thr3ads.net - R help - [R] plotting the one-dimensional density of events in time [Mar 2015]

If this information is useful, please help other people find it:
Share via:

Christopher W. Ryan

2015-Mar-06 21:03 UTC

[R] plotting the one-dimensional density of events in time

I have the dates of occurence of a repetitive event. I would like to
plot the density of these events, as well as their specific temporal
location.  This is as far as I have gotten:

# generate some sample data: dates in 2014
random.dates <- sample(1:31, 100, replace=TRUE)
random.months <- sample(1:12, 100, replace=TRUE)
dd <- as.Date(as.character((paste(random.dates, random.months,
"2014",
sep="-"))), format="%d-%m-%Y")
dd <- dd[!is.na(dd)]

# plot density with a "rug".
density(as.numeric(dd))
plot(density(as.numeric(dd)))
rug(as.numeric(dd))

# But horizontal axis label is not very informative
# would prefer labeling the start of each month
plot(density(as.numeric(dd)), axes=FALSE)
library(zoo)
new.axis <- as.yearmon(dd)

# but then what? This is where I get stuck--adding back a sensible axis

Grateful for any guidance.

Thanks.

--Chris
-- 
Christopher W. Ryan, MD, MS
cryanatbinghamtondotedu

Early success is a terrible teacher. You?re essentially being rewarded
for a lack of preparation, so when you find yourself in a situation
where you must prepare, you can?t do it. You don?t know how.
--Chris Hadfield, An Astronaut's Guide to Life on Earth


---

Tom Wright

2015-Mar-06 21:48 UTC

head link

[R] plotting the one-dimensional density of events in time

plot(density(as.numeric(dd)), 
	axes=FALSE, 
	xlim=c(as.numeric(as.Date("2014-01-01")),
	as.numeric(as.Date("2014-12-30")))
rug(as.numeric(dd))
axis(side=1,
    at=seq(from=as.numeric(as.Date('2014-01-01')),
           to=as.numeric(as.Date('2014-12-1')),length.out=12),
    labels=month.abb,
    las=2)




On Fri, 2015-03-06 at 16:03 -0500, Christopher W. Ryan
wrote:> I have the dates of occurence of a repetitive event. I would like to
> plot the density of these events, as well as their specific temporal
> location.  This is as far as I have gotten:
> 
> # generate some sample data: dates in 2014
> random.dates <- sample(1:31, 100, replace=TRUE)
> random.months <- sample(1:12, 100, replace=TRUE)
> dd <- as.Date(as.character((paste(random.dates, random.months,
"2014",
> sep="-"))), format="%d-%m-%Y")
> dd <- dd[!is.na(dd)]
> 
> # plot density with a "rug".
> density(as.numeric(dd))
> plot(density(as.numeric(dd)))
> rug(as.numeric(dd))
> 
> # But horizontal axis label is not very informative
> # would prefer labeling the start of each month
> library(zoo)
> new.axis <- as.yearmon(dd)
> 
> # but then what? This is where I get stuck--adding back a sensible axis
> 
> Grateful for any guidance.
> 
> Thanks.
> 
> --Chris

William Dunlap

2015-Mar-06 22:29 UTC

head link

[R] plotting the one-dimensional density of events in time

You could change the x component of density's output back into a Date object
and let plot choose a Date axis in its usual way.  E.g.,
  > den <- density(as.numeric(dd))
  > den$x <- as.Date(den$x, origin=as.Date("1970-01-01"))
  > plot(den$x, den$y)
(You probably will also want to normalize the y component to be on a
specific
per time unit, say day or year, basis.)



Bill Dunlap
TIBCO Software
wdunlap tibco.com

On Fri, Mar 6, 2015 at 1:03 PM, Christopher W. Ryan <cryan at
binghamton.edu>
wrote:
> I have the dates of occurence of a repetitive event. I would like to
> plot the density of these events, as well as their specific temporal
> location.  This is as far as I have gotten:
>
> # generate some sample data: dates in 2014
> random.dates <- sample(1:31, 100, replace=TRUE)
> random.months <- sample(1:12, 100, replace=TRUE)
> dd <- as.Date(as.character((paste(random.dates, random.months,
"2014",
> sep="-"))), format="%d-%m-%Y")
> dd <- dd[!is.na(dd)]
>
> # plot density with a "rug".
> density(as.numeric(dd))
> plot(density(as.numeric(dd)))
> rug(as.numeric(dd))
>
> # But horizontal axis label is not very informative
> # would prefer labeling the start of each month
> plot(density(as.numeric(dd)), axes=FALSE)
> library(zoo)
> new.axis <- as.yearmon(dd)
>
> # but then what? This is where I get stuck--adding back a sensible axis
>
> Grateful for any guidance.
>
> Thanks.
>
> --Chris
> --
> Christopher W. Ryan, MD, MS
> cryanatbinghamtondotedu
>
> Early success is a terrible teacher. You?re essentially being rewarded
> for a lack of preparation, so when you find yourself in a situation
> where you must prepare, you can?t do it. You don?t know how.
> --Chris Hadfield, An Astronaut's Guide to Life on Earth
>
>
> ---
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
	[[alternative HTML version deleted]]

Christopher W. Ryan

2015-Mar-09 17:28 UTC

head link

[R] plotting the one-dimensional density of events in time

Tom and Bill--

Thanks! Both excellent solutions.

--Chris

Christopher W. Ryan, MD, MS
cryanatbinghamtondotedu

Early success is a terrible teacher. You?re essentially being rewarded
for a lack of preparation, so when you find yourself in a situation
where you must prepare, you can?t do it. You don?t know how.
--Chris Hadfield, An Astronaut's Guide to Life on Earth

William Dunlap wrote:> You could change the x component of density's output back into a Date
object
> and let plot choose a Date axis in its usual way.  E.g.,
>   > den <- density(as.numeric(dd))
>   > den$x <- as.Date(den$x, origin=as.Date("1970-01-01"))
>   > plot(den$x, den$y)
> (You probably will also want to normalize the y component to be on a
> specific
> per time unit, say day or year, basis.)
> 
> 
> 
> Bill Dunlap
> TIBCO Software
> wdunlap tibco.com <http://tibco.com>
> 
> On Fri, Mar 6, 2015 at 1:03 PM, Christopher W. Ryan
> <cryan at binghamton.edu <mailto:cryan at binghamton.edu>>
wrote:
> 
>     I have the dates of occurence of a repetitive event. I would like to
>     plot the density of these events, as well as their specific temporal
>     location.  This is as far as I have gotten:
> 
>     # generate some sample data: dates in 2014
>     random.dates <- sample(1:31, 100, replace=TRUE)
>     random.months <- sample(1:12, 100, replace=TRUE)
>     dd <- as.Date(as.character((paste(random.dates, random.months,
"2014",
>     sep="-"))), format="%d-%m-%Y")
>     dd <- dd[!is.na <http://is.na>(dd)]
> 
>     # plot density with a "rug".
>     density(as.numeric(dd))
>     plot(density(as.numeric(dd)))
>     rug(as.numeric(dd))
> 
>     # But horizontal axis label is not very informative
>     # would prefer labeling the start of each month
>     plot(density(as.numeric(dd)), axes=FALSE)
>     library(zoo)
>     new.axis <- as.yearmon(dd)
> 
>     # but then what? This is where I get stuck--adding back a sensible axis
> 
>     Grateful for any guidance.
> 
>     Thanks.
> 
>     --Chris
>     --
>     Christopher W. Ryan, MD, MS
>     cryanatbinghamtondotedu
> 
>     Early success is a terrible teacher. You?re essentially being rewarded
>     for a lack of preparation, so when you find yourself in a situation
>     where you must prepare, you can?t do it. You don?t know how.
>     --Chris Hadfield, An Astronaut's Guide to Life on Earth
> 
> 
>     ---
> 
>     ______________________________________________
>     R-help at r-project.org <mailto:R-help at r-project.org> mailing
list --
>     To UNSUBSCRIBE and more, see
>     https://stat.ethz.ch/mailman/listinfo/r-help
>     PLEASE do read the posting guide
>     http://www.R-project.org/posting-guide.html
>     and provide commented, minimal, self-contained, reproducible code.
> 
> 

---

R help - Mar 2015 - plotting the one-dimensional density of events in time

[R] plotting the one-dimensional density of events in time

[R] plotting the one-dimensional density of events in time

[R] plotting the one-dimensional density of events in time

[R] plotting the one-dimensional density of events in time