def show_post(request,model_id,document_id):
""" Show a text analysis using a LdaModel """
ldamodel = get_object_or_404(LdaModel, pk = model_id)
document = get_object_or_404(Document, pk = document_id)
if not document.cleaned_content:
document.clean_content()
#Obtengo la prediccion en base al modelo y NBM
if ldamodel and ldamodel.stemming and d.steamed_content:
text = document.steamed_content
else:
text = document.cleaned_content
prediction = predict(ldamodel,text)
#Dejo como topics relevantes solo los mayores a un 10% de participacion
relevant_topics = cut(prediction,18)
#Preparo el output, una lista de nombres
relevant_topics = map(lambda (a,b,c,d): a.label,relevant_topics)
#Construyo un nuevo formato para la prediccion, adecuado para el template
prediction = dict(map(lambda (a,b,c,d):(a.id,b),prediction))
words = text.split(" ")
topics = Topic.objects.filter(active__exact = 1, ldamodel = ldamodel)
topicword = {}
print "Largo del texto %s" % len(words)
for topic in topics:
not_in_topic = 0
not_in_dic = 0
document_topic_score = int(math.ceil(Documenttopic.objects.filter(document = document).filter(topic = topic)[0].value*100))
topicword[topic.id] = {}
topicword[topic.id]['lda_score'] = document_topic_score
topicword[topic.id]['prediction_score'] = prediction[topic.id]
topicword[topic.id]['palabras'] = {}
topicword[topic.id]['name'] = topic.label
for w in words:
topicword[topic.id]['palabras'][w] = 0
try:
word = Word.objects.get(name__exact = w)
try:
topicw = Topicword.objects.get(topic = topic, word = word)
topicword[topic.id]['palabras'][w] = normTopicValue(topicw.value,True)
except Exception as e:
#print "Word %s not found in topic %s" % (w,topic.id)
not_in_topic += 1
except Exception:
#print "Word %s not found in dictionary" % w
not_in_dic += 1
#print topicword[topic.id]
print "Total de palabras no encontradas ",not_in_topic
print "% de palabras no encontradas en " + topic.label
print not_in_topic*100/len(words)
return render_to_response('application/post.tpl',
{'topicword':topicword.iteritems(),'documento':document,'prediction':relevant_topics,'model':ldamodel})
def classify(self,ldamodel,content,cut,value):
if not ldamodel or value < cut:
return []
else:
return [{'topic':topic.id,'topic_label':topic.label,'value':value,'quality':quality,'keywords':keywords,'subtopics':self.classify(self.getModel(topic),content,cut,value)} for (topic,value,quality,keywords) in predict(ldamodel,content)]
