most frequent words object oriented version

'''
20cw - twenty most common words
Usage: python 20cw.py shakespeare.txt
'''

class CommonWords:
    def __init__(self, nwords=20):
        self.nwords = nwords # number of words to find
        self.mincount = 0 # least common of our most common set
        self.words = {} # words and their counts
        self.maxwords = {} # the twenty (nword) most common words

def add_word(self, word):
        ''' add a word occurrence to self.words and update maxwords
        '''
        n = self.words.get(word, 0) + 1 # increment count
        self.words[word] = n

if n > self.mincount:     # if frequent update maxwords
            self.maxwords[word] = n
            while len(self.maxwords) > self.nwords: # trim as needed
                del self.maxwords[self.lfmw()]
                self.mincount = self.maxwords[self.lfmw()]

def lfmw(self):
        ''' return least frequent word in maxwords
        '''
        return min(self.maxwords, key=self.maxwords.get)

def __str__(self):
        vals = [(self.maxwords[w], w) for w in self.maxwords]
        vals.sort(key=lambda y: -y[0]) # reverse sort most freq first
        lines = ['%d %s' % x for x in vals] # build array of lines
        return '\n'.join(lines) # join together with newlines
    
import sys

test_data = """
Parallel UniverseThe Parallel Universe Blog May 01, 2014 Not Your
Father's Java: An Opinionated Guide to Modern Java Development,
Part 1

More working, useful code has been written in the Java programming
language than in any other in history, with the possible exceptions
of C and COBOL. When Java was released almost 20 years ago, it took
the software world by storm. It was a simpler, safer, alternative
to C++, and some time later its performance caught up, too (depending
on the exact usage, a large Java program can be slightly slower,
as fast, or a little faster than a comparable C++ codebase). It
offered truly tremendous productivity benefits over C++, while
sacrificing very little (if anything at all) in return.

Java is a blue-collar language  the working persons trusty tool
adopting only tried and true idioms, and adding features only if
they solve major pain points. Whether or not Java has stayed true
to its mission or not is an open question, but it certainly tries
not to let current fashions sway it too far off course. Java has
been used to write code for anything from smart-cards, through
embedded devices, and all the way to mainframes. It is even being
used to write mission- and safety-critical hard realtime software.
"""

if __name__ == '__main__':
    cw = CommonWords(20) # for twenty most frequent words
    # for line in open(sys.argv[1]): # first arg is name of file to read
    for line in test_data.split('\n'): # from test_data
        for word in line.split(): # TODO handle punctuation
            cw.add_word(word) # increment frequency count
    print cw # invokes __str__ to get string conversion

Python Fiddle

Python Cloud IDE