MissingDataVisualization

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.7     v dplyr   1.0.8
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

mi_comp <- read.csv('D:/NCSU/Summer2022/SIBS/SIBS_HackAThon/Myocardial infarction complications Database.csv', check.names = TRUE) #make sure the variable imported valid for R without special characters/symbols like tabs

More exploration of missing data

library(naniar)
#??????????? Scaling for both visualization
# Which variables contain the most missing variables?
gg_miss_var(mi_comp) 

## Warning: It is deprecated to specify `guide = FALSE` to remove a guide. Please
## use `guide = "none"` instead.

# Where are missings located?
vis_miss(mi_comp) + theme(axis.text.x = element_text(angle=80)) 

## Warning: `gather_()` was deprecated in tidyr 1.2.0.
## Please use `gather()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.