def add_master_data(self, beast):
self.filters = {}
data = xml.data(beast,
id="data_%s" % self.name,
name="data_%s" % self.name,
dataType="integer")
for lang in self.languages:
formatted_points = [
self.format_datapoint(f, self.data[lang].get(f, ["?"]))
for f in self.features
]
value_string = self.data_separator.join(formatted_points)
if not self.filters:
n = 1
for f, x in zip(self.features, formatted_points):
# Format the FilteredAlignment filter appropriately
if self.data_separator:
length = len(x.split(self.data_separator))
else:
length = len(x)
if length == 1:
self.filters[f] = str(n)
else:
self.filters[f] = "%d-%d" % (n, n + length - 1)
n += length
xml.sequence(data,
id="language_data_%s:%s" % (self.name, lang),
taxon=lang,
value=value_string)
def add_single_sitemodel_likelihood(self, likelihood):
attribs = {
"id": "DataLikelihood:%s" % self.name,
"spec": "TreeLikelihood",
"useAmbiguities": "true",
"branchRateModel": "@%s" % self.clock.branchrate_model_id,
"tree": "@Tree.t:beastlingTree",
}
distribution = xml.distribution(likelihood, attrib=attribs)
if not self.reconstruct:
pass
elif set(self.reconstruct) >= set(self.features):
# Use a different likelihood spec (also depending on whether
# the whole tree is reconstructed, or only some nodes)
if self.treewide_reconstruction:
distribution.attrib["spec"] = "ancestralstatetreelikelihood"
self.treedata.append(attribs["id"])
distribution.attrib["tag"] = f
else:
distribution.attrib[
"spec"] = "lucl.beast.statereconstruction.ancestralstateslogger"
distribution.attrib["value"] = " ".join(self.pattern_names(f))
for label in self.reconstruct_at:
langs = self.config.language_group(label)
self.beastxml.add_taxon_set(distribution, label, langs)
self.metadata.append(attribs["id"])
distribution.attrib["useAmbiguities"] = "false"
else:
raise NotImplementedError(
"The model {:} is a binarised model with a single site "
"model, so it uses a global likelihood. Reconstructing "
"only a subset of features is not supported.".format(
self.name))
self.add_sitemodel(distribution, None, None)
data = xml.data(distribution,
id="filtered_data_%s" % self.name,
spec="FilteredAlignment",
data="@data_%s" % self.name,
filter="-")
if self.recoded:
data.set("ascertained", "true")
data.set("excludefrom", "0")
if self.ascertained:
data.set("excludeto", "2")
else:
data.set("excludeto", "1")
data.append(self.get_userdatatype(None, None))
def test_validate_ids(config_factory):
config = config_factory('basic')
bml = BeastXml(config)
xml.data(bml.beast, id='theid')
xml.data(bml.beast, id='theid')
with pytest.raises(ValueError, match='Duplicate'):
bml.validate_ids()
bml = BeastXml(config)
xml.data(bml.beast, idref='theid')
with pytest.raises(ValueError, match='missing'):
bml.validate_ids()
def add_data(self, distribution):
"""
Add <data> element corresponding to the indicated feature, descending
from the indicated likelihood distribution.
"""
data = xml.data(distribution,
id="locationData",
spec="sphericalGeo.AlignmentFromTraitMap")
traitmap = xml.traitMap(data,
id="geographyTraitmap",
spec="sphericalGeo.TreeTraitMap",
initByMean="true",
randomizelower="-90 -180",
randomizeupper="90 180",
traitName="location",
tree="@Tree.t:beastlingTree")
xml.parameter(traitmap,
text="0.0 0.0",
id="locationParameter",
spec="sphericalGeo.LocationParameter",
dimension=2 *
(2 * len(self.config.languages.languages) - 1),
minordimension="2")
loc_data_text_bits = []
for lang in self.config.languages.languages:
lat, lon = self.config.locations.get(lang, ("?", "?"))
if "?" in (lat, lon):
if lang not in self.sampling_points:
self.sampling_points.append(lang)
log.info(
"Location of language %s will be sampled. You may wish to add a prior."
% lang,
model=self)
else:
bit = "%s=%.2f %.2f" % (lang, lat, lon)
loc_data_text_bits.append(bit)
traitmap.text = ",\n".join(loc_data_text_bits)
xml.userDataType(data,
id="LocationDataType",
spec="sphericalGeo.LocationDataType")
def add_single_sitemodel_likelihood(self, likelihood):
attribs = {
"id": "DataLikelihood:%s" % self.name,
"spec": "TreeLikelihood",
"useAmbiguities": "true",
"branchRateModel": "@%s" % self.clock.branchrate_model_id,
"tree": "@Tree.t:beastlingTree",
}
distribution = xml.distribution(likelihood, attrib=attribs)
self.add_sitemodel(distribution, None, None)
data = xml.data(distribution,
id="filtered_data_%s" % self.name,
spec="FilteredAlignment",
data="@data_%s" % self.name,
filter="-")
if self.recoded:
data.set("ascertained", "true")
data.set("excludefrom", "0")
if self.ascertained:
data.set("excludeto", "2")
else:
data.set("excludeto", "1")
data.append(self.get_userdatatype(None, None))
def add_feature_data(self, distribution, index, feature, fname):
"""
Add <data> element corresponding to the indicated feature, descending
from the indicated likelihood distribution.
"""
if self.pruned:
parent = xml.data(distribution,
id="pruned_data_%s" % fname,
spec="PrunedAlignment")
name = "source"
else:
parent = distribution
name = "data"
data = getattr(xml, name)(parent,
id="feature_data_%s" % fname,
spec="FilteredAlignment",
data="@data_%s" % self.name,
filter=self.filters[feature])
if self.ascertained:
data.set("ascertained", "true")
data.set("excludefrom", "0")
data.set("excludeto", str(self.valuecounts[feature]))
data.append(self.get_userdatatype(feature, fname))
return data