Package 'ordr'

Annotate factors of 'tbl_ord' objects

Description

These functions annotate the matrix factors of tbl_ords with additional variables, and retrieve these annotations.

The unexported ⁠annotation_*()⁠ and ⁠set_annotation_*()⁠ functions assign and retrieve values of the "*_annotation" attributes of x, which must have the same number of rows as get_*(x).

Arguments

annot

A data.frame having the same number of rows as get_*(x).

See Also

augmentation methods that must interface with annotation.

---

Augment factors and coordinates of 'tbl_ord' objects

Description

These functions return data associated with the cases, variables, and coordinates of an ordination object, and attach it to the object.

Usage

recover_aug_rows(x)

recover_aug_cols(x)

recover_aug_coord(x)

augment_ord(x, .matrix = "dims")

Arguments

x	An object of class 'tbl_ord'.
.matrix	A character string partially matched (lowercase) to several indicators for one or both matrices in a matrix decomposition used for ordination. The standard values are "rows", "cols", and "dims" (for both).

Details

The ⁠recover_aug_*()⁠ S3 methods produce tibbles of values associated with the rows, columns, and artificial coordinates of an object of class 'tbl_ord'. The first field of each tibble is name, which contains the row, column, or coordinate names. Additional fields contain information about the rows, columns, or coordinates extracted from the ordination object.

The function augment_ord() returns the ordination with either or both matrix factors annotated with the result of ⁠recover_aug_*()⁠. In this way augment_ord() works like generics::augment(), as popularized by the broom package, by extracting information about the rows and columns, but it differs in returning an annotated 'tbl_ord' rather than a 'tbl_df' object. The advantage of implementing separate methods for the rows, columns, and artificial coordinates is that more information contained in the original object becomes accessible to the user.

Value

The ⁠recover_aug_*()⁠ functions return tibbles having the same numbers of rows as ⁠recover_*()⁠. augment_ord() returns an augmented tbl_ord with the wrapped model unchanged.

See Also

tidiers and annotation methods that interface with augmentation.

Other generic recoverers: conference, recoverers, supplementation

---

Convenience geoms for row and column matrix factors

Description

These geometric element layers (geoms) pair conventional ggplot2 geoms with stat_rows() or stat_cols() in order to render elements for one or the other matrix factor of a tbl_ord. They understand the same aesthetics as their corresponding conventional geoms.

Usage

geom_rows_point(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_point(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_path(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  arrow = NULL,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_path(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  arrow = NULL,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_polygon(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  rule = "evenodd",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_polygon(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  rule = "evenodd",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_contour(
  mapping = NULL,
  data = NULL,
  stat = "contour",
  position = "identity",
  ...,
  bins = NULL,
  binwidth = NULL,
  breaks = NULL,
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_contour(
  mapping = NULL,
  data = NULL,
  stat = "contour",
  position = "identity",
  ...,
  bins = NULL,
  binwidth = NULL,
  breaks = NULL,
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_density_2d(
  mapping = NULL,
  data = NULL,
  stat = "density_2d",
  position = "identity",
  ...,
  contour_var = "density",
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_density_2d(
  mapping = NULL,
  data = NULL,
  stat = "density_2d",
  position = "identity",
  ...,
  contour_var = "density",
  lineend = "butt",
  linejoin = "round",
  linemitre = 10,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_density_2d_filled(
  mapping = NULL,
  data = NULL,
  stat = "density_2d_filled",
  position = "identity",
  ...,
  contour_var = "density",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_density_2d_filled(
  mapping = NULL,
  data = NULL,
  stat = "density_2d_filled",
  position = "identity",
  ...,
  contour_var = "density",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_text(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  check_overlap = FALSE,
  size.unit = "mm",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_text(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  check_overlap = FALSE,
  size.unit = "mm",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_label(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  label.padding = unit(0.25, "lines"),
  label.r = unit(0.15, "lines"),
  label.size = 0.25,
  size.unit = "mm",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_label(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  label.padding = unit(0.25, "lines"),
  label.r = unit(0.15, "lines"),
  label.size = 0.25,
  size.unit = "mm",
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_text_repel(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  parse = FALSE,
  ...,
  box.padding = 0.25,
  point.padding = 1e-06,
  min.segment.length = 0.5,
  arrow = NULL,
  force = 1,
  force_pull = 1,
  max.time = 0.5,
  max.iter = 10000,
  max.overlaps = getOption("ggrepel.max.overlaps", default = 10),
  nudge_x = 0,
  nudge_y = 0,
  xlim = c(NA, NA),
  ylim = c(NA, NA),
  na.rm = FALSE,
  show.legend = NA,
  direction = c("both", "y", "x"),
  seed = NA,
  verbose = FALSE,
  inherit.aes = TRUE
)

geom_cols_text_repel(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  parse = FALSE,
  ...,
  box.padding = 0.25,
  point.padding = 1e-06,
  min.segment.length = 0.5,
  arrow = NULL,
  force = 1,
  force_pull = 1,
  max.time = 0.5,
  max.iter = 10000,
  max.overlaps = getOption("ggrepel.max.overlaps", default = 10),
  nudge_x = 0,
  nudge_y = 0,
  xlim = c(NA, NA),
  ylim = c(NA, NA),
  na.rm = FALSE,
  show.legend = NA,
  direction = c("both", "y", "x"),
  seed = NA,
  verbose = FALSE,
  inherit.aes = TRUE
)

geom_rows_label_repel(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  parse = FALSE,
  ...,
  box.padding = 0.25,
  label.padding = 0.25,
  point.padding = 1e-06,
  label.r = 0.15,
  label.size = 0.25,
  min.segment.length = 0.5,
  arrow = NULL,
  force = 1,
  force_pull = 1,
  max.time = 0.5,
  max.iter = 10000,
  max.overlaps = getOption("ggrepel.max.overlaps", default = 10),
  nudge_x = 0,
  nudge_y = 0,
  xlim = c(NA, NA),
  ylim = c(NA, NA),
  na.rm = FALSE,
  show.legend = NA,
  direction = c("both", "y", "x"),
  seed = NA,
  verbose = FALSE,
  inherit.aes = TRUE
)

geom_cols_label_repel(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  parse = FALSE,
  ...,
  box.padding = 0.25,
  label.padding = 0.25,
  point.padding = 1e-06,
  label.r = 0.15,
  label.size = 0.25,
  min.segment.length = 0.5,
  arrow = NULL,
  force = 1,
  force_pull = 1,
  max.time = 0.5,
  max.iter = 10000,
  max.overlaps = getOption("ggrepel.max.overlaps", default = 10),
  nudge_x = 0,
  nudge_y = 0,
  xlim = c(NA, NA),
  ylim = c(NA, NA),
  na.rm = FALSE,
  show.legend = NA,
  direction = c("both", "y", "x"),
  seed = NA,
  verbose = FALSE,
  inherit.aes = TRUE
)

geom_rows_axis(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  axis_labels = TRUE,
  axis_ticks = TRUE,
  axis_text = TRUE,
  by = NULL,
  num = NULL,
  tick_length = 0.025,
  text_dodge = 0.03,
  label_dodge = 0.03,
  ...,
  axis.colour = NULL,
  axis.color = NULL,
  axis.alpha = NULL,
  label.angle = 0,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  tick.linewidth = 0.25,
  tick.colour = NULL,
  tick.color = NULL,
  tick.alpha = NULL,
  text.size = 2.6,
  text.angle = 0,
  text.hjust = 0.5,
  text.vjust = 0.5,
  text.family = NULL,
  text.fontface = NULL,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_axis(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  axis_labels = TRUE,
  axis_ticks = TRUE,
  axis_text = TRUE,
  by = NULL,
  num = NULL,
  tick_length = 0.025,
  text_dodge = 0.03,
  label_dodge = 0.03,
  ...,
  axis.colour = NULL,
  axis.color = NULL,
  axis.alpha = NULL,
  label.angle = 0,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  tick.linewidth = 0.25,
  tick.colour = NULL,
  tick.color = NULL,
  tick.alpha = NULL,
  text.size = 2.6,
  text.angle = 0,
  text.hjust = 0.5,
  text.vjust = 0.5,
  text.family = NULL,
  text.fontface = NULL,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_pointranges(
  mapping = NULL,
  data = NULL,
  stat = "center",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_pointranges(
  mapping = NULL,
  data = NULL,
  stat = "center",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_lineranges(
  mapping = NULL,
  data = NULL,
  stat = "center",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_lineranges(
  mapping = NULL,
  data = NULL,
  stat = "center",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_isoline(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  isoline_text = TRUE,
  by = NULL,
  num = NULL,
  text_dodge = 0.03,
  ...,
  text.size = 3,
  text.angle = 0,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_isoline(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  isoline_text = TRUE,
  by = NULL,
  num = NULL,
  text_dodge = 0.03,
  ...,
  text.size = 3,
  text.angle = 0,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_text_radiate(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_text_radiate(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  ...,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_vector(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  arrow = default_arrow,
  lineend = "round",
  linejoin = "mitre",
  vector_labels = TRUE,
  ...,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_vector(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  arrow = default_arrow,
  lineend = "round",
  linejoin = "mitre",
  vector_labels = TRUE,
  ...,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_bagplot(
  mapping = NULL,
  data = NULL,
  stat = "bagplot",
  position = "identity",
  ...,
  bag.linewidth = sync(),
  bag.linetype = sync(),
  bag.colour = "black",
  bag.color = NULL,
  bag.fill = sync(),
  bag.alpha = NA,
  median.shape = 21L,
  median.stroke = sync(),
  median.size = 5,
  median.colour = sync(),
  median.color = NULL,
  median.fill = "white",
  median.alpha = NA,
  fence.linewidth = 0.25,
  fence.linetype = 0L,
  fence.colour = sync(),
  fence.color = NULL,
  fence.fill = sync(),
  fence.alpha = 0.25,
  outlier.shape = sync(),
  outlier.stroke = sync(),
  outlier.size = sync(),
  outlier.colour = sync(),
  outlier.color = NULL,
  outlier.fill = NA,
  outlier.alpha = NA,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_bagplot(
  mapping = NULL,
  data = NULL,
  stat = "bagplot",
  position = "identity",
  ...,
  bag.linewidth = sync(),
  bag.linetype = sync(),
  bag.colour = "black",
  bag.color = NULL,
  bag.fill = sync(),
  bag.alpha = NA,
  median.shape = 21L,
  median.stroke = sync(),
  median.size = 5,
  median.colour = sync(),
  median.color = NULL,
  median.fill = "white",
  median.alpha = NA,
  fence.linewidth = 0.25,
  fence.linetype = 0L,
  fence.colour = sync(),
  fence.color = NULL,
  fence.fill = sync(),
  fence.alpha = 0.25,
  outlier.shape = sync(),
  outlier.stroke = sync(),
  outlier.size = sync(),
  outlier.colour = sync(),
  outlier.color = NULL,
  outlier.fill = NA,
  outlier.alpha = NA,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_rule(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  axis_labels = TRUE,
  axis_ticks = TRUE,
  axis_text = TRUE,
  by = NULL,
  num = NULL,
  snap_rule = TRUE,
  tick_length = 0.025,
  text_dodge = 0.03,
  label_dodge = 0.03,
  ...,
  axis.colour = NULL,
  axis.color = NULL,
  axis.alpha = NULL,
  label.angle = 0,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  tick.linewidth = 0.25,
  tick.colour = NULL,
  tick.color = NULL,
  tick.alpha = NULL,
  text.size = 2.6,
  text.angle = 0,
  text.hjust = 0.5,
  text.vjust = 0.5,
  text.family = NULL,
  text.fontface = NULL,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_rule(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  axis_labels = TRUE,
  axis_ticks = TRUE,
  axis_text = TRUE,
  by = NULL,
  num = NULL,
  snap_rule = TRUE,
  tick_length = 0.025,
  text_dodge = 0.03,
  label_dodge = 0.03,
  ...,
  axis.colour = NULL,
  axis.color = NULL,
  axis.alpha = NULL,
  label.angle = 0,
  label.colour = NULL,
  label.color = NULL,
  label.alpha = NULL,
  tick.linewidth = 0.25,
  tick.colour = NULL,
  tick.color = NULL,
  tick.alpha = NULL,
  text.size = 2.6,
  text.angle = 0,
  text.hjust = 0.5,
  text.vjust = 0.5,
  text.family = NULL,
  text.fontface = NULL,
  text.colour = NULL,
  text.color = NULL,
  text.alpha = NULL,
  parse = FALSE,
  check_overlap = FALSE,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_rows_interpolation(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  new_data = NULL,
  type = c("centroid", "sequence"),
  arrow = default_arrow,
  ...,
  point.fill = NA,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_cols_interpolation(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  new_data = NULL,
  type = c("centroid", "sequence"),
  arrow = default_arrow,
  ...,
  point.fill = NA,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

Arguments

mapping	Set of aesthetic mappings created by aes(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.
data	The data to be displayed in this layer. There are three options: If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot(). A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created. A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).
stat	The statistical transformation to use on the data for this layer. When using a ⁠geom_*()⁠ function to construct a layer, the stat argument can be used to override the default coupling between geoms and stats. The stat argument accepts the following: A Stat ggproto subclass, for example StatCount. A string naming the stat. To give the stat as a string, strip the function name of the stat_ prefix. For example, to use stat_count(), give the stat as "count". For more information and other ways to specify the stat, see the layer stat documentation.
position	A position adjustment to use on the data for this layer. This can be used in various ways, including to prevent overplotting and improving the display. The position argument accepts the following: The result of calling a position function, such as position_jitter(). This method allows for passing extra arguments to the position. A string naming the position adjustment. To give the position as a string, strip the function name of the position_ prefix. For example, to use position_jitter(), give the position as "jitter". For more information and other ways to specify the position, see the layer position documentation.
...	Additional arguments passed to ggplot2::layer().
na.rm	Passed to ggplot2::layer().
show.legend	logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display. To include legend keys for all levels, even when no data exists, use TRUE. If NA, all levels are shown in legend, but unobserved levels are omitted.
inherit.aes	If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. annotation_borders().
lineend	Line end style (round, butt, square).
linejoin	Line join style (round, mitre, bevel).
linemitre	Line mitre limit (number greater than 1).
arrow	Arrow specification, as created by grid::arrow().
rule	Either "evenodd" or "winding". If polygons with holes are being drawn (using the subgroup aesthetic) this argument defines how the hole coordinates are interpreted. See the examples in grid::pathGrob() for an explanation.
bins	Number of contour bins. Overridden by breaks.
binwidth	The width of the contour bins. Overridden by bins.
breaks	One of: Numeric vector to set the contour breaks A function that takes the range of the data and binwidth as input and returns breaks as output. A function can be created from a formula (e.g. ~ fullseq(.x, .y)). Overrides binwidth and bins. By default, this is a vector of length ten with pretty() breaks.
contour_var	Character string identifying the variable to contour by. Can be one of "density", "ndensity", or "count". See the section on computed variables for details.
parse	If TRUE, the labels will be parsed into expressions and displayed as described in ?plotmath.
nudge_x, nudge_y	Horizontal and vertical adjustments to nudge the starting position of each text label. The units for nudge_x and nudge_y are the same as for the data units on the x-axis and y-axis.
check_overlap	If TRUE, text that overlaps previous text in the same layer will not be plotted. check_overlap happens at draw time and in the order of the data. Therefore data should be arranged by the label column before calling geom_text(). Note that this argument is not supported by geom_label().
size.unit	How the size aesthetic is interpreted: as millimetres ("mm", default), points ("pt"), centimetres ("cm"), inches ("in"), or picas ("pc").
label.padding	Amount of padding around label. Defaults to 0.25 lines.
label.r	Radius of rounded corners. Defaults to 0.15 lines.
label.size	Replaced by the linewidth aesthetic. Size of label border, in mm.
box.padding	Amount of padding around bounding box, as unit or number. Defaults to 0.25. (Default unit is lines, but other units can be specified by passing unit(x, "units")).
point.padding	Amount of padding around labeled point, as unit or number. Defaults to 0. (Default unit is lines, but other units can be specified by passing unit(x, "units")).
min.segment.length	Skip drawing segments shorter than this, as unit or number. Defaults to 0.5. (Default unit is lines, but other units can be specified by passing unit(x, "units")).
force	Force of repulsion between overlapping text labels. Defaults to 1.
force_pull	Force of attraction between a text label and its corresponding data point. Defaults to 1.
max.time	Maximum number of seconds to try to resolve overlaps. Defaults to 0.5.
max.iter	Maximum number of iterations to try to resolve overlaps. Defaults to 10000.
max.overlaps	Exclude text labels when they overlap too many other things. For each text label, we count how many other text labels or other data points it overlaps, and exclude the text label if it has too many overlaps. Defaults to 10.
xlim, ylim	Limits for the x and y axes. Text labels will be constrained to these limits. By default, text labels are constrained to the entire plot area.
direction	direction of stairs: 'vh' for vertical then horizontal, 'hv' for horizontal then vertical, or 'mid' for step half-way between adjacent x-values.
seed	Random seed passed to set.seed. Defaults to NA, which means that set.seed will not be called.
verbose	If TRUE, some diagnostics of the repel algorithm are printed
axis_labels, axis_ticks, axis_text	Logical; whether to include labels, tick marks, and text value marks along the axes.
by, num	Intervals between elements or number of elements; specify only one.
tick_length	Numeric; the length of the tick marks, as a proportion of the minimum of the plot width and height.
text_dodge	Numeric; the orthogonal distance of tick mark text from the axis, as a proportion of the minimum of the plot width and height.
label_dodge	Numeric; the orthogonal distance of the axis label from the axis, as a proportion of the minimum of the plot width and height.
axis.colour, axis.color, axis.alpha	Default aesthetics for axes. Set to NULL to inherit from the data's aesthetics.
label.angle, label.colour, label.color, label.alpha	Default aesthetics for labels. Set to NULL to inherit from the data's aesthetics.
tick.linewidth, tick.colour, tick.color, tick.alpha	Default aesthetics for tick marks. Set to NULL to inherit from the data's aesthetics.
text.colour, text.color	Colour of the text. When NULL (default), the colour aesthetic determines the colour of the text. text.color is an alias for text.colour.
isoline_text	Logical; whether to include text value marks along the isolines.
vector_labels	Logical; whether to include labels radiating outward from the vectors.
bag.linetype, bag.linewidth, bag.colour, bag.color, bag.fill, bag.alpha	Default aesthetics for bags. Set to sync() to inherit from the data's aesthetics or to NULL to use the data's aesthetics.
median.shape, median.stroke, median.size, median.colour, median.color, median.fill, median.alpha	Default aesthetics for medians. Set to sync() to inherit from the data's aesthetics or to NULL to use the data's aesthetics.
fence.linetype, fence.linewidth, fence.colour, fence.color, fence.fill, fence.alpha	Default aesthetics for fences. Set to sync() to inherit from the data's aesthetics or to NULL to use the data's aesthetics.
outlier.shape, outlier.stroke, outlier.size, outlier.colour, outlier.color, outlier.fill, outlier.alpha	Default aesthetics for outliers. Set to sync() to inherit from the data's aesthetics or to NULL to use the data's aesthetics.
snap_rule	Logical; whether to snap rule segments to grid values.
new_data	A list (best structured as a data.frame) of row (geom_cols_interpolation()) or column (geom_rows_interpolation()) values to interpolate.
type	Character value matched to "centroid" or "sequence"; the type of operations used to visualize interpolation.
point.fill	Default aesthetics for markers. Set to NULL to inherit from the data's aesthetics.

Value

A ggproto layer.

See Also

Other biplot layers: biplot-stats, stat_rows()

Examples

# compute log-ratio analysis of Freestone primary class composition measurements
glass %>%
  ordinate(cols = c(SiO2, Al2O3, CaO, FeO, MgO),
           model = lra, compositional = TRUE) %>%
  confer_inertia("rows") %>%
  print() -> glass_lra
# row-principal biplot with ordinate-wise standard deviations
glass_lra %>%
  ggbiplot(aes(color = Site), sec.axes = "cols") +
  theme_biplot() +
  scale_color_brewer(type = "qual", palette = 6) +
  geom_cols_text(stat = "chull", aes(label = name), color = "#444444") +
  geom_rows_lineranges(fun.data = mean_sdl, linewidth = .75) +
  geom_rows_point(alpha = .5) +
  ggtitle(
    "Row-principal LRA biplot of Freestone glass measurements",
    "Ranges 2 sample standard deviations from centroids"
  )

# principal components analysis of glass composition measurements
glass[, c(5L, 7L, 8L, 10L, 11L)] %>%
  princomp(cor = TRUE) %>%
  as_tbl_ord() %>%
  cbind_rows(site = glass$Site, form = glass$Form) %>%
  augment_ord() %>%
  print() -> glass_pca
# note that column standard coordinates are unit vectors
rowSums(get_cols(glass_pca) ^ 2)
# plot column standard coordinates with a unit circle underlaid
glass_pca %>%
  ggbiplot(aes(label = name), sec.axes = "cols") +
  theme_biplot() +
  geom_rows_point(aes(color = site, shape = form), elements = "score") +
  geom_unit_circle(alpha = .5, scale.factor = 3) +
  geom_cols_vector()

---

Convenience stats for row and column matrix factors

Description

These statistical transformations (stats) adapt conventional ggplot2 stats to one or the other matrix factor of a tbl_ord, in lieu of stat_rows() or stat_cols(). They accept the same parameters as their corresponding conventional stats.

Usage

stat_rows_density_2d(
  mapping = NULL,
  data = NULL,
  geom = "density_2d",
  position = "identity",
  ...,
  contour = TRUE,
  contour_var = "density",
  n = 100,
  h = NULL,
  adjust = c(1, 1),
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_cols_density_2d(
  mapping = NULL,
  data = NULL,
  geom = "density_2d",
  position = "identity",
  ...,
  contour = TRUE,
  contour_var = "density",
  n = 100,
  h = NULL,
  adjust = c(1, 1),
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_rows_density_2d_filled(
  mapping = NULL,
  data = NULL,
  geom = "density_2d_filled",
  position = "identity",
  ...,
  contour = TRUE,
  contour_var = "density",
  n = 100,
  h = NULL,
  adjust = c(1, 1),
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_cols_density_2d_filled(
  mapping = NULL,
  data = NULL,
  geom = "density_2d_filled",
  position = "identity",
  ...,
  contour = TRUE,
  contour_var = "density",
  n = 100,
  h = NULL,
  adjust = c(1, 1),
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_rows_ellipse(
  mapping = NULL,
  data = NULL,
  geom = "path",
  position = "identity",
  ...,
  type = "t",
  level = 0.95,
  segments = 51,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_cols_ellipse(
  mapping = NULL,
  data = NULL,
  geom = "path",
  position = "identity",
  ...,
  type = "t",
  level = 0.95,
  segments = 51,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_rows_center(
  mapping = NULL,
  data = NULL,
  geom = "point",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  fun.data = NULL,
  fun = NULL,
  fun.center = NULL,
  fun.min = NULL,
  fun.max = NULL,
  fun.ord = NULL,
  fun.args = list()
)

stat_cols_center(
  mapping = NULL,
  data = NULL,
  geom = "point",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  fun.data = NULL,
  fun = NULL,
  fun.center = NULL,
  fun.min = NULL,
  fun.max = NULL,
  fun.ord = NULL,
  fun.args = list()
)

stat_rows_star(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  fun.data = NULL,
  fun = NULL,
  fun.center = NULL,
  fun.ord = NULL,
  fun.args = list()
)

stat_cols_star(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  fun.data = NULL,
  fun = NULL,
  fun.center = NULL,
  fun.ord = NULL,
  fun.args = list()
)

stat_rows_chull(
  mapping = NULL,
  data = NULL,
  geom = "polygon",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_chull(
  mapping = NULL,
  data = NULL,
  geom = "polygon",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_peel(
  mapping = NULL,
  data = NULL,
  geom = "polygon",
  position = "identity",
  num = NULL,
  by = 1L,
  breaks = c(0.5),
  cut = c("above", "below"),
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_peel(
  mapping = NULL,
  data = NULL,
  geom = "polygon",
  position = "identity",
  num = NULL,
  by = 1L,
  breaks = c(0.5),
  cut = c("above", "below"),
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_cone(
  mapping = NULL,
  data = NULL,
  geom = "path",
  position = "identity",
  origin = FALSE,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_cone(
  mapping = NULL,
  data = NULL,
  geom = "path",
  position = "identity",
  origin = FALSE,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_depth(
  mapping = NULL,
  data = NULL,
  geom = "contour",
  position = "identity",
  contour = TRUE,
  contour_var = "depth",
  notion = "zonoid",
  notion_params = list(),
  n = 100L,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_depth(
  mapping = NULL,
  data = NULL,
  geom = "contour",
  position = "identity",
  contour = TRUE,
  contour_var = "depth",
  notion = "zonoid",
  notion_params = list(),
  n = 100L,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_depth_filled(
  mapping = NULL,
  data = NULL,
  geom = "contour_filled",
  position = "identity",
  contour = TRUE,
  contour_var = "depth",
  notion = "zonoid",
  notion_params = list(),
  n = 100L,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_depth_filled(
  mapping = NULL,
  data = NULL,
  geom = "contour_filled",
  position = "identity",
  contour = TRUE,
  contour_var = "depth",
  notion = "zonoid",
  notion_params = list(),
  n = 100L,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_scale(
  mapping = NULL,
  data = NULL,
  geom = "point",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  mult = 1
)

stat_cols_scale(
  mapping = NULL,
  data = NULL,
  geom = "point",
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,
  ...,
  mult = 1
)

stat_rows_spantree(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  engine = "mlpack",
  method = "euclidean",
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_spantree(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  engine = "mlpack",
  method = "euclidean",
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_bagplot(
  mapping = NULL,
  data = NULL,
  geom = "bagplot",
  position = "identity",
  fraction = 0.5,
  coef = 3,
  median = TRUE,
  fence = TRUE,
  outliers = TRUE,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_cols_bagplot(
  mapping = NULL,
  data = NULL,
  geom = "bagplot",
  position = "identity",
  fraction = 0.5,
  coef = 3,
  median = TRUE,
  fence = TRUE,
  outliers = TRUE,
  show.legend = NA,
  inherit.aes = TRUE,
  ...
)

stat_rows_rule(
  mapping = NULL,
  data = NULL,
  geom = "rule",
  position = "identity",
  fun.lower = "minpp",
  fun.upper = "maxpp",
  fun.offset = "minabspp",
  fun.args = list(),
  referent = NULL,
  show.legend = NA,
  inherit.aes = TRUE,
  ref_subset = NULL,
  ref_elements = "active",
  ...
)

stat_cols_rule(
  mapping = NULL,
  data = NULL,
  geom = "rule",
  position = "identity",
  fun.lower = "minpp",
  fun.upper = "maxpp",
  fun.offset = "minabspp",
  fun.args = list(),
  referent = NULL,
  show.legend = NA,
  inherit.aes = TRUE,
  ref_subset = NULL,
  ref_elements = "active",
  ...
)

stat_rows_projection(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  referent = NULL,
  ref_subset = NULL,
  ref_elements = "active",
  ...,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_cols_projection(
  mapping = NULL,
  data = NULL,
  geom = "segment",
  position = "identity",
  referent = NULL,
  ref_subset = NULL,
  ref_elements = "active",
  ...,
  show.legend = NA,
  inherit.aes = TRUE
)

Arguments

mapping	Set of aesthetic mappings created by aes(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.
data	The data to be displayed in this layer. There are three options: If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot(). A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created. A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).
geom	The geometric object to use to display the data for this layer. When using a ⁠stat_*()⁠ function to construct a layer, the geom argument can be used to override the default coupling between stats and geoms. The geom argument accepts the following: A Geom ggproto subclass, for example GeomPoint. A string naming the geom. To give the geom as a string, strip the function name of the geom_ prefix. For example, to use geom_point(), give the geom as "point". For more information and other ways to specify the geom, see the layer geom documentation.
position	A position adjustment to use on the data for this layer. This can be used in various ways, including to prevent overplotting and improving the display. The position argument accepts the following: The result of calling a position function, such as position_jitter(). This method allows for passing extra arguments to the position. A string naming the position adjustment. To give the position as a string, strip the function name of the position_ prefix. For example, to use position_jitter(), give the position as "jitter". For more information and other ways to specify the position, see the layer position documentation.
...	Additional arguments passed to ggplot2::layer().
contour	If TRUE, contour the results of the 2d density estimation.
contour_var	Character string identifying the variable to contour by. Can be one of "density", "ndensity", or "count". See the section on computed variables for details.
n	Number of grid points in each direction.
h	Bandwidth (vector of length two). If NULL, estimated using MASS::bandwidth.nrd().
adjust	A multiplicative bandwidth adjustment to be used if 'h' is 'NULL'. This makes it possible to adjust the bandwidth while still using the a bandwidth estimator. For example, adjust = 1/2 means use half of the default bandwidth.
na.rm	If FALSE, the default, missing values are removed with a warning. If TRUE, missing values are silently removed.
show.legend	logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display. To include legend keys for all levels, even when no data exists, use TRUE. If NA, all levels are shown in legend, but unobserved levels are omitted.
inherit.aes	If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. annotation_borders().
type	The type of ellipse. The default "t" assumes a multivariate t-distribution, and "norm" assumes a multivariate normal distribution. "euclid" draws a circle with the radius equal to level, representing the euclidean distance from the center. This ellipse probably won't appear circular unless coord_fixed() is applied.
level	The level at which to draw an ellipse, or, if type="euclid", the radius of the circle to be drawn.
segments	The number of segments to be used in drawing the ellipse.
fun.data	A function that is given the complete data and should return a data frame with variables ymin, y, and ymax.
fun.center	Deprecated alias to fun.
fun.min, fun, fun.max	Alternatively, supply three individual functions that are each passed a vector of values and should return a single number.
fun.ord	Alternatively to the ggplot2::stat_summary_bin() parameters, supply a summary function that takes a matrix as input and returns a named column summary vector. Overridden by fun.data and fun, cannot be used together with fun.min and fun.max.
fun.args	Optional additional arguments passed on to the functions.
num	A positive integer; the number of hulls to peel. Pass Inf for all hulls.
by	A positive integer; with what frequency to include consecutive hulls, pairs with num.
breaks	A numeric vector of fractions (between 0 and 1) of the data to contain in each hull; overridden by num.
cut	Character; one of "above" and "below", indicating whether each hull should contain at least or at most breaks of the data, respectively.
origin	Logical; whether to include the origin with the transformed data. Defaults to FALSE.
notion	Character; the name of the depth function (passed to ddalpha::depth.()).
notion_params	List of additional parameters passed via ... to ddalpha::depth.().
mult	Numeric value used to scale the coordinates.
engine	A single character string specifying the package implementation to use; "mlpack", "vegan", or "ade4".
method	Passed to stats::dist() if engine is "vegan" or "ade4", ignored if "mlpack".
fraction	Fraction of the data to include in the bag.
coef	Scale factor of the fence relative to the bag.
median, fence, outliers	Logical indicators whether to include median, fence, and outliers in the composite output.
fun.lower, fun.upper, fun.offset	Functions used to determine the limits of the rules and the translations of the axes from the projections of referent onto the axes and onto their normal vectors.
referent	The reference data set, admitting the same 3 options as data; see Details.
ref_elements, ref_subset	Analogues of elements and subset applied to referent.

Value

A ggproto layer.

Ordination aesthetics

This statistical transformation is compatible with the convenience function ord_aes().

Some transformations (e.g. stat_center()) commute with projection to the lower (1 or 2)-dimensional biplot space. If they detect aesthetics of the form ⁠..coord[0-9]+⁠, then ..coord1 and ..coord2 are converted to x and y while any remaining are ignored.

Other transformations (e.g. stat_spantree()) yield different results in a lower-dimensional biplot when they are computed before versus after projection. If the stat layer detects these aesthetics, then the transformation is performed before projection, and the results in the first two dimensions are returned as x and y.

A small number of transformations (stat_rule()) are incompatible with ordination aesthetics but will accept ord_aes() without warning.

See Also

Other biplot layers: biplot-geoms, stat_rows()

Examples

iris_pca <- ordinate(iris, prcomp, cols = seq(4), scale. = TRUE)
# NB: Non-standard aesthetics are handled as in version > 3.5.1; see:
# https://github.com/tidyverse/ggplot2/issues/6191
# This prevents `scale_color_discrete(aesthetics = ...)` from synching them.
ggbiplot(iris_pca) +
  stat_rows_bagplot(
    aes(fill = Species),
    median_gp = list(color = sync()),
    fence_gp = list(linewidth = 0.25),
    outlier_gp = list(shape = "asterisk")
  ) +
  scale_color_discrete(name = "Species", aesthetics = c("color", "fill")) +
  geom_cols_vector(aes(label = name))
ggbiplot(iris_pca) +
  stat_rows_bagplot(
    aes(fill = Species, color = Species),
    median_gp = list(color = sync()),
    fence_gp = list(linewidth = 0.25),
    outlier_gp = list(shape = "asterisk")
  ) +
  geom_cols_vector(aes(label = name))

# scaled PCA of Anderson iris measurements
iris[, -5] %>%
  princomp(cor = TRUE) %>%
  as_tbl_ord() %>%
  mutate_rows(species = iris$Species) %>%
  print() -> iris_pca
# row-principal biplot with depth median-based stars
iris_pca %>%
  ggbiplot(aes(color = species)) +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  stat_rows_star(alpha = .5, fun.ord = "depth_median") +
  geom_rows_point(alpha = .5) +
  stat_rows_center(fun.ord = "depth_median", size = 4, shape = 1L) +
  ggtitle(
    "Row-principal PCA biplot of Anderson iris measurements",
    "Segments connect each observation to its within-species depth median"
  )

# correspondence analysis of combined female and male hair and eye color data
HairEyeColor %>%
  rowSums(dims = 2L) %>%
  MASS::corresp(nf = 2L) %>%
  as_tbl_ord() %>%
  augment_ord() %>%
  print() -> hec_ca
# inertia across artificial coordinates (all singular values < 1)
get_inertia(hec_ca)
# in row-principal biplot, row coordinates are weighted averages of columns
# (and vice-versa)
hec_ca %>%
  confer_inertia("rows") %>%
  ggbiplot(aes(color = .matrix, fill = .matrix, shape = .matrix)) +
  theme_bw() +
  stat_cols_chull(alpha = .1) +
  geom_cols_point() +
  geom_rows_point() +
  ggtitle("Row-principal CA of hair & eye color")

# centered principal components analysis of U.S. personal expenditure data
USPersonalExpenditure %>%
  prcomp() %>%
  as_tbl_ord() %>%
  augment_ord() %>%
  # allow radiating text to exceed plotting window
  ggbiplot(aes(label = name), clip = "off",
           sec.axes = "cols", scale.factor = 50) +
  geom_rows_label(size = 3) +
  # omit labels in the conical hull without the origin
  geom_cols_vector(vector_labels = FALSE) +
  stat_cols_cone(linetype = "dotted") +
  geom_cols_vector(stat = "cone", vector_labels = TRUE, color = "transparent") +
  ggtitle(
    "U.S. Personal Expenditure data, 1940-1960",
    "Row-principal biplot of centered PCA"
  )
# compute row-principal components of scaled iris measurements
iris[, -5] %>%
  prcomp(scale = TRUE) %>%
  as_tbl_ord() %>%
  mutate_rows(species = iris$Species) %>%
  print() -> iris_pca
# row-principal biplot with centroids and confidence elliptical disks
iris_pca %>%
  ggbiplot(aes(color = species)) +
  theme_bw() +
  geom_rows_point() +
  geom_polygon(
    aes(fill = species),
    color = NA, alpha = .25, stat = "rows_ellipse"
  ) +
  geom_cols_vector(color = "#444444") +
  scale_color_brewer(
    type = "qual", palette = 2,
    aesthetics = c("color", "fill")
  ) +
  ggtitle(
    "Row-principal PCA biplot of Anderson iris measurements",
    "Overlaid with 95% confidence disks"
  )

# hull peeling with breaks below
judge_pca <- ordinate(USJudgeRatings, princomp, cols = -c(1, 12))
ggbiplot(judge_pca, axis.type = "predictive") +
  geom_cols_axis() +
  geom_rows_point(elements = "score") +
  stat_rows_peel(
    aes(alpha = after_stat(hull)), color = "black", elements = "score",
    breaks = c(.9, .5, .1), cut = "below"
  )

# hull peeling by groups
iris_pca <- ordinate(iris, cols = 1:4, model = prcomp)
ggbiplot(iris_pca) +
  geom_rows_point(aes(color = Species), shape = "circle open") +
  stat_rows_peel(
    aes(fill = Species, alpha = after_stat(hull)),
    num = 3
  )

# unscaled PCA
iris_pca <- ordinate(iris, cols = 1:4, model = prcomp)
# biplot canvas
iris_biplot <- 
  iris_pca %>%
  ggbiplot(aes(color = Species, label = name), axis.type = "predictive") +
  geom_rows_point() +
  geom_cols_axis(aes(center = center))
# print select cases
top_cases <- c(1, 51, 101)
iris[top_cases, ]
# subset variables
length_vars <- c(1, 3)
iris[, length_vars] %>%
  aggregate(by = iris[, "Species", drop = FALSE], FUN = mean)

# project all cases onto all axes
iris_biplot + stat_rows_projection()
# project all cases onto select axes
iris_biplot + stat_rows_projection(ref_subset = length_vars)

# project select cases onto all axes
iris_biplot + stat_rows_projection(subset = top_cases)
# project select cases onto select axes
iris_biplot + stat_rows_projection(subset = top_cases, ref_subset = length_vars)

# project select cases onto manually provided axes
iris_cols <- as.data.frame(get_cols(iris_pca))[c(1, 2), ]
iris_biplot + stat_rows_projection(subset = top_cases, referent = iris_cols)

# project selected cases onto selected axes in full-dimensional space
iris_pca %>%
  ggbiplot(ord_aes(iris_pca, color = Species, label = name),
           axis.type = "predictive") +
  geom_rows_point() +
  geom_cols_axis(aes(center = center)) +
  stat_rows_projection(subset = top_cases, ref_subset = length_vars)

# default (standardized) linear discriminant analysis
glass_lda <- MASS::lda(Site ~ SiO2 + Al2O3 + FeO + MgO + CaO, glass)
# bestow 'tbl_ord' class & augment observation, centroid, and variable fields
as_tbl_ord(glass_lda) %>%
  augment_ord() %>%
  print() -> glass_lda
# row-standard biplot
glass_lda %>%
  confer_inertia(1) %>%
  ggbiplot(aes(shape = grouping)) +
  theme_bw() + theme_biplot() +
  geom_rows_point(size = 4) +
  geom_rows_point(elements = "score") +
  stat_cols_rule(
    aes(label = name), color = "#888888", num = 8L,
    ref_elements = "score", fun.offset = function(x) minabspp(x, p = .1),
    text.size = 2.5, label_dodge = .04
  ) +
  scale_shape_manual(values = c(2L, 3L, 0L, 5L)) +
  ggtitle(
    "LDA of Freestone glass measurements",
    "Row-standard biplot of standardized LDA"
  )
# contribution LDA of sites on measurements
glass_lda <-
  lda_ord(Site ~ SiO2 + Al2O3 + FeO + MgO + CaO, glass,
          axes.scale = "contribution")
# bestow 'tbl_ord' class & augment observation, centroid, and variable fields
as_tbl_ord(glass_lda) %>%
  augment_ord() %>%
  print() -> glass_lda
# symmetric biplot
glass_lda %>%
  confer_inertia(.5) %>%
  ggbiplot(aes(shape = grouping)) +
  theme_bw() + theme_biplot() +
  geom_rows_point() +
  stat_rows_density_2d(elements = "score", alpha = .5, color = "#444444") +
  stat_cols_rule(
    aes(label = name), geom = "axis", color = "#888888", num = 8L,
    ref_elements = "active", fun.offset = function(x) minabspp(x, p = .1),
    label_dodge = 0.04, text.size = 2.5, text_dodge = .025
  ) +
  scale_shape_manual(values = c(16L, 17L, 15L, 18L)) +
  ggtitle(
    "LDA of Freestone glass measurements",
    "Symmetric biplot of contribution LDA"
  )

## Not run: 
# classical multidimensional scaling of road distances between European cities
euro_mds <- ordinate(eurodist, cmdscale_ord, k = 11)
# monoplot of city locations
euro_plot <- euro_mds %>%
  negate_ord("PCo2") %>%
  ggbiplot() +
  geom_cols_text(aes(label = name), size = 3)
print(euro_plot)
# biplot with minimal spanning tree based on plotting window distances
euro_plot +
  stat_cols_spantree(
    engine = "mlpack",
    alpha = .5, linetype = "dotted"
  )
# biplot with minimal spanning tree based on full-dimensional distances
euro_plot +
  stat_cols_spantree(
    ord_aes(euro_mds), engine = "mlpack",
    alpha = .5, linetype = "dotted"
  )

## End(Not run)

---

Confer inertia to factors of a 'tbl_ord' object

Description

Re-distribute inertia between rows and columns in an ordination.

Usage

recover_conference(x)

## Default S3 method:
recover_conference(x)

get_conference(x)

revert_conference(x)

confer_inertia(x, p)

Arguments

x	A tbl_ord.
p	Numeric vector of length 1 or 2. If length 1, the proportion of the inertia assigned to the cases, with the remainder 1 - p assigned to the variables. If length 2, the proportions of the inertia assigned to the cases and to the variables, respectively.

Details

The inertia of a singular value decomposition $X=UDV'$ consists in the squares of the singular values (the diagonal elements of $D$), and represents the variance, likened to the physical inertia, in the directions of the orthogonal singular vectors (the columns of $U$ or of $V$). Biplots superimpose the projections of the rows and the columns of $X$ onto these coordinate vectors, scaled by some proportion of the total inertia: $UD^p$ and $VD^q$. A biplot is balanced if $p+q=1$. Read Orlov (2013) for more on conferring inertia in PCA.

recover_conference(), like the other recoverers, is an S3 method that is exported for convenience but not intended to be used directly.

Note: In case the "inertia" attribute is a rectangular matrix, one may only be able to confer it entirely to the cases (p = 1) or entirely to the variables (p = 0).

Value

recover_conference() returns the (statically implemented) distribution of inertia between the rows and the columns as stored in the model. confer_inertia() returns a tbl_ord with a specified distribution of inertia but the wrapped model unchanged. get_conference() returns the distribution currently conferred.

References

Orlov K (2013) Answer to "Algebra of LDA. Fisher discrimination power of a variable and Linear Discriminant Analysis". CrossValidated, accessed 2019-07-26. https://stats.stackexchange.com/a/83114/68743

See Also

Other generic recoverers: augmentation, recoverers, supplementation

Examples

# illustrative ordination: correspendence analysis of hair & eye data
haireye_ca <- ordinate(
  as.data.frame(rowSums(HairEyeColor, dims = 2L)),
  cols = everything(), model = MASS::corresp
)
print(haireye_ca)

# check distribution of inertia
get_conference(haireye_ca)
# confer inertia to rows, then to columns
confer_inertia(haireye_ca, "rows")
confer_inertia(haireye_ca, "columns")
# confer inertia symmetrically
(haireye_ca <- confer_inertia(haireye_ca, "symmetric"))
# check redistributed inertia
get_conference(haireye_ca)
# restore default distribution of inertia
revert_conference(haireye_ca)

---

Convenience coordinate system for scaffolding axes

Description

2- (and 3-) dimensional biplots require that coordinates lie on the same scale but may additionally benefit from a square plotting window. While CoordRect provides control of coordinate and window aspect ratios, the convenience CoordScaffold system also fixes the coordinate aspect ratio at 1 and gives the user control only of the plotting window.

Usage

coord_scaffold(
  window_ratio = 1,
  xlim = NULL,
  ylim = NULL,
  expand = TRUE,
  clip = "on"
)

Arguments

window_ratio

aspect ratio of plotting window

Examples

# resize the plot to see that the specified aspect ratio is maintained
p <- ggplot(mtcars, aes(mpg, hp/10)) + geom_point()
p + coord_scaffold()
p + coord_scaffold(window_ratio = 2)

# prevent rescaling in response to `theme()` aspect ratio
p <- ggplot(mtcars, aes(mpg, hp/5)) + geom_point()
p + coord_equal() + theme(aspect.ratio = 1)
p + coord_scaffold() + theme(aspect.ratio = 1)

# NB: `theme(aspect.ratio = )` overrides `Coord*$aspect`:
p + coord_fixed(ratio = 1) + theme(aspect.ratio = 1)
p + coord_scaffold(window_ratio = 2) + theme(aspect.ratio = 1)

---

dplyr verbs for tbl_ord factors

Description

These functions adapt dplyr verbs to the factors of a tbl_ord.

The raw verbs are not defined for tbl_ords; instead, each verb has two analogues, corresponding to the two matrix factors. They each rely on a common workhorse function, which takes the composition of the dplyr verb with ⁠annotation_*⁠, applied to the factor, removes any variables corresponding to coordinates or already annotated, and only then assigns it as the new "*_annotation" attribute of .data (see annotation). Note that these functions are not generics and so cannot be extended to other classes.

Usage

pull_factor(.data, var = -1, .matrix)

pull_rows(.data, var = -1)

pull_cols(.data, var = -1)

rename_rows(.data, ...)

rename_cols(.data, ...)

select_rows(.data, ...)

select_cols(.data, ...)

mutate_rows(.data, ...)

mutate_cols(.data, ...)

transmute_rows(.data, ...)

transmute_cols(.data, ...)

cbind_rows(.data, ..., elements = "all")

cbind_cols(.data, ..., elements = "all")

left_join_rows(.data, ...)

left_join_cols(.data, ...)

Arguments

.data	An object of class 'tbl_ord'.
var	A variable specified as in dplyr::pull().
.matrix	A character string partially matched (lowercase) to several indicators for one or both matrices in a matrix decomposition used for ordination. The standard values are "rows", "cols", and "dims" (for both).
...	Comma-separated unquoted expressions as in, e.g., dplyr::select().
elements	Character vector; which elements of each factor for which to render graphical elements. One of "active" (the default) or any supplementary element type defined by the specific class methods (e.g. "score" for 'factanal', 'lda_ord', and 'cancord_ord' and "intraset" and "interset" for 'cancor_ord'), via partial matching.

Value

A tbl_ord; the wrapped model is unchanged.

Examples

# illustrative ordination: LDA of iris data
(iris_lda <- ordinate(iris, cols = 1:4, lda_ord, grouping = iris$Species))

# extract a coordinate or annotation
head(pull_rows(iris_lda, Species))
pull_cols(iris_lda, LD2)

# rename an annotation
rename_cols(iris_lda, species = name)

# select annotations
select_rows(iris_lda, species = name, .element)

# create, modify, and delete annotations
mutate_cols(iris_lda, vec.length = sqrt(LD1^2 + LD2^2))
transmute_cols(iris_lda, vec.length = sqrt(LD1^2 + LD2^2))

# bind data frames of annotations
iris_medians <-
  stats::aggregate(iris[, 1:4], median, by = iris[, 5, drop = FALSE])
# TODO: Requirement of `.elements` for matching is fragile.
iris_lda %>%
  # retain '.element' in order to match by `elements`
  select_rows(.element) %>%
  cbind_rows(iris_medians, elements = "active")
iris_lda %>%
  select_rows(name, Species) %>%
  left_join_rows(iris_medians, by = c("name" = "Species"))

---

Biplot key drawing functions

Description

These key drawing functions supplement those built into ggplot2 for producing legends suitable to biplots.

Usage

draw_key_line(data, params, size)

draw_key_crosslines(data, params, size)

draw_key_crosspoint(data, params, size)

Arguments

data	A single row data frame containing the scaled aesthetics to display in this key
params	A list of additional parameters supplied to the geom.
size	Width and height of key in mm.

Details

draw_key_line() is a horizontal counterpart to ggplot2::draw_key_vline(). draw_key_crosslines() superimposes these two keys, and draw_key_crosspoint() additionally superimposes an oversized ggplot2::draw_key_point().

Value

A grid grob.

See Also

ggplot2::draw_key for key glyphs installed with ggplot2.

Examples

# scaled PCA of Anderson iris data with ranges and confidence intervals
iris[, -5] %>%
  prcomp(scale = TRUE) %>%
  as_tbl_ord() %>%
  confer_inertia(1) %>%
  augment_ord() %>%
  mutate_rows(species = iris$Species) %>%
  ggbiplot(aes(color = species)) +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_rows_lineranges(fun.data = mean_sdl, linewidth = .75) +
  geom_rows_density_2d(contour = TRUE, alpha = .5) +
  geom_cols_vector(aes(label = name), color = "#444444", size = 3) +
  ggtitle(
    "Row-principal PCA biplot of Anderson iris data",
    "Ranges 2 sample standard deviations from centroids"
  )

---

Format a tbl_ord for printing

Description

These methods of base::format() and base::print() render a (usually more) tidy readout of a tbl_ord that is consistent across all original ordination classes.

Usage

## S3 method for class 'tbl_ord'
format(
  x,
  width = NULL,
  ...,
  n = NULL,
  max_extra_cols = NULL,
  max_footer_lines = NULL
)

## S3 method for class 'tbl_ord'
print(
  x,
  width = NULL,
  ...,
  n = NULL,
  max_extra_cols = NULL,
  max_footer_lines = NULL
)

Arguments

x	A tbl_ord.
width	Width of text output to generate. This defaults to NULL, which means use the width option.
...	Additional arguments.
n	Number(s) of rows to show from each matrix factor, handled as by tibble::format.tbl(). If length 1, will apply to both matrix factors. To pass NULL to only one factor, be sure to pass as a list, e.g. n = list(6, NULL).
max_extra_cols	Number of extra columns to print abbreviated information for, if the width is too small for the entire tibble. If NULL, the max_extra_cols option is used. The previously defined n_extra argument is soft-deprecated.
max_footer_lines	Maximum number of footer lines. If NULL, the max_footer_lines option is used.

Details

The format and print methods for class 'tbl_ord' are adapted from those for class 'tbl_df' and for class 'tbl_graph' from the tidygraph package.

Note: The format() function is tedius but cannot be easily modularized without invoking recoverers, annotation, and augmentation multiple times, thereby significantly reducing performance.

Value

The format() method returns a vector of strings that are more elegantly printed by the print() method, which itself returns the tbl_ord invisibly.

Examples

iris_pca <- ordinate(iris[1:4], prcomp)

# single value applies to both factors
print(iris_pca, n = 10)

# double values apply to factors in order
print(iris_pca, n = c(6, 2))

# use `list()` to pass `NULL` (for default) to only one factor
print(iris_pca, n = list(2, NULL))
print(iris_pca, n = list(NULL, 2))

iris_lda <- ordinate(iris[1:4], lda_ord, grouping = iris$Species)

# supplementary elements appear below active elements
print(iris_lda)

---

Render interpolation of new rows from columns (or vice-versa)

Description

geom_interpolation() renders a geometric construction that interpolates a new data matrix (row or column) element from its entries to its artificial coordinates.

Usage

geom_interpolation(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  new_data = NULL,
  type = c("centroid", "sequence"),
  arrow = default_arrow,
  ...,
  point.fill = NA,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

Arguments

mapping	Set of aesthetic mappings created by aes(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.
data	The data to be displayed in this layer. There are three options: If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot(). A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created. A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).
stat	The statistical transformation to use on the data for this layer. When using a ⁠geom_*()⁠ function to construct a layer, the stat argument can be used to override the default coupling between geoms and stats. The stat argument accepts the following: A Stat ggproto subclass, for example StatCount. A string naming the stat. To give the stat as a string, strip the function name of the stat_ prefix. For example, to use stat_count(), give the stat as "count". For more information and other ways to specify the stat, see the layer stat documentation.
position	A position adjustment to use on the data for this layer. This can be used in various ways, including to prevent overplotting and improving the display. The position argument accepts the following: The result of calling a position function, such as position_jitter(). This method allows for passing extra arguments to the position. A string naming the position adjustment. To give the position as a string, strip the function name of the position_ prefix. For example, to use position_jitter(), give the position as "jitter". For more information and other ways to specify the position, see the layer position documentation.
new_data	A list (best structured as a data.frame) of row (geom_cols_interpolation()) or column (geom_rows_interpolation()) values to interpolate.
type	Character value matched to "centroid" or "sequence"; the type of operations used to visualize interpolation.
arrow	Specification for arrows, as created by grid::arrow(), or else NULL for no arrows.
...	Additional arguments passed to ggplot2::layer().
point.fill	Default aesthetics for markers. Set to NULL to inherit from the data's aesthetics.
na.rm	Passed to ggplot2::layer().
show.legend	logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display. To include legend keys for all levels, even when no data exists, use TRUE. If NA, all levels are shown in legend, but unobserved levels are omitted.
inherit.aes	If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. annotation_borders().

Details

Interpolation answers the following question: Given a new data element that might have appeared as a row (respectively, column) in the singular-value-decomposed data matrix, where should we expect the marker for this element to appear in the biplot? The solution is the vector sum of the column (row) units weighted by their values in the new row (column). Gower, Gardner–Lubbe, & le Roux (2011) provide two visualizations of this calculation: a tail-to-head sequence of weighted units (type = "sequence"), and a centroid of the weighted units scaled by the number of units (type = "centroid").

WARNING: This layer is appropriate only with axes in standard coordinates (usually confer_inertia(p = "rows")) and interpolative calibration (ggbiplot(axis.type = "interpolative")).

Biplot layers

ggbiplot() uses ggplot2::fortify() internally to produce a single data frame with a .matrix column distinguishing the subjects ("rows") and variables ("cols"). The stat layers stat_rows() and stat_cols() simply filter the data frame to one of these two.

The geom layers ⁠geom_rows_*()⁠ and ⁠geom_cols_*()⁠ call the corresponding stat in order to render plot elements for the corresponding factor matrix. ⁠geom_dims_*()⁠ selects a default matrix based on common practice, e.g. points for rows and arrows for columns.

Aesthetics

geom_interpolation() requires the custom interpolate aesthetic, which tells the internals which columns of the new_data parameter contain the variables to be used for interpolation. Except in rare cases, new_data should contain the same rows or columns as the ordinated data and interpolate should be set to name (procured by augment_ord()). geom_interpolation() additionally understands the following aesthetics (required aesthetics are in bold):

• alpha

• colour

• linetype

• size

• fill

• shape

• stroke

• center, scale

• group

References

Gower JC, Gardner–Lubbe S, & le Roux NJ (2011) Understanding Biplots. Wiley, ISBN: 978-0-470-01255-0. https://www.wiley.com/go/biplots

See Also

Other geom layers: geom_origin()

Examples

iris[, -5] %>%
  prcomp(scale = TRUE) %>%
  as_tbl_ord() %>%
  print() -> iris_pca
iris_pca <- mutate_rows(iris_pca, species = iris$Species)
iris_pca <- augment_ord(iris_pca)

# sample of one of each species, with some missing measurements
new_data <- iris[c(42, 61, 110), seq(5, 1), drop = FALSE]
new_data[3L, "Sepal.Width"] <- NA
new_data[1L, "Petal.Length"] <- NA
print(new_data)

# centroid interpolation method
iris_pca %>%
  augment_ord() %>%
  mutate_rows(obs = dplyr::row_number()) %>%
  mutate_cols(measure = name) %>%
  ggbiplot() +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_origin(marker = "cross", alpha = .5) +
  geom_cols_interpolation(
    aes(center = center, scale = scale, interpolate = name), size = 3,
    new_data = new_data, type = "centroid", alpha = .5
  ) +
  geom_rows_text(aes(label = obs, color = species), alpha = .5, size = 3)

# missing an entire variable
new_data$Petal.Length <- NULL

# sequence interpolation method
iris_pca %>%
  augment_ord() %>%
  mutate_rows(obs = dplyr::row_number()) %>%
  mutate_cols(measure = name) %>%
  ggbiplot() +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_origin(marker = "circle", alpha = .5) +
  geom_cols_interpolation(
    aes(center = center, scale = scale, interpolate = name,
        linetype = measure),
    new_data = new_data, type = "sequence", alpha = .5
  ) +
  geom_rows_text(aes(label = obs, color = species), alpha = .5, size = 3)

---

Marker or unit circle at the origin

Description

geom_origin() renders a symbol, either a set of crosshairs or a circle, at the origin. geom_unit_circle() renders the unit circle, centered at the origin with radius 1.

Usage

geom_origin(
  mapping = NULL,
  data = NULL,
  marker = "crosshairs",
  radius = unit(0.04, "snpc"),
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = FALSE
)

geom_unit_circle(
  mapping = NULL,
  data = NULL,
  segments = 60,
  scale.factor = 1,
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = FALSE
)

Arguments

mapping	Set of aesthetic mappings created by aes(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.
data	The data to be displayed in this layer. There are three options: If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot(). A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created. A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).
marker	The symbol to be drawn at the origin; matched to "crosshairs" or "circle".
radius	A grid::unit() object that sets the radius of the crosshairs or of the circle.
...	Additional arguments passed to ggplot2::layer().
na.rm	Passed to ggplot2::layer().
show.legend	logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display. To include legend keys for all levels, even when no data exists, use TRUE. If NA, all levels are shown in legend, but unobserved levels are omitted.
inherit.aes	If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. annotation_borders().
segments	The number of segments to be used in drawing the circle.
scale.factor	The circle radius; should remain at its default value 1 or passed the same value as ggbiplot(). (This is an imperfect fix that may be changed in a future version.)

Value

A ggproto layer.

Biplot layers

ggbiplot() uses ggplot2::fortify() internally to produce a single data frame with a .matrix column distinguishing the subjects ("rows") and variables ("cols"). The stat layers stat_rows() and stat_cols() simply filter the data frame to one of these two.

The geom layers ⁠geom_rows_*()⁠ and ⁠geom_cols_*()⁠ call the corresponding stat in order to render plot elements for the corresponding factor matrix. ⁠geom_dims_*()⁠ selects a default matrix based on common practice, e.g. points for rows and arrows for columns.

Aesthetics

geom_origin() accepts no aesthetics. geom_unit_circle() understands the following aesthetics (none required):

• linetype

• linewidth

• colour

• alpha

See Also

Other geom layers: geom_interpolation()

Examples

ggplot() +
  theme_void() +
  geom_origin() +
  geom_point(data = seals, aes(delta_long, delta_lat), alpha = .25)
# center each group separately
iris %>%
  split(~ Species) %>%
  lapply(subset, select = -c(Species)) %>%
  lapply(scale, center = TRUE, scale = FALSE) %>%
  lapply(as.data.frame) %>%
  unsplit(iris$Species) %>%
  transform(Species = iris$Species) ->
  iris_ctr
ggplot(iris_ctr, aes(Petal.Width, Petal.Length)) +
  coord_equal() +
  facet_wrap(vars(Species)) +
  geom_unit_circle() +
  geom_point()
# scale group mean differences uniformly
iris_ctr %>%
  subset(select = -c(Species)) %>%
  scale(center = FALSE, scale = TRUE) %>%
  transform(Species = iris$Species) %>%
  ggplot(aes(Petal.Width, Petal.Length)) +
  coord_equal() +
  facet_wrap(vars(Species)) +
  geom_unit_circle() +
  geom_point()

---

Biplots following the grammar of graphics

Description

Build a biplot visualization from ordination data wrapped as a tbl_ord object.

Usage

ggbiplot(
  ordination = NULL,
  mapping = aes(x = 1, y = 2),
  axis.type = "interpolative",
  xlim = NULL,
  ylim = NULL,
  expand = TRUE,
  clip = "on",
  axis.percents = TRUE,
  sec.axes = NULL,
  scale.factor = "inertia",
  scale_rows = NULL,
  scale_cols = NULL,
  ...
)

ord_aes(ordination, ...)

Arguments

ordination	A tbl_ord.
mapping	List of default aesthetic mappings to use for the biplot. The default assigns the first two coordinates to the aesthetics x and y. Other assignments must be supplied in each layer added to the plot.
axis.type	Character, partially matched; whether to build an "interpolative" (the default) or a "predictive" biplot. The latter requires that x and y are mapped to shared coordinates, that no other shared coordinates are mapped to, and inertia is conferred entirely onto one matrix factor. NB: This option is only implemented for linear techniques (ED, SVD, & PCA).
xlim, ylim	Limits for the x and y axes.
expand	If TRUE, the default, adds a small expansion factor to the limits to ensure that data and axes don't overlap. If FALSE, limits are taken exactly from the data or xlim/ylim. Giving a logical vector will separately control the expansion for the four directions (top, left, bottom and right). The expand argument will be recycled to length 4 if necessary. Alternatively, can be a named logical vector to control a single direction, e.g. expand = c(bottom = FALSE).
clip	Should drawing be clipped to the extent of the plot panel? A setting of "on" (the default) means yes, and a setting of "off" means no. In most cases, the default of "on" should not be changed, as setting clip = "off" can cause unexpected results. It allows drawing of data points anywhere on the plot, including in the plot margins. If limits are set via xlim and ylim and some data points fall outside those limits, then those data points may show up in places such as the axes, the legend, the plot title, or the plot margins.
axis.percents	Whether to concatenate default axis labels with inertia percentages.
sec.axes	Matrix factor character to specify a secondary set of axes.
scale.factor	Either a numeric value, used to scale the secondary axes against the primary axes, or the name of a harmonizing function (currently "range" or "inertia"); ignored if sec.axes is not specified.
scale_rows, scale_cols	Either the character name of a numeric variable in get_*(ordination) or a numeric vector of length nrow(get_*(ordination)), used to scale the coordinates of the matrix factors.
...	Additional arguments passed to ggplot2::fortify(); see fortify.tbl_ord().

Details

ggbiplot() produces a ggplot object from a tbl_ord object ordination. The baseline object is the default unadorned "ggplot"-class object p with the following differences from what ggplot2::ggplot() returns:

• p$mapping is augmented with .matrix = .matrix, which expects either .matrix = "rows" or .matrix = "cols" from the biplot.

• p$coordinates is defaulted to ggplot2::coord_equal() in order to faithfully render the geometry of an ordination. The optional parameters xlim, ylim, expand, and clip are passed to coord_equal() and default to its ggplot2 defaults.

• When x or y are mapped to coordinates of ordination, and if axis.percents is TRUE, p$labels$x or p$labels$y are defaulted to the coordinate names concatenated with the percentages of inertia captured by the coordinates.

• p is assigned the class "ggbiplot" in addition to "ggplot". This serves no functional purpose currently.

Furthermore, the user may feed single integer values to the x and y aesthetics, which will be interpreted as the corresponding coordinates in the ordination. Currently only 2-dimensional biplots are supported, so both x and y must take coordinate values.

ord_aes() is a convenience function that generates a full-rank set of coordinate aesthetics ..coord1, ..coord2, etc. mapped to the shared coordinates of the ordination object, along with any additional aesthetics that are processed internally by ggplot2::aes().

The axis.type parameter controls whether the biplot is interpolative or predictive, though predictive biplots are still experimental and limited to linear methods like PCA. Gower & Hand (1996) and Gower, Gardner–Lubbe, & le Roux (2011) thoroughly explain the construction and interpretation of predictive biplots.

Value

A ggplot object.

Biplot layers

ggbiplot() uses ggplot2::fortify() internally to produce a single data frame with a .matrix column distinguishing the subjects ("rows") and variables ("cols"). The stat layers stat_rows() and stat_cols() simply filter the data frame to one of these two.

The geom layers ⁠geom_rows_*()⁠ and ⁠geom_cols_*()⁠ call the corresponding stat in order to render plot elements for the corresponding factor matrix. ⁠geom_dims_*()⁠ selects a default matrix based on common practice, e.g. points for rows and arrows for columns.

References

Gower JC & Hand DJ (1996) Biplots. Chapman & Hall, ISBN: 0-412-71630-5.

Gower JC, Gardner–Lubbe S, & le Roux NJ (2011) Understanding Biplots. Wiley, ISBN: 978-0-470-01255-0. https://www.wiley.com/go/biplots

See Also

ggplot2::ggplot2(), on which ggbiplot() is built

Examples

# compute PCA of Anderson iris measurements
iris[, -5] %>%
  princomp(cor = TRUE) %>%
  as_tbl_ord() %>%
  confer_inertia(1) %>%
  mutate_rows(species = iris$Species) %>%
  mutate_cols(measure = gsub("\\.", " ", tolower(names(iris)[-5]))) %>%
  print() -> iris_pca

# row-principal biplot with range-harmonized secondary axis
iris_pca %>%
  ggbiplot(aes(color = species), sec.axes = "cols", scale.factor = "range") +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_rows_point() +
  geom_cols_vector(aes(label = measure), color = "#444444") +
  ggtitle(
    "Row-principal PCA biplot of Anderson iris measurements",
    "Variable loadings scaled to secondary axes"
  ) +
  expand_limits(y = c(-1, 3.5))

# row-principal biplot with manually rescaled secondary axis
iris_pca %>%
  ggbiplot(aes(color = species), sec.axes = "cols", scale.factor = 2) +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_rows_point() +
  geom_cols_vector(aes(label = measure), color = "#444444") +
  ggtitle(
    "Row-principal PCA biplot of Anderson iris measurements",
    "Variable loadings scaled to secondary axes"
  ) +
  expand_limits(y = c(-1, 3.5))
# Performance measures can be regressed on the artificial coordinates of
# ordinated vehicle specs. Because the ordination of specs ignores performance,
# these coordinates will probably not be highly predictive. The gradient of each
# performance measure along the artificial axes is visualized by projecting the
# regression coefficients onto the ordination biplot.

# scaled principal components analysis of vehicle specs
mtcars_specs_pca <- ordinate(
  mtcars, cols = c(cyl, disp, hp, drat, wt, vs, carb),
  model = ~ princomp(., cor = TRUE)
)
# data frame of vehicle performance measures
mtcars %>%
  subset(select = c(mpg, qsec)) %>%
  as.matrix() %>%
  print() -> mtcars_perf
# regress performance measures on principal components
lm(mtcars_perf ~ get_rows(mtcars_specs_pca)) %>%
  as_tbl_ord() %>%
  augment_ord() %>%
  print() -> mtcars_pca_lm
# regression biplot
ggbiplot(mtcars_specs_pca, aes(label = name),
         sec.axes = "rows", scale.factor = .5) +
  theme_minimal() +
  geom_rows_text(size = 3) +
  geom_cols_vector(data = mtcars_pca_lm) +
  expand_limits(x = c(-2.5, 2))

# multidimensional scaling based on a scaled cosine distance of vehicle specs
cosine_dist <- function(x) {
  x <- as.matrix(x)
  num <- x %*% t(x)
  denom_rt <- as.matrix(rowSums(x^2))
  denom <- sqrt(denom_rt %*% t(denom_rt))
  as.dist(1 - num / denom)
}
mtcars %>%
  subset(select = c(cyl, disp, hp, drat, wt, vs, carb)) %>%
  scale() %>%
  cosine_dist() %>%
  cmdscale() %>%
  as.data.frame() ->
  mtcars_specs_cmds
# names must be consistent with `cmdscale_ord()` below
names(mtcars_specs_cmds) <- c("PCo1", "PCo2")
# regress performance measures on principal coordinates
lm(mtcars_perf ~ as.matrix(mtcars_specs_cmds)) %>%
  as_tbl_ord() %>%
  augment_ord() %>%
  print() -> mtcars_cmds_lm
# multidimensional scaling using `cmdscale_ord()`
mtcars %>%
  subset(select = c(cyl, disp, hp, drat, wt, vs, carb)) %>%
  scale() %>%
  cosine_dist() %>%
  cmdscale_ord() %>%
  as_tbl_ord() %>%
  augment_ord() %>%
  print() -> mtcars_specs_cmds_ord
# regression biplot
ggbiplot(mtcars_specs_cmds_ord, aes(label = name),
         sec.axes = "rows", scale.factor = 3) +
  theme_minimal() +
  geom_rows_text(size = 3) +
  geom_cols_vector(data = mtcars_cmds_lm) +
  expand_limits(x = c(-2.25, 1.25), y = c(-2, 1.5))
# PCA of iris data
iris_pca <- ordinate(iris, cols = 1:4, prcomp, scale = TRUE)

# row-principal predictive biplot
iris_pca %>%
  ggbiplot(axis.type = "predictive") +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_cols_axis(aes(label = name, center = center, scale = scale)) +
  geom_rows_point(aes(color = Species), alpha = .5) +
  ggtitle("Predictive biplot of Anderson iris measurements")

# with two calibrated axes
iris_pca %>%
  ggbiplot(axis.type = "predictive") +
  theme_bw() +
  scale_color_brewer(type = "qual", palette = 2) +
  geom_origin() +
  stat_cols_rule(
    subset = c(2, 4), fontface = "bold", text.fontface = "plain",
    aes(label = name, center = center, scale = scale)
  ) +
  geom_rows_point(aes(color = Species), alpha = .5) +
  expand_limits(x = c(-5, 5), y = c(-5, 5)) +
  ggtitle("Predictive biplot of Anderson iris measurements")

---

Glass composition data

Description

Sites, types, and compositions of glass samples from archaeological sites in Israel.

Usage

data(glass)

Format

A tibble with 68 cases and 16 variables:

Site

site at which sample was found

Anal

analysis identifier

Context

furnace identifier

Form

type of sample

⁠SiO2, TiO2, Al2O3, FeO, MnO, MgO, CaO, Na2O, K2O, P2O5, Cl, SO3⁠

normalized weight percent oxide of each component

Details

Chunks of unformed glass from several furnaces found at the primary Byzantine-era site of Bet Eli'ezer, along with samples from other sites with weaker evidence of glass-making (Apollonia and Dor) and and from an Islamic-era site (Banias), were analyzed using X-ray spectrometry to determine their major components.

Baxter & Freestone (2006) used these data to illustrate log-ratio analysis.

Source

Freestone &al (2000), Table 2.

References

Freestone IC, Gorin-Rosen Y, & Hughes MJ (2000) "Primary glass from Israel and the production of glass in Late Antiquity and the early Islamic period". La route du verre: Ateliers primaires et secondaires du second millénaire av. J.-C. au Moyen Âge: 65–83. https://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=1158762

Baxter MJ & Freestone IC (2006) "Log-Ratio Compositional Data Analysis in Archaeometry". Archaeometry, 48(3): 511–531. doi:10.1111/j.1475-4754.2006.00270.x

Examples

# subset glass data to one site and major components
head(glass)
glass_main <- subset(
  glass,
  Site == "Bet Eli'ezer",
  select = c("SiO2", "Na2O", "CaO", "Al2O3", "MgO", "K2O")
)
# format as a data frame with row names
glass_main <- as.data.frame(glass_main)
rownames(glass_main) <- subset(glass, Site == "Bet Eli'ezer")$Anal

# perform log-ratio analysis
glass_lra <- lra(glass_main, compositional = TRUE, weighted = FALSE)
# inspect LRA row and column coordinates
head(glass_lra$row.coords)
glass_lra$column.coords
# inspect singular values of LRA
glass_lra$sv

# plot samples and measurements in a biplot
biplot(
  x = glass_lra$row.coords %*% diag(glass_lra$sv),
  y = glass_lra$column.coords,
  xlab = "Sample (principal coord.)", ylab = ""
)
mtext("Component (standard coord.)", side = 4L, line = 3L)

---

Measures of goodness of fit of ordination models

Description

Compute the quality, adequacy, and predictivity of a 'tbl_ord' object from the retrieved matrix factors.

Usage

ord_quality(x, rank = NULL)

ord_adequacy(x, .matrix, rank = NULL)

ord_predictivity(x, .matrix, rank = NULL)

Arguments

x	A 'tbl_ord' object.
rank	The maximum rank for which to compute statistics; the default, NULL computes statistics up to the rank of the model.
.matrix	A character string partially matched (lowercase) to several indicators for one or both matrices in a matrix decomposition used for ordination. The standard values are "rows", "cols", and "dims" (for both).

Details

Gower, Gardner–Lubbe, & le Roux (2011) detail several measures of fit for biplots, most prominently

• the quality of the $r$-dimensional biplot, measured as the proportion of variance in the plot, calculated as the quotient of the traces of $\Lambda_r = {D_r}^2$ and of $\Lambda = D^2$.

• the adequacy of the representation of the $j$-th row (respectively, column) in the $r$-dimensional biplot, calculated as the $j$-th diagonal element of $U_r\ {U_r}^\top$ (respectively, $V_r\ {V_r}^\top$), understood as the fidelity of the projections of the standard coordinates.

• the predictivity of the $j$-th row (respectively, column) in the $r$-dimensional biplot, measured as the quotient of the $j$-th diagonal elements of $U_r\ \Lambda_r\ {U_r}^\top$ and of $U\ \Lambda\ U^\top$ (respectively, of $V_r\ \Lambda_r\ {V_r}^\top$ and of $V\ \Lambda\ V^\top$), understood as the fidelity of the projections of the principal coordinates.

These can be calculated directly from any SVD or EVD and interpreted for any technique based on them. In some cases they may also be calculated for supplementary elements.

Value

A vector, matrix, or list of matrices of numeric goodness-of-fit statistics. If no items are found, a matrix will have zero rows.

References

Gower JC, Gardner–Lubbe S, & le Roux NJ (2011) Understanding Biplots. Wiley, ISBN: 978-0-470-01255-0. https://www.wiley.com/go/biplots

Examples

# log-ratio analysis of Apollonia glass composition data
glass_apollonia <- subset(
  glass,
  Site == "Apollonia",
  select = c("SiO2", "Na2O", "CaO", "Al2O3", "MgO", "K2O")
)
glass_lra <- lra(glass_apollonia, weighted = FALSE)

# quality (cumulative proportion of inertia included)
ord_quality(glass_lra)
# adequacy (fidelity of projections to standard coordinates)
ord_adequacy(glass_lra, "rows", rank = 3)
ord_adequacy(glass_lra, "cols", rank = 3)
# predictivity (fidelity of projections to principal coordinates)
ord_predictivity(glass_lra, "dims", rank = 2)

# principal components analysis of setosa iris data
iris_pca <- princomp(iris3[, , "Setosa"])

# quality (cumulative proportion of inertia included)
ord_quality(iris_pca)
# adequacy (fidelity of projections to standard coordinates)
ord_adequacy(iris_pca, "both")
# predictivity (fidelity of projections to principal coordinates)
ord_predictivity(iris_pca, "f")
ord_predictivity(iris_pca, "g")

---