def addEvent(self, raw_event):
# do not call the method saveDocument, instead, call this method
# add an event to the db. raw_event can either be a json or an instance of Event
if not type(raw_event) is types.DictType:
new_event = raw_event.toJSON()
else:
new_event = raw_event
new_event = Event(new_event)
new_event.sortPhotos()
new_event = new_event.toJSON()
# before adding, find if any event can be merged
condition = {'region':new_event['region']}
# condition = {'lat':new_event['lat'], 'lng':new_event['lng']}
old_events = self.getAllDocuments(condition).sort('created_time', -1)
for old_event in old_events:
end_time1 = int(new_event['photos'][0]['created_time'])
begin_time1 = int(new_event['photos'][-1]['created_time'])
end_time2 = int(old_event['photos'][0]['created_time'])
begin_time2 = int(old_event['photos'][-1]['created_time'])
time_interval = InstagramConfig.merge_time_interval
if end_time1 + time_interval >= begin_time2 and end_time2 + time_interval >= begin_time1:
# if can merge
merged_event = Event(old_event)
merged = merged_event.mergeWith(new_event)
if merged >= 0:
print '%d out of %d photos are merged into an old event' % (merged, len(new_event['photos']))
# print old_event['_id'], new_event['_id']
if merged > 0:
self.updateDocument(merged_event)
return
# cannot merge
print 'create a new event'
super(EventInterface, self).saveDocument(new_event)
def __init__(self, vectorizer = None, db='AmazonMT', collection='candidate_event_25by25_merged'):
"""Given an event, return a list incices of the photos in 'photos' filed
which are representative to stands for this cluster
Could overwrite TfidfVectorizer as a parameter so that you could customize
your own tfidf parameters.
see http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html
"""
self.ei = EventInterface()
self.ei.setDB(db)
self.ei.setCollection(collection)
self.events = []
for e in self.ei.getAllDocuments():
event = Event(e)
event.selectOnePhotoForOneUser()
e = event.toJSON()
self.events.append(e)
#self.events = [e for e in self.ei.getAllDocuments()]
self._captions = self._getAllCaptions()
if vectorizer is None:
self.vectorizer = TfidfVectorizer( max_df=0.05, min_df = 1, strip_accents='ascii', smooth_idf=True, preprocessor = self._preProcessor, sublinear_tf=True, norm = 'l2', analyzer='char_wb', ngram_range=(4,4), stop_words = 'english')
else:
self.vectorizer = vectorizer
self.vectorizer.fit_transform(self._captions)
def addEvent(self, raw_event):
# do not call the method saveDocument, instead, call this method
# add an event to the db. raw_event can either be a json or an instance of Event
if not type(raw_event) is types.DictType:
new_event = raw_event.toJSON()
else:
new_event = raw_event
new_event = Event(new_event)
new_event.sortPhotos()
new_event = new_event.toJSON()
# before adding, find if any event can be merged
region = new_event['region']
condition = ({
'region.min_lat': region['min_lat'],
'region.min_lng': region['min_lng'],
'region.max_lat': region['max_lat'],
'region.max_lng': region['max_lng']
})
# condition = {'region.' + k:v for k,v in region.items()}
old_events = self.getAllDocuments(condition).sort('created_time', -1)
# print 'condition1:', condition
# print 'results1:',
# for oe in old_events:
# print '**************'
# condition = {'region':new_event['region']}
# old_events = self.getAllDocuments(condition).sort('created_time', -1)
# print 'condition2:', condition
# print 'results2:',
# for oe in old_events:
# print '**************'
for old_event in old_events:
end_time1 = int(new_event['photos'][0]['created_time'])
begin_time1 = int(new_event['photos'][-1]['created_time'])
end_time2 = int(old_event['photos'][0]['created_time'])
begin_time2 = int(old_event['photos'][-1]['created_time'])
time_interval = InstagramConfig.merge_time_interval
# print 'new: ',end_time1,begin_time1
# print 'old: ',end_time2,begin_time2
if end_time1 + time_interval >= begin_time2 and end_time2 + time_interval >= begin_time1:
# if can merge
merged_event = Event(old_event)
merged = merged_event.mergeWith(new_event)
if merged >= 0:
print '%d out of %d photos are merged into an old event' % (
merged, len(new_event['photos']))
# print old_event['_id'], new_event['_id']
if merged > 0:
self.updateDocument(merged_event)
return
# cannot merge
print 'create a new event'
super(EventInterface, self).saveDocument(new_event)
def addEvent(self, raw_event):
# do not call the method saveDocument, instead, call this method
# add an event to the db. raw_event can either be a json or an instance of Event
if not type(raw_event) is types.DictType:
new_event = raw_event.toJSON()
else:
new_event = raw_event
new_event = Event(new_event)
new_event.sortPhotos()
new_event = new_event.toJSON()
# before adding, find if any event can be merged
region = new_event['region']
condition = ({'region.min_lat':region['min_lat'],
'region.min_lng':region['min_lng'],
'region.max_lat':region['max_lat'],
'region.max_lng':region['max_lng']})
# condition = {'region.' + k:v for k,v in region.items()}
old_events = self.getAllDocuments(condition).sort('created_time', -1)
# print 'condition1:', condition
# print 'results1:',
# for oe in old_events:
# print '**************'
# condition = {'region':new_event['region']}
# old_events = self.getAllDocuments(condition).sort('created_time', -1)
# print 'condition2:', condition
# print 'results2:',
# for oe in old_events:
# print '**************'
for old_event in old_events:
end_time1 = int(new_event['photos'][0]['created_time'])
begin_time1 = int(new_event['photos'][-1]['created_time'])
end_time2 = int(old_event['photos'][0]['created_time'])
begin_time2 = int(old_event['photos'][-1]['created_time'])
time_interval = InstagramConfig.merge_time_interval
# print 'new: ',end_time1,begin_time1
# print 'old: ',end_time2,begin_time2
if end_time1 + time_interval >= begin_time2 and end_time2 + time_interval >= begin_time1:
# if can merge
merged_event = Event(old_event)
merged = merged_event.mergeWith(new_event)
if merged >= 0:
print '%d out of %d photos are merged into an old event' % (merged, len(new_event['photos']))
# print old_event['_id'], new_event['_id']
if merged > 0:
self.updateDocument(merged_event)
return
# cannot merge
print 'create a new event'
super(EventInterface, self).saveDocument(new_event)
def __init__(self, vectorizer=None, db="AmazonMT", collection="candidate_event_25by25_merged"):
"""Given an event, return a list incices of the photos in 'photos' filed
which are representative to stands for this cluster
Could overwrite TfidfVectorizer as a parameter so that you could customize
your own tfidf parameters.
see http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html
"""
self.ei = EventInterface()
self.ei.setDB(db)
self.ei.setCollection(collection)
self.events = []
for e in self.ei.getAllDocuments():
event = Event(e)
event.selectOnePhotoForOneUser()
e = event.toJSON()
self.events.append(e)
# self.events = [e for e in self.ei.getAllDocuments()]
self._captions = self._getAllCaptions()
if vectorizer is None:
self.vectorizer = TfidfVectorizer(
max_df=0.05,
min_df=1,
strip_accents="ascii",
smooth_idf=True,
preprocessor=self._preProcessor,
sublinear_tf=True,
norm="l2",
analyzer="char_wb",
ngram_range=(4, 4),
stop_words="english",
)
else:
self.vectorizer = vectorizer
self.vectorizer.fit_transform(self._captions)
def addEvent(self, raw_event):
# do not call the method saveDocument, instead, call this method
# add an event to the db. raw_event can either be a json or an instance of Event
if not type(raw_event) is types.DictType:
new_event = raw_event.toJSON()
else:
new_event = raw_event
new_event = Event(new_event)
new_event.sortPhotos()
new_event = new_event.toJSON()
# before adding, find if any event can be merged
condition = {'region': new_event['region']}
# condition = {'lat':new_event['lat'], 'lng':new_event['lng']}
old_events = self.getAllDocuments(condition).sort('created_time', -1)
for old_event in old_events:
end_time1 = int(new_event['photos'][0]['created_time'])
begin_time1 = int(new_event['photos'][-1]['created_time'])
end_time2 = int(old_event['photos'][0]['created_time'])
begin_time2 = int(old_event['photos'][-1]['created_time'])
time_interval = InstagramConfig.merge_time_interval
if end_time1 + time_interval >= begin_time2 and end_time2 + time_interval >= begin_time1:
# if can merge
merged_event = Event(old_event)
merged = merged_event.mergeWith(new_event)
if merged >= 0:
print '%d out of %d photos are merged into an old event' % (
merged, len(new_event['photos']))
# print old_event['_id'], new_event['_id']
if merged > 0:
self.updateDocument(merged_event)
return
# cannot merge
print 'create a new event'
super(EventInterface, self).saveDocument(new_event)
