def getEvidenceByTopic(request):
if request.method == 'POST':
data = json.loads(request.body)
print data
collection_id = data['collection_id']
topic_id = data['topic_id']
user_id = data['user_id']
evidence = Evidence.objects.filter(Q(evidencetopic__created_by=collection_id)&Q(evidencetopic__primary_topic=topic_id)).order_by('-evidencetopic__primary_topic_prob').distinct()[:500]
evidenceBookmarks = EvidenceBookmark.objects.filter(user_id=user_id)
evidencePersonal = Evidence.objects.filter(Q(created_by=user_id))
serialized_json = serializers.serialize('json', evidence)
evidence_json = flattenSerializedJson(serialized_json)
serialized_json = serializers.serialize('json', evidenceBookmarks)
evidenceBookmark_json = flattenSerializedJson(serialized_json)
serialized_json = serializers.serialize('json', evidencePersonal)
evidencePersonal_json = flattenSerializedJson(serialized_json)
evidencePersonal = json.loads(evidencePersonal_json)
output = {}
output['evidencePersonal'] = []
for e in evidencePersonal:
if len(e['abstract']) > 50:
name = Collection.objects.get(collection_id=collection_id).collection_name
topic_dist, primary_topic_terms = TopicModeler.get_document_topics(e['abstract'], name)
primary_topic_tuple = max(topic_dist, key=lambda x:x[1])
this_topic = primary_topic_tuple[0]
if this_topic == topic_id:
output['evidencePersonal'].append(e)
output['evidence'] = json.loads(evidence_json)
output['evidenceBookmarks'] = json.loads(evidenceBookmark_json)
return HttpResponse(json.dumps(output), status=status.HTTP_200_OK)
def searchEvidenceByTitle(request):
if request.method == 'POST':
data = json.loads(request.body)
collection_id = data['collection_id']
title = data['title']
result_limit = data['result_limit']
include_personal = data['include_personal']
user_id = data['user_id']
# DONE: we can alternatively change this to treat given title as a series of separated terms
title_terms = title.split(' ')
print title_terms
evidence = Evidence.objects.filter(Q(created_by=collection_id)&reduce(lambda x, y: x & y, [Q(title__icontains=word) for word in title_terms]))
if include_personal:
personal_evidence = Evidence.objects.filter(Q(created_by=user_id)&reduce(lambda x, y: x & y, [Q(title__icontains=word) for word in title_terms]))
evidence = chain(evidence, personal_evidence)
serialized_json = serializers.serialize('json', evidence)
evidence_json = flattenSerializedJson(serialized_json)
evidence = json.loads(evidence_json)
pprint.pprint(evidence)
for e in evidence:
e['dist'] = edit_distance(title, e['title'])
print 'result limit'
print result_limit
evidence = sorted(evidence, key=lambda e:e['dist'])[:result_limit]
for e in evidence:
e['topic'] = -1
try:
e['topic'] = EvidenceTopic.objects.get(evidence=e['id']).primary_topic
except ObjectDoesNotExist:
if len(e['abstract']) > 50:
name = Collection.objects.get(collection_id=collection_id).collection_name
topic_dist, primary_topic_terms = TopicModeler.get_document_topics(e['abstract'], name)
primary_topic_tuple = max(topic_dist, key=lambda x:x[1])
e['topic'] = primary_topic_tuple[0]
else:
print 'warning: evidence with no topic'
return HttpResponse(json.dumps(evidence), status=status.HTTP_200_OK)
elif request.method == 'GET':
collection_id = 13
title = 'UpSet: Visualization of Intersecting Sets'
evidence = Evidence.objects.filter(created_by=collection_id)
serialized_json = serializers.serialize('json', evidence)
evidence_json = flattenSerializedJson(serialized_json)
evidence = json.loads(evidence_json)
for e in evidence:
e['dist'] = edit_distance(title, e['title'])
evidence = sorted(evidence, key=lambda e:e['dist'])
return HttpResponse(json.dumps(evidence[:20]), status=status.HTTP_200_OK)
def getEvidenceRecommendation(request):
if request.method == 'POST':
data = json.loads(request.body)
# data = {}
# data['text'] = 'Using brain imaging in humans, we showed that the lateral PFC is organized as a cascade of executive processes from premotor to anterior PFC regions that control behavior according to stimuli, the present perceptual context, and the temporal episode in which stimuli occur, respectively.'
collection_id = int(data['collectionId'])
name = Collection.objects.get(collection_id=collection_id).collection_name
topic_dist, primary_topic_terms = TopicModeler.get_document_topics(data['text'], name)
if len(topic_dist) > 0:
primary_topic_tuple = max(topic_dist, key=lambda x:x[1])
else:
primary_topic_tuple = ('', 0)
output = {}
output['topics'] = [{}]
output['topics'][0]['terms'] = primary_topic_terms
output['topics'][0]['prob'] = primary_topic_tuple[1]
# evidence = getEvidenceRecommendationAcrossTopics(topic_dist, name)
output['evidence'] = getEvidenceRecommendationWithinTopics(topic_dist, name, collection_id)[:100]
return HttpResponse(json.dumps(output), status=status.HTTP_200_OK)
