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_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 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 compute_acf(cls, filename, 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
-----------
filename : str
Name of a samples file to compute ACFs 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.
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
-------
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 cls._io(filename, 'r') as fp:
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_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 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 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_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 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 compute_acf(cls, filename, start_index=None, end_index=None,
per_walker=False, walkers=None, parameters=None,
temps=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 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 : {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.
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 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 cls._io(filename, 'r') as fp:
if parameters is None:
parameters = fp.variable_params
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(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
