def test_valid_no_headers(self):
"""Test the function with valid Sequences and no variable headers."""
seq1 = Sequence(name='seq1')
seq1.set_cont_values([1.0, 2.0, 3.0])
seq2 = Sequence(name='seq2')
seq2.set_cont_values([3.0, 3.2, 4.1])
test_sequence_list = [seq1, seq2]
mtx = dr.get_character_matrix_from_sequences_list(test_sequence_list)
assert isinstance(mtx, Matrix)
def test_valid_with_headers(self):
"""Test the function with valid Sequences and include headers."""
seq1 = Sequence(name='seq1')
seq1.set_cont_values([1.0, 2.0, 3.0])
seq2 = Sequence(name='seq2')
seq2.set_cont_values([3.0, 3.2, 4.1])
test_sequence_list = [seq1, seq2]
col_headers = ['Val 1', 'Val 2', 'Val 3']
mtx = dr.get_character_matrix_from_sequences_list(
test_sequence_list, var_headers=col_headers)
assert isinstance(mtx, Matrix)
assert mtx.get_column_headers() == col_headers
# try:
# # Try looking for the string
# label_column = headers.index(args.annotate_labels)
# except:
# try:
# # Treat it as an integer
# label_column = int(args.annotate_labels)
# except:
# raise Exception(
# 'Could not find column to use for labels. '
# 'Check the name to make sure it matches or use column'
# ' index.')
# Convert data to PAM format
# TODO: CJG - This should use our Matrix class to read a csv or matrix lmm
pam = data_readers.get_character_matrix_from_sequences_list(
sequences, headers)
# Read the tree
tree = TreeWrapper.get(path=args.in_tree_filename,
schema=args.in_tree_schema)
# Run analysis
if args.family_name == 'jaccard':
results = phylo_beta_diversity.calculate_phylo_beta_diversity_jaccard(
pam, tree)
res_names = [
'beta_jtu', 'phylo_beta_jtu', 'beta_jne', 'phylo_beta_jne',
'beta_jac', 'phylo_beta_jac'
]
elif args.family_name == 'sorensen':
results = phylo_beta_diversity.calculate_phylo_beta_diversity_sorensen(
if args.annotate_labels is not None:
try:
# Try looking for the string
label_column = headers.index(args.annotate_labels)
except Exception:
try:
# Treat it as an integer
label_column = int(args.annotate_labels)
except Exception:
raise Exception(
'Could not find column to use for labels. '
'Check the name to make sure it matches or use column'
' index.')
# Get character matrix
char_mtx = data_readers.get_character_matrix_from_sequences_list(
sequences, var_headers=headers)
# Run analysis
tree, results = anc_dp.calculate_ancestral_distributions(tree, char_mtx)
# Should we annotate the tree labels?
if label_column is not None:
annotators.annotate_tree_with_label(tree,
results,
label_column=label_column)
else:
# Annotate tree
annotators.add_all_annotations(tree, results, update=True)
# Write the tree
tree.write(path=args.out_tree_filename, schema=args.out_tree_schema)