def getHistoricFeatures(self, entropy_para):
# this method computes the features that capture the difference between current
# event and background knowledge
end_time = self.getLatestPhotoTime()
begin_time = self.getEarliestPhotoTime()
pi = PhotoInterface()
pi.setDB('citybeat')
pi.setCollection('photos')
photos = []
dt = 0
for day in xrange(1,15):
# here 15 is hard coded because we use 14 days' data as the training
et = end_time - day * 24 * 3600 + dt / 2
bt = begin_time - day * 24 * 3600 - dt / 2
day_photos = pi.rangeQuery(self._event['region'], [str(bt), str(et)])
for photo in day_photos:
# since rangeQuery sorts the photos from the most current to the most early
# thus all the photos in the List "photos" are sorted by their created time from
# the most current to the most early
photos.append(photo)
random.shuffle(photos)
photos = photos[0:min(len(self._event['photos']), len(photos))]
# fake a historic event
historic_event = Event()
historic_event.setPhotos(photos)
historic_event.setRegion(self._event['region'])
historic_event.setActualValue(historic_event._getActualValueByCounting())
historic_event = EventFeature(historic_event)
# compute the difference between entropy
# this has been smoothed
pro1 = self._divideAndCount(entropy_para)
pro2 = historic_event._divideAndCount(entropy_para)
entropy_divergence = KLDivergence.averageKLDivergence(pro1, pro2)
# compute the difference between top words
topic_divergence = self.computeWordKLDivergenceWith(historic_event)
return [historic_event.getPhotoDisFeatures()[3], topic_divergence,
# historic_event.getEntropy(entropy_para),
entropy_divergence]
def getHistoricFeatures(self, entropy_para):
# this method computes the features that capture the difference between current
# event and background knowledge
end_time = self.getLatestPhotoTime()
begin_time = self.getEarliestPhotoTime()
pi = PhotoInterface()
pi.setDB('citybeat')
pi.setCollection('photos')
photos = []
dt = 3600
for day in xrange(1, 15):
# here 15 is hard coded because we use 14 days' data as the training
et = end_time - day * 24 * 3600 + dt / 2
bt = begin_time - day * 24 * 3600 - dt / 2
day_photos = pi.rangeQuery(self._event['region'],
[str(bt), str(et)])
for photo in day_photos:
# since rangeQuery sorts the photos from the most current to the most early
# thus all the photos in the List "photos" are sorted by their created time from
# the most current to the most early
photos.append(photo)
event = Event()
event.setPhotos(photos)
event.setRegion(self._event['region'])
event.setActualValue(event.getActualValueByCounting())
event = EventFeature(event)
# compute the difference between entropy
# this has been smoothed
pro1 = self._divideAndCount(entropy_para)
pro2 = event._divideAndCount(entropy_para)
entropy_divergence = KLDivergence.averageKLDivergence(pro1, pro2)
# compute the difference between top words
event_topword_list = self._getTopWords(-1, True)
historic_topword_list = event._getTopWords(-1, True)
n_ind = 0
ind = {}
for word, freq in event_topword_list + historic_topword_list:
if not ind.has_key(word):
ind[word] = n_ind
n_ind += 1
freq1 = [0] * n_ind
freq2 = [0] * n_ind
for word, freq in event_topword_list:
freq1[ind[word]] = freq
for word, freq in historic_topword_list:
freq2[ind[word]] = freq
topic_divergence = KLDivergence.averageKLDivergence(freq1, freq2)
return [
event.getAvgPhotoDis(),
topic_divergence,
# event.getEntropy(entropy_para),
entropy_divergence,
event.getAvgCaptionLen(),
event.getRatioOfPeopleToPhoto()
]
def filterRegions(self,
region_list,
percentage=InstagramConfig.region_percentage,
test=False,
n=10,
m=10):
if test:
#n and m should be set if test is true
#this is only for test
new_region_list = []
folder = '/res/users/kx19/Citybeat/CityBeat/distributed_gp/utility/region_cache/'
file_name = str(n) + '_' + str(m) + '.txt'
fid = open(folder + file_name)
for line in fid:
region = line.split()
for i in xrange(0, 4):
region[i] = float(region[i])
region = Region(region)
new_region_list.append(region)
return new_region_list
# this method should not be a member of this class
# TODO: change the period to one week
# print 'Begin to filter sparse regions with less photos than the threshold'
end_time = 1359704845 - 7 * 3600 * 24
begin_time = end_time - 14 * 3600 * 24
pi = PhotoInterface()
photos = pi.rangeQuery(period=[str(begin_time), str(end_time)])
region_number = len(region_list)
number_photo_in_region = [0] * region_number
for photo in photos:
lat = float(photo['location']['latitude'])
lng = float(photo['location']['longitude'])
flag = 0
for i in xrange(region_number):
if region_list[i].insideRegion([lat, lng]):
number_photo_in_region[i] += 1
flag = 1
break
if flag == 0:
print 'bad photo:', photo
region_tuples = []
for i in xrange(0, region_number):
region_tuples.append((region_list[i], number_photo_in_region[i]))
region_tuples.sort(key=operator.itemgetter(1), reverse=True)
valid_region_number = int(0.5 + 1.0 * region_number * percentage)
valid_regions = []
# print region_tuples[valid_region_number-1][1]
for i in xrange(0, valid_region_number):
region = region_tuples[i][0]
lat = (self._region['min_lat'] + self._region['max_lat']) / 2
lng = (self._region['min_lng'] + self._region['max_lng']) / 2
cnt = region_tuples[i][1]
for i in xrange(0, valid_region_number):
valid_regions.append(region_tuples[i][0])
return valid_regions
valid_region_number = int(0.5 + 1.0 * region_number * percentage)
valid_regions = []
# print region_tuples[valid_region_number-1][1]
for i in xrange(0, valid_region_number):
region = region_tuples[i][0]
lat = (self._region['min_lat'] + self._region['max_lat']) / 2
lng = (self._region['min_lng'] + self._region['max_lng']) / 2
cnt = region_tuples[i][1]
for i in xrange(0, valid_region_number):
valid_regions.append(region_tuples[i][0])
return valid_regions
if __name__ == "__main__":
coordinates = [
InstagramConfig.photo_min_lat, InstagramConfig.photo_min_lng,
InstagramConfig.photo_max_lat, InstagramConfig.photo_max_lng
]
nyc = Region(coordinates)
pi = PhotoInterface()
pi.rangeQuery(nyc)
region_list = nyc.divideRegions(20, 20)
region_list = nyc.filterRegions(region_list, test=True, n=10, m=10)
for region in region_list:
region = region.toJSON()
print region['min_lat'], region['min_lng'], region['max_lat'], region[
'max_lng']
