ggplot2 R 中不相关变量的堆叠条形图将变量转换为基于存在不存在的百分比

Question

Following is a sample data frame

df <- data.frame(SampleID = c(1, 2, 3, 4, 5, 6, 7, 8),
                 Var1 = c(0.1 , 0.5,    0.7,    0,  0,  0,  0.5,    0.2), 
                 Var1PA = c("Present", "Present", "Present", "Absent", "Absent", "Absent",  "Present", "Present"), 
                 Var2 = c(0, 0, 0, 0, 0.1, 0.5, 0.7, 0.2), 
                 Var2PA = c("Absent", "Absent", "Absent", "Absent", "Present", "Present", "Present", "Present"))

My question started off as seemingly simple, but I could not find a way to edit the dataframe suitably to plot a barplot.

For Var1, I want to plot a stacked barplot of the percent of times var1 was present in the sample (ie var1 value > 0) or absent (Similarly for var2 and so on).

I could determine this percentage by:

(1 - sum(df$Var1 == 0) / length(df$Var1)) * 100

But how do I convert this into a percentage while plotting? I looked at many melt options, but there is no unifying criteria for these variables that would make a common X axis

Finally, how does one answer the question above if I want to plot 5 variables from a dataframe of 1000 such column variables?

Edit: Thanks for the answers so far! I have a slight edit to the question I just added one more variable to my data frame

df <- data.frame(SampleID = c(1, 2, 3, 4, 5, 6, 7, 8),
             Var1 = c(0.1 , 0.5,    0.7,    0,  0,  0,  0.5,    0.2), 
             Var1PA = c("Present", "Present", "Present", "Absent", "Absent", "Absent",  "Present", "Present"), 
             Var2 = c(0, 0, 0, 0, 0.1, 0.5, 0.7, 0.2), 
             Var2PA = c("Absent", "Absent", "Absent", "Absent", "Present", "Present", "Present", "Present"),
             Disease = c("Case", "Control", "Case", "Control", "Case", "Control", "Case", "Control"))

I am trying to figure out how to plot the barplot for cases and controls with presence absence stacked within them for Var1PA, Var2PA and so on. If I have the right data frame input, the ggplot2 code would be: vars <- c('Var1PA', 'Var2PA', 'Var2PA') ##based on the first comment by @rawr tt <- data.frame(prop.table(as.table(sapply(df[, vars], table)), 2) * 100) ggplot(tt, aes(Disease, Freq)) +
geom_bar(aes(fill = Var1), position = "stack", stat="identity") + facet_grid(~vars)

How do I get percentages for cases (present and absent) and controls (present and absent) for each of the vars? Thanks!

Answer 1

This should generalize nicely. You can, of course, be more selective about the variables you pick.

library(dplyr)
library(tidyr)
mdf = df %>% select(SampleID, ends_with("PA")) %>%
    gather(key = Var, value = PA, -SampleID) %>%
    mutate(PA = factor(PA, levels = c("Present", "Absent")))

ggplot(mdf, aes(x = Var, fill = PA)) +
    geom_bar(position = "fill") +
    scale_y_continuous(labels = scales::percent)

You can add the percentage columns to the long data frame:

mdf %>% group_by(Var) %>%
    mutate(p_present = mean(PA == "Present"),
           p_absent = mean(PA == "Absent"))
# Source: local data frame [16 x 5]
# Groups: Var [2]
# 
#    SampleID    Var      PA p_present p_absent
#       <dbl>  <chr>  <fctr>     <dbl>    <dbl>
# 1         1 Var1PA Present     0.625    0.375
# 2         2 Var1PA Present     0.625    0.375
# 3         3 Var1PA Present     0.625    0.375
# 4         4 Var1PA  Absent     0.625    0.375
# 5         5 Var1PA  Absent     0.625    0.375
# 6         6 Var1PA  Absent     0.625    0.375
# 7         7 Var1PA Present     0.625    0.375
# 8         8 Var1PA Present     0.625    0.375
# 9         1 Var2PA  Absent     0.500    0.500
# 10        2 Var2PA  Absent     0.500    0.500

Or if you'd rather see a 1-line-per-group summary, replace mutate with summarize :

mdf %>% group_by(Var) %>%
    summarize(p_present = mean(PA == "Present"),
           p_absent = mean(PA == "Absent"))
# # A tibble: 2 × 3
#      Var p_present p_absent
#    <chr>     <dbl>    <dbl>
# 1 Var1PA     0.625    0.375
# 2 Var2PA     0.500    0.500

Answer 2

My solution for this

library(ggplot2)
library(reshape)
library(dplyr)

df <- data.frame(
  SampleID = c(1, 2, 3, 4, 5, 6, 7, 8),
  Var1 = c(0.1, 0.5, 0.7, 0, 0, 0, 0.5, 0.2),
  Var1PA = c("Present", "Present", "Present", "Absent", "Absent", "Absent", "Present", "Present"),
  Var2 = c(0, 0, 0, 0, 0.1, 0.5, 0.7, 0.2),
  Var2PA = c("Absent", "Absent", "Absent", "Absent", "Present", "Present", "Present", "Present")
)

reshape::melt(df, c('SampleID')) |> 
  filter(variable == 'Var1' | variable == 'Var2') |> 
  mutate(value1 = ifelse(value == 0, 'Absent', 'Present')) |> 
  group_by(variable) |> count(variable, value1) |> 
  mutate(
    prc = n/sum(n)
  ) |>  as.data.frame() |> 
  ggplot( aes(x = variable, y = prc, fill = value1)) +
    geom_bar(stat = 'identity', position = 'fill', width = 0.7) +
    scale_y_continuous(labels = scales::percent) +
    labs(fill = 'Presence status') +
    geom_text(aes(x = variable, y = prc, label = stat(y)),
              position = position_fill(vjust = 0.5))