def main():
"""Main method for script."""
parser = argparse.ArgumentParser()
parser.add_argument('in_tree_filename',
type=str,
help='Path to initial tree')
parser.add_argument('in_tree_schema',
type=str,
choices=['nexus', 'newick'],
help='The input tree schema')
parser.add_argument('out_tree_filename', type=str, help='Ouput tree path')
parser.add_argument('out_tree_schema',
type=str,
choices=['nexus', 'newick'],
help='The output tree schema')
parser.add_argument('accepted_taxa_filename',
type=str,
help='File path to write out accepted taxon names')
args = parser.parse_args()
tree = TreeWrapper.get(path=args.in_tree_filename,
schema=args.in_tree_schema)
out_tree, accepted_taxa = get_and_replace_names(tree)
# Write tree
out_tree.write(path=args.out_tree_filename, schema=args.out_tree_schema)
# Write accepted taxa
with open(args.accepted_taxa_filename, 'w') as taxa_out_file:
for taxon_name in accepted_taxa:
taxa_out_file.write(taxon_name)
def test_valid(self):
"""Test the function with valid inputs."""
# Create a tree
tree = TreeWrapper.get(data='(A,(B,((C,D),(E,F))));', schema='newick')
mtx = Matrix(np.random.random((6, 2, 1)),
headers={
'0': ['A', 'B', 'C', 'D', 'E', 'F'],
'1': ['label', 'other_val']
})
# This should not fail
annotators.annotate_tree_with_label(tree, mtx, label_column=0)
def main():
pam_fn = 'C:/Users/cj/Desktop/ryan_v3/pam.lmm'
tree_fn = 'C:/Users/cj/Desktop/ryan_v3/squid_tree.nex'
out_fn = 'C:/Users/cj/Desktop/ryan_v3/tree_mtx.lmm'
with open(pam_fn, 'rb') as in_file:
pam = Matrix.load_flo(in_file)
tree = TreeWrapper.get(path=tree_fn, schema='nexus')
tree_mtx = calculate_tree_site_statistics(pam, tree)
with open(out_fn, 'wb') as out_file:
tree_mtx.save(out_file)
print(tree_mtx.max(axis=1))
print(tree_mtx.max(axis=0))
def purge_tree(tree_filename, tree_schema, occurrence_filename, species_col):
"""Get a tree and purge taxa not in occurrence data."""
tree = TreeWrapper.get(path=tree_filename, schema=tree_schema)
species = set([])
with open(occurrence_filename, 'r') as in_file:
for line in in_file:
parts = line.split(', ')
sp_name = parts[species_col].strip()
species.add(sp_name)
purge_taxa = []
for taxon in tree.taxon_namespace:
if not taxon.label in species:
purge_taxa.append(taxon)
tree.prune_taxa(purge_taxa)
tree.purge_taxon_namespace()
return tree
def test_valid(self, tmpdir):
"""Test the function with valid inputs.
Args:
tmpdir (:obj:`py.path.local`): A temporary directory test fixture
generated by pytest.
"""
# Create a tree
tree = TreeWrapper.get(data='(A,(B,((C,D),(E,F))));', schema='newick')
mtx = Matrix(
np.random.random((6, 3, 2)),
headers={'0': ['A', 'B', 'C', 'D', 'E', 'F'],
'1': ['label', 'other_val', 'one_more_val']})
# This should not fail
output_directory = os.path.join(tmpdir.dirname, 'plots')
create_distribution_plots(tree, mtx, output_directory)
def get_squidded_tree(tree_fn, tree_schema, squid_json):
tree = TreeWrapper.get(path=tree_fn, schema=tree_schema)
json_data_lines = []
with open(squid_json) as in_file:
first_line = True
for line in in_file:
if first_line:
first_line = False
else:
json_data_lines.append(line)
squid_list_json = json.loads(''.join(json_data_lines))
squid_dict = {
i['scientific_name'].replace('_', ' '): i['header']
for i in squid_list_json
}
tree.annotate_tree_tips('squid', squid_dict)
return tree
def main():
"""Main method for script."""
parser = argparse.ArgumentParser()
parser.add_argument('shapegrid_filename',
type=str,
help='File location of the shapegrid shapefile')
parser.add_argument('pam_filename',
type=str,
help='File location of the PAM matrix for statistics')
parser.add_argument('tree_filename',
type=str,
help='File location of the tree to use for statistics')
parser.add_argument('tree_schema',
choices=['newick', 'nexus'],
help='The tree schema')
parser.add_argument('out_geojson_filename',
type=str,
help='File location to write the output GeoJSON')
parser.add_argument('--layer',
nargs=2,
action='append',
help='File location of a layer followed by a label')
args = parser.parse_args()
# Load data
pam = Matrix.load(args.pam_filename)
tree = TreeWrapper.get(path=args.tree_filename, schema=args.tree_schema)
# Encode layers
encoded_layers = encode_environment_layers(args.shapegrid_filename,
args.layer)
# Calculate PAM statistics
stats_mtx = calculate_tree_site_statistics(pam, tree)
# Join encoded layers and PAM statistics
mtx = join_encoded_layers_and_pam_stats(encoded_layers, stats_mtx)
# Generate GeoJSON
geojson_data = create_geojson(args.shapegrid_filename, mtx)
# Write GeoJSON
with open(args.out_geojson_filename, 'w') as out_file:
json.dump(geojson_data, out_file)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('in_tree_filename',
type=str,
help='The file location of the input tree')
parser.add_argument('in_tree_schema',
type=str,
choices=['newick', 'nexus'],
help='The schema of the input tree')
parser.add_argument('out_tree_filename',
type=str,
help='The file location of the output tree')
parser.add_argument('out_tree_schema',
type=str,
choices=['newick', 'nexus'],
help='The schema of the output tree')
args = parser.parse_args()
tree = TreeWrapper.get(path=args.in_tree_filename,
schema=args.in_tree_schema)
out_tree = get_and_replace_names(tree)
out_tree.write(path=args.out_tree_filename, schema=args.out_tree_schema)
'-c', '--out_csv_filename', type=str,
help='If provided, write the output character matrix CSV '
'to this file location')
args = parser.parse_args()
# Check that input files exist
if not os.path.exists(args.in_tree_filename):
raise IOError(
'Input tree {} does not exist'.format(args.in_tree_filename))
if not os.path.exists(args.data_filename):
raise IOError(
'Input data file {} does not exist'.format(args.data_filename))
# Read the tree
tree = TreeWrapper.get(
path=args.in_tree_filename, schema=args.in_tree_schema)
# Read data
if args.data_format == 'csv':
with open(args.data_filename) as in_file:
sequences, headers = data_readers.read_csv_alignment_flo(
in_file)
elif args.data_format == 'json':
with open(args.data_filename) as in_file:
sequences, headers = data_readers.read_json_alginment_flo(
inf_file)
elif args.data_format == 'phylip':
with open(args.data_filename) as in_file:
sequences = data_reders.read_phylip_alignment_flo(in_file)
headers = None
elif args.data_format == 'table':
def main():
"""Main method for script."""
parser = argparse.ArgumentParser()
parser.add_argument('--out_stats_matrix_filename',
type=str,
help='Location to write statistics matrix.')
parser.add_argument('shapegrid_filename',
type=str,
help='File location of the shapegrid shapefile')
parser.add_argument('pam_filename',
type=str,
help='File location of the PAM matrix for statistics')
parser.add_argument('tree_filename',
type=str,
help='File location of the tree to use for statistics')
parser.add_argument('tree_schema',
choices=['newick', 'nexus'],
help='The tree schema')
parser.add_argument('out_geojson_filename',
type=str,
help='File location to write the output GeoJSON')
parser.add_argument('out_csv_filename',
type=str,
help='File location to write the output CSV')
parser.add_argument('out_matrix_filename',
type=str,
help='File location to write the output matrix')
parser.add_argument('--layer',
nargs=2,
action='append',
help='File location of a layer followed by a label')
args = parser.parse_args()
# Load data
pam = Matrix.load(args.pam_filename)
tree = TreeWrapper.get(path=args.tree_filename, schema=args.tree_schema)
# Encode layers
encoded_layers = encode_environment_layers(args.shapegrid_filename,
args.layer)
# Calculate PAM statistics
stats_mtx = calculate_tree_site_statistics(pam, tree)
if args.out_stats_matrix_filename:
stats_mtx.write(args.out_stats_matrix_filename)
# Join encoded layers and PAM statistics
mtx = join_encoded_layers_and_pam_stats(encoded_layers, stats_mtx)
# Generate GeoJSON
geojson_data = create_geojson(args.shapegrid_filename, mtx)
# Write GeoJSON
with open(args.out_geojson_filename, 'w') as out_file:
json.dump(geojson_data, out_file, indent=4)
# Write matrix data
new_rh = []
res = 0.5
for _, x, y in mtx.get_row_headers():
min_x = x - res
max_x = x + res
min_y = y - res
max_y = y + res
new_rh.append('"POLYGON (({} {},{} {},{} {},{} {},{} {}))"'.format(
min_x, max_y, max_x, max_y, max_x, min_y, min_x, min_y, min_x,
max_y))
mtx.write(args.out_matrix_filename)
mtx.set_row_headers(new_rh)
with open(args.out_csv_filename, 'w') as out_file:
mtx.write_csv(out_file)
def test_package_valid(self, valid_ancestral_state_package):
"""Tests the calculate_continusous_ancestral_states method.
Args:
valid_ancestral_state_package (pytest.fixture): A parameterized
pytest fixture defined in conftest.py that provides a valid
test package.
Note:
* This test will need to evolve as the output format changes. It
will probably be better to return a data structure with various
values for each node rather than assigning the value to the
node label.
Raises:
IOError: When the tree or alignment cannot be loaded for the
specified file extension.
Exception: When a specified successful result value cannot be
found.
"""
# Get the data files
(tree_filename, alignment_filename,
results_filename) = valid_ancestral_state_package
# Process the tree file
_, tree_ext = os.path.splitext(tree_filename)
if tree_ext == '.nex':
tree_schema = 'nexus'
elif tree_ext == '.xml':
tree_schema = 'nexml'
elif tree_ext == '.tre':
tree_schema = 'newick'
else:
raise IOError(
'Cannot handle tree with extension: {}'.format(tree_ext))
# tree = dendropy.Tree.get(path=tree_filename, schema=tree_schema)
tree = TreeWrapper.get(path=tree_filename, schema=tree_schema)
# Process the alignment file
_, align_ext = os.path.splitext(alignment_filename)
if align_ext == '.csv':
with open(alignment_filename) as align_file:
sequences, headers = data_readers.read_csv_alignment_flo(
align_file)
elif align_ext == '.json':
with open(alignment_filename) as align_file:
sequences, headers = data_readers.read_json_alignment_flo(
align_file)
elif align_ext == '.phylip':
with open(alignment_filename) as align_file:
sequences = data_readers.read_phylip_alignment_flo(align_file)
elif align_ext == '.tbl':
with open(alignment_filename) as align_file:
sequences = data_readers.read_table_alignment_flo(align_file)
else:
raise IOError('Cannot handle alignments with extension: {}'.format(
align_ext))
char_mtx = data_readers.get_character_matrix_from_sequences_list(
sequences)
# Run analysis
_, anc_mtx = anc_dp.calculate_continuous_ancestral_states(
tree, char_mtx, calc_std_err=True, sum_to_one=False)
# New testing method
# (For now) assume that results file is csv with row headers for
# node labels and column headers for variables
results = []
h = None
with open(results_filename) as results_file:
for line in results_file:
if h is None:
# Get headers
h = line.strip().split(',')[1:]
else:
# Add result (without label) to list
node_result = [
float(i) for i in line.strip().split(',')[1:]
]
results.append(np.array(node_result, dtype=float))
# Look for all results (only maximum likelihood)
for row in anc_mtx[:, :, 0]:
found = False
for i in range(len(results)):
# Allow for some wiggle room with decimal precision
if np.all(np.isclose(row, results[i])):
found = True
results.pop(i)
break
if not found:
raise Exception(
'Could not find expected result: {} in results'.format(
row))
def test_package_valid(self, valid_ancestral_distribution_package):
"""Tests the calculate_ancestral_distributions method.
Args:
invalid_ancestral_distribution_package (pytest.fixture): A pytest
fixture that is parametrized to provide invalid ancestral
distributions, one at a time, so that there are multiple test
functions defined for each invalid package.
Raises:
IOError: When the tree or alignment cannot be loaded for the
specified file extension.
Exception: When a specified successful result value cannot be
found.
"""
# Get the data files
(tree_filename, alignment_filename,
results_filename) = valid_ancestral_distribution_package
# Process the tree file
_, tree_ext = os.path.splitext(tree_filename)
if tree_ext == '.nex':
tree_schema = 'nexus'
elif tree_ext == '.xml':
tree_schema = 'nexml'
elif tree_ext == '.tre':
tree_schema = 'newick'
else:
raise IOError(
'Cannot handle tree with extension: {}'.format(tree_ext))
# tree = dendropy.Tree.get(path=tree_filename, schema=tree_schema)
tree = TreeWrapper.get(path=tree_filename, schema=tree_schema)
# Process the alignment file
_, align_ext = os.path.splitext(alignment_filename)
if align_ext == '.csv':
with open(alignment_filename) as align_file:
sequences, headers = data_readers.read_csv_alignment_flo(
align_file)
elif align_ext == '.json':
with open(alignment_filename) as align_file:
sequences, headers = data_readers.read_json_alignment_flo(
align_file)
elif align_ext == '.phylip':
with open(alignment_filename) as align_file:
sequences = data_readers.read_phylip_alignment_flo(align_file)
elif align_ext == '.tbl':
with open(alignment_filename) as align_file:
sequences = data_readers.read_table_alignment_flo(align_file)
else:
raise IOError('Cannot handle alignments with extension: {}'.format(
align_ext))
char_mtx = data_readers.get_character_matrix_from_sequences_list(
sequences)
# Run analysis
_, anc_mtx = anc_dp.calculate_ancestral_distributions(tree, char_mtx)
# Testing method
# Assume that the results file is a csv with row headers for node
# labels and output layer (maximum_likeliehood / standard_error)
# and column headers for variables
ml_results = []
std_err_results = []
h = None
with open(results_filename) as results_file:
for line in results_file:
if h is None:
# Get headers
h = line.strip().split(',')[1:]
else:
# Add result (without label) to appropriate list
parts = line.strip().split(',')
layer = parts[1].lower()
values = np.array([float(i) for i in parts[2:]],
dtype=float)
if layer == 'maximum_likelihood':
ml_results.append(values)
else:
std_err_results.append(values)
assert (len(ml_results) == len(std_err_results))
print('ml results')
print(ml_results)
print('std err results')
print(std_err_results)
# Look for all results (ml and std err results should match rows)
for row_idx in range(anc_mtx.shape[0]):
found = False
# Get rows from data
ml_row = anc_mtx[row_idx, :, 0]
std_err_row = anc_mtx[row_idx, :, 1]
for i in range(len(ml_results)):
print(ml_results[i])
print(std_err_results[i])
if np.all(np.isclose(ml_row, ml_results[i])) and \
np.all(np.isclose(
std_err_row, std_err_results[i])):
found = True
ml_results.pop(i)
std_err_results.pop(i)
break
if not found:
raise Exception('Could not find {}, {} in results'.format(
ml_row, std_err_row))