def setup(self, known_graphs=None, candidate_graphs=None):
"""Setup."""
# compute the nearest neighbors for the 'proposal_graphs' w.r.t. the
# known graphs in the list 'known_graphs'
parameters_priors = dict(n_neighbors=self.n_neighbors)
parameters_priors.update(dict(vectorizer__complexity=self.complexity,
vectorize__n_jobs=-1,
vectorize__fit_flag=False,
vectorize__n_blocks=5,
vectorize__block_size=100))
fit_wrapped_knn_predictor_known = \
model(known_graphs,
program=KNNWrapper(program=NearestNeighbors()),
parameters_priors=parameters_priors)
# compute distances of candidate_graphs to known_graphs
knn_candidate_graphs = predict(candidate_graphs,
program=fit_wrapped_knn_predictor_known)
knn_candidate_graphs = list(knn_candidate_graphs)
self.distances_to_known_graphs = []
for knn_candidate_graph in knn_candidate_graphs:
distances = knn_candidate_graph.graph['distances']
self.distances_to_known_graphs.append(distances)
# compute candidate_graphs encodings
self.candidate_graphs_data_matrix = \
vectorize(candidate_graphs,
vectorizer=Vectorizer(complexity=self.complexity),
block_size=400, n_jobs=-1)
def setup(self, known_graphs=None, candidate_graphs=None):
"""Setup."""
# compute the nearest neighbors for the 'proposal_graphs' w.r.t. the
# known graphs in the list 'known_graphs'
parameters_priors = dict(n_neighbors=self.n_neighbors)
parameters_priors.update(dict(vectorizer__complexity=self.complexity,
vectorize__n_jobs=-1,
vectorize__fit_flag=False,
vectorize__n_blocks=5,
vectorize__block_size=100))
fit_wrapped_knn_predictor_known = \
model(known_graphs,
program=KNNWrapper(program=NearestNeighbors()),
parameters_priors=parameters_priors)
# compute distances of candidate_graphs to known_graphs
knn_candidate_graphs = predict(candidate_graphs,
program=fit_wrapped_knn_predictor_known)
knn_candidate_graphs = list(knn_candidate_graphs)
self.distances_to_known_graphs = []
for knn_candidate_graph in knn_candidate_graphs:
distances = knn_candidate_graph.graph['distances']
self.distances_to_known_graphs.append(distances)
# compute candidate_graphs encodings
self.candidate_graphs_data_matrix = \
vectorize(candidate_graphs,
vectorizer=Vectorizer(complexity=self.complexity),
block_size=400, n_jobs=-1)
def setup(self, known_graphs=None, candidate_graphs=None):
"""Setup."""
# compute the nearest neighbors for the 'proposal_graphs' w.r.t. the
# known graphs in the list 'known_graphs'
parameters_priors = dict(n_neighbors=self.n_neighbors)
parameters_priors.update(dict(vectorizer__complexity=self.complexity,
vectorizer__discrete=True))
fit_wrapped_knn_predictor_known = \
model(known_graphs,
program=KNNWrapper(program=NearestNeighbors()),
parameters_priors=parameters_priors)
# compute distances of candidate_graphs to known_graphs
knn_candidate_graphs = predict(candidate_graphs,
program=fit_wrapped_knn_predictor_known)
knn_candidate_graphs = list(knn_candidate_graphs)
self.distances_to_known_graphs = []
for knn_candidate_graph in knn_candidate_graphs:
distances = knn_candidate_graph.graph['distances']
self.distances_to_known_graphs.append(distances)
# compute candidate_graphs encodings
vec = Vectorizer(complexity=self.complexity)
self.candidate_graphs_data_matrix = vec.transform(candidate_graphs)
def setup(self, known_graphs=None, candidate_graphs=None):
"""Setup."""
# compute the nearest neighbors for the 'proposal_graphs' w.r.t. the
# known graphs in the list 'known_graphs'
parameters_priors = dict(n_neighbors=self.n_neighbors)
parameters_priors.update(
dict(vectorizer__complexity=self.complexity,
vectorizer__discrete=True))
fit_wrapped_knn_predictor_known = \
model(known_graphs,
program=KNNWrapper(program=NearestNeighbors()),
parameters_priors=parameters_priors)
# compute distances of candidate_graphs to known_graphs
knn_candidate_graphs = predict(candidate_graphs,
program=fit_wrapped_knn_predictor_known)
knn_candidate_graphs = list(knn_candidate_graphs)
self.distances_to_known_graphs = []
for knn_candidate_graph in knn_candidate_graphs:
distances = knn_candidate_graph.graph['distances']
self.distances_to_known_graphs.append(distances)
# compute candidate_graphs encodings
vec = Vectorizer(complexity=self.complexity)
self.candidate_graphs_data_matrix = vec.transform(candidate_graphs)
def efficient_selection(self,
candidate_graphs,
known_graphs=None):
"""Propose a small number of alternative structures.
Parameters
----------
candidate_graphs : networkx graphs
The iterator over the seed graphs, i.e. the graphs that are used
as a starting point for the proposal.
known_graphs : networkx graphs
The iterator over the already known graphs. These are used to bias
the exploration towards less similar proposals.
"""
start = time.time()
candidate_graphs = transform(
candidate_graphs,
program=AnnotateImportance(
program=self.fit_wrapped_predictor.program))
candidate_graphs = list(candidate_graphs)
# transform graphs according to importance
# this allows similarity notion to be task dependent
known_graphs = transform(
known_graphs,
program=AnnotateImportance(
program=self.fit_wrapped_predictor.program))
known_graphs = list(known_graphs)
# store the nearest neighbors in knn_manager
# compute the k nearest neighbors distances of each proposal graph
knn_manager = KNNManager(n_neighbors=self.n_neighbors, complexity=3)
knn_manager.setup(known_graphs=known_graphs,
candidate_graphs=candidate_graphs)
delta_time = datetime.timedelta(seconds=(time.time() - start))
logger.info('Knn computation took: %s' % (str(delta_time)))
# compute predictions
predicted_graphs = predict(candidate_graphs,
program=self.fit_wrapped_predictor)
predicted_graphs = list(predicted_graphs)
scores = np.array([graph.graph['score']
for graph in predicted_graphs]).reshape(-1, 1)
# iterations
tradeoff = self.exploration_vs_exploitation_tradeoff
selection_ids = []
for i in range(self.n_proposals):
uncertainties = knn_manager.average_distances()
# run the acquisition function (n_proposals times)
# and return best_id
maximal_id = self._acquisition(
scores,
uncertainties,
exploration_vs_exploitation_tradeoff=tradeoff)
# update distances with new selection
knn_manager.add_element(maximal_id)
# store id
selection_ids.append(maximal_id)
graph = candidate_graphs[maximal_id]
logger.debug('>%s' % graph.graph['header'])
logger.debug(graph.graph['sequence'])
return selection_ids
def efficient_selection(self,
candidate_graphs,
known_graphs=None):
"""Propose a small number of alternative structures.
Parameters
----------
candidate_graphs : networkx graphs
The iterator over the seed graphs, i.e. the graphs that are used
as a starting point for the proposal.
known_graphs : networkx graphs
The iterator over the already known graphs. These are used to bias
the exploration towards less similar proposals.
"""
start = time.time()
candidate_graphs = transform(
candidate_graphs,
program=AnnotateImportance(
program=self.fit_wrapped_predictor.program))
candidate_graphs = list(candidate_graphs)
# transform graphs according to importance
# this allows similarity notion to be task dependent
known_graphs = transform(
known_graphs,
program=AnnotateImportance(
program=self.fit_wrapped_predictor.program))
known_graphs = list(known_graphs)
# store the nearest neighbors in knn_manager
# compute the k nearest neighbors distances of each proposal graph
knn_manager = KNNManager(n_neighbors=self.n_neighbors, complexity=3)
knn_manager.setup(known_graphs=known_graphs,
candidate_graphs=candidate_graphs)
delta_time = datetime.timedelta(seconds=(time.time() - start))
logger.info('Knn computation took: %s' % (str(delta_time)))
# compute predictions
predicted_graphs = predict(candidate_graphs,
program=self.fit_wrapped_predictor)
predicted_graphs = list(predicted_graphs)
scores = np.array([graph.graph['score']
for graph in predicted_graphs]).reshape(-1, 1)
# iterations
tradeoff = self.exploration_vs_exploitation_tradeoff
selection_ids = []
for i in range(self.n_proposals):
uncertainties = knn_manager.average_distances()
# run the acquisition function (n_proposals times)
# and return best_id
maximal_id = self._acquisition(
scores,
uncertainties,
exploration_vs_exploitation_tradeoff=tradeoff)
# update distances with new selection
knn_manager.add_element(maximal_id)
# store id
selection_ids.append(maximal_id)
graph = candidate_graphs[maximal_id]
logger.debug('>%s' % graph.graph['header'])
logger.debug(graph.graph['sequence'])
return selection_ids