def tree_from_splits(self,
split_distribution,
min_freq=0.5,
include_edge_lengths=True):
"""Returns a consensus tree from splits in `split_distribution`.
If include_edge_length_var is True, then the sample variance of the
edge length will also be calculated and will be stored as
a length_var attribute.
"""
taxon_set = split_distribution.taxon_set
taxa_mask = taxon_set.all_taxa_bitmask()
if self.weighted_splits:
split_freqs = split_distribution.weighted_split_frequencies
else:
split_freqs = split_distribution.split_frequencies
is_rooted = split_distribution.is_rooted
#include_edge_lengths = self.support_as_labels and include_edge_lengths
if self.support_as_edge_lengths and include_edge_lengths:
raise Exception("Cannot map support as edge lengths if edge lengths are to be set on consensus tree")
to_try_to_add = []
_almost_one = lambda x: abs(x - 1.0) <= 0.0000001
for s, freq in split_freqs.iteritems():
if (min_freq is None) or (freq > min_freq) or (_almost_one(min_freq) and _almost_one(freq)):
to_try_to_add.append((freq, s))
to_try_to_add.sort(reverse=True)
splits_for_tree = [i[1] for i in to_try_to_add]
con_tree = treesplit.tree_from_splits(splits=splits_for_tree,
taxon_set=taxon_set,
is_rooted=is_rooted)
treesplit.encode_splits(con_tree)
if include_edge_lengths:
split_edge_lengths = {}
for split, edges in split_distribution.split_edge_lengths.items():
if len(edges) > 0:
mean, var = mean_and_sample_variance(edges)
elen = mean
else:
elen = None
split_edge_lengths[split] = elen
else:
split_edge_lengths = None
for node in con_tree.postorder_node_iter():
split = node.edge.split_bitmask
if split in split_freqs:
self.map_split_support_to_node(node=node, split_support=split_freqs[split])
if include_edge_lengths and split in split_distribution.split_edge_lengths:
edges = split_distribution.split_edge_lengths[split]
if len(edges) > 0:
mean, var = mean_and_sample_variance(edges)
elen = mean
else:
elen = None
node.edge.length = elen
return con_tree
def testReferenceTree(self):
ref_tree_list = datagen.reference_tree_list()
t_tree_list = dendropy.TreeList()
for ref_tree in ref_tree_list:
treesplit.encode_splits(ref_tree)
splits = ref_tree.split_edges.keys()
t_tree = treesplit.tree_from_splits(splits=splits,
taxon_set=ref_tree_list.taxon_set,
is_rooted=ref_tree.is_rooted)
self.assertEqual(ref_tree.symmetric_difference(t_tree), 0)
def testReferenceTree(self):
ref_tree_list = datagen.reference_tree_list()
t_tree_list = dendropy.TreeList()
for ref_tree in ref_tree_list:
treesplit.encode_splits(ref_tree)
splits = ref_tree.split_edges.keys()
t_tree = treesplit.tree_from_splits(splits=splits,
taxon_set=ref_tree_list.taxon_set,
is_rooted=ref_tree.is_rooted)
self.assertEqual(ref_tree.symmetric_difference(t_tree), 0)
def calc_tree_freqs(self, taxon_set, is_rooted=False):
"""
Returns an ordered dictionary (OrderedDict) of DendroPy trees mapped
to a tuple, (raw numbers of occurrences, proportion of total trees
counted) in (descending) order of the proportion of occurrence.
"""
hash_freqs = self.calc_hash_freqs()
tree_freqs = OrderedDict()
for topology_hash, (count, freq) in hash_freqs.items():
tree = treesplit.tree_from_splits(splits=topology_hash,
taxon_set=taxon_set,
is_rooted=is_rooted)
tree_freqs[tree] = (count, freq)
return tree_freqs
def testUltrametricTrees(self):
tree_files = [
"pythonidae.beast.summary.tre", "primates.beast.mcct.medianh.tre"
]
for tree_file in tree_files:
ref_tree = dendropy.Tree.get_from_path(
pathmap.tree_source_path(tree_file), "nexus", as_rooted=True)
treesplit.encode_splits(ref_tree)
splits = ref_tree.split_edges.keys()
t_tree = treesplit.tree_from_splits(splits=splits,
taxon_set=ref_tree.taxon_set,
is_rooted=ref_tree.is_rooted)
treesplit.encode_splits(t_tree)
self.assertEqual(ref_tree.symmetric_difference(t_tree), 0)
def testUltrametricTrees(self):
tree_files = [
"pythonidae.beast.summary.tre",
"primates.beast.mcct.medianh.tre"
]
for tree_file in tree_files:
ref_tree = dendropy.Tree.get_from_path(pathmap.tree_source_path(tree_file),
"nexus",
as_rooted=True)
treesplit.encode_splits(ref_tree)
splits = ref_tree.split_edges.keys()
t_tree = treesplit.tree_from_splits(splits=splits,
taxon_set=ref_tree.taxon_set,
is_rooted=ref_tree.is_rooted)
treesplit.encode_splits(t_tree)
self.assertEqual(ref_tree.symmetric_difference(t_tree), 0)