ssc_ea_mental_health_2020_analysis.R

## Description: 
## Libraries
library(ggplot2)
## Helpers
formatAsPercent <- function (float){
  return(sprintf("%0.1f%%", float * 100))
}

## Body
data <- read.csv("2020ssc_public.csv", header=TRUE, stringsAsFactors = FALSE)
data_EAs <- data[data["EAID"] == "Yes",]
View(data_EAs)
n=dim(data_EAs)[1]
n ## 993 EAs answered the survey.

List_of_Mental_Illnesses <- colnames(data)[56:67]
cat("Illness, rate diagnosed, rate suspected")
for(x in List_of_Mental_Illnesses){
  rate_diagnosed=sum(data_EAs[x] == "I have a formal diagnosis of this condition")/n ## 18%
  rate_suspected=sum(data_EAs[x] == "I think I might have this condition, although I have never been formally diagnosed")/n ## 18%
  cat(paste(x, formatAsPercent(rate_diagnosed), formatAsPercent(rate_suspected), sep=", "), "\n")
}

## Processing
tally_diagnosed=list()
for( j in List_of_Mental_Illnesses){
  tally_diagnosed$count = c(tally_diagnosed$count, 
               sum(
                 data_EAs[j] == "I have a formal diagnosis of this condition"
               )
  )
  tally_diagnosed$type = c(tally_diagnosed$type, j)
}
tally_diagnosed

tally_diagnosed$frequency = 100*tally_diagnosed$count / n
as.data.frame(tally_diagnosed) -> tally_diagnosed
tally_diagnosed

## Intuited
titulo="Prevalence of mental health ilnesses in EAs"
subtitulo="using 2020 SlateStarCodex survey data"
tally_intuited=list()
for( j in List_of_Mental_Illnesses){
  tally_intuited$count = c(tally_intuited$count, 
                            sum(
                              data_EAs[j] == "I have a formal diagnosis of this condition"
                            )
  )
  tally_intuited$type = c(tally_intuited$type, j)
}
tally_intuited

tally_intuited$frequency = 100*tally_intuited$count / n
as.data.frame(tally_intuited) -> tally_intuited
tally_intuited

## Together

tally_diagnosed$diagnosed = "Diagnosed"
tally_intuited$diagnosed = "Intuited"

as.data.frame(rbind(tally_diagnosed, tally_intuited)) -> tally_mental_health

## Plotting
titulo="Prevalence of mental health ilnesses in EAs"
subtitulo="using self-indentified EAs who answered the 2020 SlateStarCodex survey (n=993)"

(ggplot(data = tally_mental_health, aes(x =type, y = frequency, fill=diagnosed)) +
    geom_histogram(
      stat="identity",
      position= position_stack(reverse = TRUE)
    )+
    scale_fill_manual(
      values=c("royalblue3","steelblue2"))+
    scale_x_discrete(
      limits=
        List_of_Mental_Illnesses[
          order(tally_diagnosed$count +tally_intuited$count ) ## This orders the ilnesses by frequency
        ]
    )+
    scale_y_continuous(
      labels=function(x) paste0(x,"%"))+
    coord_flip()+
    labs(
      title=titulo, 
      subtitle=subtitulo, 
      x=NULL, 
      y="Frequency (%)", 
      caption="@NunoSempere"
    )+
    theme(
      legend.title = element_blank(), 
      plot.subtitle = element_text(hjust = 0.5), 
      plot.title = element_text(hjust = 0.5),
      legend.position="bottom"
    ) 
)

height=5
width=height*(1+sqrt(5))/2

ggsave("Q5and6.png" , units="in", width=width, height=height, dpi=800)