def setUp(self):
"""Prep the self"""
self.simple_t = TreeNode.read(StringIO(u"((a,b)i1,(c,d)i2)root;"))
nodes = dict([(x, TreeNode(x)) for x in 'abcdefgh'])
nodes['a'].append(nodes['b'])
nodes['b'].append(nodes['c'])
nodes['c'].append(nodes['d'])
nodes['c'].append(nodes['e'])
nodes['c'].append(nodes['f'])
nodes['f'].append(nodes['g'])
nodes['a'].append(nodes['h'])
self.TreeNode = nodes
self.TreeRoot = nodes['a']
def rev_f(items):
items.reverse()
def rotate_f(items):
tmp = items[-1]
items[1:] = items[:-1]
items[0] = tmp
self.rev_f = rev_f
self.rotate_f = rotate_f
self.complex_tree = TreeNode.read(
StringIO(u"(((a,b)int1,(x,y,(w,z)int"
"2,(c,d)int3)int4),(e,f)int"
"5);"))
def test_tip_tip_distances_missing_length(self):
t = TreeNode.read(StringIO(u"((a,b:6)c:4,(d,e:0)f);"))
exp_t = TreeNode.read(StringIO(u"((a:0,b:6)c:4,(d:0,e:0)f:0);"))
exp_t_dm = exp_t.tip_tip_distances()
t_dm = npt.assert_warns(RepresentationWarning, t.tip_tip_distances)
self.assertEqual(t_dm, exp_t_dm)
def test_validate_otu_ids_and_tree(self):
# basic valid input
t = TreeNode.read(
StringIO(u'(((((OTU1:0.5,OTU2:0.5):0.5,OTU3:1.0):1.0):0.0,(OTU4:'
u'0.75,OTU5:0.75):1.25):0.0)root;'))
counts = [1, 1, 1]
otu_ids = ['OTU1', 'OTU2', 'OTU3']
self.assertTrue(_validate_otu_ids_and_tree(counts, otu_ids, t) is None)
# all tips observed
t = TreeNode.read(
StringIO(u'(((((OTU1:0.5,OTU2:0.5):0.5,OTU3:1.0):1.0):0.0,(OTU4:'
u'0.75,OTU5:0.75):1.25):0.0)root;'))
counts = [1, 1, 1, 1, 1]
otu_ids = ['OTU1', 'OTU2', 'OTU3', 'OTU4', 'OTU5']
self.assertTrue(_validate_otu_ids_and_tree(counts, otu_ids, t) is None)
# no tips observed
t = TreeNode.read(
StringIO(u'(((((OTU1:0.5,OTU2:0.5):0.5,OTU3:1.0):1.0):0.0,(OTU4:'
u'0.75,OTU5:0.75):1.25):0.0)root;'))
counts = []
otu_ids = []
self.assertTrue(_validate_otu_ids_and_tree(counts, otu_ids, t) is None)
# all counts zero
t = TreeNode.read(
StringIO(u'(((((OTU1:0.5,OTU2:0.5):0.5,OTU3:1.0):1.0):0.0,(OTU4:'
u'0.75,OTU5:0.75):1.25):0.0)root;'))
counts = [0, 0, 0, 0, 0]
otu_ids = ['OTU1', 'OTU2', 'OTU3', 'OTU4', 'OTU5']
self.assertTrue(_validate_otu_ids_and_tree(counts, otu_ids, t) is None)
def test_index_tree(self):
"""index_tree should produce correct index and node map"""
# test for first tree: contains singleton outgroup
t1 = TreeNode.read(StringIO(u'(((a,b),c),(d,e));'))
t2 = TreeNode.read(StringIO(u'(((a,b),(c,d)),(e,f));'))
t3 = TreeNode.read(StringIO(u'(((a,b,c),(d)),(e,f));'))
id_1, child_1 = t1.index_tree()
nodes_1 = [
n.id for n in t1.traverse(self_before=False, self_after=True)
]
self.assertEqual(nodes_1, [0, 1, 2, 3, 6, 4, 5, 7, 8])
npt.assert_equal(
child_1, np.array([[2, 0, 1], [6, 2, 3], [7, 4, 5], [8, 6, 7]]))
# test for second tree: strictly bifurcating
id_2, child_2 = t2.index_tree()
nodes_2 = [
n.id for n in t2.traverse(self_before=False, self_after=True)
]
self.assertEqual(nodes_2, [0, 1, 4, 2, 3, 5, 8, 6, 7, 9, 10])
npt.assert_equal(
child_2,
np.array([[4, 0, 1], [5, 2, 3], [8, 4, 5], [9, 6, 7], [10, 8, 9]]))
# test for third tree: contains trifurcation and single-child parent
id_3, child_3 = t3.index_tree()
nodes_3 = [
n.id for n in t3.traverse(self_before=False, self_after=True)
]
self.assertEqual(nodes_3, [0, 1, 2, 4, 3, 5, 8, 6, 7, 9, 10])
npt.assert_equal(
child_3,
np.array([[4, 0, 2], [5, 3, 3], [8, 4, 5], [9, 6, 7], [10, 8, 9]]))
def test_compare_subsets(self):
"""compare_subsets should return the fraction of shared subsets"""
t = TreeNode.read(StringIO(u'((H,G),(R,M));'))
t2 = TreeNode.read(StringIO(u'(((H,G),R),M);'))
t4 = TreeNode.read(StringIO(u'(((H,G),(O,R)),X);'))
result = t.compare_subsets(t)
self.assertEqual(result, 0)
result = t2.compare_subsets(t2)
self.assertEqual(result, 0)
result = t.compare_subsets(t2)
self.assertEqual(result, 0.5)
result = t.compare_subsets(t4)
self.assertEqual(result, 1 - 2. / 5)
result = t.compare_subsets(t4, exclude_absent_taxa=True)
self.assertEqual(result, 1 - 2. / 3)
result = t.compare_subsets(self.TreeRoot, exclude_absent_taxa=True)
self.assertEqual(result, 1)
result = t.compare_subsets(self.TreeRoot)
self.assertEqual(result, 1)
def test_majority_rule(self):
trees = [
TreeNode.read(StringIO("(A,(B,(H,(D,(J,(((G,E),(F,I)),C))))));")),
TreeNode.read(StringIO("(A,(B,(D,((J,H),(((G,E),(F,I)),C)))));")),
TreeNode.read(StringIO("(A,(B,(D,(H,(J,(((G,E),(F,I)),C))))));")),
TreeNode.read(StringIO("(A,(B,(E,(G,((F,I),((J,(H,D)),C))))));")),
TreeNode.read(StringIO("(A,(B,(E,(G,((F,I),(((J,H),D),C))))));")),
TreeNode.read(StringIO("(A,(B,(E,((F,I),(G,((J,(H,D)),C))))));")),
TreeNode.read(StringIO("(A,(B,(E,((F,I),(G,(((J,H),D),C))))));")),
TreeNode.read(StringIO("(A,(B,(E,((G,(F,I)),((J,(H,D)),C)))));")),
TreeNode.read(StringIO("(A,(B,(E,((G,(F,I)),(((J,H),D),C)))));"))
]
exp = TreeNode.read(StringIO("(((E,(G,(F,I),(C,(D,J,H)))),B),A);"))
obs = majority_rule(trees)
self.assertEqual(exp.compare_subsets(obs[0]), 0.0)
self.assertEqual(len(obs), 1)
tree = obs[0]
exp_supports = sorted([9.0, 9.0, 9.0, 6.0, 6.0, 6.0])
obs_supports = sorted([n.support for n in tree.non_tips()])
self.assertEqual(obs_supports, exp_supports)
obs = majority_rule(trees, weights=np.ones(len(trees)) * 2)
self.assertEqual(exp.compare_subsets(obs[0]), 0.0)
self.assertEqual(len(obs), 1)
tree = obs[0]
exp_supports = sorted([18.0, 18.0, 12.0, 18.0, 12.0, 12.0])
obs_supports = sorted([n.support for n in tree.non_tips()])
with self.assertRaises(ValueError):
majority_rule(trees, weights=[1, 2])
def test_extend(self):
"""Extend a few nodes"""
second_tree = TreeNode.read(StringIO(u"(x1,y1)z1;"))
third_tree = TreeNode.read(StringIO(u"(x2,y2)z2;"))
first_tree = TreeNode.read(StringIO(u"(x1,y1)z1;"))
fourth_tree = TreeNode.read(StringIO(u"(x2,y2)z2;"))
self.simple_t.extend([second_tree, third_tree])
first_tree.extend(fourth_tree.children)
self.assertEqual(0, len(fourth_tree.children))
self.assertEqual(first_tree.children[0].name, 'x1')
self.assertEqual(first_tree.children[1].name, 'y1')
self.assertEqual(first_tree.children[2].name, 'x2')
self.assertEqual(first_tree.children[3].name, 'y2')
self.assertEqual(self.simple_t.children[0].name, 'i1')
self.assertEqual(self.simple_t.children[1].name, 'i2')
self.assertEqual(self.simple_t.children[2].name, 'z1')
self.assertEqual(self.simple_t.children[3].name, 'z2')
self.assertEqual(len(self.simple_t.children), 4)
self.assertEqual(self.simple_t.children[2].children[0].name, 'x1')
self.assertEqual(self.simple_t.children[2].children[1].name, 'y1')
self.assertEqual(self.simple_t.children[3].children[0].name, 'x2')
self.assertEqual(self.simple_t.children[3].children[1].name, 'y2')
self.assertIs(second_tree.parent, self.simple_t)
self.assertIs(third_tree.parent, self.simple_t)
def test_newick_to_tree_node_invalid_files(self):
for invalid, error_fragments in self.invalid_newicks:
fh = StringIO(invalid)
with self.assertRaises(NewickFormatError) as cm:
_newick_to_tree_node(fh)
for frag in error_fragments:
self.assertIn(frag, str(cm.exception))
fh.close()
def test_newick_to_tree_node_invalid_files(self):
for invalid, error_fragments in self.invalid_newicks:
fh = StringIO(invalid)
with self.assertRaises(NewickFormatError) as cm:
_newick_to_tree_node(fh)
for frag in error_fragments:
self.assertIn(frag, str(cm.exception))
fh.close()
def test_tree_node_to_newick(self):
for tree, newicks in self.trees_newick_lists:
newick = newicks[0]
fh = StringIO()
_tree_node_to_newick(tree, fh)
self.assertEqual(newick, fh.getvalue())
fh.close()
def test_newick_to_tree_node_valid_files(self):
for tree, newicks in self.trees_newick_lists:
for newick in newicks:
fh = StringIO(newick)
read_tree = _newick_to_tree_node(fh)
self._assert_equal(tree, read_tree)
fh.close()
def test_tree_node_to_newick(self):
for tree, newicks in self.trees_newick_lists:
newick = newicks[0]
fh = StringIO()
_tree_node_to_newick(tree, fh)
self.assertEqual(newick, fh.getvalue())
fh.close()
def test_newick_to_tree_node_valid_files(self):
for tree, newicks in self.trees_newick_lists:
for newick in newicks:
fh = StringIO(newick)
read_tree = _newick_to_tree_node(fh)
self._assert_equal(tree, read_tree)
fh.close()
def test_compare_tip_distances(self):
t = TreeNode.read(StringIO(u'((H:1,G:1):2,(R:0.5,M:0.7):3);'))
t2 = TreeNode.read(StringIO(u'(((H:1,G:1,O:1):2,R:3):1,X:4);'))
obs = t.compare_tip_distances(t2)
# note: common taxa are H, G, R (only)
m1 = np.array([[0, 2, 6.5], [2, 0, 6.5], [6.5, 6.5, 0]])
m2 = np.array([[0, 2, 6], [2, 0, 6], [6, 6, 0]])
r = pearsonr(m1.flat, m2.flat)[0]
self.assertAlmostEqual(obs, (1 - r) / 2)
def test_tip_tip_distances_no_length(self):
t = TreeNode.read(StringIO(u"((a,b)c,(d,e)f);"))
exp_t = TreeNode.read(StringIO(u"((a:0,b:0)c:0,(d:0,e:0)f:0);"))
exp_t_dm = exp_t.tip_tip_distances()
t_dm = npt.assert_warns(RepresentationWarning, t.tip_tip_distances)
self.assertEqual(t_dm, exp_t_dm)
for node in t.preorder():
self.assertIs(node.length, None)
def test_root_at_midpoint_tie(self):
nwk = u"(((a:1,b:1)c:2,(d:3,e:4)f:5),g:1)root;"
t = TreeNode.read(StringIO(nwk))
exp = u"((d:3,e:4)f:2,((a:1,b:1)c:2,(g:1)):3)root;"
texp = TreeNode.read(StringIO(exp))
obs = t.root_at_midpoint()
for o, e in zip(obs.traverse(), texp.traverse()):
self.assertEqual(o.name, e.name)
self.assertEqual(o.length, e.length)
def test_walk_clades(self):
trees = [
TreeNode.read(StringIO("((A,B),(D,E));")),
TreeNode.read(StringIO("((A,B),(D,(E,X)));"))
]
exp_clades = [(frozenset(['A']), 2.0), (frozenset(['B']), 2.0),
(frozenset(['A', 'B']), 2.0), (frozenset(['D',
'E']), 1.0),
(frozenset(['D', 'E', 'A', 'B']), 1.0),
(frozenset(['D']), 2.0), (frozenset(['E']), 2.0),
(frozenset(['X']), 1.0), (frozenset(['E', 'X']), 1.0),
(frozenset(['D', 'E', 'X']), 1.0),
(frozenset(['A', 'B', 'D', 'E', 'X']), 1.0)]
exp_lengths_nolength = {
frozenset(['A']): None,
frozenset(['B']): None,
frozenset(['A', 'B']): None,
frozenset(['D', 'E']): None,
frozenset(['D', 'E', 'A', 'B']): None,
frozenset(['D']): None,
frozenset(['E']): None,
frozenset(['X']): None,
frozenset(['E', 'X']): None,
frozenset(['D', 'E', 'X']): None,
frozenset(['A', 'B', 'D', 'E', 'X']): None
}
exp_lengths = {
frozenset(['A']): 2.0,
frozenset(['B']): 2.0,
frozenset(['A', 'B']): 2.0,
frozenset(['D', 'E']): 1.0,
frozenset(['D', 'E', 'A', 'B']): 1.0,
frozenset(['D']): 2.0,
frozenset(['E']): 2.0,
frozenset(['X']): 1.0,
frozenset(['E', 'X']): 1.0,
frozenset(['D', 'E', 'X']): 1.0,
frozenset(['A', 'B', 'D', 'E', 'X']): 1.0
}
obs_clades, obs_lengths = _walk_clades(trees, np.ones(len(trees)))
self.assertEqual(set(obs_clades), set(exp_clades))
self.assertEqual(obs_lengths, exp_lengths_nolength)
for t in trees:
for n in t.traverse(include_self=True):
n.length = 2.0
obs_clades, obs_lengths = _walk_clades(trees, np.ones(len(trees)))
self.assertEqual(set(obs_clades), set(exp_clades))
self.assertEqual(obs_lengths, exp_lengths)
def test_newick_to_tree_node_convert_underscores(self):
fh = StringIO('(_:0.1, _a, _b)__;')
tree = _newick_to_tree_node(fh, convert_underscores=False)
fh2 = StringIO()
_tree_node_to_newick(tree, fh2)
self.assertEqual(fh2.getvalue(), "('_':0.1,'_a','_b')'__';\n")
fh2.close()
fh.close()
def test_bifurcate(self):
t1 = TreeNode.read(StringIO(u'(((a,b),c),(d,e));'))
t2 = TreeNode.read(StringIO(u'((a,b,c));'))
t3 = t2.copy()
t1.bifurcate()
t2.bifurcate()
t3.bifurcate(insert_length=0)
self.assertEqual(str(t1), '(((a,b),c),(d,e));\n')
self.assertEqual(str(t2), '((c,(a,b)));\n')
self.assertEqual(str(t3), '((c,(a,b):0));\n')
def test_find_by_id(self):
"""Find a node by id"""
t1 = TreeNode.read(StringIO(u"((,),(,,));"))
t2 = TreeNode.read(StringIO(u"((,),(,,));"))
exp = t1.children[1]
obs = t1.find_by_id(6) # right inner node with 3 children
self.assertEqual(obs, exp)
exp = t2.children[1]
obs = t2.find_by_id(6) # right inner node with 3 children
self.assertEqual(obs, exp)
with self.assertRaises(MissingNodeError):
t1.find_by_id(100)
def setUp(self):
self.table1 = np.array([[1, 3, 0, 1, 0], [0, 2, 0, 4, 4],
[0, 0, 6, 2, 1], [0, 0, 1, 1, 1]])
self.sids1 = list('ABCD')
self.oids1 = ['OTU%d' % i for i in range(1, 6)]
self.tree1 = TreeNode.read(
StringIO(u'(((((OTU1:0.5,OTU2:0.5):0.5,OTU3:1.0):1.0):'
u'0.0,(OTU4:0.75,OTU5:0.75):1.25):0.0)root;'))
self.table2 = np.array([[1, 3], [0, 2], [0, 0]])
self.sids2 = list('xyz')
self.oids2 = ['OTU1', 'OTU5']
self.tree2 = TreeNode.read(
StringIO(u'(((((OTU1:42.5,OTU2:0.5):0.5,OTU3:1.0):1.0):'
u'0.0,(OTU4:0.75,OTU5:0.0001):1.25):0.0)root;'))
def test_compare_tip_distances_sample(self):
t = TreeNode.read(StringIO(u'((H:1,G:1):2,(R:0.5,M:0.7):3);'))
t2 = TreeNode.read(StringIO(u'(((H:1,G:1,O:1):2,R:3):1,X:4);'))
obs = t.compare_tip_distances(t2, sample=3, shuffle_f=sorted)
# note: common taxa are H, G, R (only)
m1 = np.array([[0, 2, 6.5], [2, 0, 6.5], [6.5, 6.5, 0]])
m2 = np.array([[0, 2, 6], [2, 0, 6], [6, 6, 0]])
r = pearsonr(m1.flat, m2.flat)[0]
self.assertAlmostEqual(obs, (1 - r) / 2)
# 4 common taxa, still picking H, G, R
s = u'((H:1,G:1):2,(R:0.5,M:0.7,Q:5):3);'
t = TreeNode.read(StringIO(s))
s3 = u'(((H:1,G:1,O:1):2,R:3,Q:10):1,X:4);'
t3 = TreeNode.read(StringIO(s3))
obs = t.compare_tip_distances(t3, sample=3, shuffle_f=sorted)
def test_get_max_distance(self):
"""get_max_distance should get max tip distance across tree"""
tree = TreeNode.read(
StringIO(u"((a:0.1,b:0.2)c:0.3,(d:0.4,e:0.5)f:0.6)root;"))
dist, nodes = tree.get_max_distance()
npt.assert_almost_equal(dist, 1.6)
self.assertEqual(sorted([n.name for n in nodes]), ['b', 'e'])
def test_lowest_common_ancestor(self):
"""TreeNode lowestCommonAncestor should return LCA for set of tips"""
t1 = TreeNode.read(StringIO(u"((a,(b,c)d)e,f,(g,h)i)j;"))
t2 = t1.copy()
t3 = t1.copy()
t4 = t1.copy()
input1 = ['a'] # return self
input2 = ['a', 'b'] # return e
input3 = ['b', 'c'] # return d
input4 = ['a', 'h', 'g'] # return j
exp1 = t1.find('a')
exp2 = t2.find('e')
exp3 = t3.find('d')
exp4 = t4
obs1 = t1.lowest_common_ancestor(input1)
obs2 = t2.lowest_common_ancestor(input2)
obs3 = t3.lowest_common_ancestor(input3)
obs4 = t4.lowest_common_ancestor(input4)
self.assertEqual(obs1, exp1)
self.assertEqual(obs2, exp2)
self.assertEqual(obs3, exp3)
self.assertEqual(obs4, exp4)
# verify multiple calls work
t_mul = t1.copy()
exp_1 = t_mul.find('d')
exp_2 = t_mul.find('i')
obs_1 = t_mul.lowest_common_ancestor(['b', 'c'])
obs_2 = t_mul.lowest_common_ancestor(['g', 'h'])
self.assertEqual(obs_1, exp_1)
self.assertEqual(obs_2, exp_2)
# empty case
with self.assertRaises(ValueError):
t1.lowest_common_ancestor([])
def test_vectorize_counts_and_tree(self):
t = TreeNode.read(StringIO(u"((a:1, b:2)c:3)root;"))
counts = np.array([[0, 1], [1, 5], [10, 1]])
count_array, indexed, branch_lengths = \
_vectorize_counts_and_tree(counts, np.array(['a', 'b']), t)
exp_counts = np.array([[0, 1, 10], [1, 5, 1], [1, 6, 11], [1, 6, 11]])
npt.assert_equal(count_array, exp_counts.T)
def test_set_max_distance(self):
"""set_max_distance sets MaxDistTips across tree"""
tree = TreeNode.read(
StringIO(u"((a:0.1,b:0.2)c:0.3,(d:0.4,e:0.5)f:0.6)root;"))
tree._set_max_distance()
tip_a, tip_b = tree.MaxDistTips
self.assertEqual(tip_a[0] + tip_b[0], 1.6)
self.assertEqual(sorted([tip_a[1].name, tip_b[1].name]), ['b', 'e'])
def setUp(self):
data1 = [[0, 5, 9, 9, 8], [5, 0, 10, 10, 9], [9, 10, 0, 8, 7],
[9, 10, 8, 0, 3], [8, 9, 7, 3, 0]]
ids1 = list('abcde')
self.dm1 = DistanceMatrix(data1, ids1)
# this newick string was confirmed against http://www.trex.uqam.ca/
# which generated the following (isomorphic) newick string:
# (d:2.0000,e:1.0000,(c:4.0000,(a:2.0000,b:3.0000):3.0000):2.0000);
self.expected1_str = ("(d:2.000000, (c:4.000000, (b:3.000000,"
" a:2.000000):3.000000):2.000000, e:1.000000);")
self.expected1_TreeNode = TreeNode.read(StringIO(self.expected1_str))
# this example was pulled from the Phylip manual
# http://evolution.genetics.washington.edu/phylip/doc/neighbor.html
data2 = [[0.0000, 1.6866, 1.7198, 1.6606, 1.5243, 1.6043, 1.5905],
[1.6866, 0.0000, 1.5232, 1.4841, 1.4465, 1.4389, 1.4629],
[1.7198, 1.5232, 0.0000, 0.7115, 0.5958, 0.6179, 0.5583],
[1.6606, 1.4841, 0.7115, 0.0000, 0.4631, 0.5061, 0.4710],
[1.5243, 1.4465, 0.5958, 0.4631, 0.0000, 0.3484, 0.3083],
[1.6043, 1.4389, 0.6179, 0.5061, 0.3484, 0.0000, 0.2692],
[1.5905, 1.4629, 0.5583, 0.4710, 0.3083, 0.2692, 0.0000]]
ids2 = [
"Bovine", "Mouse", "Gibbon", "Orang", "Gorilla", "Chimp", "Human"
]
self.dm2 = DistanceMatrix(data2, ids2)
self.expected2_str = ("(Mouse:0.76891, (Gibbon:0.35793, (Orang:0.28469"
", (Gorilla:0.15393, (Chimp:0.15167, Human:0.117"
"53):0.03982):0.02696):0.04648):0.42027, Bovine:"
"0.91769);")
self.expected2_TreeNode = TreeNode.read(StringIO(self.expected2_str))
data3 = [[0, 5, 4, 7, 6, 8], [5, 0, 7, 10, 9, 11], [4, 7, 0, 7, 6, 8],
[7, 10, 7, 0, 5, 8], [6, 9, 6, 5, 0, 8], [8, 11, 8, 8, 8, 0]]
ids3 = map(str, range(6))
self.dm3 = DistanceMatrix(data3, ids3)
self.expected3_str = ("((((0:1.000000,1:4.000000):1.000000,2:2.000000"
"):1.250000,5:4.750000):0.750000,3:2.750000,4:2."
"250000);")
self.expected3_TreeNode = TreeNode.read(StringIO(self.expected3_str))
# this dm can yield negative branch lengths
data4 = [[0, 5, 9, 9, 800], [5, 0, 10, 10, 9], [9, 10, 0, 8, 7],
[9, 10, 8, 0, 3], [800, 9, 7, 3, 0]]
ids4 = list('abcde')
self.dm4 = DistanceMatrix(data4, ids4)
def test_assign_ids(self):
"""Assign IDs to the tree"""
t1 = TreeNode.read(StringIO(u"(((a,b),c),(e,f),(g));"))
t2 = TreeNode.read(StringIO(u"(((a,b),c),(e,f),(g));"))
t3 = TreeNode.read(StringIO(u"((g),(e,f),(c,(a,b)));"))
t1_copy = t1.copy()
t1.assign_ids()
t2.assign_ids()
t3.assign_ids()
t1_copy.assign_ids()
self.assertEqual([(n.name, n.id) for n in t1.traverse()],
[(n.name, n.id) for n in t2.traverse()])
self.assertEqual([(n.name, n.id) for n in t1.traverse()],
[(n.name, n.id) for n in t1_copy.traverse()])
self.assertNotEqual([(n.name, n.id) for n in t1.traverse()],
[(n.name, n.id) for n in t3.traverse()])
def test_compare_rfd(self):
"""compare_rfd should return the Robinson Foulds distance"""
t = TreeNode.read(StringIO(u'((H,G),(R,M));'))
t2 = TreeNode.read(StringIO(u'(((H,G),R),M);'))
t4 = TreeNode.read(StringIO(u'(((H,G),(O,R)),X);'))
obs = t.compare_rfd(t2)
exp = 2.0
self.assertEqual(obs, exp)
self.assertEqual(t.compare_rfd(t2), t2.compare_rfd(t))
obs = t.compare_rfd(t2, proportion=True)
exp = 0.5
self.assertEqual(obs, exp)
with self.assertRaises(ValueError):
t.compare_rfd(t4)
def test_roundtrip(self):
for tree, newicks in self.trees_newick_lists:
newick = newicks[0]
fh = StringIO(newick)
tree = _newick_to_tree_node(fh)
fh2 = StringIO()
_tree_node_to_newick(tree, fh2)
fh2.seek(0)
tree2 = _newick_to_tree_node(fh2)
self.assertEqual(newick, fh2.getvalue())
self._assert_equal(tree, tree2)
fh.close()
fh2.close()
def test_newick_to_tree_node_convert_underscores(self):
fh = StringIO('(_:0.1, _a, _b)__;')
tree = _newick_to_tree_node(fh, convert_underscores=False)
fh2 = StringIO()
_tree_node_to_newick(tree, fh2)
self.assertEqual(fh2.getvalue(), "('_':0.1,'_a','_b')'__';\n")
fh2.close()
fh.close()
def test_invalidate_attr_caches(self):
tree = TreeNode.read(StringIO(u"((a,b,(c,d)e)f,(g,h)i)root;"))
def f(n):
return [n.name] if n.is_tip() else []
tree.cache_attr(f, 'tip_names')
tree.invalidate_caches()
for n in tree.traverse(include_self=True):
self.assertFalse(hasattr(n, 'tip_names'))
def test_root_at(self):
"""Form a new root"""
t = TreeNode.read(StringIO(u"(((a,b)c,(d,e)f)g,h)i;"))
with self.assertRaises(TreeError):
t.root_at(t.find('h'))
exp = "(a,b,((d,e)f,(h)g)c)root;\n"
rooted = t.root_at('c')
obs = str(rooted)
self.assertEqual(obs, exp)
def test_has_children(self):
"""Test if has children"""
t = TreeNode.read(StringIO(u"((a,b)c,(d,e)f);"))
self.assertTrue(t.has_children())
self.assertTrue(t.children[0].has_children())
self.assertTrue(t.children[1].has_children())
self.assertFalse(t.children[0].children[0].has_children())
self.assertFalse(t.children[0].children[1].has_children())
self.assertFalse(t.children[1].children[0].has_children())
self.assertFalse(t.children[1].children[1].has_children())
def test_find_by_func(self):
"""Find nodes by a function"""
t = TreeNode.read(StringIO(u"((a,b)c,(d,e)f);"))
def func(x):
return x.parent == t.find('c')
exp = ['a', 'b']
obs = [n.name for n in t.find_by_func(func)]
self.assertEqual(obs, exp)
def test_roundtrip_read_write(self):
for reader_fn, writer_fn, fhs in (
(_lsmat_to_dissimilarity_matrix, _dissimilarity_matrix_to_lsmat, self.dissim_fhs),
(_lsmat_to_distance_matrix, _distance_matrix_to_lsmat, self.dist_fhs),
):
for fh in fhs:
# Read.
fh.seek(0)
lsmat1 = reader_fn(fh)
# Write.
out_fh = StringIO()
writer_fn(lsmat1, out_fh)
out_fh.seek(0)
# Read.
lsmat2 = reader_fn(out_fh)
out_fh.close()
self.assertEqual(lsmat1, lsmat2)
def test_write(self):
for fn, objs, strs in (
(_dissimilarity_matrix_to_lsmat, self.dissim_objs, self.dissim_strs),
(_distance_matrix_to_lsmat, self.dist_objs, self.dist_strs),
):
for obj, str_ in zip(objs, strs):
fh = StringIO()
fn(obj, fh)
obs = fh.getvalue()
fh.close()
self.assertEqual(obs, str_)
# Test writing CSV (TSV is written above).
for fn, cls in (
(_dissimilarity_matrix_to_lsmat, DissimilarityMatrix),
(_distance_matrix_to_lsmat, DistanceMatrix),
):
obj = cls(self.lsmat_3x3_data, ["a", "b", "c"])
fh = StringIO()
fn(obj, fh, delimiter=",")
obs = fh.getvalue()
fh.close()
self.assertEqual(obs, LSMat_3x3_CSV)
def test_newick_sniffer_valid_files(self):
for _, newicks in self.trees_newick_lists:
for newick in newicks:
fh = StringIO(newick)
self.assertEqual(_newick_sniffer(fh), (True, {}))
fh.close()
def test_newick_sniffer_invalid_files(self):
for invalid, _ in self.invalid_newicks:
fh = StringIO(invalid)
self.assertEqual(_newick_sniffer(fh), (False, {}))
fh.close()
