stacked_mean.R

setwd("~/Downloads")
datos<-read.table("bdcedro10.csv", header=T, sep=',')
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.1.2

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.1.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

df2 <- datos %>%
  group_by(Finca) %>%
  arrange(Finca, desc(Tejido))
df2

## # A tibble: 60 × 6
## # Groups:   Finca [10]
##    Finca finca       cultivo Tejido genotipo cadmio
##    <chr> <chr>       <chr>   <chr>  <chr>     <dbl>
##  1 F13   El Porvenir Cedro   Tallos Cedro     0.151
##  2 F13   El Porvenir Cedro   Tallos Cedro     0.142
##  3 F13   El Porvenir Cedro   Tallos Cedro     0.163
##  4 F13   El Porvenir Cedro   Hojas  Cedro     0.085
##  5 F13   El Porvenir Cedro   Hojas  Cedro     0.082
##  6 F13   El Porvenir Cedro   Hojas  Cedro     0.065
##  7 F14   La Loma     Cedro   Tallos Cedro     0.079
##  8 F14   La Loma     Cedro   Tallos Cedro     0.091
##  9 F14   La Loma     Cedro   Tallos Cedro     0.12 
## 10 F14   La Loma     Cedro   Hojas  Cedro     0.085
## # ℹ 50 more rows

df3<-df2%>%
  group_by(Finca, cultivo, Tejido) %>%
  summarise(mean = round(mean(cadmio), 2))

## `summarise()` has grouped output by 'Finca', 'cultivo'. You can override using
## the `.groups` argument.

df4<-df3%>%
    mutate(lab_ypos = cumsum(mean) - 0.3 * mean)         
            
p <- ggplot(data = df4, aes(x = Finca, y = mean)) +
  geom_col(aes(fill = Tejido), width = 0.7)+
  geom_text(aes(y = lab_ypos, label = mean, group =Tejido), color = "white")
p

library(emmeans)
fit1<-aov(mean~Finca, data=df4)
meandiam<-emmeans(fit1, ~ Finca)
multcomp::cld(meandiam, adjust="none", Letters=LETTERS, reversed=T)

##  Finca emmean     SE df lower.CL upper.CL .group
##  F9     1.015 0.0917 10   0.8108    1.219  A    
##  F8     0.760 0.0917 10   0.5558    0.964  A    
##  F18    0.460 0.0917 10   0.2558    0.664   B   
##  F16    0.420 0.0917 10   0.2158    0.624   BC  
##  F24    0.300 0.0917 10   0.0958    0.504   BCD 
##  F22    0.145 0.0917 10  -0.0592    0.349    CD 
##  F19    0.135 0.0917 10  -0.0692    0.339    CD 
##  F13    0.115 0.0917 10  -0.0892    0.319     D 
##  F14    0.085 0.0917 10  -0.1192    0.289     D 
##  F7     0.080 0.0917 10  -0.1242    0.284     D 
## 
## Confidence level used: 0.95 
## significance level used: alpha = 0.05 
## NOTE: Compact letter displays can be misleading
##       because they show NON-findings rather than findings.
##       Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.

plot(meandiam, comparisons = TRUE)