Package 'ggordiplots'

Vegan envfit plot

Description

Fits environmental parameters to an ordination plot of sites and plots them as arrows or centroid labels.

Usage

gg_envfit(
  ord,
  env,
  groups = NA,
  scaling = 1,
  choices = c(1, 2),
  perm = 999,
  alpha = 0.05,
  angle = 20,
  len = 0.5,
  unit = "cm",
  arrow.col = "red",
  pt.size = 3,
  show_factors = FALSE,
  plot = TRUE
)

Arguments

ord	An ordination object.
env	A data frame of environmental parameters.
groups	A vector of groups.
scaling	Scaling value for plot.
choices	Axes to plot.
perm	Number of permutations.
alpha	Maximum alpha value to be included in plot.
angle	Angle of arrow tips.
len	Arrow tip length.
unit	Unit for length ("cm", "in")
arrow.col	Arrow color.
pt.size	Symbol size.
show_factors	A logical for including factors on the plot; defaults to FALSE.
plot	A logical for plotting; defaults to TRUE.

Details

Vegan's envfit function fits environmental variables to an ordination. If the variable is numeric, an arrow is fitted to the ordination plot indicating the direction in which that variable increases. If the variable is a factor (or character vector), vegan's envfit plotting function treats levels of the factor as groups and adds labels for the factor's level to the ordination plot at each group's centroid center. This behavior is now enabled in gg_envfit() if show_factors is set to TRUE.

Value

Silently returns the plot and data frames used for the plotting if the fit of any variable is significant at alpha. Otherwise returns a message that no variable is significant.

Note

In order for the arrow tips to be labeled with the names of the variables, they must be supplied as a matrix or data frame. If a single variable is supplied as a vector, the arrow tip will be labeled with "1". A way-around is to convert the vector to a data frame with the column named for the variable.

Examples

data("varespec")
data("varechem")
vare.dist <- vegdist(varespec)
vare.mds <- monoMDS(vare.dist)
gg_envfit(ord=vare.mds, env=varechem)

data("dune")
data("dune.env")
dune.dist <- vegdist(dune)
dune.mds <- monoMDS(dune.dist)
# A1 supplied as a vector
gg_envfit(dune.mds, env=dune.env$A1, groups=dune.env$Management)
# A1 supplied as a data frame
A1 <- as.data.frame(dune.env$A1)
colnames(A1) <- "A1"
gg_envfit(dune.mds, env=A1, groups=dune.env$Management)

---

Ordination Bubble Plot

Description

Makes a simple ordination plot of site with the symbol size scaled to an environmental variable. Result is similar to that of BiodiversityR's ordibubble function.

Usage

gg_ordibubble(
  ord,
  env.var,
  groups = NA,
  var.label = "Level",
  choices = c(1, 2),
  plot = TRUE
)

Arguments

ord	An ordination object
env.var	An environmental variable.
groups	A vector of groups (optional).
var.label	Label for the legend; default is "Level."
choices	Axes to be plotted.
plot	A logical for plotting; defaults to TRUE.

Value

Silently returns the plot and data frames used for the plotting.

Examples

data(dune)
data(dune.env)
dune.bray <- vegdist(dune, method = "bray")
ord <- cmdscale(dune.bray, k=(nrow(dune)-1), eig=TRUE, add=TRUE)
gg_ordibubble(ord, env.var=dune.env$A1, var.label="A1")

---

Add Dendrogram to Ordination Plot

Description

Modeled after the ordicluster function in vegan, this function overlays an ordination object with a cluster dendogram. Functionality has been added to include treatment groups.

Usage

gg_ordicluster(
  ord,
  cluster,
  treatments = NA,
  choices = c(1, 2),
  prune = 0,
  col = 1,
  pt.size = 3,
  plot = TRUE
)

Arguments

ord	An ordination object.
cluster	A cluster object from 'hclust' based on the same distance as 'ord.'
treatments	A vector assigning treatments to samples.
choices	Ordination axes to be plotted.
prune	Number of upper level hierarchies removed from the dendrogram. If prune > 0, dendrogram will be disconnected.
col	A vector of cluster group memberships. Used to assign colors to line segments for each cluster group.
pt.size	Symbol size.
plot	A logical; defaults to TRUE.

Details

'treatments' should be a vector of class factor and length equal to the number of samples included in the ordination and cluster; integers are not coerced into factors.

Value

Invisibly returns a list of the data frames used to make the plot (df_ord, df_segments) and the plot itself (plot).

Author(s)

Jari Oksanen, John Quensen

Examples

data(dune)
data(dune.env)
dune.bray <- vegdist(dune, method="bray")
ord <- metaMDS(dune, k=3)
cl <- hclust(dune.bray, method="complete")
gg_ordicluster(ord, cluster=cl, treatments=dune.env$Management, prune=3, col=cutree(cl, 4))

---

Plot with Ellipses, Hulls, Spiders

Description

gg_ordiplot uses ggplot2 to make an ordination plot with group ellipses by default, and optionally hulls and/or spiders. It is patterned after vegan's functions ordiellipse, ordihull, and ordispider and accepts similar parameters.

Usage

gg_ordiplot(
  ord,
  groups,
  scaling = 1,
  choices = c(1, 2),
  kind = c("sd", "se", "ehull"),
  conf = NULL,
  show.groups = "all",
  ellipse = TRUE,
  label = FALSE,
  hull = FALSE,
  spiders = FALSE,
  pt.size = 3,
  plot = TRUE
)

Arguments

ord	An ordination object.
groups	A vector of groups.
scaling	Scaling for ordination plot.
choices	Axes to be plotted.
kind	Type of ellipses to show ("se", sd", "ehull").
conf	Confidence value for ellipses if "se" or "sd."
show.groups	Subset of groups to plot.
ellipse	A logical for plotting ellipses; defaults to TRUE.
label	A logical for labeling group centroids.
hull	A logical for plotting group hulls.
spiders	A logical for plotting group spiders.
pt.size	Symbol size.
plot	A logical for plotting; defaults to TRUE.

Value

Silently returns the plot and data frames used for the plotting.

Examples

data("dune")
data("dune.env")
dune.hel <- decostand(dune, method = "hellinger")
ord <- rda(dune.hel)
gg_ordiplot(ord, groups = dune.env$Management)

---

Ordisurf with ggplot2

Description

Fits a surface (contour) plot of an environmental variable to an ordination plot.

Usage

gg_ordisurf(
  ord,
  env.var,
  groups = NA,
  choices = c(1, 2),
  var.label = "Level",
  binwidth,
  pt.size = 3,
  family = "gaussian",
  plot = TRUE
)

Arguments

ord	An ordination object.
env.var	Environmental variable to fit to plot.
groups	A vector of groups (optional).
choices	Axes to plot.
var.label	Label for the contour legend; default is "Level."
binwidth	Controls the number of contours in the plot.
pt.size	Symbol size.
family	Error distribution and link function used by the gam function to fit the contours.
plot	A logical for plotting; defaults to TRUE.

Details

By default, 'binwidth' is calculated as the difference between minimum and maximum values of the variable divided by 15.

The colors for the points are mapped to fill; if you want to rename the legend for the groups (points), use labs(fill="New name").

See the help for stats::family for possible values for family.

Value

Silently returns the plot and data frames used for the plotting.

Note

Code for extracting plot data from the ordisurf result was taken from a blog by Oliviea Rata Burge.

Author(s)

Olivia Rata Burge, John Quensen

References

https://oliviarata.wordpress.com/2014/07/17/ordinations-in-ggplot2-v2-ordisurf/'

Examples

data(varespec)
data(varechem)
vare.dist <- vegdist(varespec)
vare.mds <- monoMDS(vare.dist)
gg_ordisurf(vare.mds, env.var = varechem$Baresoil, var.label="Bare Soil")

---

ggordiplots: Make ggplots with ordiplot-type features.

Description

The vegan and BiodiversityR packages include several functions for adding features to ordination plots: ordiarrows, ordibubbles, ordiellipse, ordihull, ordispider, ordisurf, ordicluster. This package adds these same features to ordination plots made with ggplot2.

Functions

gg_enfit Fits vectors representing environmental variables to ordination plots.

gg_ordibubble Sizes site symbols in proportion to environmental variable.

gg_ordicluster Overlays cluster diagram on ordination plot.

gg_ordiplot Ordination plot with options for ellipses, hulls, and spiders distinguishing treatment groups.

gg_ordisurf Ordination plot with surface contours for environmental variable.

---

Make Ordination Axis Labels

Description

Makes ordination axis labels that include, if appropriate, the % total variance explained by each axis.

Usage

ord_labels(ord)

Arguments

ord	A vegan ordination object.

Details

If there are no eigenvalues in ord, or if any eigenvalues are less than 0, each element of the vector returned has the form "DIMn" where n is the axis number. Otherwise, each element of the vector returned has the form "AxisN xx.x%" where "Axis" is taken from the vector of eigenvalues in ord if they are named or simply "DIM" if they are not, N is the number of the axis, and xx.x is the % of total variance explained by the axis.

Value

A character vector, each element of which can be used to label the corresponding axis of an ordination plot.

Examples

data("dune")
data("dune.env")
dune_hel <- decostand(dune, method = "hellinger")
ord <- rda(dune_hel)
axis_labels <- ord_labels(ord)
axis_labels[c(1,2)]

---

Scale Arrows to Plot

Description

Scales envfit arrows to fit within 75

Usage

scale_arrow(arrows, data, at = c(0, 0), fill = 0.75)

Arguments

arrows	A two column data frame of coordinates from envfit result.
data	A two column data frame of coordinates for ordination plot.
at	coordinates of origin (0, 0)
fill	proportion of plot area to fill with maximum arrow length

Value

Silently returns a data frame of scaled coordinates for adding arrows to ordination plot.

Author(s)

Jari Oksanen with modifications by Gavin Simpson and John Quensen

Examples

data("varespec")
data("varechem")
vare_dist <- vegdist(varespec)
vare_mds <- monoMDS(vare_dist)
plt1 <- gg_envfit(ord=vare_mds, env=varechem, plot = FALSE)
mult <- scale_arrow(plt1$df_arrows, plt1$df_ord[ , c("x", "y")])
mult

---