# positive set contains 2401 elements, of which we use 30% to test of we cen improve them , # the rest is used for the oracle lenpo=int(2401*.3) # we select those 30% randomly: splitset= range(2014) random.shuffle(splitset) sample=splitset[:lenpo] oracle=splitset[lenpo:] path='../example/' # we create an oracle estimator=make_estimator(picker(gspan_to_eden(path+'bursi.pos.gspan'),oracle),gspan_to_eden(path+'bursi.neg.gspan')) print 'estimator ok' # ok we create an iterator over the graphs we want to work with... graphs_pos= picker( gspan_to_eden(path+'bursi.pos.gspan') , sample) # save results here: originals=[] improved=[] # we want to use an increasing part of the test set..
# how many graphs will be used for sampling?
count_pos = int(NUMPOS * 0.7 * perc)
count_neg = int(NUMNEG * 0.7 * perc)
# copy the mega set
graphs_pos, graphs_pos_, graphs_pos__ = itertools.tee(graphs_pos, 3)
graphs_neg, graphs_neg_, graphs_neg__ = itertools.tee(graphs_neg, 3)
# create a shuffeld list of graph ids
pos_id = range(NUMPOS)
neg_id = range(NUMNEG)
random.shuffle(pos_id)
random.shuffle(neg_id)
# use shuffled list to create test and sample set
pos, pos_ = itertools.tee(picker(graphs_pos_, pos_id[:count_pos]))
neg, neg_ = itertools.tee(picker(graphs_neg_, neg_id[:count_neg]))
postest = picker(graphs_pos__, pos_id[count_pos : int(NUMPOS * 0.3)])
negtest = picker(graphs_neg__, neg_id[count_neg : int(NUMNEG * 0.3)])
############### then we sample #####################
improved_neg = sample(neg)
improved_pos = sample(pos)
######### and last we evaluate ###########
print "evaluating.."
imp, ori = train_estimator_and_evaluate_testsets(pos_, neg_, improved_pos, improved_neg, postest, negtest)
improved.append(imp)
originals.append(ori)
print "done:" + str(perc)
print "*" * 80
# positive set contains 2401 elements, of which we use 30% to test of we cen improve them , # the rest is used for the oracle lenpo=int(2401*.3) # we select those 30% randomly: splitset= range(2014) random.shuffle(splitset) sample=splitset[:lenpo] oracle=splitset[lenpo:] path='../example/' # we create an oracle estimator=make_estimator(picker(gspan_to_eden(path+'bursi.pos.gspan'),oracle),gspan_to_eden(path+'bursi.neg.gspan')) print 'estimator ok' # ok we create an iterator over the graphs we want to work with... graphs_pos= picker( gspan_to_eden(path+'bursi.pos.gspan') , sample) # save results here: originals=[] improved=[] # we want to use an increasing part of the test set..
# how many graphs will be used for sampling?
count_pos = int(NUMPOS*.7*perc)
count_neg = int(NUMNEG*.7*perc)
# copy the mega set
graphs_pos, graphs_pos_, graphs_pos__ = itertools.tee(graphs_pos,3)
graphs_neg, graphs_neg_ , graphs_neg__= itertools.tee(graphs_neg,3)
#create a shuffeld list of graph ids
pos_id = range(NUMPOS)
neg_id = range(NUMNEG)
random.shuffle(pos_id)
random.shuffle(neg_id)
# use shuffled list to create test and sample set
pos,pos_ = itertools.tee( picker(graphs_pos_,pos_id[:count_pos]) )
neg,neg_ = itertools.tee( picker (graphs_neg_,neg_id[:count_neg]))
postest = picker(graphs_pos__,pos_id[count_pos:int(NUMPOS*.3)])
negtest = picker(graphs_neg__,neg_id[count_neg:int(NUMNEG*.3)])
############### then we sample #####################
improved_neg= sample(neg)
improved_pos= sample(pos)
######### and last we evaluate ###########
print 'evaluating..'
imp,ori=train_estimator_and_evaluate_testsets( pos_,neg_,improved_pos, improved_neg, postest,negtest)
improved.append(imp)