word frequency count

''' Word_frequency3a.py
experiments with string processing
preprocess the string and do a word frequency count
words with matching frequency are in order too
'''

from string import punctuation
from collections import Counter

# sample text for testing (could come from a text file)
text = """\
A mouse can slip through a hole the size of a penny.
A giraffe can clean its ears with its tongue.
A giraffe's heart beats 50 times a minute.
A dog's heart beats 100 times a minute.
A hedgehog's heart beats 300 times a minute.
"""

# since giraffe's would turn into giraffes, optionally remove 's
text2 = text.replace("'s", "")

# remove punctuation marks and change to lower case
text3 = ''.join(c for c in text2.lower() if c not in punctuation)

# text3.split() splits text3 at white spaces
word_list = text3.split()
# creates a list of (word, frequency) tuples of the 10
# most common words sorted by frequency
wf_tuple_list = Counter(word_list).most_common(10)

for w, f in wf_tuple_list:
    # newer string formatting style Python27 and higher
    print("{:3d}  {}".format(f, w))

''' result (10 most common words) ...
 10  a
  3  heart
  3  times
  3  beats
  3  minute
  2  can
  2  its
  2  giraffe
  1  slip
  1  mouse
'''