[R] Time Series STL
Jeff Newmiller
jdnewmil at dcn.davis.CA.us
Sat Jan 11 07:52:16 CET 2014
This might not seem helpful, but there really is a communication gap here. You need to read the Posting Guide, post in plain text so your example code is not mangled by the HTML, and include a bit of data that is representative of the data you are working with. You may find some helpful advice here: http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example, including how to use the dput function.
---------------------------------------------------------------------------
Jeff Newmiller The ..... ..... Go Live...
DCN:<jdnewmil at dcn.davis.ca.us> Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playing
Research Engineer (Solar/Batteries O.O#. #.O#. with
/Software/Embedded Controllers) .OO#. .OO#. rocks...1k
---------------------------------------------------------------------------
Sent from my phone. Please excuse my brevity.
Thomas Barningham <stbarningham at gmail.com> wrote:
>Hi,
>
>I'm relatively new to R and need to some help in converting some of my
>data
>into a ts object that can then be used to run an STL analysis.
>
>My initial input file is a .csv output from some atmospheric
>measurement
>instruments. The first column is the year fraction and extends over 2
>years
>with a new data point being collected roughly every 2 minutes. Lots of
>data
>are recorded in the subsequent columns (such as met info) and
>concentrations of particular atmospheric species (which I want to run
>STL
>on).
>
>Here's my initial code:
>
>*#Read in file as an object, defined "BHD" from original file*
>*BHD <-
>read.csv("C:/Work/PhD/R_Directory/BHD_2009_2012_all_samp_cal.csv",
>header=T, dec=".", sep=",")*
>
>
>*#Define Columns from original files (comment out if using IDL output)*
>*yearfrac <- BHD[,1]*
>*APO <- BHD[,30]*
>*O2 <- BHD [,29]*
>*CO2 <- BHD[,28]*
>
>(end of code)
>
>What I want to do is take the objects defined above (APO, CO2, O2) and
>perform stl analyses on them, but I need to convert them to time series
>objects first based on the information in the yearfrac object.
>
>How do I go about this?!
>
>Thanks in advance
>Barney
More information about the R-help
mailing list