def fit(self, graphs):
"""fit."""
try:
# make matrix
data_matrix = vectorize(graphs,
vectorizer=self.vectorizer,
**self.params_vectorize)
data_matrix_neg = data_matrix.multiply(-1)
data_matrix_both = vstack([data_matrix, data_matrix_neg], format="csr")
# make labels
length = data_matrix.shape[0]
y = [-1] * length + [1] * length
y = np.ravel(y)
# fit:
estimator = self.program.fit(data_matrix_both, y)
# moving intercept:
scores = [estimator.decision_function(sparse_vector)[0]
for sparse_vector in data_matrix]
scores_sorted = sorted(scores)
pivot = scores_sorted[int(len(scores_sorted) * self.nu)]
estimator.intercept_ -= pivot
# calibration:
data_y = np.asarray([1 if score >= pivot else -1 for score in scores])
self.program = CalibratedClassifierCV(estimator, method='sigmoid')
self.program.fit(data_matrix, data_y)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def fit(self, graphs):
"""fit."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
y = self._extract_targets(graphs)
# manage case for single class learning
if len(set(y)) == 1:
# make negative data matrix
negative_data_matrix = data_matrix.multiply(-1)
# make targets
y = list(y)
y_neg = [-1] * len(y)
# concatenate elements
data_matrix = vstack([data_matrix, negative_data_matrix],
format="csr")
y = y + y_neg
y = np.ravel(y)
self.program = self.program.fit(data_matrix, y)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
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 fit(self, graphs):
"""fit."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
y = self._extract_targets(graphs)
# manage case for single class learning
if len(set(y)) == 1:
# make negative data matrix
negative_data_matrix = data_matrix.multiply(-1)
# make targets
y = list(y)
y_neg = [-1] * len(y)
# concatenate elements
data_matrix = vstack(
[data_matrix, negative_data_matrix], format="csr")
y = y + y_neg
y = np.ravel(y)
self.program = self.program.fit(data_matrix, y)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
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 _cluster(self, seqs, clustering_algorithm=None):
data_matrix = vectorize(seqs,
vectorizer=self.seq_vectorizer,
n_blocks=self.n_blocks,
block_size=self.block_size,
n_jobs=self.n_jobs)
predictions = clustering_algorithm.fit_predict(data_matrix)
# collect instance ids per cluster id
for i in range(len(predictions)):
self.clusters[predictions[i]] += [i]
def _cluster(self, seqs, clustering_algorithm=None):
data_matrix = vectorize(seqs,
vectorizer=self.seq_vectorizer,
n_blocks=self.n_blocks,
block_size=self.block_size,
n_jobs=self.n_jobs)
predictions = clustering_algorithm.fit_predict(data_matrix)
# collect instance ids per cluster id
for i in range(len(predictions)):
self.clusters[predictions[i]] += [i]
def fit(self, graphs):
"""fit."""
try:
self.graphs = list(graphs)
data_matrix = vectorize(self.graphs, vectorizer=self.vectorizer, **self.params_vectorize)
self.program = self.program.fit(data_matrix)
return self
except Exception as e:
logger.debug("Failed iteration. Reason: %s" % e)
logger.debug("Exception", exc_info=True)
def fit(self, graphs):
"""fit."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_, vectorizer=self.vectorizer, **self.params_vectorize)
y = self._extract_targets(graphs)
self.program = self.program.fit(data_matrix, y)
return self
except Exception as e:
logger.debug("Failed iteration. Reason: %s" % e)
logger.debug("Exception", exc_info=True)
def fit_predict(self, graphs):
"""fit_predict."""
try:
data_matrix = vectorize(graphs,
vectorizer=self.vectorizer,
**self.params_vectorize)
predictions = self.program.fit_predict(data_matrix)
return predictions
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def fit(self, graphs):
"""fit."""
try:
self.graphs = list(graphs)
data_matrix = vectorize(self.graphs,
vectorizer=self.vectorizer,
**self.params_vectorize)
self.program = self.program.fit(data_matrix)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def decision_function(self, graphs):
"""decision_function."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
scores = self.program.decision_function(data_matrix)
return scores
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def decision_function(self, graphs):
"""decision_function."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
scores = self.program.decision_function(data_matrix)
return scores
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def predict(self, graphs):
"""predict."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_, vectorizer=self.vectorizer, **self.params_vectorize)
predictions = self.program.predict(data_matrix)
for prediction, graph in izip(predictions, graphs):
graph.graph["prediction"] = prediction
graph.graph["score"] = prediction
yield graph
except Exception as e:
logger.debug("Failed iteration. Reason: %s" % e)
logger.debug("Exception", exc_info=True)
def fit(self, graphs):
"""fit."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
y = self._extract_targets(graphs)
self.program = self.program.fit(data_matrix, y)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def _data_matrix(self, iterable, fit_vectorizer=False):
assert(is_iterable(iterable)), 'Not iterable'
graphs = mp_pre_process(iterable,
pre_processor=self.pre_processor,
pre_processor_args=self.pre_processor_args,
n_blocks=self.pre_processor_n_blocks,
block_size=self.pre_processor_block_size,
n_jobs=self.pre_processor_n_jobs)
graphs, graphs_ = tee(graphs)
self.vectorizer.set_params(**self.vectorizer_args)
if fit_vectorizer:
self.vectorizer.fit(graphs_)
X = vectorize(graphs, vectorizer=self.vectorizer, n_jobs=self.n_jobs, n_blocks=self.n_blocks)
return X
def predict(self, graphs):
"""predict."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_, vectorizer=self.vectorizer, **self.params_vectorize)
distances, indices = self.program.kneighbors(data_matrix)
for knn_ids, graph in izip(indices, graphs):
neighbor_graphs = []
for knn_id in knn_ids:
neighbor_graphs.append(self.graphs[knn_id])
graph.graph["neighbors"] = neighbor_graphs
yield graph
except Exception as e:
logger.debug("Failed iteration. Reason: %s" % e)
logger.debug("Exception", exc_info=True)
def predict(self, graphs):
"""predict."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
predictions = self.program.predict(data_matrix)
for prediction, graph in izip(predictions, graphs):
graph.graph['prediction'] = prediction
graph.graph['score'] = prediction
yield graph
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def seq_to_data_matrix(self, sequences=None):
# Transform sequences to matrix
graphs = mp_pre_process(sequences, pre_processor=self.pre_processor, pre_processor_args={}, n_jobs=-1)
seq_data_matrix = vectorize(graphs, vectorizer=self.vectorizer, n_jobs=-1)
# Densify the matrix
seq_data_matrx = seq_data_matrix.toarray()
# Standardize the matrix
self.scale.fit(seq_data_matrx)
std_seq_data_matrx = self.scale.transform(seq_data_matrx)
return std_seq_data_matrx
def predict(self, graphs):
"""predict."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
predictions = self.program.predict(data_matrix)
scores = self.program.decision_function(data_matrix)
for score, prediction, graph in izip(scores, predictions, graphs):
graph.graph['prediction'] = prediction
graph.graph['score'] = score
yield graph
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def predict(self, graphs):
"""predict."""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
distances, indices = self.program.kneighbors(data_matrix)
for knn_ids, graph in izip(indices, graphs):
neighbor_graphs = []
for knn_id in knn_ids:
neighbor_graphs.append(self.graphs[knn_id])
graph.graph['neighbors'] = neighbor_graphs
yield graph
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def predict(self, graphs):
"""predict.
only overwrite is this:
decision_function -> predict_proba
graph.graph['score'] will be a (len 2) list
"""
try:
graphs, graphs_ = tee(graphs)
data_matrix = vectorize(graphs_,
vectorizer=self.vectorizer,
**self.params_vectorize)
predictions = self.program.predict(data_matrix)
# scores = self.program.decision_function(data_matrix)
scores = self.program.predict_proba(data_matrix)
for score, prediction, graph in izip(scores, predictions, graphs):
graph.graph['prediction'] = prediction
graph.graph['score'] = score
yield graph
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
def fit(self, graphs):
"""fit."""
try:
# make matrix
data_matrix = vectorize(graphs,
vectorizer=self.vectorizer,
**self.params_vectorize)
data_matrix_neg = data_matrix.multiply(-1)
data_matrix_both = vstack([data_matrix, data_matrix_neg],
format="csr")
# make labels
length = data_matrix.shape[0]
y = [-1] * length + [1] * length
y = np.ravel(y)
# fit:
estimator = self.program.fit(data_matrix_both, y)
# moving intercept:
scores = [
estimator.decision_function(sparse_vector)[0]
for sparse_vector in data_matrix
]
scores_sorted = sorted(scores)
pivot = scores_sorted[int(len(scores_sorted) * self.nu)]
estimator.intercept_ -= pivot
# calibration:
data_y = np.asarray(
[1 if score >= pivot else -1 for score in scores])
self.program = CalibratedClassifierCV(estimator, method='sigmoid')
self.program.fit(data_matrix, data_y)
return self
except Exception as e:
logger.debug('Failed iteration. Reason: %s' % e)
logger.debug('Exception', exc_info=True)
