# estimator, if the user is providing a negative graph set, we use
# the twoclass esti OO
import graphlearn.estimate as estimate
if args['negative_input']==None:
args['estimator']=estimate.OneClassEstimator(nu=.5, cv=2, n_jobs=-1)
else:
args['estimator']=estimate.TwoClassEstimator( cv=2, n_jobs=-1)
#args for fitting:
from eden.converter.graph.gspan import gspan_to_eden
from itertools import islice
fitargs={ k:args.pop(k) for k in ['lsgg_include_negatives','grammar_n_jobs','grammar_batch_size']}
if args['negative_input']!=None:
fitargs['negative_input'] = islice(gspan_to_eden(args.pop('negative_input')),args.pop('num_graphs_neg'))
else:
args.pop('negative_input')
args.pop('num_graphs_neg')
fitargs['input'] = islice(gspan_to_eden(args.pop('input')),args.pop('num_graphs'))
#output
OUTFILE=args.pop('output')
print "*Sampler init"
print "*"*80
print args
# CREATE SAMPLER, dumping the rest of the parsed args :)
from graphlearn.graphlearn import Sampler
# 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..
sampler.transform(
graphs_,
same_radius=False,
size_constrained_core_choice=False,
sampling_interval=9999,
select_cip_max_tries=100,
batch_size=30,
n_steps=100,
n_jobs=-1,
improving_threshold=0.9,
)
)
# initializing
graphs_pos = gspan_to_eden(path + "bursi.pos.gspan")
graphs_neg = gspan_to_eden(path + "bursi.neg.gspan")
originals = []
improved = []
percentages = [0.2, 0.4, 0.6, 0.8, 1]
for perc in percentages:
######### first we generate all the iterators ###########
# 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)
# 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..
sampler =GraphLearnSampler()
graphs, graphs_ = itertools.tee(graphs)
sampler.fit(graphs)
return unpack(sampler.sample(graphs_,
same_radius=False,
max_size_diff=False,
sampling_interval=9999,
select_cip_max_tries=100,
batch_size=30,
n_steps=100,
n_jobs=-1,
improving_threshold=0.9
))
# initializing
graphs_pos= gspan_to_eden(path+'bursi.pos.gspan')
graphs_neg= gspan_to_eden(path+'bursi.neg.gspan')
originals=[]
improved=[]
percentages=[.2,.4,.6,.8,1]
for perc in percentages:
######### first we generate all the iterators ###########
# 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)