def _validate_otu_ids_and_tree(counts, otu_ids, tree):
len_otu_ids = len(otu_ids)
set_otu_ids = set(otu_ids)
if len_otu_ids != len(set_otu_ids):
raise ValueError("``otu_ids`` cannot contain duplicated ids.")
if len(counts) != len_otu_ids:
raise ValueError("``otu_ids`` must be the same length as ``counts`` "
"vector(s).")
if len(tree.root().children) == 0:
raise ValueError("``tree`` must contain more than just a root node.")
if len(tree.root().children) > 2:
# this is an imperfect check for whether the tree is rooted or not.
# can this be improved?
raise ValueError("``tree`` must be rooted.")
# all nodes (except the root node) have corresponding branch lengths
# all tip names in tree are unique
# all otu_ids correspond to tip names in tree
branch_lengths = []
tip_names = []
for e in tree.traverse():
if not e.is_root():
branch_lengths.append(e.length)
if e.is_tip():
tip_names.append(e.name)
set_tip_names = set(tip_names)
if len(tip_names) != len(set_tip_names):
raise DuplicateNodeError("All tip names must be unique.")
if np.array([l is None for l in branch_lengths]).any():
raise ValueError("All non-root nodes in ``tree`` must have a branch "
"length.")
missing_tip_names = set_otu_ids - set_tip_names
if missing_tip_names != set():
n_missing_tip_names = len(missing_tip_names)
raise MissingNodeError("All ``otu_ids`` must be present as tip names "
"in ``tree``. ``otu_ids`` not corresponding to "
"tip names (n=%d): %s" %
(n_missing_tip_names,
" ".join(missing_tip_names)))
def _validate_otu_ids_and_tree(counts, otu_ids, tree):
# all otu_ids are unique
# len(otu_ids) == len(counts)
len_otu_ids = len(otu_ids)
set_otu_ids = set(otu_ids)
if len_otu_ids != len(set_otu_ids):
raise ValueError("OTU IDs vector cannot contain duplicated ids.")
if len(counts) != len_otu_ids:
raise ValueError("OTU IDs vector must be the same length as counts "
"vector(s).")
# the tree is rooted
if len(tree.root().children) > 2:
# this is an imperfect check for whether the tree is rooted or not.
# can this be improved?
raise ValueError("Tree must be rooted.")
# all nodes (except the root node) have corresponding branch lengths
# all tip names in tree are unique
# all otu_ids correspond to tip names in tree
branch_lengths = []
tip_names = []
for e in tree.traverse():
if not e.is_root():
branch_lengths.append(e.length)
if e.is_tip():
tip_names.append(e.name)
set_tip_names = set(tip_names)
if len(tip_names) != len(set_tip_names):
raise DuplicateNodeError("All tip names must be unique.")
if np.array([l is None for l in branch_lengths]).any():
raise ValueError("All non-root nodes in tree must have a branch "
"length.")
missing_tip_names = set_otu_ids - set_tip_names
if missing_tip_names != set():
raise MissingNodeError("All otu_ids must be present as tip names in "
"tree. Tree is missing tips with names: %s" %
" ".join(missing_tip_names))