def _getTopWords(self, k, stopword_removal=False):
# get top words by counting the frequecy
text_parser = TextParser(stopword_removal=stopword_removal)
for photo in self._event['photos']:
p = Photo(photo)
caption = p.getCaption()
if not caption is None:
text_parser.insertCaption(caption)
return text_parser.getTopWords(k)
def PhotoDistanceByCaption(photo1, photo2):
p1 = Photo(photo1)
p2 = Photo(photo2)
cap1 = p1.getCaption()
cap2 = p2.getCaption()
cp1 = TextParser(True)
cp1.insertCaption(cap1)
cp2 = TextParser(True)
cp2.insertCaption(cap2)
word_list1 = cp1.getTopWords(-1)
word_list2 = cp2.getTopWords(-1)
if len(word_list1) == 0 or len(word_list2) == 0:
# unable to compare
return None
word_dict1 = {}
for word, freq in word_list1:
word_dict1[word] = freq
word_dict2 = {}
for word, freq in word_list2:
word_dict2[word] = freq
return kldiv(word_dict1, word_dict2)
