The GITS Blog

>>> # Create a random list of numbers
>>> from random import random
>>> numbers = [int(random() * 10) for x in range(20)]
>>> numbers
[8, 0, 3, 2, 3, 9, 8, 2, 8, 3, 0, 2, 3, 8, 6, 5, 3, 6, 1, 8]
>>> # Now create a dictionary of numbers and numbers
>>> # of occurrences. Feed generator expression of
>>> # (number, frequency) pairs to dict().
>>> from itertools import groupby
>>> valdict = dict((k, len(list(g)))
           for k, g in groupby(sorted(numbers)))
>>> for key, val in valdict.items():
    print key, ":", val

   
0 : 2
1 : 1
2 : 3
3 : 5
5 : 1
6 : 2
8 : 5
9 : 1

from itertools import groupby

def count_occurrences(iterable):
    """return a dictionary with items and numbers of occurrences
    in iterable"""
   
    return dict((item, len(list(group)))
        for item, group
        in groupby(sorted(iterable)))

>>> # get a wordlist from the Python README
>>> text = open("/python25/readme.txt").read()
>>> words = text.lower().split()
>>> words[:5]
['this', 'is', 'python', 'version', '2.5.2′]
>>> # get the frequency list, using DSU to sort top words
>>> freqs = [(len(list(g)), k)
     for k, g in groupby((sorted(words)))]
>>> # sort the freqs, get last 20, and reverse
>>> # to put most frequent first
>>> for a, b in reversed(sorted(freqs)[-20:]):
    print "%s %s" % (b.ljust(7), str(a).rjust(3))

   
the     442
to      227
is      127
and     127
you     118
a       117
of      110
in      107
for      94
python   81
on       79
if       77
this     72
or       62
be       58
with     56
it       53
are      53
that     52
as       47

from itertools import groupby

def get_top_freqs(filename, num=20):
    """Get the top num words from filename as a list
    of (word, freq) tuples
    """

    text = open(filename).read()
    words = text.lower().split()
   
    freqs = ((len(list(g)), k) for k, g in groupby(sorted(words)))
   
    return [(b, a) for a, b in reversed(sorted(freqs)[num*-1:])]