Data frequency analysis script

gistfile1.txt

#!/usr/bin/python

"""
Input:
    [visitor, element, t]

Output:
    [element, count(visitor)].sort(lambda a,b: b[1]-a[1])
"""

if __name__=='__main__':
    fh = open('sequence', 'r')
    lines = fh.readlines()
    elemCount = {}
    for l in lines:
        #print l
        (vis, elem, t) = l.split("\t")
        if elem not in elemCount:
            elemCount[elem] = 1
        else:
            elemCount[elem] += 1

    for e,count in elemCount.iteritems():
        print "%s\t%i" % (e, count)

    sortedElem = elemCount.keys().sort(
            lambda a,b: 
                elemCount[b] - elemCount[a]
                )