Given a flash object, produces up to two figures: one showing
the proportion of variance explained per factor/loadings pair, and one that
plots posterior means for either factors or loadings (depending on the
argument to parameter pm_which).
# S3 method for flash
plot(
x,
include_scree = TRUE,
include_pm = TRUE,
order_by_pve = TRUE,
kset = NULL,
pm_which = c("factors", "loadings"),
pm_subset = NULL,
pm_groups = NULL,
pm_colors = NULL,
...
)If arguments include_scree and include_pm specify that
only one figure be produced, then plot.flash() returns a
ggplot2 object. If both figures are to be produced, then
plot.flash() prints both plots but does not return a value.
An object inheriting from class flash.
Whether to include a figure ("scree plot") showing the proportion of variance explained by each factor/loadings pair.
Whether to include a figure showing the posterior means for
either loadings \(L\) or factors \(F\) (depending on the argument to
parameter pm_which). One plot panel is produced for each
factor/loadings pair \(k\). If argument pm_groups
is left unspecified, then bar plots will be produced, with each bar
corresponding to a single value \(\ell_{ik}\) or \(f_{jk}\).
Otherwise, overlapping histograms will be
produced, with each histogram corresponding to one of the groups
specified by pm_groups.
If TRUE, then the factor/loadings pairs will be
re-ordered according to proportion of variance explained (from
highest to lowest).
A vector of integers specifying the factor/loadings pairs to be
plotted. If kset = NULL, then all will be plotted.
Whether to plot loadings \(L\) or factors \(F\) in the
plots of posterior means.
This parameter is ignored when include_pm = FALSE.
A vector of row indices \(i\) or column indices
\(j\) (depending on the argument to pm_which)
specifying which values \(\ell_{i \cdot}\) or \(f_{j \cdot}\) are
to be shown in the plots of posterior means. If the dataset has row or
column names, then names rather than indices may be specified. If
pm_subset = NULL, then all values will be plotted.
This parameter is ignored when include_pm = FALSE.
A vector specifying the group to which each row of the data
\(y_{i \cdot}\) or column \(y_{\cdot j}\) belongs
(groups may be numeric indices or strings). If pm_groups = NULL,
then a bar plot of the ungrouped data is produced (see include_pm
above). Otherwise, a group must be provided for each plotted row \(i\) or
column \(j\), so that
the length of pm_groups is exactly equal to the number of rows or
columns in the full dataset or, if pm_subset is specified, in the
subsetted dataset. When pm_groups is not NULL, a set of
overlapping histograms is produced for each factor/loadings pair, with
one histogram per group (again see include_pm).
This parameter is ignored when include_pm = FALSE.
A vector specifying a color for each bar (if
pm_groups = NULL) or histogram (if pm_groups is not
NULL). Passed directly to parameter values in ggplot2
function scale_color_manual.
This parameter is ignored when include_pm = FALSE.
Additional parameters are ignored.