def sample(graphs):
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
))
def sample(graphs):
sampler = GraphLearnSampler()
graphs, graphs_ = itertools.tee(graphs)
sampler.fit(graphs)
return unpack(
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,
)
)
for perc in percentages:
# we work with count many graphs
count = int(lenpo*perc)
# make copy of graphiterator
# select count random elements
# triplicate the count long iterator
graphs_pos, graphs_pos_ = itertools.tee(graphs_pos)
x=range(count)
random.shuffle(x)
graphs_pos_ = picker(graphs_pos_, x )
graphs_pos_,graphs_pos__,graphs_pos___ = itertools.tee(graphs_pos_,3)
# do sampling
sampler.fit(graphs_pos__, grammar_n_jobs=4)
improved_graphs = sampler.sample(graphs_pos_,
same_radius=False,
max_size_diff=True,
sampling_interval=9999,
select_cip_max_tries=100,
batch_size=int(count/4)+1,
n_steps=100,
n_jobs=-1,
improving_threshold=0.9)
#calculate the score of the improved versions
#calculate score of the originals
for perc in percentages:
# we work with count many graphs
count = int(lenpo*perc)
# make copy of graphiterator
# select count random elements
# triplicate the count long iterator
graphs_pos, graphs_pos_ = itertools.tee(graphs_pos)
x=range(count)
random.shuffle(x)
graphs_pos_ = picker(graphs_pos_, x )
graphs_pos_,graphs_pos__,graphs_pos___ = itertools.tee(graphs_pos_,3)
# do sampling
sampler.fit(graphs_pos__, grammar_n_jobs=4)
improved_graphs = sampler.transform(graphs_pos_,
same_radius=False,
size_constrained_core_choice=True,
sampling_interval=9999,
select_cip_max_tries=100,
batch_size=int(count/4)+1,
n_steps=100,
n_jobs=-1,
improving_threshold=0.9)
#calculate the score of the improved versions
#calculate score of the originals
