def testReroot(self):
newick = "((t5,t6),((t4,(t2,t1)),t3));"
d = dataio.trees_from_newick([newick])
tree = d.trees_blocks[0][0]
taxa_block = d.taxa_blocks[0]
ref = dataio.trees_from_newick(
[newick], taxa_block=taxa_block).trees_blocks[0][0]
encode_splits(ref)
o_newick = "((t2, t1),((t4,(t5,t6)),t3));"
o_tree = dataio.trees_from_newick(
[o_newick], taxa_block=taxa_block).trees_blocks[0][0]
encode_splits(o_tree)
self.assertEqual(symmetric_difference(o_tree, ref), 2)
taxa_labels = ["t%d" % i for i in xrange(1, 7)]
for leaf_name in taxa_labels:
f = lambda x: x.label == leaf_name
nd = tree.find_taxon_node(f)
tree.to_outgroup_position(nd)
r_newick = str(tree)
r_tree = dataio.trees_from_newick(
[r_newick], taxa_block=taxa_block).trees_blocks[0][0]
encode_splits(r_tree)
self.assertEqual(symmetric_difference(r_tree, ref), 0)
def testCollapseClade(self):
tree = dataio.trees_from_newick(["(t5,t6,((t4,(t2,t1)),t3));"
]).trees_blocks[0][0]
encode_splits(tree)
root = tree.seed_node
root_children = root.child_nodes()
fc = root_children[0]
collapse_clade(fc)
tree.debug_check_tree(splits=True)
self.assertEqual(str(tree), "(t5,t6,((t4,(t2,t1)),t3))")
fc2 = root_children[2]
fc2children = fc2.child_nodes()
t124child = fc2children[0]
collapse_clade(t124child)
tree.debug_check_tree(logger_obj=_LOG)
self.assertEqual(str(tree), "(t5,t6,((t4,t2,t1),t3))")
collapse_clade(fc2)
tree.debug_check_tree(logger_obj=_LOG)
self.assertEqual(str(tree), "(t5,t6,(t4,t2,t1,t3))")
collapse_clade(root)
tree.debug_check_tree(logger_obj=_LOG)
tree.debug_check_tree(logger_obj=_LOG)
self.assertEqual(str(tree), "(t5,t6,t4,t2,t1,t3)")
tree = dataio.trees_from_newick(["((t5,t6),((t4,(t2,t1)),t3));"
]).trees_blocks[0][0]
root = tree.seed_node
collapse_clade(root)
tree.debug_check_tree(logger_obj=_LOG)
self.assertEqual(str(tree), "(t5,t6,t4,t2,t1,t3)")
def testRerootSplits(self):
newick = "((Athrotaxi,(Callitris,(Juniperusc,Libocedrus))),(((((((Basichlsac,(Mougeotisp,Lamprothma)),Thuidium),(Petalaphy,Haplomitr2)),((Botrychbit,(Vittarifle,((Dicksonant,((Polypodapp,Oleandrapi),Dennstasam)),Azollacaro))),Angiopteri)),Isoetesmel),((Sagittari,(Calochort,(Tacca,(Calathea,Ravenala)))),((Nelumbo,((((((Verbena,((Thunbergi,Acanthus),(Proboscid,Harpogoph))),Asclepias),Menyanthe),(Phyllonom,(Chamaedap,Pyrola))),((((Mirabilus,Pisum),Circaea),((Rheinward,Octomeles),Greyia)),Dudleya)),Phoradend)),(((Liriodchi,Annona),Gyrocarpu),Illicium)))),(Pseudotsu,(Agathisova,Agathismac))));"
d = dataio.trees_from_newick([newick])
tree = d.trees_blocks[0][0]
taxa_block = d.taxa_blocks[0]
ref = dataio.trees_from_newick(
[newick], taxa_block=taxa_block).trees_blocks[0][0]
encode_splits(tree)
encode_splits(ref)
r = tree.seed_node
curr_n = r.child_nodes()[1]
former_mask = curr_n.edge.clade_mask
tm = r.edge.clade_mask
nbits = count_bits(tm)
from dendropy.splits import split_as_string
tree.reroot_at(curr_n, splits=True, delete_deg_two=False)
new_root = tree.seed_node
self.assertEqual(tm, new_root.edge.clade_mask)
self.assertEqual(True, new_root is curr_n)
self.assertEqual(True, r.parent_node is curr_n)
flipped = (~(r.edge.clade_mask)) & tm
self.assertEqual(True, (former_mask == r.edge.clade_mask)
or (flipped == former_mask))
def testConflict(self):
o = [
'(1,5,(2,((3,6),4)))',
'(2,1,(3,(6,4)))',
]
m = [o[0], o[1], '(1,5,(2,(3,6,4)))']
n = list(m)
dataset = trees_from_newick(n,
taxa_block=TaxaBlock(
[str(i) for i in xrange(1, 7)]))
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
rng = DebuggingRandom()
for i in xrange(50):
n = list(m)
dataset = trees_from_newick(n,
taxa_block=TaxaBlock(
[str(i) for i in xrange(1, 7)]))
trees = [i[0] for i in dataset.trees_blocks]
for t in trees:
randomly_reorient_tree(t, rng=rng)
self.kernelOfTest(trees)
o = [
'(1,5,(3,((2,6),4)))',
'(2,1,(3,(6,4)))',
]
n = [o[0], o[1], '((1,5),2,3,6,4)']
dataset = trees_from_newick(n,
taxa_block=TaxaBlock(
[str(i) for i in xrange(1, 7)]))
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def dofour_five_compat(self, four_taxon_newick, five_taxon_newick):
#sys.stdout.write("\n4 taxon:%s\n" % four_taxon_newick)
#sys.stdout.write("5 taxon:%s\n" % five_taxon_newick)
dataset = trees_from_newick(
[five_taxon_newick, four_taxon_newick, five_taxon_newick])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
# make sure that the behavior is not order dependent
dataset = trees_from_newick(
[four_taxon_newick, five_taxon_newick, five_taxon_newick])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testSymmDiff(self):
newick = "((t5,t6),((t4,(t2,t1)),t3));"
d = dataio.trees_from_newick([newick])
ref = d.trees_blocks[0][0]
taxa_block = d.taxa_blocks[0]
encode_splits(ref)
o_newick = "((t1,t2),((t4,(t5,t6)),t3));"
o_tree = dataio.trees_from_newick(
[o_newick], taxa_block=taxa_block).trees_blocks[0][0]
encode_splits(o_tree)
self.assertEqual(treedists.symmetric_difference(o_tree, ref), 2)
def testEuclideanDist(self):
d = dataio.trees_from_newick([
"((t5:0.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
"((t5:2.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
"((t5:0.161175,t6:0.161175):0.392293,((t2:0.075411,(t4:0.104381,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
"((t5:0.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):0.028969):0.065840,t3:0.170221):0.383247);",
])
tree_list = [i[0] for i in d.trees_blocks]
#print "\n".join([str(i) for i in tree_list])
for i in tree_list:
encode_splits(i)
assert_approx_equal(
treedists.euclidean_distance(tree_list[0], tree_list[1]), 2.0)
assert_approx_equal(
treedists.euclidean_distance(tree_list[0], tree_list[2]),
math.sqrt(2.0))
assert_approx_equal(
treedists.euclidean_distance(tree_list[0], tree_list[3]),
0.97103099999999998)
assert_approx_equal(
treedists.euclidean_distance(tree_list[1], tree_list[2]),
math.sqrt(6.0))
assert_approx_equal(
treedists.euclidean_distance(tree_list[1], tree_list[3]),
2.2232636377544162)
assert_approx_equal(
treedists.euclidean_distance(tree_list[2], tree_list[3]),
1.000419513484718)
def testCladeMasks(self):
dataset = dataio.trees_from_newick([
"((t5:0.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
])
tree_list = [i[0] for i in dataset.trees_blocks]
for i in tree_list:
_LOG.debug(i.get_indented_form())
encode_splits(i)
_LOG.debug(i.get_indented_form(splits=True))
i.debug_check_tree(splits=True, logger_obj=_LOG)
root1 = tree_list[0].seed_node
root1e = root1.edge
self.assertEqual(split_to_list(root1e.clade_mask), range(6))
self.assertEqual(split_to_list(root1e.clade_mask, one_based=True), range(1,7))
self.assertEqual(split_to_list(root1e.clade_mask, mask=21, one_based=True), [1, 3, 5])
self.assertEqual(split_to_list(root1e.clade_mask, mask=21), [0, 2, 4])
self.assertEqual(count_bits(root1e.clade_mask), 6)
fc1 = root1.child_nodes()[0]
fc1e = fc1.edge
self.assertEqual(split_to_list(fc1e.clade_mask), [0, 1])
self.assertEqual(split_to_list(fc1e.clade_mask, one_based=True), [1, 2])
self.assertEqual(split_to_list(fc1e.clade_mask, mask=0x15, one_based=True), [1])
self.assertEqual(split_to_list(fc1e.clade_mask, mask=0x15), [0])
self.assertEqual(count_bits(fc1e.clade_mask), 2)
def testOrderDependent(self):
o = ['(1,5,(2,(3,4)))', '(2,4,(3,(6,7)))', '(3,4,(6,(7,8)))']
n = [o[0], o[2], o[1], '(1,2,3,4,5,6,7,8)']
dataset = trees_from_newick(n)
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
expected = '(1,5,(2,((3,(6,(7,8))),4)))'
dataset = trees_from_newick(o + [expected])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
o.reverse()
dataset = trees_from_newick(o + [expected])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testThree(self):
o = [
'(Athrotaxi,(Liriodchi,Nelumbo),Sagittari);',
'(Basichlsac,(Lamprothma,Mougeotisp),(((Haplomitr2,Petalaphy),((Angiopteri,(((Azollacaro,((Dennstasam,(Oleandrapi,Polypodapp)),Dicksonant)),Vittarifle),Botrychbit)),(Isoetesmel,((((Agathismac,Agathisova),Pseudotsu),(((Libocedrus,Juniperusc),Callitris),Athrotaxi)),((Liriodchi,Nelumbo),Sagittari))))),Thuidium));',
'(Athrotaxi,((((((((Verbena,((Thunbergi,Acanthus),(Proboscid,Harpogoph))),Asclepias),Menyanthe),(Phyllonom,(Chamaedap,Pyrola))),((((Mirabilus,Pisum),Circaea),((Rheinward,Octomeles),Greyia)),Dudleya)),Phoradend),Nelumbo),Liriodchi),Sagittari);',
'(Athrotaxi,((((Liriodchi,Annona),Gyrocarpu),Illicium),Nelumbo),((((Ravenala,Calathea),Tacca),Calochort),Sagittari));',
]
expected = '((Athrotaxi,(Callitris,(Juniperusc,Libocedrus))),(((((((Basichlsac,(Mougeotisp,Lamprothma)),Thuidium),(Petalaphy,Haplomitr2)),((Botrychbit,(Vittarifle,((Dicksonant,((Polypodapp,Oleandrapi),Dennstasam)),Azollacaro))),Angiopteri)),Isoetesmel),((Sagittari,(Calochort,(Tacca,(Calathea,Ravenala)))),((Nelumbo,((((((Verbena,((Thunbergi,Acanthus),(Proboscid,Harpogoph))),Asclepias),Menyanthe),(Phyllonom,(Chamaedap,Pyrola))),((((Mirabilus,Pisum),Circaea),((Rheinward,Octomeles),Greyia)),Dudleya)),Phoradend)),(((Liriodchi,Annona),Gyrocarpu),Illicium)))),(Pseudotsu,(Agathisova,Agathismac))));'
n = o + [expected]
dataset = trees_from_newick(n)
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
o.reverse()
n = o + [expected]
dataset = trees_from_newick(n)
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testPolytomy(self):
dataset = trees_from_newick([
'(Athrotaxi,(Liriodchi,Nelumbo2),Sagittari2);',
'(Basichlsac,(Lamprothma,Mougeotisp),(((Haplomitr2,Petalaphy),((Angiopteri,(((Azollacaro,((Dennstasam,(Oleandrapi,Polypodapp)),Dicksonant)),Vittarifle),Botrychbit)),(Isoetesmel,((((Agathismac,Agathisova),Pseudotsu),(((Libocedrus,Juniperusc),Callitris),Athrotaxi)),((Liriodchi,Nelumbo),Sagittari))))),Thuidium));',
'(Athrotaxi,Liriodchi,Nelumbo2,Sagittari2,Basichlsac,Lamprothma,Mougeotisp,Haplomitr2,Petalaphy,Angiopteri,Azollacaro,Dennstasam,Oleandrapi,Polypodapp,Dicksonant,Vittarifle,Botrychbit,Isoetesmel,Agathismac,Agathisova,Pseudotsu,Libocedrus,Juniperusc,Callitris,Nelumbo,Sagittari,Thuidium);',
])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testInsertPath(self):
dataset = trees_from_newick([
'(((1,2),3),4,5);',
'(1,2,(3,(7,(8,(9,(4,5))))));',
'(1,2,(3,(7,(8,(9,(4,5))))));',
])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testMultiEdgeCollision(self):
dataset = trees_from_newick([
'(1,2,(3,(4,(5,6))));',
'(1,2,(3,(7,(8,6))));',
'(1,2,(3,(4,5,6,7,8)));',
])
trees = [i[0] for i in dataset.trees_blocks]
self.kernelOfTest(trees)
def testCollapseEdge(self):
tree = dataio.trees_from_newick(["((t5,t6),((t4,(t2,t1)),t3));"
]).trees_blocks[0][0]
root = tree.seed_node
self.assertEqual(str(tree), "((t5,t6),((t4,(t2,t1)),t3))")
fc = root.child_nodes()[0]
collapse_edge(fc.edge)
tree.debug_check_tree(logger_obj=_LOG)
self.assertEqual(str(tree), "(t5,t6,((t4,(t2,t1)),t3))")
def testRandomlyReorient(self):
n = '(Basichlsac,(Lamprothma,Mougeotisp),(((Haplomitr2,Petalaphy),((Angiopteri,(((Azollacaro,((Dennstasam,(Oleandrapi,Polypodapp)),Dicksonant)),Vittarifle),Botrychbit)),(Isoetesmel,((((Agathismac,Agathisova),Pseudotsu),(((Libocedrus,Juniperusc),Callitris),Athrotaxi)),((Liriodchi,Nelumbo),Sagittari))))),Thuidium));'
m = [n, n]
dataset = dataio.trees_from_newick(m)
trees = [i[0] for i in dataset.trees_blocks]
ref = trees[0]
changing = trees[1]
rng = DebuggingRandom()
encode_splits(ref)
encode_splits(changing)
for i in xrange(50):
randomly_reorient_tree(changing, rng=rng, splits=True)
self.assertNotEqual(str(changing), n)
changing.debug_check_tree(logger_obj=_LOG, splits=True)
if symmetric_difference(ref, changing) != 0:
self.fail("\n%s\n!=\n%s" % (str(ref), str(changing)))
def pairwiseMerger(self, tree1, tree2):
data = trees_from_newick((tree1, tree2))
trees = [i[0] for i in data.trees_blocks]
output = strict_consensus_merge(trees,
gordons_supertree=self.useGordons)
return (str(output))
help="Specify to use the Gordon's strict consensus")
(options, args) = parser.parse_args()
if len(args) == 0:
sys.exit("Expecting a filename as an argument")
format = options.format.upper()
trees = []
if format == "NEXUS" or format == "NEXML":
for fn in args:
fo = open(fn, "rU")
d = dataset_from_file(fo, format=format)
t = []
for tb in d.trees_blocks:
t.extend(tb)
trees.extend(t)
elif format == "PHYLIP" or format == "NEWICK":
newicks = []
for f in args:
fo = open(f, "rU")
for line in fo:
l = line.strip()
if l:
newicks.append(l)
dataset = trees_from_newick(newicks)
trees = [i[0] for i in dataset.trees_blocks]
else:
sys.exit("Unknown format %s" % format)
o = strict_consensus_merge(trees, gordons_supertree=options.gordons)
sys.stdout.write("%s;\n" % str(o))
