gistfile1.py

from math import log
from sussex_nltk.corpus_readers import WSJCorpusReader

def get_entropy_ambiguity(word):
# Get the PoS ambiguity of *word* according to its occurrence in WSJ
    pos_counts = {}                     # keep track of the number of times *word* 
                                        # appears with each PoS tag
    for token, tag in WSJCorpusReader().tagged_words():   #for each token and tag in WSJ
        if token == word:               # if this token is the word we're interested in
            try:
                pos_counts[tag] += 1    # if we've seen the tag before, increment the 
                                        # counter keeping track of occurrences
            except KeyError:            # Otherwise a KeyError will be thrown, catch it
                pos_counts[tag] = 1     # Then start the counter at 1 for that tag
    return entropy(pos_counts.values()) # return the entropy of the counts
        
def entropy(counts):            # counts = list of counts of occurrences of tags
    total = sum(counts)         # get total number of occurrences
    if not total: return 0      # if zero occurrences in total, then 0 entropy
    entropy = 0
    for i in counts:            # for each tag count
        p = i/float(total)      # probability that the token occurs with this tag
        try:
            entropy += p * log(p,2) # add to entropy
        except ValueError: pass     # if p==0, then ignore this p
    return -entropy if entropy else entropy   # only negate if nonzero, otherwise 
                                              # floats can return -0.0, which is weird.

# Usage:
print 'Ambiguity of "blue": %s' % get_entropy_ambiguity("blue")