def getgraphs(aid):
if aid == 'bursi':
return list(gspan.gspan_to_eden("bursi.pos.gspan")), list(
gspan.gspan_to_eden("bursi.neg.gspan"))
download_active = curry(download)(active=True, stepsize=50)
download_inactive = curry(download)(active=False, stepsize=50)
active = pipe(aid, download_active, sdf_to_nx, list)
inactive = pipe(aid, download_inactive, sdf_to_nx, list)
return active, inactive
def bursi_get_extremes(num=200):
po, ne = list(gspan.gspan_to_eden("bursi.pos.gspan")), list(
gspan.gspan_to_eden("bursi.neg.gspan"))
X, y = graphs_to_Xy(po, ne)
esti = SGDClassifier(average=True,
class_weight='balanced',
shuffle=True,
n_jobs=4,
loss='log')
esti.fit(X, y)
res = [(score, idd)
for idd, score in enumerate(esti.decision_function(X))] # list
res.sort()
graphs = po + ne
# returns pos/neg
return [graphs[idd] for (score, idd) in res[0 - num:]
], [graphs[idd] for (score, idd) in res[:num]]
exit()
print "*raw args"
print "*" * 80
print args
# verbosity
from eden.util import configure_logging
import logging
configure_logging(logging.getLogger(),verbosity=args['verbose'])
args.pop('verbose')
# graphs
from eden.io.gspan import gspan_to_eden
from itertools import islice
args['graph_iter'] = islice(gspan_to_eden(args.pop('start_graphs')),args.pop('num_graphs'))
#output
OUTFILE=args.pop('out')
MODEL=args.pop('model')
# CREATE SAMPLER
from graphlearn01.graphlearn import Sampler
s=Sampler()
s.load(MODEL)
results=s.transform(**args)
import graphlearn01.utils.draw_openbabel as ob
exit()
print "*raw args"
print "*" * 80
print args
# verbosity
from eden.util import configure_logging
import logging
configure_logging(logging.getLogger(), verbosity=args['verbose'])
args.pop('verbose')
# graphs
from eden.io.gspan import gspan_to_eden
from itertools import islice
args['graph_iter'] = islice(gspan_to_eden(args.pop('start_graphs')),
args.pop('num_graphs'))
#output
OUTFILE = args.pop('out')
MODEL = args.pop('model')
# CREATE SAMPLER
from graphlearn01.graphlearn import Sampler
s = Sampler()
s.load(MODEL)
results = s.transform(**args)
import graphlearn01.utils.draw_openbabel as ob
for i, samplepath in enumerate(results):
# estimator, if the user is providing a negative graph set, we use
# the twoclass esti OO
import graphlearn01.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.io.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 graphlearn01.graphlearn import Sampler
def get_graphs(dataset_fname='../../toolsdata/bursi.pos.gspan', size=100):
return list(islice(gspan_to_eden(dataset_fname), size))