lalinference.bayespputils.Posterior Class Reference

Detailed Description

Data structure for a table of posterior samples .

Definition at line 901 of file bayespputils.py.

Inherits object.

Inherited by lalinference.bayespputils.BurstPosterior.

Public Member Functions
def	__init__ (self, commonResultsFormatData, SimInspiralTableEntry=None, inj_spin_frame='OrbitalL', injFref=100, SnglInspiralList=None, name=None, description=None)
	Constructor. More...
def	extend_posterior (self)
	Add some useful derived parameters (such as tilt angles, time delays, etc) in the Posterior object. More...
def	bootstrap (self)
	Returns a new Posterior object that contains a bootstrap sample of self. More...
def	delete_samples_by_idx (self, samples)
	Remove samples from all OneDPosteriors. More...
def	delete_NaN_entries (self, param_list)
	Remove samples containing NaN in request params. More...
def	DIC (self)
	Returns the Deviance Information Criterion estimated from the posterior samples. More...
def	injection (self)
	Return the injected values. More...
def	triggers (self)
	Return the trigger values . More...
def	longest_chain_cycles (self)
	Returns the number of cycles in the longest chain. More...
def	set_injection (self, injection)
	Set the injected values of the parameters. More...
def	set_triggers (self, triggers)
	Set the trigger values of the parameters. More...
def	__getitem__ (self, key)
	Container method . More...
def	__len__ (self)
	Container method. More...
def	__iter__ (self)
	Container method. More...
def	forward (self)
	Generate a forward iterator (in sense of list of names) over Posterior with name,one_d_pos. More...
def	bySample (self)
	Generate a forward iterator over the list of samples corresponding to the data stored within the Posterior instance. More...
def	dim (self)
	Return number of parameters. More...
def	names (self)
	Return list of parameter names. More...
def	means (self)
	Return dict {paramName:paramMean} . More...
def	medians (self)
	Return dict {paramName:paramMedian} . More...
def	stdevs (self)
	Return dict {paramName:paramStandardDeviation} . More...
def	name (self)
	Return qualified string containing the 'name' of the Posterior instance. More...
def	description (self)
	Return qualified string containing a 'description' of the Posterior instance. More...
def	append (self, one_d_posterior)
	Container method. More...
def	pop (self, param_name)
	Container method. More...
def	append_mapping (self, new_param_names, func, post_names)
	Append posteriors pos1,pos2,...=func(post_names) More...
def	di_evidence (self, boxing=64)
	Returns the log of the direct-integration evidence for the posterior samples. More...
def	elliptical_subregion_evidence (self)
	Returns an approximation to the log(evidence) obtained by fitting an ellipse around the highest-posterior samples and performing the harmonic mean approximation within the ellipse. More...
def	harmonic_mean_evidence (self)
	Returns the log of the harmonic mean evidence for the set of posterior samples. More...
def	maxL (self)
	Return the maximum likelihood probability and the corresponding set of parameters. More...
def	maxP (self)
	Return the maximum a posteriori probability and the corresponding set of parameters. More...
def	samples (self)
	Return an (M,N) numpy.array of posterior samples; M = len(self); N = dim(self) . More...
def	write_to_file (self, fname)
	Dump the posterior table to a file in the 'common format'. More...
def	gelman_rubin (self, pname)
	Returns an approximation to the Gelman-Rubin statistic (see Gelman, A. More...
def	healpix_map (self, resol, nest=True)
	Returns a healpix map in the pixel ordering that represents the posterior density (per square degree) on the sky. More...
def	__str__ (self)
	Define a string representation of the Posterior class ; returns a html formatted table of various properties of posteriors. More...

Constructor & Destructor Documentation

__init__()

def lalinference.bayespputils.Posterior.__init__	(		self,
			commonResultsFormatData,
			SimInspiralTableEntry = None,
			inj_spin_frame = 'OrbitalL',
			injFref = 100,
			SnglInspiralList = None,
			name = None,
			description = None
	)

Constructor.

Parameters

commonResultsFormatData	A 2D array containing the posterior samples and related data. The samples chains form the columns.
SimInspiralTableEntry	A SimInspiralTable row containing the injected values.
SnglInspiralList	A list of SnglInspiral objects containing the triggers.
inj_spin_frame	spin frame
injFref	reference frequency
name	optional name
description	optional description

Definition at line 915 of file bayespputils.py.

Member Function Documentation

extend_posterior()

def lalinference.bayespputils.Posterior.extend_posterior

(

self

)

Add some useful derived parameters (such as tilt angles, time delays, etc) in the Posterior object.

Definition at line 1023 of file bayespputils.py.

bootstrap()

def lalinference.bayespputils.Posterior.bootstrap

(

self

)

Returns a new Posterior object that contains a bootstrap sample of self.

Definition at line 1396 of file bayespputils.py.

delete_samples_by_idx()

def lalinference.bayespputils.Posterior.delete_samples_by_idx	(		self,
			samples
	)

Remove samples from all OneDPosteriors.

Parameters

samples

The indexes of the samples to be removed.

Definition at line 1420 of file bayespputils.py.

delete_NaN_entries()

def lalinference.bayespputils.Posterior.delete_NaN_entries	(		self,
			param_list
	)

Remove samples containing NaN in request params.

Parameters

param_list

The parameters to be checked for NaNs.

Definition at line 1430 of file bayespputils.py.

DIC()

def lalinference.bayespputils.Posterior.DIC

(

self

)

Returns the Deviance Information Criterion estimated from the posterior samples.

The DIC is defined as -2*(<log(L)> - Var(log(L))); smaller values are "better."

Definition at line 1454 of file bayespputils.py.

injection()

def lalinference.bayespputils.Posterior.injection

(

self

)

Return the injected values.

Definition at line 1463 of file bayespputils.py.

triggers()

def lalinference.bayespputils.Posterior.triggers

(

self

)

Return the trigger values .

Definition at line 1472 of file bayespputils.py.

longest_chain_cycles()

def lalinference.bayespputils.Posterior.longest_chain_cycles

(

self

)

Returns the number of cycles in the longest chain.

Definition at line 1490 of file bayespputils.py.

set_injection()

def lalinference.bayespputils.Posterior.set_injection	(		self,
			injection
	)

Set the injected values of the parameters.

Parameters

injection

A SimInspiralTable row object containing the injected parameters.

Definition at line 1514 of file bayespputils.py.

set_triggers()

def lalinference.bayespputils.Posterior.set_triggers	(		self,
			triggers
	)

Set the trigger values of the parameters.

Parameters

triggers

A list of SnglInspiral objects.

Definition at line 1527 of file bayespputils.py.

__getitem__()

def lalinference.bayespputils.Posterior.__getitem__	(		self,
			key
	)

Container method .

Returns posterior chain,one_d_pos, with name one_d_pos.name.

Definition at line 1568 of file bayespputils.py.

__len__()

def lalinference.bayespputils.Posterior.__len__

(

self

)

Container method.

Defined as number of samples.

Definition at line 1574 of file bayespputils.py.

__iter__()

def lalinference.bayespputils.Posterior.__iter__

(

self

)

Container method.

Returns iterator from self.forward for use in for (...) in (...) etc.

Definition at line 1581 of file bayespputils.py.

forward()

def lalinference.bayespputils.Posterior.forward

(

self

)

Generate a forward iterator (in sense of list of names) over Posterior with name,one_d_pos.

Definition at line 1588 of file bayespputils.py.

bySample()

def lalinference.bayespputils.Posterior.bySample

(

self

)

Generate a forward iterator over the list of samples corresponding to the data stored within the Posterior instance.

These are returned as ParameterSamples instances.

Definition at line 1601 of file bayespputils.py.

dim()

def lalinference.bayespputils.Posterior.dim

(

self

)

Return number of parameters.

Definition at line 1614 of file bayespputils.py.

names()

def lalinference.bayespputils.Posterior.names

(

self

)

Return list of parameter names.

Definition at line 1621 of file bayespputils.py.

means()

def lalinference.bayespputils.Posterior.means

(

self

)

Return dict {paramName:paramMean} .

Definition at line 1631 of file bayespputils.py.

medians()

def lalinference.bayespputils.Posterior.medians

(

self

)

Return dict {paramName:paramMedian} .

Definition at line 1641 of file bayespputils.py.

stdevs()

def lalinference.bayespputils.Posterior.stdevs

(

self

)

Return dict {paramName:paramStandardDeviation} .

Definition at line 1651 of file bayespputils.py.

name()

def lalinference.bayespputils.Posterior.name

(

self

)

Return qualified string containing the 'name' of the Posterior instance.

Definition at line 1661 of file bayespputils.py.

description()

def lalinference.bayespputils.Posterior.description

(

self

)

Return qualified string containing a 'description' of the Posterior instance.

Definition at line 1668 of file bayespputils.py.

append()

def lalinference.bayespputils.Posterior.append	(		self,
			one_d_posterior
	)

Container method.

Add a new OneDParameter to the Posterior instance.

Definition at line 1674 of file bayespputils.py.

pop()

def lalinference.bayespputils.Posterior.pop	(		self,
			param_name
	)

Container method.

Remove PosteriorOneDPDF from the Posterior instance.

Definition at line 1681 of file bayespputils.py.

append_mapping()

def lalinference.bayespputils.Posterior.append_mapping	(		self,
			new_param_names,
			func,
			post_names
	)

Append posteriors pos1,pos2,...=func(post_names)

Definition at line 1687 of file bayespputils.py.

di_evidence()

def lalinference.bayespputils.Posterior.di_evidence	(		self,
			boxing = 64
	)

Returns the log of the direct-integration evidence for the posterior samples.

Definition at line 1789 of file bayespputils.py.

elliptical_subregion_evidence()

def lalinference.bayespputils.Posterior.elliptical_subregion_evidence

(

self

)

Returns an approximation to the log(evidence) obtained by fitting an ellipse around the highest-posterior samples and performing the harmonic mean approximation within the ellipse.

Because the ellipse should be well-sampled, this provides a better approximation to the evidence than the full-domain HM.

Definition at line 1817 of file bayespputils.py.

harmonic_mean_evidence()

def lalinference.bayespputils.Posterior.harmonic_mean_evidence

(

self

)

Returns the log of the harmonic mean evidence for the set of posterior samples.

Definition at line 1884 of file bayespputils.py.

maxL()

def lalinference.bayespputils.Posterior.maxL

(

self

)

Return the maximum likelihood probability and the corresponding set of parameters.

Definition at line 1939 of file bayespputils.py.

maxP()

def lalinference.bayespputils.Posterior.maxP

(

self

)

Return the maximum a posteriori probability and the corresponding set of parameters.

Definition at line 1952 of file bayespputils.py.

samples()

def lalinference.bayespputils.Posterior.samples

(

self

)

Return an (M,N) numpy.array of posterior samples; M = len(self); N = dim(self) .

Definition at line 1965 of file bayespputils.py.

write_to_file()

def lalinference.bayespputils.Posterior.write_to_file	(		self,
			fname
	)

Dump the posterior table to a file in the 'common format'.

Definition at line 1978 of file bayespputils.py.

gelman_rubin()

def lalinference.bayespputils.Posterior.gelman_rubin	(		self,
			pname
	)

Returns an approximation to the Gelman-Rubin statistic (see Gelman, A.

and Rubin, D. B., Statistical Science, Vol 7, No. 4, pp. 457–511 (1992)) for the parameter given, accurate as the number of samples in each chain goes to infinity. The posterior samples must have a column named 'chain' so that the different chains can be separated.

Definition at line 1996 of file bayespputils.py.

healpix_map()

def lalinference.bayespputils.Posterior.healpix_map	(		self,
			resol,
			nest = True
	)

Returns a healpix map in the pixel ordering that represents the posterior density (per square degree) on the sky.

The pixels will be chosen to have at least the given resolution (in degrees).

Definition at line 2029 of file bayespputils.py.

__str__()

def lalinference.bayespputils.Posterior.__str__

(

self

)

Define a string representation of the Posterior class ; returns a html formatted table of various properties of posteriors.

Definition at line 2062 of file bayespputils.py.