I would like to do some fairly basic stem-and-leaf displays in R.
I am aware (I might even say painfully aware) of stem(base) and
have tried it. That's why I'm hoping someone has a usable stem-
and-leaf display for R so that I don't have to write my own.
r-project.org > Search > R Site Search > "stem and leaf
display"
finds nothing.
I also tried the mail archive search, but couldn't figure out how
to search the bodies of the messages.
For the record, there are some less important things that I would
like to have (like depths and outlier lines), and it is a pity that
the "atom" argument of stem() is effectively undocumented (it's a
tolerance, fine, but what _of_ and how used?), but I'd put up with
stem() the way it is if only it didn't do things like displaying
5.67 and 5.78 as
56 | 78
which makes it effectively unusable. What good is a stem and leaf
plot where you can't recover the leading digits of the numbers correctly?
At 18:08 16/07/03 +1200, Richard A. O'Keefe wrote:>I would like to do some fairly basic stem-and-leaf displays in R. >I am aware (I might even say painfully aware) of stem(base) and >have tried it. That's why I'm hoping someone has a usable stem- >and-leaf display for R so that I don't have to write my own. > >r-project.org > Search > R Site Search > "stem and leaf display" >finds nothing. > >I also tried the mail archive search, but couldn't figure out how >to search the bodies of the messages. > >For the record, there are some less important things that I would >like to have (like depths and outlier lines), and it is a pity that >the "atom" argument of stem() is effectively undocumented (it's a >tolerance, fine, but what _of_ and how used?),Source is available ...> but I'd put up with stem() the way it is if only it didn't do things > like displaying >5.67 and 5.78 as > 56 | 78 >which makes it effectively unusable. What good is a stem and leaf >plot where you can't recover the leading digits of the numbers correctly?????? > x<-c(5.67, 5.78) > stem(x) The decimal point is 1 digit(s) to the left of the | 56 | 7 57 | 57 | 8 What are you doing? Richard Rowe Senior Lecturer Department of Zoology and Tropical Ecology, James Cook University Townsville, Queensland 4811, Australia fax (61)7 47 25 1570 phone (61)7 47 81 4851 e-mail: Richard.Rowe at jcu.edu.au http://www.jcu.edu.au/school/tbiol/zoology/homepage.html
Some weeks ago I wrote a function to construct a stem-and-leaf-display
because we want to have some more parameters to control the result.
D.Trenkler remind me of
/Velleman/Hoaglin: ABC of EDA, page 15: "It is easy to construct a
Stem-and-Leaf-Display by hand...
It is not nearly as easy to write a general computer program to produce
Stem-and-Leaf-Displays./"
so the programming was a great challange also.
Here is the link to the code:
http://www.wiwi.uni-bielefeld.de/~wolf/software/mystem/ms.sch
German documentation:
http://www.wiwi.uni-bielefeld.de/~wolf/software/mystem/ms.ps
http://www.wiwi.uni-bielefeld.de/~wolf/software/mystem/ms.html
Syntax of stem.leaf
##################################################################
#Description: #
# stem.leaf produces a stem-and-leaf-display of a data set #
# #
#Usage: #
# stem.leaf(data) #
# stem.leaf(data,unit=100,m=5,Min=50,Max=1000,rule.line="Dixon"#
# #
#Arguments: #
# data: vector of input data #
# unit: unit of leafs in: { ...,100,10,1,.1,.01,... } #
# m: 1, 2 or 5 -- 10/m=number of possible leaf digits #
# Min: minimum of stem #
# Max: maximum of stem #
# rule.line: = "Dixon" => number of lines <- 10*log(n,10)
#
# = "Velleman" => number of lines <- 2*sqrt(n)
#
# = "Sturges" => number of lines <- 1 + log(n,2)
#
# style: = "UREDA" => UREDA like stem ( m = 2, 5 ) #
# #
#Author: #
# Peter Wolf 05/2003 #
##################################################################
Hope it helps
Peter Wolf
Richard A. O'Keefe wrote:
>I would like to do some fairly basic stem-and-leaf displays in R.
>I am aware (I might even say painfully aware) of stem(base) and
>have tried it. That's why I'm hoping someone has a usable stem-
>and-leaf display for R so that I don't have to write my own.
>
>r-project.org > Search > R Site Search > "stem and leaf
display"
>finds nothing.
>
>I also tried the mail archive search, but couldn't figure out how
>to search the bodies of the messages.
>
>For the record, there are some less important things that I would
>like to have (like depths and outlier lines), and it is a pity that
>the "atom" argument of stem() is effectively undocumented
(it's a
>tolerance, fine, but what _of_ and how used?), but I'd put up with
>stem() the way it is if only it didn't do things like displaying
>5.67 and 5.78 as
> 56 | 78
>which makes it effectively unusable. What good is a stem and leaf
>plot where you can't recover the leading digits of the numbers
correctly?
>
>______________________________________________
>R-help at stat.math.ethz.ch mailing list
>https://www.stat.math.ethz.ch/mailman/listinfo/r-help
>
>
-----------------------------------------------------------------------------------
Peter Wolf, Department of Economics and Business Administration,
University of Bielefeld
pwolf at wiwi.uni-bielefeld.de,
http://www.wiwi.uni-bielefeld.de/~wolf/wolf.html