def __init__(self,
graph: GraphSignalGraph,
obj: GraphSignalData,
node2id: Optional[Mapping[object, int]] = None):
"""Should **ALWAYS** instantiate graph signals with the method to_signal,
which handles non-instantiation semantics."""
self.graph = graph
self.node2id = {v: i
for i, v in enumerate(graph)
} if node2id is None else node2id
if backend.is_array(obj):
if backend.length(graph) != backend.length(obj):
raise Exception("Graph signal array dimensions " +
str(backend.length(obj)) +
" should be equal to graph nodes " +
str(backend.length(graph)))
self.np = backend.to_array(obj)
elif obj is None:
self.np = backend.repeat(1.0, len(graph))
else:
self.np = np.repeat(
0.0, len(graph)
) # tensorflow does not initialize editing of eager tensors
for key, value in obj.items():
self[key] = value
self.np = backend.to_array(
self.np
) # make all operations with numpy and then potentially switch to tensorflow
def to_numpy(
self,
scores: GraphSignalData,
normalization: bool = False
) -> Union[Tuple[GraphSignal, GraphSignal], Tuple[BackendPrimitive,
BackendPrimitive]]:
if isinstance(scores, numbers.Number) and isinstance(
self.known_scores, numbers.Number):
return backend.to_array([self.known_scores
]), backend.to_array([scores])
elif isinstance(scores, GraphSignal):
return to_signal(scores, self.known_scores).filter(
exclude=self.exclude), scores.normalized(normalization).filter(
exclude=self.exclude)
elif isinstance(self.known_scores, GraphSignal):
return self.known_scores.filter(exclude=self.exclude), to_signal(
self.known_scores,
scores).normalized(normalization).filter(exclude=self.exclude)
else:
if self.exclude is not None:
raise Exception(
"Needs to parse graph signal scores or known_scores to be able to exclude specific nodes"
)
scores = backend.self_normalize(
backend.to_array(scores, copy_array=True)
) if normalization else backend.to_array(scores)
return backend.to_array(self.known_scores), scores
def _tune(self, graph=None, personalization=None, *args, **kwargs):
previous_backend = backend.backend_name()
personalization = to_signal(graph, personalization)
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(self.tuning_backend)
backend_personalization = to_signal(
graph, backend.to_array(personalization.np))
prev_dropout = kwargs.get("graph_dropout")
kwargs["graph_dropout"] = 0
best_value = -float('inf')
best_ranker = None
fraction_of_training = self.fraction_of_training if isinstance(
self.fraction_of_training,
Iterable) else [self.fraction_of_training]
for ranker in self.rankers:
values = list()
for seed, fraction in enumerate(fraction_of_training):
training, validation = split(backend_personalization,
fraction,
seed=seed)
measure = self.measure(validation, training)
values.append(
measure.best_direction() *
measure.evaluate(ranker.rank(training, *args, **kwargs)))
value = np.min(values)
if value > best_value:
best_value = value
best_ranker = ranker
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(previous_backend)
# TODO: make training back-propagate through tensorflow for combined_prediction==False
kwargs["graph_dropout"] = prev_dropout
return best_ranker, personalization if self.combined_prediction else training
def __init__(self,
graph: GraphSignalGraph,
obj: GraphSignalData,
node2id: Optional[Mapping[object, int]] = None):
"""Should **ALWAYS** instantiate graph signals with the method to_signal,
which handles non-instantiation semantics."""
if node2id is not None:
self.node2id = node2id
elif hasattr(graph, "_pygrank_node2id"): # obtained from preprocessing
self.node2id = graph._pygrank_node2id
elif hasattr(graph, "shape"): # externally defined type
self.node2id = {i: i for i in range(graph.shape[0])}
else: # this is the case where it is an actual graph
self.node2id = {v: i for i, v in enumerate(graph)}
self.graph = graph
#self.node2id = ({i: i for i in range(graph.shape[0])} if hasattr(graph, "shape")
# else {v: i for i, v in enumerate(graph)}) if node2id is None else node2id
graph_len = graph.shape[0] if hasattr(graph, "shape") else len(graph)
if backend.is_array(obj):
if graph_len != backend.length(obj):
raise Exception("Graph signal array dimensions " +
str(backend.length(obj)) +
" should be equal to graph nodes " +
str(len(graph)))
self._np = backend.to_array(obj)
elif obj is None:
self._np = backend.repeat(1.0, graph_len)
else:
import numpy as np
self._np = np.repeat(
0.0, graph_len
) # tensorflow does not initialize editing of eager tensors
for key, value in obj.items():
self[key] = value
self._np = backend.to_array(
self._np
) # make all operations with numpy and then potentially switch to tensorflow
def _tune(self, graph=None, personalization=None, *args, **kwargs):
previous_backend = backend.backend_name()
personalization = to_signal(graph, personalization)
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(self.tuning_backend)
backend_personalization = to_signal(
graph, backend.to_array(personalization.np))
training, validation = split(backend_personalization,
self.fraction_of_training)
measure = self.measure(validation, training)
best_params = optimize(
lambda params: -measure.best_direction() * measure.evaluate(
self._run(training, params, *args, **kwargs)),
**self.optimize_args)
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(previous_backend)
# TODO: make training back-propagate through tensorflow for combined_prediction==False (do this with a gather in the split method)
return self.ranker_generator(
best_params
), personalization if self.combined_prediction else training
def _tune(self, graph=None, personalization=None, *args, **kwargs):
previous_backend = backend.backend_name()
personalization = to_signal(graph, personalization)
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(self.tuning_backend)
backend_personalization = to_signal(
graph, backend.to_array(personalization.np))
training, validation = split(backend_personalization,
self.fraction_of_training)
measure = self.measure(validation, training)
best_value = -float('inf')
best_ranker = None
for ranker in self.rankers:
value = measure.best_direction() * measure.evaluate(
ranker.rank(training, *args, **kwargs))
if value > best_value:
best_value = value
best_ranker = ranker
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(previous_backend)
# TODO: make training back-propagate through tensorflow for combined_prediction==False
return best_ranker, personalization if self.combined_prediction else training
def np(self, value):
self._np = backend.to_array(self.__compliant_value(value))
def np(self):
return backend.to_array(self._np)
def krylov2original(V, filterH, krylov_space_degree: int):
if isinstance(V, int) or isinstance(V, float):
V = backend.ones((krylov_space_degree, krylov_space_degree)) * V
ret = V @ filterH
return backend.to_array(ret[:, 0])
def _tune(self, graph=None, personalization=None, *args, **kwargs):
#graph_dropout = kwargs.get("graph_dropout", 0)
#kwargs["graph_dropout"] = 0
previous_backend = backend.backend_name()
personalization = to_signal(graph, personalization)
graph = personalization.graph
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(self.tuning_backend)
backend_personalization = to_signal(
personalization, backend.to_array(personalization.np))
#training, validation = split(backend_personalization, 0.8)
#training2, validation2 = split(backend_personalization, 0.6)
#measure_weights = [1, 1, 1, 1, 1]
#propagated = [training.np, validation.np, backend_personalization.np, training2.np, validation2.np]
measure_values = [None] * (self.num_parameters + self.autoregression)
M = self.ranker_generator(measure_values).preprocessor(graph)
#for _ in range(10):
# backend_personalization.np = backend.conv(backend_personalization.np, M)
training, validation = split(backend_personalization, 0.8)
training1, training2 = split(training, 0.5)
propagated = [training1.np, training2.np]
measures = [
self.measure(backend_personalization, training1),
self.measure(backend_personalization, training2)
]
#measures = [self.measure(validation, training), self.measure(training, validation)]
if self.basis == "krylov":
for i in range(len(measure_values)):
measure_values[i] = [
measure(p) for p, measure in zip(propagated, measures)
]
propagated = [backend.conv(p, M) for p in propagated]
else:
basis = [
arnoldi_iteration(M, p, len(measure_values))[0]
for p in propagated
]
for i in range(len(measure_values)):
measure_values[i] = [
float(measure(base[:, i]))
for base, measure in zip(basis, measures)
]
measure_values = backend.to_primitive(measure_values)
mean_value = backend.mean(measure_values, axis=0)
measure_values = measure_values - mean_value
best_parameters = measure_values
measure_weights = [1] * measure_values.shape[1]
if self.autoregression != 0:
#vals2 = -measure_values-mean_value
#measure_values = np.concatenate([measure_values, vals2-np.mean(vals2, axis=0)], axis=1)
window = backend.repeat(1. / self.autoregression,
self.autoregression)
beta1 = 0.9
beta2 = 0.999
beta1t = 1
beta2t = 1
rms = window * 0
momentum = window * 0
error = float('inf')
while True:
beta1t *= beta1
beta2t *= beta2
prev_error = error
parameters = backend.copy(measure_values)
for i in range(len(measure_values) - len(window) - 2, -1, -1):
parameters[i, :] = backend.dot(
(window),
measure_values[(i + 1):(i + len(window) + 1), :])
errors = (parameters - measure_values
) * measure_weights / backend.sum(measure_weights)
for j in range(len(window)):
gradient = 0
for i in range(len(measure_values) - len(window) - 1):
gradient += backend.dot(measure_values[i + j + 1, :],
errors[i, :])
momentum[j] = beta1 * momentum[j] + (
1 - beta1) * gradient #*np.sign(window[j])
rms[j] = beta2 * rms[j] + (1 - beta2) * gradient * gradient
window[j] -= 0.01 * momentum[j] / (1 - beta1t) / (
(rms[j] / (1 - beta2t))**0.5 + 1.E-8)
#window[j] -= 0.01*gradient*np.sign(window[j])
error = backend.mean(backend.abs(errors))
if error == 0 or abs(error - prev_error) / error < 1.E-6:
best_parameters = parameters
break
best_parameters = backend.mean(best_parameters[:self.num_parameters, :]
* backend.to_primitive(measure_weights),
axis=1) + backend.mean(mean_value)
if self.tunable_offset is not None:
div = backend.max(best_parameters)
if div != 0:
best_parameters /= div
measure = self.tunable_offset(validation, training)
base = basis[0] if self.basis != "krylov" else None
best_offset = optimize(
lambda params: -measure.best_direction() * measure(
self._run(training, [(best_parameters[i] + params[
2]) * params[0]**i + params[1] for i in range(
len(best_parameters))], base, *args, **kwargs)),
#lambda params: - measure.evaluate(self._run(training, best_parameters + params[0], *args, **kwargs)),
max_vals=[1, 0, 0],
min_vals=[0, 0, 0],
deviation_tol=0.005,
parameter_tol=1,
partitions=5,
divide_range=2)
#best_parameters += best_offset[0]
best_parameters = [
(best_parameters[i] + best_offset[2]) * best_offset[0]**i +
best_offset[1] for i in range(len(best_parameters))
]
best_parameters = backend.to_primitive(best_parameters)
if backend.sum(backend.abs(best_parameters)) != 0:
best_parameters /= backend.mean(backend.abs(best_parameters))
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
best_parameters = [
float(param) for param in best_parameters
] # convert parameters to backend-independent list
backend.load_backend(previous_backend)
#kwargs["graph_dropout"] = graph_dropout
if self.basis != "krylov":
return Tautology(), self._run(
personalization, best_parameters, *args,
**kwargs) # TODO: make this unecessary
return self.ranker_generator(best_parameters), personalization
def _tune(self, graph=None, personalization=None, *args, **kwargs):
previous_backend = backend.backend_name()
personalization = to_signal(graph, personalization)
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(self.tuning_backend)
backend_personalization = to_signal(
graph, backend.to_array(personalization.np))
total_params = list()
for seed0 in range(self.cross_validate):
fraction_of_training = self.fraction_of_training if isinstance(
self.fraction_of_training,
Iterable) else [self.fraction_of_training]
#fraction_of_training = [random.choice(fraction_of_training)]
internal_training_list = list()
validation_list = list()
for seed, fraction in enumerate(fraction_of_training):
training, validation = split(backend_personalization, fraction,
seed0 + seed)
internal_training = training
if self.pre_diffuse is not None:
internal_training = self.pre_diffuse(internal_training)
validation = self.pre_diffuse(validation)
internal_training_list.append(internal_training)
validation_list.append(validation)
def eval(params):
val = 0
for internal_training, validation in zip(
internal_training_list, validation_list):
"""import pygrank as pg
scores = self._run(backend_personalization, params, *args, **kwargs)
internal_training = pg.Undersample(int(backend.sum(internal_training)))(scores*backend_personalization)
validation = backend_personalization - internal_training"""
measure = self.measure(
validation, internal_training
if internal_training != validation else None)
val = val - measure.best_direction() * measure.evaluate(
self._run(internal_training, params, *args, **kwargs))
return val / len(internal_training_list)
best_params = self.optimizer(eval, **self.optimize_args)
"""import cma
es = cma.CMAEvolutionStrategy([0.5 for _ in range(len(self.optimize_args["max_vals"]))], 1./12**0.5)
es.optimize(eval, verb_disp=False)
best_params = es.result.xbest"""
total_params.append(best_params)
best_params = [0 for _ in best_params]
best_squares = [0 for _ in best_params]
best_means = [0 for _ in best_params]
for params in total_params:
for i in range(len(best_params)):
best_params[i] = max(best_params[i], params[i])
best_means[i] += params[i] / self.cross_validate
best_squares[i] += params[i]**2 / self.cross_validate
best_params = best_means
if self.tuning_backend is not None and self.tuning_backend != previous_backend:
backend.load_backend(previous_backend)
# TODO: make training back-propagate through tensorflow for combined_prediction==False (do this with a gather in the split method)
self.last_params = best_params
return self.ranker_generator(
best_params
), personalization if self.combined_prediction else internal_training