paulponcet/modeest

Mode estimation

modeest's Issues

Calculating mode on factor

I have found this question on stackoverflow . When trying to calculate the mode from a factor like this:

color <- c("blue","green","blue","blue","green","yellow","pink","blue")
color <- as.factor(color)

The mode is NA:

mlv.factor(x=color,method='mfv')

Mode (most frequent value): NA 
Bickel's modal skewness: -2 
Call: mlv.factor(x = color, method = "mfv") 
Warning message:
In discrete(x, ...) : NAs introduced by coercion

I have looked into the function an found that mlv.factor() calls discrete():
th <- discrete(x, ...)

f <- factor(x)
f
[1] blue   green  blue   blue   green  yellow pink   blue  
Levels: blue green pink yellow

tf <- tabulate(f)
tf
[1] 4 2 1 1

as.numeric(levels(f)[tf == max(tf)])
[1] NA
Warning message:
NAs introduced by coercion 

It cannot coerce "blue" to numeric, hence the function does not return anything.

argument 'x' contains missing values

Estimating the mode of a trimmed G prime set using the 'modeest' package...
Error: argument 'x' contains missing values

I encountered the above error. Please help.

Encoding

Hi @polmath, I don't understanding file encoding issues well, and I typically run away from them, or take the path of least resistance.

In case it helps you to know, it may be difficult for Americans to edit and resubmit existing code. Characters like the accented 'e' in the file below aren't interpreted correctly with my installations of RStudio, Notepad++, Notepad, or NetBeans. From what I could tell, the GitHub browser did a better job, so I edited it directly in there.

I'm not saying you should change anything so it's easier for us to work with. But I wanted to let you know there might be extra friction/obstacles developing.

argument 'x' contains missing values_QTLseqr

Estimating the mode of a trimmed G prime set using the 'modeest' package...
Error: argument 'x' contains missing values

I encountered the above error. Please help.