def getWordList(self, event): # word_list is a list of (word, freq) cp = CaptionParser(True) for photo in event['photos']: photo = Photo(photo) cp.insertCaption(photo.getCaption()) return cp.getTopWords(-1, False)
def _getTopWords(self, k, stopword_removal=False):
caption_parser = CaptionParser(stopword_removal=stopword_removal)
for photo in self._event["photos"]:
p = Photo(photo)
caption = p.getCaption()
if not caption is None:
caption_parser.insertCaption(caption)
return caption_parser.getTopWords(k)
def _getTopWords(self, k, stopword_removal=False):
caption_parser = CaptionParser(stopword_removal=stopword_removal)
for photo in self._event['photos']:
p = Photo(photo)
caption = p.getCaption()
if not caption is None:
caption_parser.insertCaption(caption)
return caption_parser.getTopWords(k)
def _getTopWords(self, k, stopword_removal=False): # get top words by counting the frequecy caption_parser = CaptionParser(stopword_removal=stopword_removal) for photo in self._event['photos']: p = Photo(photo) caption = p.getCaption() if not caption is None: caption_parser.insertCaption(caption) return caption_parser.getTopWords(k)
def PhotoDistanceByCaption(photo1, photo2):
p1 = Photo(photo1)
p2 = Photo(photo2)
cap1 = p1.getCaption()
cap2 = p2.getCaption()
cp1 = CaptionParser(True)
cp1.insertCaption(cap1)
cp2 = CaptionParser(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)
from photo_interface import PhotoInterface
from caption_parser import CaptionParser
from mongodb_interface import MongoDBInterface
from photo import Photo
import random
if __name__ == '__main__':
mi = MongoDBInterface()
mi.setDB('test_caption')
mi.setCollection('captions')
cp = CaptionParser(True)
i = 0
captions = mi.getAllDocuments()
for caption in captions:
i += 1
if i % 1000 == 0:
# print cp.getTopWords(200)
print i
print len(cp._)
cp.insertCaption(caption['caption'])
for word, value in cp.getTopWords(300):
print '\''+word+'\',',
print
from photo_interface import PhotoInterface
from caption_parser import CaptionParser
from mongodb_interface import MongoDBInterface
from photo import Photo
import random
if __name__ == '__main__':
mi = MongoDBInterface()
mi.setDB('test_caption')
mi.setCollection('captions')
cp = CaptionParser(True)
i = 0
captions = mi.getAllDocuments()
for caption in captions:
i += 1
if i % 1000 == 0:
# print cp.getTopWords(200)
print i
print len(cp._)
cp.insertCaption(caption['caption'])
for word, value in cp.getTopWords(300):
print '\'' + word + '\',',
print