def fit(self, graphs, targets, randomize=True):
"""fit."""
if self.balance:
if randomize:
bal_graphs, bal_targets = balance(graphs,
targets,
None,
ratio=self.ratio)
else:
samp_graphs, samp_targets = subsample(
graphs, targets, subsample_size=self.subsample_size)
x = self.transform(samp_graphs)
self.model.fit(x, samp_targets)
bal_graphs, bal_targets = balance(graphs,
targets,
self,
ratio=self.ratio)
size = len(bal_targets)
logger.debug('Dataset size=%d' % (size))
x = self.transform(bal_graphs)
self.model = self.model.fit(x, bal_targets)
else:
x = self.transform(graphs)
self.model = self.model.fit(x, targets)
return self
def model_selection(self, graphs, targets,
n_iter=30, subsample_size=None):
"""model_selection_randomized."""
param_distr = {"r": list(range(1, 5)), "d": list(range(0, 10))}
if subsample_size:
graphs, targets = subsample(
graphs, targets, subsample_size=subsample_size)
pool = mp.Pool()
scores = pool.map(_eval, [(graphs, targets, param_distr)] * n_iter)
pool.close()
pool.join()
best_params = max(scores)[1]
logger.debug("Best parameters:\n%s" % (best_params))
self = EdenEstimator(**best_params)
return self
def model_selection(self, graphs, targets,
n_iter=30, subsample_size=None):
"""model_selection_randomized."""
param_distr = {"r": list(range(1, 5)), "d": list(range(0, 10))}
if subsample_size:
graphs, targets = subsample(
graphs, targets, subsample_size=subsample_size)
pool = mp.Pool()
scores = pool.map(_eval, [(graphs, targets, param_distr)] * n_iter)
pool.close()
pool.join()
best_params = max(scores)[1]
logger.debug("Best parameters:\n%s" % (best_params))
self = EdenEstimator(**best_params)
return self
def fit(self, graphs, targets, randomize=True):
"""fit."""
if self.balance:
if randomize:
bal_graphs, bal_targets = balance(
graphs, targets, None, ratio=self.ratio)
else:
samp_graphs, samp_targets = subsample(
graphs, targets, subsample_size=self.subsample_size)
x = self.transform(samp_graphs)
self.model.fit(x, samp_targets)
bal_graphs, bal_targets = balance(
graphs, targets, self, ratio=self.ratio)
size = len(bal_targets)
logger.debug('Dataset size=%d' % (size))
x = self.transform(bal_graphs)
self.model = self.model.fit(x, bal_targets)
else:
x = self.transform(graphs)
self.model = self.model.fit(x, targets)
return self
