def likelihood_stats(self): """Returns the log likelihood ratio and log prior as a FieldArray. The returned array has shape ntemps x nwalkers x niterations. """ # likelihood has shape ntemps x nwalkers x niterations logl = self._sampler.lnlikelihood # get prior from posterior logp = self._sampler.lnprobability - logl # compute the likelihood ratio loglr = logl - self.likelihood_evaluator.lognl return FieldArray.from_kwargs(loglr=loglr, prior=logp)
def likelihood_stats(self): """Returns the likelihood stats as a FieldArray, with field names corresponding to the type of data returned by the likelihood evaluator. The returned array has shape nwalkers x niterations. If no additional stats were returned to the sampler by the likelihood evaluator, returns None. """ stats = numpy.array(self._sampler.blobs) if stats.size == 0: return None arrays = dict([[field, stats[:, :, fi]] for fi, field in enumerate(self.likelihood_evaluator.metadata_fields)]) return FieldArray.from_kwargs(**arrays).transpose()
def likelihood_stats(self): """Returns the likelihood stats as a FieldArray, with field names corresponding to the type of data returned by the likelihood evaluator. The returned array has shape nwalkers x niterations. If no additional stats were returned to the sampler by the likelihood evaluator, returns None. """ stats = numpy.array(self._sampler.blobs) if stats.size == 0: return None # we'll force arrays to float; this way, if there are `None`s in the # blobs, they will be changed to `nan`s arrays = {field: stats[..., fi].astype(float) for fi, field in enumerate(self.likelihood_evaluator.metadata_fields)} return FieldArray.from_kwargs(**arrays).transpose()
def compute_acls(cls, fp, start_index=None, end_index=None): """Computes the autocorrleation length for all variable args and temperatures in the given file. Parameter values are averaged over all walkers at each iteration and temperature. The ACL is then calculated over the averaged chain. If the returned ACL is `inf`, will default to the number of current iterations. Parameters ----------- fp : InferenceFile An open file handler to read the samples from. 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. Returns ------- FieldArray An ntemps-long `FieldArray` containing the ACL for each temperature and for each variable argument, with the variable arguments as fields. """ acls = {} if end_index is None: end_index = fp.niterations tidx = numpy.arange(fp.ntemps) for param in fp.variable_args: these_acls = numpy.zeros(fp.ntemps, dtype=int) for tk in tidx: samples = cls.read_samples(fp, 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,:] acl = autocorrelation.calculate_acl(samples) if numpy.isinf(acl): acl = samples.size these_acls[tk] = acl acls[param] = these_acls return FieldArray.from_kwargs(**acls)
def copy_samples(self, other, parameters=None, parameter_names=None, read_args=None, write_args=None): """Should copy samples to the other files. Parameters ---------- other : InferenceFile An open inference file to write to. parameters : list of str, optional List of parameters to copy. If None, will copy all parameters. parameter_names : dict, optional Rename one or more parameters to the given name. The dictionary should map parameter -> parameter name. If None, will just use the original parameter names. read_args : dict, optional Arguments to pass to ``read_samples``. write_args : dict, optional Arguments to pass to ``write_samples``. """ # select the samples to copy logging.info("Reading samples to copy") if parameters is None: parameters = self.variable_params # if list of desired parameters is different, rename if set(parameters) != set(self.variable_params): other.attrs['variable_params'] = parameters samples = self.read_samples(parameters, **read_args) logging.info("Copying {} samples".format(samples.size)) # if different parameter names are desired, get them from the samples if parameter_names: arrs = {pname: samples[p] for p, pname in parameter_names.items()} arrs.update({ p: samples[p] for p in parameters if p not in parameter_names }) samples = FieldArray.from_kwargs(**arrs) other.attrs['variable_params'] = samples.fieldnames logging.info("Writing samples") other.write_samples(other, samples, **write_args)
def likelihood_stats(self): """Returns the log likelihood ratio and log prior as a FieldArray. The returned array has shape ntemps x nwalkers x niterations. """ # likelihood has shape ntemps x nwalkers x niterations logl = self._sampler.lnlikelihood # get prior from posterior logp = self._sampler.lnprobability - logl # compute the likelihood ratio loglr = logl - self.likelihood_evaluator.lognl kwargs = {'loglr': loglr, 'prior': logp} # if different coordinates were used for sampling, get the jacobian if self.likelihood_evaluator.sampling_transforms is not None: samples = self.samples # convert to dict d = {param: samples[param] for param in samples.fieldnames} logj = self.likelihood_evaluator.logjacobian(**d) kwargs['logjacobian'] = logj return FieldArray.from_kwargs(**kwargs)
def likelihood_stats(self): """Returns the log likelihood ratio and log prior as a FieldArray. The returned array has shape ntemps x nwalkers x niterations. """ # likelihood has shape ntemps x nwalkers x niterations logl = self._sampler.lnlikelihood # get prior from posterior logp = self._sampler.lnprobability - logl # compute the likelihood ratio loglr = logl - self.likelihood_evaluator.lognl kwargs = {'loglr': loglr, 'prior': logp} # if different coordinates were used for sampling, get the jacobian if self.likelihood_evaluator.sampling_transforms is not None: samples = self.samples # convert to dict d = {param: samples[param] for param in samples.fieldnames} logj = self.likelihood_evaluator.logjacobian(**d) kwargs['logjacobian'] = logj return FieldArray.from_kwargs(**kwargs)
def compute_acls(cls, fp, start_index=None, end_index=None): """Computes the autocorrleation length for all variable args for all walkers for all temps in the given file. If the returned acl is inf, will default to the number of requested iterations. Parameters ----------- fp : InferenceFile An open file handler to read the samples from. 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. Returns ------- FieldArray An ntemps x nwalkers `FieldArray` containing the acl for each walker and temp for each variable argument, with the variable arguments as fields. """ acls = {} if end_index is None: end_index = fp.niterations tidx = numpy.arange(fp.ntemps) widx = numpy.arange(fp.nwalkers) for param in fp.variable_args: these_acls = numpy.zeros((fp.ntemps, fp.nwalkers), dtype=int) for tk in tidx: for wi in widx: samples = cls.read_samples( fp, param, thin_start=start_index, thin_interval=1, thin_end=end_index, walkers=wi, temps=tk)[param] acl = autocorrelation.calculate_acl(samples) these_acls[tk, wi] = int(min(acl, samples.size)) acls[param] = these_acls return FieldArray.from_kwargs(**acls)
def read_acls(fp): """Reads the acls of all the walker chains saved in the given file. Parameters ---------- fp : InferenceFile An open file handler to read the acls from. Returns ------- FieldArray An nwalkers-long `FieldArray` containing the acl for each walker and each variable argument, with the variable arguments as fields. """ group = fp.samples_group + '/{param}/walker{wi}' widx = numpy.arange(fp.nwalkers) arrays = {} for param in fp.variable_args: arrays[param] = numpy.array([ fp[group.format(param=param, wi=wi)].attrs['acl'] for wi in widx]) return FieldArray.from_kwargs(**arrays)
def _oldstyle_read_acls(fp): """Deprecated: reads acls from older style files. Parameters ---------- fp : InferenceFile An open file handler to read the acls from. Returns ------- FieldArray An ntemps-long ``FieldArray`` containing the acls for every temperature, with the variable arguments as fields. """ group = fp.samples_group + '/{param}/temp{tk}' tidx = numpy.arange(fp.ntemps) arrays = {} for param in fp.variable_args: arrays[param] = numpy.array([ fp[group.format(param=param, tk=tk)].attrs['acl'] for tk in tidx]) return FieldArray.from_kwargs(**arrays)
def read_acls(fp): """Reads the acls of all the walker chains saved in the given file. Parameters ---------- fp : InferenceFile An open file handler to read the acls from. Returns ------- FieldArray An ntemps-long ``FieldArray`` containing the acls for every temperature, with the variable arguments as fields. """ group = fp.samples_group + '/{param}/temp{tk}' tidx = numpy.arange(fp.ntemps) arrays = {} for param in fp.variable_args: arrays[param] = numpy.array([ fp[group.format(param=param, tk=tk)].attrs['acl'] for tk in tidx]) return FieldArray.from_kwargs(**arrays)
def read_acls(fp): """Reads the acls of all the walker chains saved in the given file. Parameters ---------- fp : InferenceFile An open file handler to read the acls from. Returns ------- FieldArray An nwalkers-long `FieldArray` containing the acl for each walker and each variable argument, with the variable arguments as fields. """ group = fp.samples_group + '/{param}/walker{wi}' widx = numpy.arange(fp.nwalkers) arrays = {} for param in fp.variable_args: arrays[param] = numpy.array([ fp[group.format(param=param, wi=wi)].attrs['acl'] for wi in widx]) return FieldArray.from_kwargs(**arrays)
def copy_samples(self, other, parameters=None, parameter_names=None, read_args=None, write_args=None): """Should copy samples to the other files. Parameters ---------- other : InferenceFile An open inference file to write to. parameters : list of str, optional List of parameters to copy. If None, will copy all parameters. parameter_names : dict, optional Rename one or more parameters to the given name. The dictionary should map parameter -> parameter name. If None, will just use the original parameter names. read_args : dict, optional Arguments to pass to ``read_samples``. write_args : dict, optional Arguments to pass to ``write_samples``. """ # select the samples to copy logging.info("Reading samples to copy") if parameters is None: parameters = self.variable_params # if list of desired parameters is different, rename if set(parameters) != set(self.variable_params): other.attrs['variable_params'] = parameters samples = self.read_samples(parameters, **read_args) logging.info("Copying {} samples".format(samples.size)) # if different parameter names are desired, get them from the samples if parameter_names: arrs = {pname: samples[p] for p, pname in parameter_names.items()} arrs.update({p: samples[p] for p in parameters if p not in parameter_names}) samples = FieldArray.from_kwargs(**arrs) other.attrs['variable_params'] = samples.fieldnames logging.info("Writing samples") other.write_samples(other, samples, **write_args)
def compute_acfs(cls, fp, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None, temps=None): """Computes the autocorrleation function of the variable args in the given file. 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 ----------- fp : InferenceFile An open file handler to read the samples from. 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. per_walker : optional, bool Return the ACF for each walker separately. Default is False. walkers : optional, int or array Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. 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 variable args. 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 ------- FieldArray A ``FieldArray`` of the ACF vs iteration for each parameter. If `per-walker` is True, the FieldArray will have shape ``ntemps x nwalkers x niterations``. Otherwise, the returned array will have shape ``ntemps x niterations``. """ acfs = {} if parameters is None: parameters = fp.variable_args if isinstance(parameters, str) or isinstance(parameters, unicode): parameters = [parameters] if isinstance(temps, int): temps = [temps] elif temps == 'all': temps = numpy.arange(fp.ntemps) elif temps is None: temps = [0] 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 = [ cls.compute_acfs(fp, 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 = cls.read_samples(fp, 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 # FIXME: the following if/else can be condensed to a single line # using numpy.stack, once the version requirements are bumped to # numpy >= 1.10 if per_walker: nw, ni = subacfs[0].shape acfs[param] = numpy.zeros((len(temps), nw, ni), dtype=float) for tk in range(len(temps)): acfs[param][tk, ...] = subacfs[tk] else: acfs[param] = numpy.vstack(subacfs) return FieldArray.from_kwargs(**acfs)
def copy(self, other, parameters=None, parameter_names=None, posterior_only=False, **kwargs): """Copies data in this file to another file. The samples and stats to copy may be down selected using the given kwargs. All other data (the "metadata") are copied exactly. Parameters ---------- other : str or InferenceFile The file to write to. May be either a string giving a filename, or an open hdf file. If the former, the file will be opened with the write attribute (note that if a file already exists with that name, it will be deleted). parameters : list of str, optional List of parameters to copy. If None, will copy all parameters. parameter_names : dict, optional Rename one or more parameters to the given name. The dictionary should map parameter -> parameter name. If None, will just use the original parameter names. posterior_only : bool, optional Write the samples and likelihood stats as flattened arrays, and set other's posterior_only attribute. For example, if this file has a parameter's samples written to `{samples_group}/{param}/walker{x}`, then other will have all of the selected samples from all walkers written to `{samples_group}/{param}/`. \**kwargs : All other keyword arguments are passed to `read_samples`. Returns ------- InferenceFile The open file handler to other. """ if not isinstance(other, h5py.File): # check that we're not trying to overwrite this file if other == self.name: raise IOError("destination is the same as this file") other = InferenceFile(other, 'w') # copy metadata over self.copy_metadata(other) # update other's posterior attribute if posterior_only: other.attrs['posterior_only'] = posterior_only # select the samples to copy logging.info("Reading samples to copy") if parameters is None: parameters = self.variable_args # if list of desired parameters is different, rename variable args if set(parameters) != set(self.variable_args): other.attrs['variable_args'] = parameters # if only the posterior is desired, we'll flatten the results if not posterior_only and not self.posterior_only: kwargs['flatten'] = False samples = self.read_samples(parameters, **kwargs) logging.info("Copying {} samples".format(samples.size)) # if different parameter names are desired, get them from the samples if parameter_names: arrs = {pname: samples[p] for p,pname in parameter_names.items()} arrs.update({p: samples[p] for p in parameters if p not in parameter_names}) samples = FieldArray.from_kwargs(**arrs) other.attrs['variable_args'] = samples.fieldnames logging.info("Writing samples") other.samples_parser.write_samples_group(other, self.samples_group, samples.fieldnames, samples) # do the same for the likelihood stats logging.info("Reading stats to copy") stats = self.read_likelihood_stats(**kwargs) logging.info("Writing stats") other.samples_parser.write_samples_group(other, self.stats_group, stats.fieldnames, stats) # if any down selection was done, re-set the burn in iterations and # the acl, and the niterations. # The last dimension of the samples returned by the sampler should # be the number of iterations. if samples.shape[-1] != self.niterations: other.attrs['acl'] = 1 other.attrs['burn_in_iterations'] = 0 other.attrs['niterations'] = samples.shape[-1] return other
def copy(self, other, parameters=None, parameter_names=None, posterior_only=False, **kwargs): """Copies data in this file to another file. The samples and stats to copy may be down selected using the given kwargs. All other data (the "metadata") are copied exactly. Parameters ---------- other : str or InferenceFile The file to write to. May be either a string giving a filename, or an open hdf file. If the former, the file will be opened with the write attribute (note that if a file already exists with that name, it will be deleted). parameters : list of str, optional List of parameters to copy. If None, will copy all parameters. parameter_names : dict, optional Rename one or more parameters to the given name. The dictionary should map parameter -> parameter name. If None, will just use the original parameter names. posterior_only : bool, optional Write the samples and likelihood stats as flattened arrays, and set other's posterior_only attribute. For example, if this file has a parameter's samples written to `{samples_group}/{param}/walker{x}`, then other will have all of the selected samples from all walkers written to `{samples_group}/{param}/`. \**kwargs : All other keyword arguments are passed to `read_samples`. Returns ------- InferenceFile The open file handler to other. """ if not isinstance(other, h5py.File): # check that we're not trying to overwrite this file if other == self.name: raise IOError("destination is the same as this file") other = InferenceFile(other, 'w') # copy metadata over self.copy_metadata(other) # update other's posterior attribute if posterior_only: other.attrs['posterior_only'] = posterior_only # select the samples to copy logging.info("Reading samples to copy") if parameters is None: parameters = self.variable_args # if list of desired parameters is different, rename variable args if set(parameters) != set(self.variable_args): other.attrs['variable_args'] = parameters # if only the posterior is desired, we'll flatten the results if not posterior_only and not self.posterior_only: kwargs['flatten'] = False samples = self.read_samples(parameters, **kwargs) logging.info("Copying {} samples".format(samples.size)) # if different parameter names are desired, get them from the samples if parameter_names: arrs = {pname: samples[p] for p,pname in parameter_names.items()} arrs.update({p: samples[p] for p in parameters if p not in parameter_names}) samples = FieldArray.from_kwargs(**arrs) other.attrs['variable_args'] = samples.fieldnames logging.info("Writing samples") other.samples_parser.write_samples_group(other, self.samples_group, samples.fieldnames, samples) # do the same for the likelihood stats logging.info("Reading stats to copy") stats = self.read_likelihood_stats(**kwargs) logging.info("Writing stats") other.samples_parser.write_samples_group(other, self.stats_group, stats.fieldnames, stats) # if any down selection was done, re-set the burn in iterations and # the acl, and the niterations. # The last dimension of the samples returned by the sampler should # be the number of iterations. if samples.shape[-1] != self.niterations: other.attrs['acl'] = 1 other.attrs['burn_in_iterations'] = 0 other.attrs['niterations'] = samples.shape[-1] return other
def create_density_plot(xparam, yparam, samples, plot_density=True, plot_contours=True, percentiles=None, cmap='viridis', contour_color=None, xmin=None, xmax=None, ymin=None, ymax=None, exclude_region=None, fig=None, ax=None, use_kombine=False): """Computes and plots posterior density and confidence intervals using the given samples. Parameters ---------- xparam : string The parameter to plot on the x-axis. yparam : string The parameter to plot on the y-axis. samples : dict, numpy structured array, or FieldArray The samples to plot. plot_density : {True, bool} Plot a color map of the density. plot_contours : {True, bool} Plot contours showing the n-th percentiles of the density. percentiles : {None, float or array} What percentile contours to draw. If None, will plot the 50th and 90th percentiles. cmap : {'viridis', string} The name of the colormap to use for the density plot. contour_color : {None, string} What color to make the contours. Default is white for density plots and black for other plots. xmin : {None, float} Minimum value to plot on x-axis. xmax : {None, float} Maximum value to plot on x-axis. ymin : {None, float} Minimum value to plot on y-axis. ymax : {None, float} Maximum value to plot on y-axis. exclue_region : {None, str} Exclude the specified region when plotting the density or contours. Must be a string in terms of `xparam` and `yparam` that is understandable by numpy's logical evaluation. For example, if `xparam = m_1` and `yparam = m_2`, and you want to exclude the region for which `m_2` is greater than `m_1`, then exclude region should be `'m_2 > m_1'`. fig : {None, pyplot.figure} Add the plot to the given figure. If None and ax is None, will create a new figure. ax : {None, pyplot.axes} Draw plot on the given axis. If None, will create a new axis from `fig`. use_kombine : {False, bool} Use kombine's KDE to calculate density. Otherwise, will use `scipy.stats.gaussian_kde.` Default is False. Returns ------- fig : pyplot.figure The figure the plot was made on. ax : pyplot.axes The axes the plot was drawn on. """ if percentiles is None: percentiles = numpy.array([50., 90.]) percentiles = 100. - percentiles percentiles.sort() if ax is None and fig is None: fig = pyplot.figure() if ax is None: ax = fig.add_subplot(111) # convert samples to array and construct kde xsamples = samples[xparam] ysamples = samples[yparam] arr = numpy.vstack((xsamples, ysamples)).T kde = construct_kde(arr, use_kombine=use_kombine) # construct grid to evaluate on if xmin is None: xmin = xsamples.min() if xmax is None: xmax = xsamples.max() if ymin is None: ymin = ysamples.min() if ymax is None: ymax = ysamples.max() npts = 100 X, Y = numpy.mgrid[xmin:xmax:complex(0,npts), ymin:ymax:complex(0,npts)] pos = numpy.vstack([X.ravel(), Y.ravel()]) if use_kombine: Z = numpy.exp(kde(pos.T).reshape(X.shape)) draw = kde.draw else: Z = kde(pos).T.reshape(X.shape) draw = kde.resample if exclude_region is not None: # convert X,Y to a single FieldArray so we can use it's ability to # evaluate strings farr = FieldArray.from_kwargs(**{xparam: X, yparam: Y}) Z[farr[exclude_region]] = 0. if plot_density: ax.imshow(numpy.rot90(Z), extent=[xmin, xmax, ymin, ymax], aspect='auto', cmap=cmap, zorder=1) if contour_color is None: contour_color = 'w' if plot_contours: # compute the percentile values resamps = kde(draw(int(npts**2))) if use_kombine: resamps = numpy.exp(resamps) s = numpy.percentile(resamps, percentiles) if contour_color is None: contour_color = 'k' # make linewidths thicker if not plotting density for clarity if plot_density: lw = 1 else: lw = 2 ct = ax.contour(X, Y, Z, s, colors=contour_color, linewidths=lw, zorder=3) # label contours lbls = ['{p}%'.format(p=int(p)) for p in (100. - percentiles)] fmt = dict(zip(ct.levels, lbls)) fs = 12 ax.clabel(ct, ct.levels, inline=True, fmt=fmt, fontsize=fs) return fig, ax
def compute_acfs(cls, fp, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None): """Computes the autocorrleation function of the model params in the given file. 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 ----------- fp : InferenceFile An open file handler to read the samples from. 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. per_walker : optional, bool Return the ACF for each walker separately. Default is False. walkers : optional, int or array Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. 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. Returns ------- FieldArray A ``FieldArray`` of the ACF vs iteration for each parameter. If `per-walker` is True, the FieldArray will have shape ``nwalkers x niterations``. """ acfs = {} if parameters is None: parameters = fp.variable_params if isinstance(parameters, str) or isinstance(parameters, unicode): 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 = [ cls.compute_acfs(fp, 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 = cls.read_samples(fp, 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 FieldArray.from_kwargs(**acfs)
def create_density_plot(xparam, yparam, samples, plot_density=True, plot_contours=True, percentiles=None, cmap='viridis', contour_color=None, xmin=None, xmax=None, ymin=None, ymax=None, exclude_region=None, fig=None, ax=None, use_kombine=False): """Computes and plots posterior density and confidence intervals using the given samples. Parameters ---------- xparam : string The parameter to plot on the x-axis. yparam : string The parameter to plot on the y-axis. samples : dict, numpy structured array, or FieldArray The samples to plot. plot_density : {True, bool} Plot a color map of the density. plot_contours : {True, bool} Plot contours showing the n-th percentiles of the density. percentiles : {None, float or array} What percentile contours to draw. If None, will plot the 50th and 90th percentiles. cmap : {'viridis', string} The name of the colormap to use for the density plot. contour_color : {None, string} What color to make the contours. Default is white for density plots and black for other plots. xmin : {None, float} Minimum value to plot on x-axis. xmax : {None, float} Maximum value to plot on x-axis. ymin : {None, float} Minimum value to plot on y-axis. ymax : {None, float} Maximum value to plot on y-axis. exclue_region : {None, str} Exclude the specified region when plotting the density or contours. Must be a string in terms of `xparam` and `yparam` that is understandable by numpy's logical evaluation. For example, if `xparam = m_1` and `yparam = m_2`, and you want to exclude the region for which `m_2` is greater than `m_1`, then exclude region should be `'m_2 > m_1'`. fig : {None, pyplot.figure} Add the plot to the given figure. If None and ax is None, will create a new figure. ax : {None, pyplot.axes} Draw plot on the given axis. If None, will create a new axis from `fig`. use_kombine : {False, bool} Use kombine's KDE to calculate density. Otherwise, will use `scipy.stats.gaussian_kde.` Default is False. Returns ------- fig : pyplot.figure The figure the plot was made on. ax : pyplot.axes The axes the plot was drawn on. """ if percentiles is None: percentiles = numpy.array([50., 90.]) percentiles = 100. - numpy.array(percentiles) percentiles.sort() if ax is None and fig is None: fig = pyplot.figure() if ax is None: ax = fig.add_subplot(111) # convert samples to array and construct kde xsamples = samples[xparam] ysamples = samples[yparam] arr = numpy.vstack((xsamples, ysamples)).T kde = construct_kde(arr, use_kombine=use_kombine) # construct grid to evaluate on if xmin is None: xmin = xsamples.min() if xmax is None: xmax = xsamples.max() if ymin is None: ymin = ysamples.min() if ymax is None: ymax = ysamples.max() npts = 100 X, Y = numpy.mgrid[xmin:xmax:complex(0, npts), # pylint:disable=invalid-slice-index ymin:ymax:complex(0, npts)] # pylint:disable=invalid-slice-index pos = numpy.vstack([X.ravel(), Y.ravel()]) if use_kombine: Z = numpy.exp(kde(pos.T).reshape(X.shape)) draw = kde.draw else: Z = kde(pos).T.reshape(X.shape) draw = kde.resample if exclude_region is not None: # convert X,Y to a single FieldArray so we can use it's ability to # evaluate strings farr = FieldArray.from_kwargs(**{xparam: X, yparam: Y}) Z[farr[exclude_region]] = 0. if plot_density: ax.imshow(numpy.rot90(Z), extent=[xmin, xmax, ymin, ymax], aspect='auto', cmap=cmap, zorder=1) if contour_color is None: contour_color = 'w' if plot_contours: # compute the percentile values resamps = kde(draw(int(npts**2))) if use_kombine: resamps = numpy.exp(resamps) s = numpy.percentile(resamps, percentiles) if contour_color is None: contour_color = 'k' # make linewidths thicker if not plotting density for clarity if plot_density: lw = 1 else: lw = 2 ct = ax.contour(X, Y, Z, s, colors=contour_color, linewidths=lw, zorder=3) # label contours lbls = ['{p}%'.format(p=int(p)) for p in (100. - percentiles)] fmt = dict(zip(ct.levels, lbls)) fs = 12 ax.clabel(ct, ct.levels, inline=True, fmt=fmt, fontsize=fs) return fig, ax
def compute_acfs(cls, fp, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None): """Computes the autocorrleation function of the variable args in the given file. 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 ----------- fp : InferenceFile An open file handler to read the samples from. 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. per_walker : optional, bool Return the ACF for each walker separately. Default is False. walkers : optional, int or array Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. 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 variable args. Returns ------- FieldArray A ``FieldArray`` of the ACF vs iteration for each parameter. If `per-walker` is True, the FieldArray will have shape ``nwalkers x niterations``. """ acfs = {} if parameters is None: parameters = fp.variable_args if isinstance(parameters, str) or isinstance(parameters, unicode): 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 = [cls.compute_acfs(fp, 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 = cls.read_samples(fp, 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 FieldArray.from_kwargs(**acfs)
def compute_acfs(cls, fp, start_index=None, end_index=None, per_walker=False, walkers=None, parameters=None, temps=None): """Computes the autocorrleation function of the variable args in the given file. 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 ----------- fp : InferenceFile An open file handler to read the samples from. 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. per_walker : optional, bool Return the ACF for each walker separately. Default is False. walkers : optional, int or array Calculate the ACF using only the given walkers. If None (the default) all walkers will be used. 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 variable args. 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 ------- FieldArray A ``FieldArray`` of the ACF vs iteration for each parameter. If `per-walker` is True, the FieldArray will have shape ``ntemps x nwalkers x niterations``. Otherwise, the returned array will have shape ``ntemps x niterations``. """ acfs = {} if parameters is None: parameters = fp.variable_args if isinstance(parameters, str) or isinstance(parameters, unicode): parameters = [parameters] if isinstance(temps, int): temps = [temps] elif temps == 'all': temps = numpy.arange(fp.ntemps) elif temps is None: temps = [0] 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 = [cls.compute_acfs(fp, 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 = cls.read_samples(fp, 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 # FIXME: the following if/else can be condensed to a single line # using numpy.stack, once the version requirements are bumped to # numpy >= 1.10 if per_walker: nw, ni = subacfs[0].shape acfs[param] = numpy.zeros((len(temps), nw, ni), dtype=float) for tk in range(len(temps)): acfs[param][tk,...] = subacfs[tk] else: acfs[param] = numpy.vstack(subacfs) return FieldArray.from_kwargs(**acfs)