[Tutor] group txt files by month

[questions anon]

Thank you for this response it was a tremedous help.
It still took me awhile to work it all out and thought I would post what
worked for me.
Thanks again

GLOBTEMPLATE = r"e:/rainfall-{year}/r{year}{month:02}??.txt"

def accumulate_month(year, month):
    files = glob.glob(GLOBTEMPLATE.format(year=year, month=month))
    monthlyrain=[]
    for ifile in files:
        f=np.genfromtxt(ifile,skip_header=6)
        monthlyrain.append(f)
    print "year-month: ",year,"-",month, ", maximum: ",
np.max(monthlyrain), "minimum: ", np.min(monthlyrain), "mean: ",
np.mean(monthlyrain)

stop_month = datetime(2011, 12, 31)
month = datetime(2011, 01, 01)
while month < stop_month:
    accumulate_month(month.year, month.month)
    month += timedelta(days=32)
    month = month.replace(day=01)


On Thu, Apr 5, 2012 at 4:57 PM, Peter Otten <__peter__ at web.de> wrote:

> questions anon wrote:
>
> > I have been able to write up what I want to do (using glob) but I am not
> > sure how to loop it or simplify it to make the script more efficient.
> > I am currently:
> > -grouping the same months in a year using glob
> > -opening the files in a group and combining the data using a list
> > -finding max, min etc for the list and printing it
> >
> > I need to do this for many years and therefore many months so really need
> > a way to make this more efficient.
> > Any feedback will be greatly appreciated
> >
> > MainFolder=r"E:/rainfall-2011/"
> > OutputFolder=r"E:/test_out/"
> > r201101=glob.glob(MainFolder+"r201101??.txt")
> > r201102=glob.glob(MainFolder+"r201102??.txt")
> > r201103=glob.glob(MainFolder+"r201103??.txt")
> >
> > rain201101=[]
> > rain201102=[]
> > rain201103=[]
> > monthlyrainfall=[]
> >
> > for ifile in r201101:
> >     f=np.genfromtxt(ifile, skip_header=6)
> >     rain201101.append(f)
> >
> > for ifile in r201102:
> >     f=np.genfromtxt(ifile, skip_header=6)
> >     rain201102.append(f)
> >
> > for ifile in r201103:
> >     f=np.genfromtxt(ifile, skip_header=6)
> >     rain201103.append(f)
> >
> > print "jan", np.max(rain201101), np.min(rain201101), np.mean(rain201101),
> > np.median(rain201101), np.std(rain201101)
> > print "feb", np.max(rain201102), np.min(rain201102), np.mean(rain201102),
> > np.median(rain201102), np.std(rain201102)
> > print "mar", np.max(rain201103), np.min(rain201103), np.mean(rain201103),
> > np.median(rain201103), np.std(rain201103)
>
> Strip the code down to one month
>
> > r201103=glob.glob(MainFolder+"r201103??.txt")
> > rain201101=[]
> > for ifile in r201101:
> >     f=np.genfromtxt(ifile, skip_header=6)
> >     rain201101.append(f)
>
>
> then turn it into a function, roughly
>
> GLOBTEMPLATE = "e:/rainfall-{year}/r{year}{month:02}??.txt"
> def accumulate_month(year, month):
>    files = glob.glob(GLOBTEMPLATE.format(year=year, month=month))
>    # read files, caculate and write stats
>
> and finally put it into a loop:
>
> from datetime import date, timedelta
> stop_month = date(2012, 4, 1)
> month = datetime(2011, 1, 1)
> while month < stop_month:
>    accumulate_month(month.year, month.month)
>    month += timedelta(days=32)
>    month = month.replace(day=1)
>
>
>
>
> _______________________________________________
> Tutor maillist  -  Tutor at python.org
> To unsubscribe or change subscription options:
> http://mail.python.org/mailman/listinfo/tutor
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/tutor/attachments/20120411/3590b473/attachment-0001.html>