Support for counts in density distributions

[DillonHammill]

To further improve the statistical capabilities of CytoExploreR, I will be adding support for counts in 1-D plots (on y axis). I will be tackling this today, but I am just putting some notes here:

Adding support for counts

• It should be relatively straightforward to add support for counts but there will some things to consider. It is quite easy to convert the kernel density estimates to counts, but due to the smoothing nature of density this will only give an approximation of the counts. One way to improve the resolution would be to reduce the bin width and set adjust = 0, this will provide more accurate counts but will introduce some noise. This may however result in inconsistencies with the smoothing parameters of the percent and density options. I will play around with this to see what works best.
• It is important to retain the range information with the density object for downstream plotting, currently this information is assign to the names() but might be better attched to attributes().

Changes to cyto_plot()

• All arguments prefixed with density_ will be updated to be prefixed with hist_ instead, as it no longer makes sense to keep the density_ prefix when counts are supported as well.
• Add new hist_stat argument to control what is displayed on the y axis, options include count, density or percent. The percent option will replace the current density_modal implementation.
• Drop density_modal argument as it will no longer be required as outlined above.
• Add new hist_bin_width argument to allow control over bin width, this just ensures that all histograms within the plot use the same bin width. Currently, the bin width is calculated on a per plot basis, so multiplot methods do not use the same bin width in each plot. I will add a new statistical function to compute the bin widths so that a consistent bin width can be used across plots as well.
• Add a message to indicate the chosen bin width. Should users wish to change the default bin width, it would be handy if there was a message to indicate what the current bin width is - similar to the approach used in ggridges.
• Revisit the stacking to decide on a consistent way of stacking these distributions, it is easy with percent as all layers have the same height but it gets more complicated for density and count where each layer can have vastly different heights. I think the current implementation uses the mean height across layers when determining the degree of stacking. I will need to test this once these changes have been made and decide whether it needs changing or not.
• Possibly add a hist_quantile argument to add vertical lines to mark quantiles on density distributions, this will be particularly useful for stat = "median".

[DillonHammill]

Significant improvements have been made to the plotting of histograms within CytoExploreR version 2.0.0.

I will summarise some of the key changes below:

• all density_ arguments have been renamed to hist_
• bandwidths are now computed based on the scale (256 bins to match flowJo)
• counts are now supported by setting hist_stat = "count" (options include count, percent or density)
• behaviour of hist_smooth has now changed to only accept values greater than 1 (too much or too little smoothing affects count estimates)
• users can changes the number bins required to compute bandwidths through hist_bins but this is not recommended.