def checkpoint(self): """Checkpoint function for dynesty sampler """ with loadfile(self.checkpoint_file, 'a') as fp: fp.write_random_state() # Dynesty has its own __getstate__ which deletes # random state information and the pool saved = {} for key in self.no_pickle: if hasattr(self._sampler, key): saved[key] = getattr(self._sampler, key) setattr(self._sampler, key, None) # For the dynamic sampler, we must also handle the internal # sampler object #saved_internal = {} #if self.nlive < 0: # for key in self.no_pickle: # if hasattr(self._sampler.sampler, key): # saved[key] = getattr(self._sampler.sampler, key) # setattr(self._sampler.sampler, key, None) #for key in self._sampler.__dict__: # print(key, type(self._sampler.__dict__[key])) #for key in self._sampler.sampler.__dict__: # print(key, type(self._sampler.sampler.__dict__[key])) fp.write_pickled_data_into_checkpoint_file(self._sampler) # Restore properties that couldn't be pickled if we are continuing for key in saved: setattr(self._sampler, key, saved[key])
def ensemble_compute_acl(filename, start_index=None, end_index=None, min_nsamples=10): """Computes the autocorrleation length for a parallel tempered, ensemble MCMC. Parameter values are averaged over all walkers at each iteration and temperature. The ACL is then calculated over the averaged chain. Parameters ----------- filename : str Name of a samples file to compute ACLs for. start_index : int, optional The start index to compute the acl from. If None (the default), will try to use the number of burn-in iterations in the file; otherwise, will start at the first sample. end_index : int, optional The end index to compute the acl to. If None, will go to the end of the current iteration. min_nsamples : int, optional Require a minimum number of samples to compute an ACL. If the number of samples per walker is less than this, will just set to ``inf``. Default is 10. Returns ------- dict A dictionary of ntemps-long arrays of the ACLs of each parameter. """ acls = {} with loadfile(filename, 'r') as fp: if end_index is None: end_index = fp.niterations tidx = numpy.arange(fp.ntemps) for param in fp.variable_params: these_acls = numpy.zeros(fp.ntemps) for tk in tidx: samples = fp.read_raw_samples(param, thin_start=start_index, thin_interval=1, thin_end=end_index, temps=tk, flatten=False)[param] # contract the walker dimension using the mean, and flatten # the (length 1) temp dimension samples = samples.mean(axis=1)[0, :] if samples.size < min_nsamples: acl = numpy.inf else: acl = autocorrelation.calculate_acl(samples) if acl <= 0: acl = numpy.inf these_acls[tk] = acl acls[param] = these_acls maxacl = numpy.array(list(acls.values())).max() logging.info("ACT: %s", str(maxacl * fp.thinned_by)) return acls
def compute_acf(filename, start_index=None, end_index=None, chains=None, parameters=None, temps=None): """Computes the autocorrleation function for independent MCMC chains with parallel tempering. Parameters ----------- filename : str Name of a samples file to compute ACFs for. start_index : int, optional The start index to compute the acl from. If None (the default), will try to use the burn in iteration for each chain; otherwise, will start at the first sample. end_index : {None, int} The end index to compute the acl to. If None, will go to the end of the current iteration. chains : optional, int or array Calculate the ACF for only the given chains. If None (the default) ACFs for all chains will be estimated. parameters : optional, str or array Calculate the ACF for only the given parameters. If None (the default) will calculate the ACF for all of the model params. temps : optional, (list of) int or 'all' The temperature index (or list of indices) to retrieve. If None (the default), the ACF will only be computed for the coldest (= 0) temperature chain. To compute an ACF for all temperates pass 'all', or a list of all of the temperatures. Returns ------- dict : Dictionary parameter name -> ACF arrays. The arrays have shape ``ntemps x nchains x niterations``. """ acfs = {} with loadfile(filename, 'r') as fp: if parameters is None: parameters = fp.variable_params if isinstance(parameters, string_types): parameters = [parameters] temps = _get_temps_idx(fp, temps) if chains is None: chains = numpy.arange(fp.nchains) for param in parameters: subacfs = [] for tk in temps: subsubacfs = [] for ci in chains: samples = fp.read_raw_samples( param, thin_start=start_index, thin_interval=1, thin_end=end_index, chains=ci, temps=tk)[param] thisacf = autocorrelation.calculate_acf(samples).numpy() subsubacfs.append(thisacf) # stack the chains subacfs.append(subsubacfs) # stack the temperatures acfs[param] = numpy.stack(subacfs) return acfs
def ensemble_compute_acl(filename, start_index=None, end_index=None, min_nsamples=10): """Computes the autocorrleation length for an ensemble MCMC. Parameter values are averaged over all walkers at each iteration. The ACL is then calculated over the averaged chain. If an ACL cannot be calculated because there are not enough samples, it will be set to ``inf``. Parameters ----------- filename : str Name of a samples file to compute ACLs for. start_index : int, optional The start index to compute the acl from. If None, will try to use the number of burn-in iterations in the file; otherwise, will start at the first sample. end_index : int, optional The end index to compute the acl to. If None, will go to the end of the current iteration. min_nsamples : int, optional Require a minimum number of samples to compute an ACL. If the number of samples per walker is less than this, will just set to ``inf``. Default is 10. Returns ------- dict A dictionary giving the ACL for each parameter. """ acls = {} with loadfile(filename, 'r') as fp: for param in fp.variable_params: samples = fp.read_raw_samples(param, thin_start=start_index, thin_interval=1, thin_end=end_index, flatten=False)[param] samples = samples.mean(axis=0) # if < min number of samples, just set to inf if samples.size < min_nsamples: acl = numpy.inf else: acl = autocorrelation.calculate_acl(samples) if acl <= 0: acl = numpy.inf acls[param] = acl maxacl = numpy.array(list(acls.values())).max() logging.info("ACT: %s", str(maxacl * fp.thin_interval)) return acls
def resume_from_checkpoint(self): try: with loadfile(self.checkpoint_file, 'r') as fp: sampler = fp.read_pickled_data_from_checkpoint_file() for key in sampler.__dict__: if key not in self.no_pickle: value = getattr(sampler, key) setattr(self._sampler, key, value) self.set_state_from_file(self.checkpoint_file) logging.info("Found valid checkpoint file: %s", self.checkpoint_file) except Exception as e: print(e) logging.info("Failed to load checkpoint file")
def __init__(self, variable_params, posterior_file, nsamples, **kwargs): super(TestPosterior, self).__init__(variable_params, **kwargs) from pycbc.inference.io import loadfile # avoid cyclic import logging.info('loading test posterior model') inf_file = loadfile(posterior_file) logging.info('reading samples') samples = inf_file.read_samples(variable_params) samples = numpy.array([samples[v] for v in variable_params]) # choose only the requested amount of samples idx = numpy.arange(0, samples.shape[-1]) idx = numpy.random.choice(idx, size=int(nsamples), replace=False) samples = samples[:, idx] logging.info('making kde with %s samples', samples.shape[-1]) self.kde = stats.gaussian_kde(samples) logging.info('done initializing test posterior model')
def ensemble_compute_acf(filename, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None): """Computes the autocorrleation function for an ensemble MCMC. By default, parameter values are averaged over all walkers at each iteration. The ACF is then calculated over the averaged chain. An ACF per-walker will be returned instead if ``per_walker=True``. Parameters ----------- filename : str Name of a samples file to compute ACFs for. start_index : int, optional The start index to compute the acl from. If None (the default), will try to use the number of burn-in iterations in the file; otherwise, will start at the first sample. end_index : int, optional The end index to compute the acl to. If None (the default), will go to the end of the current iteration. per_walker : bool, optional Return the ACF for each walker separately. Default is False. walkers : int or array, optional Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. parameters : str or array, optional Calculate the ACF for only the given parameters. If None (the default) will calculate the ACF for all of the model params. Returns ------- dict : Dictionary of arrays giving the ACFs for each parameter. If ``per-walker`` is True, the arrays will have shape ``nwalkers x niterations``. """ acfs = {} with loadfile(filename, 'r') as fp: if parameters is None: parameters = fp.variable_params if isinstance(parameters, string_types): parameters = [parameters] for param in parameters: if per_walker: # just call myself with a single walker if walkers is None: walkers = numpy.arange(fp.nwalkers) arrays = [ ensemble_compute_acf(filename, start_index=start_index, end_index=end_index, per_walker=False, walkers=ii, parameters=param)[param] for ii in walkers ] acfs[param] = numpy.vstack(arrays) else: samples = fp.read_raw_samples(param, thin_start=start_index, thin_interval=1, thin_end=end_index, walkers=walkers, flatten=False)[param] samples = samples.mean(axis=0) acfs[param] = autocorrelation.calculate_acf(samples).numpy() return acfs
def ensemble_compute_acf(filename, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None, temps=None): """Computes the autocorrleation function for a parallel tempered, ensemble MCMC. By default, parameter values are averaged over all walkers at each iteration. The ACF is then calculated over the averaged chain for each temperature. An ACF per-walker will be returned instead if ``per_walker=True``. Parameters ---------- filename : str Name of a samples file to compute ACFs for. start_index : int, optional The start index to compute the acl from. If None (the default), will try to use the number of burn-in iterations in the file; otherwise, will start at the first sample. end_index : int, optional The end index to compute the acl to. If None (the default), will go to the end of the current iteration. per_walker : bool, optional Return the ACF for each walker separately. Default is False. walkers : int or array, optional Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. parameters : str or array, optional Calculate the ACF for only the given parameters. If None (the default) will calculate the ACF for all of the model params. temps : (list of) int or 'all', optional The temperature index (or list of indices) to retrieve. If None (the default), the ACF will only be computed for the coldest (= 0) temperature chain. To compute an ACF for all temperates pass 'all', or a list of all of the temperatures. Returns ------- dict : Dictionary of arrays giving the ACFs for each parameter. If ``per-walker`` is True, the arrays will have shape ``ntemps x nwalkers x niterations``. Otherwise, the returned array will have shape ``ntemps x niterations``. """ acfs = {} with loadfile(filename, 'r') as fp: if parameters is None: parameters = fp.variable_params if isinstance(parameters, str): parameters = [parameters] temps = _get_temps_idx(fp, temps) for param in parameters: subacfs = [] for tk in temps: if per_walker: # just call myself with a single walker if walkers is None: walkers = numpy.arange(fp.nwalkers) arrays = [ ensemble_compute_acf(filename, start_index=start_index, end_index=end_index, per_walker=False, walkers=ii, parameters=param, temps=tk)[param][0, :] for ii in walkers ] # we'll stack all of the walker arrays to make a single # nwalkers x niterations array; when these are stacked # below, we'll get a ntemps x nwalkers x niterations # array subacfs.append(numpy.vstack(arrays)) else: samples = fp.read_raw_samples(param, thin_start=start_index, thin_interval=1, thin_end=end_index, walkers=walkers, temps=tk, flatten=False)[param] # contract the walker dimension using the mean, and # flatten the (length 1) temp dimension samples = samples.mean(axis=1)[0, :] thisacf = autocorrelation.calculate_acf(samples).numpy() subacfs.append(thisacf) # stack the temperatures acfs[param] = numpy.stack(subacfs) return acfs
def compute_acl(filename, start_index=None, end_index=None, min_nsamples=10): """Computes the autocorrleation length for independent MCMC chains with parallel tempering. ACLs are calculated separately for each chain. Parameters ----------- filename : str Name of a samples file to compute ACLs for. start_index : {None, int} The start index to compute the acl from. If None, will try to use the number of burn-in iterations in the file; otherwise, will start at the first sample. end_index : {None, int} The end index to compute the acl to. If None, will go to the end of the current iteration. min_nsamples : int, optional Require a minimum number of samples to compute an ACL. If the number of samples per walker is less than this, will just set to ``inf``. Default is 10. Returns ------- dict A dictionary of ntemps x nchains arrays of the ACLs of each parameter. """ # following is a convenience function to calculate the acl for each chain # defined here so that we can use map for this below def _getacl(si): # si: the samples loaded for a specific chain; may have nans in it si = si[~numpy.isnan(si)] if len(si) < min_nsamples: acl = numpy.inf else: acl = autocorrelation.calculate_acl(si) if acl <= 0: acl = numpy.inf return acl acls = {} with loadfile(filename, 'r') as fp: tidx = numpy.arange(fp.ntemps) for param in fp.variable_params: these_acls = numpy.zeros((fp.ntemps, fp.nchains)) for tk in tidx: samples = fp.read_raw_samples(param, thin_start=start_index, thin_interval=1, thin_end=end_index, temps=tk, flatten=False)[param] # flatten out the temperature samples = samples[0, ...] # samples now has shape nchains x maxiters if samples.shape[-1] < min_nsamples: these_acls[tk, :] = numpy.inf else: these_acls[tk, :] = list(map(_getacl, samples)) acls[param] = these_acls # report the mean ACL: take the max over the temps and parameters act = acl_from_raw_acls(acls) * fp.thinned_by finite = act[numpy.isfinite(act)] logging.info("ACTs: min %s, mean (of finite) %s, max %s", str(act.min()), str(finite.mean() if finite.size > 0 else numpy.inf), str(act.max())) return acls