def test_all_nonroot_branchlengths_zero(self):
newicks = ['((b:0)a:0)root:0;', '((b:0)a:0)root:1;']
for nwk in newicks:
st = parse_newick(nwk)
with self.assertRaisesRegex(ValueError,
"must have a positive length"):
validate_tree(st)
def test_nonroot_negative_branchlengths(self):
newicks = [
'((b:-1)a:1)root:1;', '((b:100)a:-100)root:0;', '(b:1,c:-1)a:2;',
'((b:-1)a:0)root;'
]
for nwk in newicks:
st = parse_newick(nwk)
with self.assertRaisesRegex(ValueError,
"must have nonnegative lengths"):
validate_tree(st)
def _validate_and_match_data(self, ignore_missing_samples,
filter_extra_samples,
filter_missing_features,
shear_to_table,
shear_to_feature_metadata):
if self.is_community_plot:
self.table, self.samples, self.tip_md, self.int_md = match_inputs(
self.tree, self.table, self.samples, self.features,
self.ordination, ignore_missing_samples, filter_extra_samples,
filter_missing_features
)
# Remove empty samples and features from the table (and remove the
# removed samples from the sample metadata). We also pass in the
# ordination, if present, to this function -- so we can throw an
# error if the ordination actually contains these empty
# samples/features.
#
# We purposefully do this removal *after* matching (so we know the
# data inputs match up) and *before* shearing (so empty features
# in the table are no longer included as tips in the tree).
self.table, self.samples = remove_empty_samples_and_features(
self.table, self.samples, self.ordination
)
# remove unobserved features from the phylogeny (shear the tree)
if shear_to_table:
features = set(self.table.ids(axis='observation'))
self.tree = self.tree.shear(features)
# Remove features in the feature metadata that are no longer
# present in the tree, due to being shorn off
if self.tip_md is not None or self.int_md is not None:
# (Technically they should always both be None or both be
# DataFrames -- there's no in-between)
self.tip_md, self.int_md = filter_feature_metadata_to_tree(
self.tip_md, self.int_md, self.tree
)
else:
if shear_to_feature_metadata:
features = set(self.features.index)
all_tips = set(bp_tree_tips(self.tree))
# check that feature metadata contains at least 1 tip
if not features.intersection(all_tips):
raise ValueError(
"Cannot shear tree to feature metadata: no tips in "
"the tree are present in the feature metadata."
)
self.tree = self.tree.shear(features)
self.tip_md, self.int_md = match_tree_and_feature_metadata(
self.tree, self.features
)
validate_tree(self.tree)
def test_validate_tree_duplicate_internal_node_names(self):
bad_newicks = [
# Two non-root internal nodes have same name
'((a:1,b:3)c:2,(d:2,e:3)c:5)r:2;',
# Two internal nodes (one of which is the root) have same name
'((a:1,b:3)c:2,(d:2,e:3)f:5)c:2;'
]
for nwk in bad_newicks:
t = parse_newick(nwk)
with self.assertWarnsRegex(
TreeFormatWarning,
"Internal node names in the tree are not unique"):
validate_tree(t)
def test_validate_tree_overlapping_tip_and_internal_node_names(self):
bad_newicks = [
# Tip overlaps with non-root internal node
'((a:1,b:3)a:2,d:5)e:2;',
# Tip overlaps with root node
'((a:1,b:3)c:2,d:5)a:2;',
# Tip overlaps with both non-root and root internal nodes
'((a:1,b:3)a:2,d:5)a:2;'
]
for nwk in bad_newicks:
t = parse_newick(nwk)
with self.assertRaisesRegex(
ValueError,
"Tip names in the tree cannot overlap with internal node names"
):
validate_tree(t)
def test_validate_tree(self):
validate_tree(self.tree)
# check the tree is still equivalent
obs = self.tree
exp = parse_newick(self.nwk)
self.assertEqual(len(obs), len(exp))
for i in range(1, len(exp) + 1):
node_o = obs.postorderselect(i)
node_e = exp.postorderselect(i)
self.assertEqual(node_o, node_e)
self.assertEqual(obs.length(node_o), exp.length(node_e))
self.assertEqual(obs.name(node_o), exp.name(node_e))
def test_validate_tree_duplicate_tip_names(self):
t = parse_newick('((i:1,a:3)b:2,i:5)r:2;')
with self.assertRaisesRegex(ValueError,
"Tip names in the tree must be unique"):
validate_tree(t)
