Convenience stats for row and column matrix factors

Source: R/zzz-biplot-stats.r

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.

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.center = NULL,
  fun.min = NULL,
  fun.max = 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.center = NULL,
  fun.min = NULL,
  fun.max = 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.center = 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.center = 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_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_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
)

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_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,
  ...
)

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.

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. 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, fun.center, fun.min, fun.max

Functions treated as in ggplot2::stat_summary(), with fun.center, fun.min, and fun.max behaving as fun.y, fun.ymin, and fun.ymax.

fun.args

Arguments passed to the fun.*.

origin

Logical; whether to include the origin with the transformed data. Defaults to FALSE.

referent

The reference data set; see Details.

ref_elements, ref_subset

Analogues of elements and subset applied to referent.

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.

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".

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_referent(), stat_rows()

Examples

# compute row-principal components of scaled iris measurements
iris[, -5] %>%
  prcomp(scale = TRUE) %>%
  as_tbl_ord() %>%
  mutate_rows(species = iris$Species) %>%
  print() -> iris_pca
#> # A tbl_ord of class 'prcomp': (150 x 4) x (4 x 4)'
#> # 4 coordinates: PC1, PC2, ..., PC4
#> # 
#> # Rows (principal): [ 150 x 4 | 1 ]
#>     PC1    PC2     PC3 ... |   species
#>                            |   <fct>  
#> 1 -2.26 -0.478  0.127      | 1 setosa 
#> 2 -2.07  0.672  0.234  ... | 2 setosa 
#> 3 -2.36  0.341 -0.0441     | 3 setosa 
#> 4 -2.29  0.595 -0.0910     | 4 setosa 
#> 5 -2.38 -0.645 -0.0157     | 5 setosa 
#> # ℹ 145 more rows
#> # 
#> # Columns (standard): [ 4 x 4 | 0 ]
#>      PC1     PC2    PC3 ... | 
#>                             | 
#> 1  0.521 -0.377   0.720     | 
#> 2 -0.269 -0.923  -0.244 ... | 
#> 3  0.580 -0.0245 -0.142     | 
#> 4  0.565 -0.0669 -0.634     | 

# 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"
  )