def run(
task: Task,
num_samples: int,
num_simulations: int,
num_observation: Optional[int] = None,
observation: Optional[torch.Tensor] = None,
num_top_samples: Optional[int] = 100,
quantile: Optional[float] = None,
eps: Optional[float] = None,
distance: str = "l2",
batch_size: int = 1000,
save_distances: bool = False,
kde_bandwidth: Optional[str] = "cv",
sass: bool = False,
sass_fraction: float = 0.5,
sass_feature_expansion_degree: int = 3,
lra: bool = False,
) -> Tuple[torch.Tensor, int, Optional[torch.Tensor]]:
"""Runs REJ-ABC from `sbi`
Choose one of `num_top_samples`, `quantile`, `eps`.
Args:
task: Task instance
num_samples: Number of samples to generate from posterior
num_simulations: Simulation budget
num_observation: Observation number to load, alternative to `observation`
observation: Observation, alternative to `num_observation`
num_top_samples: If given, will use `top=True` with num_top_samples
quantile: Quantile to use
eps: Epsilon threshold to use
distance: Distance to use
batch_size: Batch size for simulator
save_distances: If True, stores distances of samples to disk
kde_bandwidth: If not None, will resample using KDE when necessary, set
e.g. to "cv" for cross-validated bandwidth selection
sass: If True, summary statistics are learned as in
Fearnhead & Prangle 2012.
sass_fraction: Fraction of simulation budget to use for sass.
sass_feature_expansion_degree: Degree of polynomial expansion of the summary
statistics.
lra: If True, posterior samples are adjusted with
linear regression as in Beaumont et al. 2002.
Returns:
Samples from posterior, number of simulator calls, log probability of true params if computable
"""
assert not (num_observation is None and observation is None)
assert not (num_observation is not None and observation is not None)
assert not (num_top_samples is None and quantile is None and eps is None)
log = sbibm.get_logger(__name__)
log.info(f"Running REJ-ABC")
prior = task.get_prior_dist()
simulator = task.get_simulator(max_calls=num_simulations)
kde = kde_bandwidth is not None
if observation is None:
observation = task.get_observation(num_observation)
if num_top_samples is not None and quantile is None:
if sass:
quantile = num_top_samples / (num_simulations -
int(sass_fraction * num_simulations))
else:
quantile = num_top_samples / num_simulations
inference_method = MCABC(
simulator=simulator,
prior=prior,
simulation_batch_size=batch_size,
distance=distance,
show_progress_bars=True,
)
# Returns samples or kde posterior in output.
output, summary = inference_method(
x_o=observation,
num_simulations=num_simulations,
eps=eps,
quantile=quantile,
return_summary=True,
kde=kde,
kde_kwargs={} if run_kde else {"kde_bandwidth": kde_bandwidth},
lra=lra,
sass=sass,
sass_expansion_degree=sass_feature_expansion_degree,
sass_fraction=sass_fraction,
)
assert simulator.num_simulations == num_simulations
if save_distances:
save_tensor_to_csv("distances.csv", summary["distances"])
if kde:
kde_posterior = output
samples = kde_posterior.sample(num_simulations)
# LPTP can only be returned with KDE posterior.
if num_observation is not None:
true_parameters = task.get_true_parameters(
num_observation=num_observation)
log_prob_true_parameters = kde_posterior.log_prob(
true_parameters.squeeze())
return samples, simulator.num_simulations, log_prob_true_parameters
else:
samples = output
return samples, simulator.num_simulations, None
def run(
task: Task,
num_samples: int,
num_simulations: int,
num_observation: Optional[int] = None,
observation: Optional[torch.Tensor] = None,
num_rounds: int = 10,
neural_net: str = "nsf",
hidden_features: int = 50,
simulation_batch_size: int = 1000,
training_batch_size: int = 10000,
num_atoms: int = 10,
automatic_transforms_enabled: bool = False,
z_score_x: bool = True,
z_score_theta: bool = True,
) -> Tuple[torch.Tensor, int, Optional[torch.Tensor]]:
"""Runs (S)NPE from `sbi`
Args:
task: Task instance
num_samples: Number of samples to generate from posterior
num_simulations: Simulation budget
num_observation: Observation number to load, alternative to `observation`
observation: Observation, alternative to `num_observation`
num_rounds: Number of rounds
neural_net: Neural network to use, one of maf / mdn / made / nsf
hidden_features: Number of hidden features in network
simulation_batch_size: Batch size for simulator
training_batch_size: Batch size for training network
num_atoms: Number of atoms, -1 means same as `training_batch_size`
automatic_transforms_enabled: Whether to enable automatic transforms
z_score_x: Whether to z-score x
z_score_theta: Whether to z-score theta
Returns:
Samples from posterior, number of simulator calls, log probability of true params if computable
"""
assert not (num_observation is None and observation is None)
assert not (num_observation is not None and observation is not None)
log = logging.getLogger(__name__)
if num_rounds == 1:
log.info(f"Running NPE")
num_simulations_per_round = num_simulations
else:
log.info(f"Running SNPE")
num_simulations_per_round = math.floor(num_simulations / num_rounds)
if simulation_batch_size > num_simulations_per_round:
simulation_batch_size = num_simulations_per_round
log.warn("Reduced simulation_batch_size to num_simulation_per_round")
if training_batch_size > num_simulations_per_round:
training_batch_size = num_simulations_per_round
log.warn("Reduced training_batch_size to num_simulation_per_round")
prior = task.get_prior_dist()
if observation is None:
observation = task.get_observation(num_observation)
simulator = task.get_simulator(max_calls=num_simulations)
transforms = task._get_transforms(
automatic_transforms_enabled)["parameters"]
if automatic_transforms_enabled:
prior = wrap_prior_dist(prior, transforms)
simulator = wrap_simulator_fn(simulator, transforms)
density_estimator_fun = posterior_nn(
model=neural_net.lower(),
hidden_features=hidden_features,
z_score_x=z_score_x,
z_score_theta=z_score_theta,
)
inference_method = inference.SNPE_C(
prior, density_estimator=density_estimator_fun)
posteriors = []
proposal = prior
for _ in range(num_rounds):
theta, x = inference.simulate_for_sbi(
simulator,
proposal,
num_simulations=num_simulations_per_round,
simulation_batch_size=simulation_batch_size,
)
density_estimator = inference_method.append_simulations(
theta, x, proposal=proposal).train(
num_atoms=num_atoms,
training_batch_size=training_batch_size,
retrain_from_scratch_each_round=False,
discard_prior_samples=False,
use_combined_loss=False,
show_train_summary=True,
)
posterior = inference_method.build_posterior(density_estimator,
sample_with_mcmc=False)
proposal = posterior.set_default_x(observation)
posteriors.append(posterior)
posterior = wrap_posterior(posteriors[-1], transforms)
assert simulator.num_simulations == num_simulations
samples = posterior.sample((num_samples, )).detach()
if num_observation is not None:
true_parameters = task.get_true_parameters(
num_observation=num_observation)
log_prob_true_parameters = posterior.log_prob(true_parameters)
return samples, simulator.num_simulations, log_prob_true_parameters
else:
return samples, simulator.num_simulations, None
def run(
task: Task,
num_samples: int,
num_simulations: int,
num_observation: Optional[int] = None,
observation: Optional[torch.Tensor] = None,
population_size: Optional[int] = None,
distance: str = "l2",
epsilon_decay: float = 0.2,
distance_based_decay: bool = True,
ess_min: Optional[float] = None,
initial_round_factor: int = 5,
batch_size: int = 1000,
kernel: str = "gaussian",
kernel_variance_scale: float = 0.5,
use_last_pop_samples: bool = True,
algorithm_variant: str = "C",
save_summary: bool = False,
sass: bool = False,
sass_fraction: float = 0.5,
sass_feature_expansion_degree: int = 3,
lra: bool = False,
lra_sample_weights: bool = True,
kde_bandwidth: Optional[str] = "cv",
kde_sample_weights: bool = False,
) -> Tuple[torch.Tensor, int, Optional[torch.Tensor]]:
"""Runs SMC-ABC from `sbi`
SMC-ABC supports two different ways of scheduling epsilon:
1) Exponential decay: eps_t+1 = epsilon_decay * eps_t
2) Distance based decay: the new eps is determined from the "epsilon_decay"
quantile of the distances of the accepted simulations in the previous population. This is used if `distance_based_decay` is set to True.
Args:
task: Task instance
num_samples: Number of samples to generate from posterior
num_simulations: Simulation budget
num_observation: Observation number to load, alternative to `observation`
observation: Observation, alternative to `num_observation`
population_size: If None, uses heuristic: 1000 if `num_simulations` is greater
than 10k, else 100
distance: Distance function, options = {l1, l2, mse}
epsilon_decay: Decay for epsilon; treated as quantile in case of distance based decay.
distance_based_decay: Whether to determine new epsilon from quantile of
distances of the previous population.
ess_min: Threshold for resampling a population if effective sampling size is
too small.
initial_round_factor: Used to determine initial round size
batch_size: Batch size for the simulator
kernel: Kernel distribution used to perturb the particles.
kernel_variance_scale: Scaling factor for kernel variance.
use_last_pop_samples: If True, samples of a population that was quit due to
budget are used by filling up missing particles from the previous
population.
algorithm_variant: There are three SMCABC variants implemented: A, B, and C.
See doctstrings in SBI package for more details.
save_summary: Whether to save a summary containing all populations, distances,
etc. to file.
sass: If True, summary statistics are learned as in
Fearnhead & Prangle 2012.
sass_fraction: Fraction of simulation budget to use for sass.
sass_feature_expansion_degree: Degree of polynomial expansion of the summary
statistics.
lra: If True, posterior samples are adjusted with
linear regression as in Beaumont et al. 2002.
lra_sample_weights: Whether to weigh LRA samples
kde_bandwidth: If not None, will resample using KDE when necessary, set
e.g. to "cv" for cross-validated bandwidth selection
kde_sample_weights: Whether to weigh KDE samples
Returns:
Samples from posterior, number of simulator calls, log probability of true params if computable
"""
assert not (num_observation is None and observation is None)
assert not (num_observation is not None and observation is not None)
log = sbibm.get_logger(__name__)
smc_papers = dict(A="Toni 2010", B="Sisson et al. 2007", C="Beaumont et al. 2009")
log.info(f"Running SMC-ABC as in {smc_papers[algorithm_variant]}.")
prior = task.get_prior_dist()
simulator = task.get_simulator(max_calls=num_simulations)
if observation is None:
observation = task.get_observation(num_observation)
if population_size is None:
population_size = 100
if num_simulations > 10_000:
population_size = 1000
population_size = min(population_size, num_simulations)
initial_round_size = clip_int(
value=initial_round_factor * population_size,
minimum=population_size,
maximum=max(0.5 * num_simulations, population_size),
)
inference_method = SMCABC(
simulator=simulator,
prior=prior,
simulation_batch_size=batch_size,
distance=distance,
show_progress_bars=True,
kernel=kernel,
algorithm_variant=algorithm_variant,
)
posterior, summary = inference_method(
x_o=observation,
num_particles=population_size,
num_initial_pop=initial_round_size,
num_simulations=num_simulations,
epsilon_decay=epsilon_decay,
distance_based_decay=distance_based_decay,
ess_min=ess_min,
kernel_variance_scale=kernel_variance_scale,
use_last_pop_samples=use_last_pop_samples,
return_summary=True,
lra=lra,
lra_with_weights=lra_sample_weights,
sass=sass,
sass_fraction=sass_fraction,
sass_expansion_degree=sass_feature_expansion_degree,
)
if save_summary:
log.info("Saving smcabc summary to csv.")
pd.DataFrame.from_dict(summary,).to_csv("summary.csv", index=False)
assert simulator.num_simulations == num_simulations
if kde_bandwidth is not None:
samples = posterior._samples
log.info(
f"KDE on {samples.shape[0]} samples with bandwidth option {kde_bandwidth}"
)
kde = get_kde(
samples,
bandwidth=kde_bandwidth,
sample_weight=posterior._log_weights.exp() if kde_sample_weights else None,
)
samples = kde.sample(num_samples)
else:
samples = posterior.sample((num_samples,)).detach()
if num_observation is not None:
true_parameters = task.get_true_parameters(num_observation=num_observation)
log_prob_true_parameters = posterior.log_prob(true_parameters)
return samples, simulator.num_simulations, log_prob_true_parameters
else:
return samples, simulator.num_simulations, None
