def simulate(self,
calculatePatterns=True,
resetSequences=True,
resetNexusSetsConstantMask=True):
"""Simulate into the attached data.
The tree self needs to have a data and model attached.
This week, generation of random numbers uses the C language random
function, which is in stdlib on Linux. It will use the same
series of random numbers over and over, unless you tell it
otherwise. That means that (unless you tell it otherwise) it will
generate the same simulated data if you run it twice. To reset
the randomizer, you can use func.reseedCRandomizer(), eg
func.reseedCRandomizer(os.getpid())
"""
self._commonCStuff()
# If there is a NexusSets object attached to any of the alignments
# in the Data, the constant sites mask at least will become out of sync, but we can't just
# delete the whole nexusSets object, as they define what the parts are.
#for a in self.data.alignments:
#
# if a.nexusSets:
# a.nexusSets = None
# Probably better to do something like this
# a.nexusSets.constant.mask = self.constantMask()
# at the end.
#print "About to pf.p4_simulate(self.cTree)"
pf.p4_simulate(self.cTree)
if calculatePatterns:
for p in self.data.parts:
pf.makePatterns(p.cPart)
pf.setGlobalInvarSitesVec(p.cPart)
if resetSequences:
self.data.resetSequencesFromParts()
if resetNexusSetsConstantMask:
for a in self.data.alignments:
if a.nexusSets:
a.nexusSets.constant.mask = a.constantMask()
else:
if resetNexusSetsConstantMask:
gm = ['Tree.simulate().']
gm.append(
"resetSequences is not set, but resetNexusSetsConstantMask is set,"
)
gm.append("which is probably not going to work as you want.")
raise Glitch, gm
def simulate(self, calculatePatterns=True, resetSequences=True, resetNexusSetsConstantMask=True):
"""Simulate into the attached data.
The tree self needs to have a data and model attached.
This week, generation of random numbers uses the C language random
function, which is in stdlib on Linux. It will use the same
series of random numbers over and over, unless you tell it
otherwise. That means that (unless you tell it otherwise) it will
generate the same simulated data if you run it twice. To reset
the randomizer, you can use func.reseedCRandomizer(), eg
func.reseedCRandomizer(os.getpid())
"""
self._commonCStuff()
# If there is a NexusSets object attached to any of the alignments
# in the Data, the constant sites mask at least will become out of sync, but we can't just
# delete the whole nexusSets object, as they define what the parts are.
#for a in self.data.alignments:
#
# if a.nexusSets:
# a.nexusSets = None
# Probably better to do something like this
# a.nexusSets.constant.mask = self.constantMask()
# at the end.
#print "About to pf.p4_simulate(self.cTree)"
pf.p4_simulate(self.cTree)
if calculatePatterns:
for p in self.data.parts:
pf.makePatterns(p.cPart)
pf.setGlobalInvarSitesVec(p.cPart)
if resetSequences:
self.data.resetSequencesFromParts()
if resetNexusSetsConstantMask:
for a in self.data.alignments:
if a.nexusSets:
a.nexusSets.constant.mask = a.constantMask()
else:
if resetNexusSetsConstantMask:
gm = ['Tree.simulate().']
gm.append("resetSequences is not set, but resetNexusSetsConstantMask is set,")
gm.append("which is probably not going to work as you want.")
raise Glitch(gm)
def simulate(self, calculatePatterns=True, resetSequences=True, resetNexusSetsConstantMask=True, refTree=None):
"""Simulate into the attached data.
The tree self needs to have a data and model attached.
This week, generation of random numbers uses the C language random
function, which is in stdlib on Linux. It will use the same
series of random numbers over and over, unless you tell it
otherwise. That means that (unless you tell it otherwise) it will
generate the same simulated data if you run it twice. To reset
the randomizer, you can use func.reseedCRandomizer(), eg
func.reseedCRandomizer(os.getpid())
The usual way to simulate does not use reference data. An unsual way to
simulate comes from (inspired by?) PhyloBayes, where the simulation is
conditional on the original data. It uses conditional likelihoods of
that reference data at the root. To turn that on, set refTree to the
tree+model+data that you would like to use. Calculate a likelihood with
that refTree before using it, so that conditional likelihoods are set.
The tree and model for refTree should be identical to the tree and model
for self.
Args:
calculatePatterns (bool): True by default. Whether to "compress" the
newly simulated data to facilitate a faster likelihood
calculation.
resetSequences (bool): True by default. whether to bring the
simulated sequences in C back into Python
resetNexusSetsConstantMask (bool): True by default. When
simulations are made, the constant mask in any associated nexus
sets will get out of sync. Setting this to True makes a new
mask and sets it.
refTree (Tree): None by default. If supplied, a tree+model+data
which has had its likelihood calculated, where the tree+model is
identical to self.
"""
if refTree:
from tree import Tree
assert isinstance(refTree, Tree)
assert refTree.model
assert refTree.data
if not refTree.cTree:
refTree.calcLogLike(verbose=False)
assert refTree.model.cModel
assert refTree.data.cData
self._commonCStuff()
if refTree:
assert refTree.data.cData != self.data.cData
assert refTree.data.nParts == self.data.nParts
assert refTree.data.nTax == self.data.nTax
for i in range(self.data.nTax):
assert refTree.data.taxNames[i] == self.data.taxNames[i]
assert len(refTree.data.alignments) == len(self.data.alignments)
assert refTree.logLike, "Do a likelihood calculation with the refTree before using it here."
# could have some more checks ...
# If there is a NexusSets object attached to any of the alignments
# in the Data, the constant sites mask at least will become out of sync, but we can't just
# delete the whole nexusSets object, as they define what the parts are.
# for a in self.data.alignments:
#
# if a.nexusSets:
# a.nexusSets = None
# Probably better to do something like this
# a.nexusSets.constant.mask = self.constantMask()
# at the end.
# print "About to pf.p4_simulate(self.cTree)"
if refTree:
pf.p4_simulate(self.cTree, refTree.cTree)
else:
pf.p4_simulate(self.cTree, 0)
if calculatePatterns:
for p in self.data.parts:
pf.makePatterns(p.cPart)
pf.setGlobalInvarSitesVec(p.cPart)
if resetSequences:
self.data.resetSequencesFromParts()
if resetNexusSetsConstantMask:
for a in self.data.alignments:
if a.nexusSets:
a.nexusSets.constant.mask = a.constantMask()
else:
if resetNexusSetsConstantMask:
gm = ['Tree.simulate().']
gm.append(
"resetSequences is not set, but resetNexusSetsConstantMask is set,")
gm.append("which is probably not going to work as you want.")
raise P4Error(gm)
