Closed jsalinas69 closed 1 year ago
Great find! With low dispersed data the percentage does not work, because it takes the values itself. I will rewrite the selected based on the positions of values in vector. I have done only a test on high volumes of data and high dispersity (spread).
Fixed. New release available.
Thanks, but when I test this statement
library(DataExplorer) iris$Sepal.Length2 <- addMissingValues(iris, Sepal.Length, pc = 10) plot_missing(iris)
it gives me more than 40% data lost
Thanks