x-axis text.
fill_mode: A character string to specify the fill mode. Either "dodge", "x", "mean", "median".
fill_reverse: A logical value to reverse the fill colors for gradient fill (mean/median).
theme: A character string or a theme class (i.e. ggplot2::theme_classic) specifying the theme to use. Default is "theme_this".
theme_args: A list of arguments to pass to the theme function.
palette: A character string specifying the palette to use. A named list or vector can be used to specify the palettes for different split_by values.
palcolor: A character string specifying the color to use in the palette. A named list can be used to specify the colors for different split_by values. If some values are missing, the values from the palette will be used (palcolor will be NULL for those values).
alpha: A numeric value specifying the transparency of the plot.
aspect.ratio: A numeric value specifying the aspect ratio of the plot.
legend.position: A character string specifying the position of the legend. if waiver(), for single groups, the legend will be "none", otherwise "right".
legend.direction: A character string specifying the direction of the legend.
add_point: A logical value to add (jitter) points to the plot.
pt_color: A character string to specify the color of the points.
pt_size: A numeric value to specify the size of the points.
pt_alpha: A numeric value to specify the transparency of the points.
jitter_width: A numeric value to specify the width of the jitter.
jitter_height: A numeric value to specify the height of the jitter.
stack: A logical value whether to stack the facetted plot by 'facet_by'.
y_max: A numeric value or a character string to specify the maximum value of the y-axis.
y_min: A numeric value or a character string to specify the minimum value of the y-axis.
add_trend: A logical value to add trend line to the plot.
trend_color: A character string to specify the color of the trend line.
trend_linewidth: A numeric value to specify the width of the trend line.
trend_ptsize: A numeric value to specify the size of the trend line points.
add_stat: A character string to add statistical test to the plot.
stat_name: A character string to specify the name of the stat legend.
stat_color: A character string to specify the color of the statistical test.
stat_size: A numeric value to specify the size of the statistical test.
stat_stroke: A numeric value to specify the stroke of the statistical test.
stat_shape: A numeric value to specify the shape of the statistical test.
add_bg: A logical value to add background to the plot.
bg_palette: A character string to specify the palette of the background.
bg_palcolor: A character vector to specify the colors of the background.
bg_alpha: A numeric value to specify the transparency of the background.
add_line: A character string to add a line to the plot.
line_color: A character string to specify the color of the line.
line_width: A numeric value to specify the size of the line.
line_type: A numeric value to specify the type of the line.
highlight: A vector of character strings to highlight the points. It should be a subset of the row names of the data. If TRUE, it will highlight all points.
highlight_color: A character string to specify the color of the highlighted points.
highlight_size: A numeric value to specify the size of the highlighted points.
highlight_alpha: A numeric value to specify the transparency of the highlighted points.
comparisons: A logical value or a list of vectors to perform pairwise comparisons. If TRUE, it will perform pairwise comparisons for all pairs.
ref_group: A character string to specify the reference group for comparisons.
pairwise_method: A character string to specify the pairwise comparison method.
multiplegroup_comparisons: A logical value to perform multiple group comparisons.
multiple_method: A character string to specify the multiple group comparison method.
sig_label: A character string to specify the label of the significance test.
sig_labelsize: A numeric value to specify the size of the significance test label.
facet_by: A character string specifying the column name of the data frame to facet the plot. Otherwise, the data will be split by split_by and generate multiple plots and combine them into one using patchwork::wrap_plots
facet_scales: Whether to scale the axes of facets. Default is "fixed" Other options are "free", "free_x", "free_y". See ggplot2::facet_wrap
facet_ncol: A numeric value specifying the number of columns in the facet. When facet_by is a single column and facet_wrap is used.
facet_nrow: A numeric value specifying the number of rows in the facet. When facet_by is a single column and facet_wrap is used.
facet_byrow: A logical value indicating whether to fill the plots by row. Default is TRUE.
title: A character string specifying the title of the plot. A function can be used to generate the title based on the default title. This is useful when split_by is used and the title needs to be dynamic.
subtitle: A character string specifying the subtitle of the plot.
xlab: A character string specifying the x-axis label.
ylab: A character string specifying the y-axis label.
seed: The random seed to use. Default is 8525.
combine: Whether to combine the plots into one when facet is FALSE. Default is TRUE.
nrow: A numeric value specifying the number of rows in the facet.
ncol: A numeric value specifying the number of columns in the facet.
byrow: A logical value indicating whether to fill the plots by row.
...: Additional arguments.
add_box: A logical value to add box plot to the plot.
box_color: A character string to specify the color of the box plot.
box_width: A numeric value to specify the width of the box plot.
box_ptsize: A numeric value to specify the size of the box plot points in the middle.

Value

The Box / Violin plot(s). When split_by is not provided, it returns a ggplot object. When split_by is provided, it returns a object of plots wrapped by patchwork::wrap_plots if combine = TRUE; otherwise, it returns a list of ggplot objects.

Examples

# \donttest{
set.seed(8525)
data <- data.frame(
    x = rep(LETTERS[1:8], 40),
    y = rnorm(320),
    group1 = sample(c("g1", "g2"), 320, replace = TRUE),
    group2 = sample(c("h1", "h2", "h3", "h4"), 320, replace = TRUE)
)

BoxPlot(data, x = "x", y = "y")

BoxPlot(data,
    x = "x", y = "y",
    stack = TRUE, flip = TRUE, facet_by = "group1",
    add_bg = TRUE, bg_palette = "Paired"
)

BoxPlot(data,
    x = "x", y = "y",
    stack = TRUE, flip = TRUE, split_by = "group1",
    add_bg = TRUE, bg_palette = "Paired",
    palcolor = list(g1 = c("red", "blue"), g2 = c("blue", "red"))
)


# wide form data
data_wide <- data.frame(
    A = rnorm(100),
    B = rnorm(100),
    C = rnorm(100)
)
BoxPlot(data_wide, x = c("A", "B", "C"), in_form = "wide")

# }
# \donttest{
ViolinPlot(data, x = "x", y = "y")

ViolinPlot(data, x = "x", y = "y", add_box = TRUE)

ViolinPlot(data, x = "x", y = "y", add_point = TRUE)

ViolinPlot(data, x = "x", y = "y", add_trend = TRUE)

ViolinPlot(data, x = "x", y = "y", add_stat = mean)

ViolinPlot(data, x = "x", y = "y", add_bg = TRUE)

ViolinPlot(data, x = "x", y = "y", add_line = 0)

ViolinPlot(data, x = "x", y = "y", group_by = "group1")

ViolinPlot(data,
    x = "x", y = "y", group_by = "group1",
    facet_by = "group2", add_box = TRUE
)
#> Warning: Groups with fewer than two datapoints have been dropped.
#> ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
#> Warning: Groups with fewer than two datapoints have been dropped.
#> ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.

ViolinPlot(data, x = "x", y = "y", add_point = TRUE, highlight = 'group1 == "g1"',
    alpha = 0.8, highlight_size = 1.5, pt_size = 1, add_box = TRUE)

ViolinPlot(data,
    x = "x", y = "y", group_by = "group1",
    comparisons = TRUE
)

ViolinPlot(data,
    x = "x", y = "y", sig_label = "p.format",
    facet_by = "group2", comparisons = list(c("A", "B"))
)

ViolinPlot(data,
    x = "x", y = "y", fill_mode = "mean",
    facet_by = "group2", palette = "Blues"
)

ViolinPlot(data,
    x = "x", y = "y", fill_mode = "mean",
    split_by = "group1", palette = c(g1 = "Blues", g2 = "Reds")
)

ViolinPlot(data,
    x = "x", y = "y", stack = TRUE,
    facet_by = "group2", add_box = TRUE, add_bg = TRUE,
    bg_palette = "Paired"
)

# }