ggeffectsize: visualization of effect size by the Linear Discriminant...

In xiangpin/MicrobitaProcess: A comprehensive R package for managing and analyzing microbiome and other ecological data within the tidy framework

visualization of effect size by the Linear Discriminant Analysis or randomForest

Description

visualization of effect size by the Linear Discriminant Analysis or randomForest

Usage

ggeffectsize(obj, ...)

## S3 method for class 'data.frame'
ggeffectsize(
  obj,
  factorName,
  effectsizename,
  factorLevels = NULL,
  linecolor = "grey50",
  linewidth = 0.4,
  lineheight = 0.2,
  pointsize = 1.5,
  setFacet = TRUE,
  ...
)

## S3 method for class 'diffAnalysisClass'
ggeffectsize(obj, removeUnknown = TRUE, setFacet = TRUE, ...)

Arguments

obj	object, diffAnalysisClass see diff_analysis, or data.frame, contained effect size and the group information.
...	additional arguments.
factorName	character, the column name contained group information in data.frame.
effectsizename	character, the column name contained effect size information.
factorLevels	list, the levels of the factors, default is NULL, if you want to order the levels of factor, you can set this.
linecolor	character, the color of horizontal error bars, default is grey50.
linewidth	numeric, the width of horizontal error bars, default is 0.4.
lineheight	numeric, the height of horizontal error bars, default is 0.2.
pointsize	numeric, the size of points, default is 1.5.
setFacet	logical, whether use facet to plot, default is TRUE.
removeUnknown	logical, whether do not show unknown taxonomy, default is TRUE.

Value

the figures of effect size show the LDA or MDA (MeanDecreaseAccuracy).

Author(s)

Shuangbin Xu

Examples

## Not run: 
data(kostic2012crc)
kostic2012crc %<>% as.phyloseq()
head(phyloseq::sample_data(kostic2012crc),3)
kostic2012crc <- phyloseq::rarefy_even_depth(kostic2012crc,rngseed=1024)
table(phyloseq::sample_data(kostic2012crc)$DIAGNOSIS)
set.seed(1024)
diffres <- diff_analysis(kostic2012crc, classgroup="DIAGNOSIS",
                        mlfun="lda", filtermod="fdr",
                        firstcomfun = "kruskal.test",
                        firstalpha=0.05, strictmod=TRUE,
                        secondcomfun = "wilcox.test", 
                        subclmin=3, subclwilc=TRUE,
                        secondalpha=0.01, ldascore=3) 
library(ggplot2)
effectplot <- ggeffectsize(diffres) +
              scale_color_manual(values=c('#00AED7', 
                                          '#FD9347', 
                                          '#C1E168'))+
              theme_bw()+
              theme(strip.background=element_rect(fill=NA),
                    panel.spacing = unit(0.2, "mm"),
                    panel.grid=element_blank(),
                    strip.text.y=element_blank())

## End(Not run)

xiangpin/MicrobitaProcess documentation built on April 12, 2024, 9:03 p.m.