def getCaptionStatistics():
pi = PhotoInterface()
pi.setDB('citybeat')
pi.setCollection('photos_no_duplicate')
tot = 0
withCap = 0
l = 0
for photo in pi.getAllDocuments():
cap = Photo(photo).getCaption()
tot += 1
if len(cap) == 0:
continue
withCap += 1
l += len(cap)
print 1.0*withCap / tot
print 1.0*l / withCap
from photo_interface import PhotoInterface
from caption_parser import CaptionParser
from photo import Photo
from mongodb_interface import MongoDBInterface
import random
if __name__ == '__main__':
pi = PhotoInterface()
pi.setDB('citybeat')
pi.setCollection('photos')
mi = MongoDBInterface()
mi.setDB('test_caption')
mi.setCollection('captions')
photos = pi.getAllDocuments()
for photo in photos:
i = random.randint(0,10)
if i > 0:
continue
p = Photo(photo)
cap = p.getCaption()
if len(cap) > 0:
cap = {'caption':cap}
mi.saveDocument(cap)
from photo_interface import PhotoInterface
from caption_parser import CaptionParser
from photo import Photo
from mongodb_interface import MongoDBInterface
import random
if __name__ == '__main__':
pi = PhotoInterface()
pi.setDB('citybeat')
pi.setCollection('photos')
mi = MongoDBInterface()
mi.setDB('test_caption')
mi.setCollection('captions')
photos = pi.getAllDocuments()
for photo in photos:
i = random.randint(0, 10)
if i > 0:
continue
p = Photo(photo)
cap = p.getCaption()
if len(cap) > 0:
cap = {'caption': cap}
mi.saveDocument(cap)
