From a data.frame, runs stats on column of interest, and returns the ggplot for it.

Usage

Utility_Behemoth(
  data,
  var,
  myfactor,
  normality = NULL,
  specifiedNormality = NULL,
  correction = "none",
  override = 0.05,
  shape_palette,
  fill_palette,
  cex = 2,
  size = 3,
  corral.width = 1,
  XAxisLevels = NULL,
  statLines = TRUE,
  statsHeight = NULL,
  showClose = TRUE,
  scalePercent = FALSE,
  keepNS = TRUE
)

Arguments

data: A data.frame object with metadata and data columns
var: The column name for your variable of interest
myfactor: The column name for your column containing your factor to group by
normality: The Normality test to be applied, "dagostino" or "shapiro". Default NULL
specifiedNormality: Default NULL leading to non-parametric, can switch by specifying "parametric" or "nonparametric".
correction: Multiple comparison correction argument, default is set at "none"
override: Internal, default 0.05. Set to 0.99 to force pairwise comparison in anova/kw.
shape_palette: Palette corresponding to factor levels, designating each's shape
fill_palette: Palette corresponding to factor levels, designating each's fill
cex: The width of the ggbeeswarm bin
size: Size for the ggbeeswarm circles.
corral.width: width of corral bin argument for beeswarm.
XAxisLevels: Provide list marker names correct order for x-axis reordering, default NULL
statLines: Default is TRUE, otherwise skips plotting pvalue and brackets
statsHeight: Default is NULL, when provided, sets stat line y-axis height.
showClose: Default is TRUE, displays pvalues between 0.05 and 0.10 instead returning n.s
scalePercent: Default is FALSE, scales 0 to 1 to 0-100
keepNS: Default is TRUE, when false, removes ns from the plots.

Value

A ggplot2 object for the corresponding data of interest.

Examples


shape_ptype <- c("HU" = 22, "HEU-lo" = 21, "HEU-hi" = 21)
fill_ptype <- c("HU" = "white", "HEU-lo" = "darkgray", "HEU-hi" = "black")

File_Location <- system.file("extdata", package = "Coereba")
panelPath <- file.path(File_Location, "ILTPanelTetramer.csv")
binaryPath <- file.path(File_Location, "HeatmapExample.csv")
dataPath <- file.path(File_Location, "ReadyFileExample.csv")
panelData <- read.csv(panelPath, check.names=FALSE)
binaryData <- read.csv(binaryPath, check.names=FALSE)
dataData <- read.csv(dataPath, check.names=FALSE)

All <- Coereba_MarkerExpressions(data=dataData, binary=binaryData,
 panel=panelData, starter="SparkBlue550")

Plot <- Utility_Behemoth(data=All, var="CD62L", myfactor="ptype",
 normality="dagostino", correction="none", shape_palette=shape_ptype,
 fill_palette=fill_ptype, XAxisLevels = c("HU", "HEU-lo", "HEU-hi"))
#> Error in if (at$p.value[1] < override) {    subset_data <- subset(data, select = c(var, myfactor))    ptt <- tidy(pairwise.t.test(subset_data[[var]], subset_data[[myfactor]],         p.adjust.method = correction))    ptt$method <- "Pairwise t-test"    ptt} else (at): missing value where TRUE/FALSE needed