import numpy as N
import pylab,itertools,csv
from itertools import imap,izip,chain



string_conversions=[
    # conversion function,  numpy dtype
    ( int,                  N.dtype(int)    ),
    ( float,                N.dtype(float)  ),
    ( pylab.datestr2num,    N.dtype(float)  ),
    ]

def string_to_dt_cvt(s):
    """
    Converting data to the appropriate type
    """
    for fn,dt in string_conversions:
        try:
            v=fn(s)
            return dt,fn
        except:
            pass
    return str,N.dtype(object)


def load(fname,delim = ',',has_varnm = True, prn_report = True):
    """
    Loading data from a file using the csv module. Returns a recarray.
    """
    global data_iterator,cvt,descr
    
    f=open(fname,'rb')
    row_iterator=itertools.imap(lambda x: x.split(delim),f)

    first_row=row_iterator.next()
    cols=len(first_row)
    if not has_varnm:
        varnm = ['col%s' % str(i+1) for i in xrange(cols)]
        dt_row=first_row
    else:
        varnm = [i.strip() for i in first_row]
        dt_row=row_iterator.next()

    descr=[]
    conversion_functions=[]
    for name,item in zip(varnm,dt_row):
        dtype,cvt_fn=string_to_dt_cvt(item)
        descr.append((name,dtype))
        conversion_functions.append(cvt_fn)
    convert_row=lambda r: tuple(fn(x) for fn,x in izip(conversion_functions,r))

    data_iterator=imap(convert_row,chain([dt_row],row_iterator))
    data=N.fromiter(data_iterator,dtype=descr).view(N.recarray)

    # load report
    if prn_report:
        print "##########################################\n"
        print "Loaded file: %s\n" % fname
        print "Nr obs: %s\n" % data.shape[0]
        print "Variables and datatypes:\n"
        for i in data.dtype.descr:
            print "Varname: %s, Type: %s, Sample: %s" % (i[0], i[1], str(data[i[0]][0:3]))
            print "\n##########################################\n"

    return data

def show_dates(dates):
	return N.array([i.strftime('%d %b %y') for i in pylab.num2date(dates)])

if __name__ == '__main__':

	# creating data
	data = [['col1', 'col2', 'col3', 'col4', 'col5', 'col6'],
			['1','3','1/97','1.12','2.11','1.2'],
			['1','2','3/97','1.21','3.12','1.43'],
			['2','1','2/97','1.12','2.11','1.28'],
			['2','2','4/97','1.33','2.26','1.23'],
			['2','2','5/97','1.73','2.42','1.26']]

	# saving data to csv file
	f = open('testdata.csv','wb')
	output = csv.writer(f)
	for i in data:
		output.writerow(i)
	f.close()

	# opening data file with variable names
	ra = load('testdata.csv')