def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if opts.show_metrics:
print("Known metrics are: %s\n"
% (', '.join(list_known_metrics()),))
exit(0)
almost_required_options = ['input_path', 'output_dir', 'metrics']
for option in almost_required_options:
if getattr(opts, option) is None:
option_parser.error('Required option --%s omitted.' % option)
if opts.output_dir.endswith('.txt'):
stderr.write('output must be a directory, files will be named' +
' automatically. And we refuse to make .txt directories\n')
exit(1)
if opts.tree_path == "None":
opts.tree_path = None
try:
os.makedirs(opts.output_dir)
except OSError:
pass # hopefully dir already exists
if os.path.isdir(opts.input_path):
multiple_file_beta(opts.input_path, opts.output_dir, opts.metrics,
opts.tree_path, opts.rows, full_tree=opts.full_tree)
elif os.path.isfile(opts.input_path):
single_file_beta(opts.input_path, opts.metrics, opts.tree_path,
opts.output_dir, opts.rows, full_tree=opts.full_tree)
else:
stderr.write("io error, input path not valid. Does it exist?")
exit(1)
def single_file_beta(self, otu_table_string, tree_string, missing_sams=None,
use_metric_list=False):
""" running single_file_beta should give same result using --rows"""
if missing_sams==None:
missing_sams = []
# setup
input_path = get_tmp_filename()
in_fname = os.path.split(input_path)[1]
f = open(input_path,'w')
f.write(otu_table_string)
f.close()
tree_path = get_tmp_filename()
f = open(tree_path,'w')
f.write(tree_string)
f.close()
metrics = list_known_nonphylogenetic_metrics()
metrics.extend(list_known_phylogenetic_metrics())
output_dir = get_tmp_filename(suffix = '')
os.mkdir(output_dir)
# new metrics that don't trivially parallelize must be dealt with
# carefully
warnings.filterwarnings('ignore','dissimilarity binary_dist_chisq is\
not parallelized, calculating the whole matrix...')
warnings.filterwarnings('ignore','dissimilarity dist_chisq is not\
parallelized, calculating the whole matrix...')
warnings.filterwarnings('ignore','dissimilarity dist_gower is not\
parallelized, calculating the whole matrix...')
warnings.filterwarnings('ignore','dissimilarity dist_hellinger is\
not parallelized, calculating the whole matrix...')
warnings.filterwarnings('ignore','unifrac had no information for\
sample M*')
self.files_to_remove.extend([input_path,tree_path])
self.folders_to_remove.append(output_dir)
os.mkdir(output_dir+'/ft/')
for metric in metrics:
# do it
if use_metric_list:
single_file_beta(input_path, [metric], tree_path, output_dir,
rowids=None)
else:
single_file_beta(input_path, metric, tree_path, output_dir,
rowids=None)
sams, dmtx = parse_distmat(open(output_dir + '/' +\
metric + '_' + in_fname))
# do it by rows
for i in range(len(sams)):
if sams[i] in missing_sams: continue
rows = sams[i]
row_outname = output_dir + '/' + metric + '_' +\
in_fname
if use_metric_list:
single_file_beta(input_path, [metric], tree_path,
output_dir, rowids=rows)
else:
single_file_beta(input_path, metric, tree_path, output_dir,
rowids=rows)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape, (len(rows.split(',')),
len(sams)))
# make sure rows same as full
for j in range(len(rows.split(','))):
for k in range(len(sams)):
row_v1 = row_dmtx[j,k]
full_v1 =\
dmtx[sams.index(row_sams[j]),
sams.index(col_sams[k])]
self.assertFloatEqual(row_v1, full_v1)
### full tree run:
if 'full_tree' in str(metric).lower(): continue
# do it by rows with full tree
for i in range(len(sams)):
if sams[i] in missing_sams: continue
rows = sams[i]
row_outname = output_dir + '/ft/' + metric + '_' +\
in_fname
if use_metric_list:
single_file_beta(input_path, [metric], tree_path,
output_dir+'/ft/', rowids=rows, full_tree=True)
else:
single_file_beta(input_path, metric, tree_path,
output_dir+'/ft/', rowids=rows, full_tree=True)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape, (len(rows.split(',')),
len(sams)))
# make sure rows same as full
for j in range(len(rows.split(','))):
for k in range(len(sams)):
row_v1 = row_dmtx[j,k]
full_v1 =\
dmtx[sams.index(row_sams[j]),
sams.index(col_sams[k])]
self.assertFloatEqual(row_v1, full_v1)
# # do it with full tree
if use_metric_list:
single_file_beta(input_path, [metric], tree_path,
output_dir+'/ft/', rowids=None, full_tree=True)
else:
single_file_beta(input_path, metric, tree_path,
output_dir+'/ft/', rowids=None, full_tree=True)
sams_ft, dmtx_ft = parse_distmat(open(output_dir + '/ft/' +\
metric + '_' + in_fname))
self.assertEqual(sams_ft, sams)
self.assertFloatEqual(dmtx_ft, dmtx)
def single_file_beta(self,
otu_table_string,
tree_string,
missing_sams=None,
use_metric_list=False):
""" running single_file_beta should give same result using --rows"""
if missing_sams is None:
missing_sams = []
# setup
fd, input_path = mkstemp(suffix='.txt')
close(fd)
in_fname = os.path.split(input_path)[1]
f = open(input_path, 'w')
f.write(otu_table_string)
f.close()
fd, tree_path = mkstemp(suffix='.tre')
close(fd)
f = open(tree_path, 'w')
f.write(tree_string)
f.close()
metrics = list_known_nonphylogenetic_metrics()
metrics.extend(list_known_phylogenetic_metrics())
output_dir = mkdtemp()
# new metrics that don't trivially parallelize must be dealt with
# carefully
warnings.filterwarnings(
'ignore', 'dissimilarity binary_dist_chisq is\
not parallelized, calculating the whole matrix...')
warnings.filterwarnings(
'ignore', 'dissimilarity dist_chisq is not\
parallelized, calculating the whole matrix...')
warnings.filterwarnings(
'ignore', 'dissimilarity dist_gower is not\
parallelized, calculating the whole matrix...')
warnings.filterwarnings(
'ignore', 'dissimilarity dist_hellinger is\
not parallelized, calculating the whole matrix...')
warnings.filterwarnings('ignore', 'unifrac had no information for\
sample M*')
self.files_to_remove.extend([input_path, tree_path])
self.folders_to_remove.append(output_dir)
os.mkdir(output_dir + '/ft/')
for metric in metrics:
# do it
if use_metric_list:
single_file_beta(input_path, [metric],
tree_path,
output_dir,
rowids=None)
else:
single_file_beta(input_path,
metric,
tree_path,
output_dir,
rowids=None)
sams, dmtx = parse_distmat(
open(output_dir + '/' + metric + '_' + in_fname))
# do it by rows
for i in range(len(sams)):
if sams[i] in missing_sams:
continue
rows = sams[i]
row_outname = output_dir + '/' + metric + '_' +\
in_fname
if use_metric_list:
single_file_beta(input_path, [metric],
tree_path,
output_dir,
rowids=rows)
else:
single_file_beta(input_path,
metric,
tree_path,
output_dir,
rowids=rows)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape,
(len(rows.split(',')), len(sams)))
# make sure rows same as full
for j in range(len(rows.split(','))):
for k in range(len(sams)):
row_v1 = row_dmtx[j, k]
full_v1 =\
dmtx[sams.index(row_sams[j]),
sams.index(col_sams[k])]
assert_almost_equal(row_v1, full_v1)
# full tree run:
if 'full_tree' in str(metric).lower():
continue
# do it by rows with full tree
for i in range(len(sams)):
if sams[i] in missing_sams:
continue
rows = sams[i]
row_outname = output_dir + '/ft/' + metric + '_' +\
in_fname
if use_metric_list:
single_file_beta(input_path, [metric],
tree_path,
output_dir + '/ft/',
rowids=rows,
full_tree=True)
else:
single_file_beta(input_path,
metric,
tree_path,
output_dir + '/ft/',
rowids=rows,
full_tree=True)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape,
(len(rows.split(',')), len(sams)))
# make sure rows same as full
for j in range(len(rows.split(','))):
for k in range(len(sams)):
row_v1 = row_dmtx[j, k]
full_v1 =\
dmtx[sams.index(row_sams[j]),
sams.index(col_sams[k])]
assert_almost_equal(row_v1, full_v1)
# do it with full tree
if use_metric_list:
single_file_beta(input_path, [metric],
tree_path,
output_dir + '/ft/',
rowids=None,
full_tree=True)
else:
single_file_beta(input_path,
metric,
tree_path,
output_dir + '/ft/',
rowids=None,
full_tree=True)
sams_ft, dmtx_ft = parse_distmat(
open(output_dir + '/ft/' + metric + '_' + in_fname))
self.assertEqual(sams_ft, sams)
assert_almost_equal(dmtx_ft, dmtx)
def single_file_beta(self, otu_table_string, tree_string, missing_sams=None, use_metric_list=False):
""" running single_file_beta should give same result using --rows"""
if missing_sams is None:
missing_sams = []
# setup
fd, input_path = mkstemp(suffix=".txt")
os.close(fd)
in_fname = os.path.split(input_path)[1]
f = open(input_path, "w")
f.write(otu_table_string)
f.close()
fd, tree_path = mkstemp(suffix=".tre")
os.close(fd)
f = open(tree_path, "w")
f.write(tree_string)
f.close()
metrics = list_known_nonphylogenetic_metrics()
metrics.extend(list_known_phylogenetic_metrics())
output_dir = mkdtemp()
# new metrics that don't trivially parallelize must be dealt with
# carefully
warnings.filterwarnings(
"ignore",
"dissimilarity binary_dist_chisq is\
not parallelized, calculating the whole matrix...",
)
warnings.filterwarnings(
"ignore",
"dissimilarity dist_chisq is not\
parallelized, calculating the whole matrix...",
)
warnings.filterwarnings(
"ignore",
"dissimilarity dist_gower is not\
parallelized, calculating the whole matrix...",
)
warnings.filterwarnings(
"ignore",
"dissimilarity dist_hellinger is\
not parallelized, calculating the whole matrix...",
)
warnings.filterwarnings(
"ignore",
"unifrac had no information for\
sample M*",
)
self.files_to_remove.extend([input_path, tree_path])
self.folders_to_remove.append(output_dir)
os.mkdir(output_dir + "/ft/")
for metric in metrics:
# do it
if use_metric_list:
single_file_beta(input_path, [metric], tree_path, output_dir, rowids=None)
else:
single_file_beta(input_path, metric, tree_path, output_dir, rowids=None)
sams, dmtx = parse_distmat(open(output_dir + "/" + metric + "_" + in_fname))
# do it by rows
for i in range(len(sams)):
if sams[i] in missing_sams:
continue
rows = sams[i]
row_outname = output_dir + "/" + metric + "_" + in_fname
if use_metric_list:
single_file_beta(input_path, [metric], tree_path, output_dir, rowids=rows)
else:
single_file_beta(input_path, metric, tree_path, output_dir, rowids=rows)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape, (len(rows.split(",")), len(sams)))
# make sure rows same as full
for j in range(len(rows.split(","))):
for k in range(len(sams)):
row_v1 = row_dmtx[j, k]
full_v1 = dmtx[sams.index(row_sams[j]), sams.index(col_sams[k])]
npt.assert_almost_equal(row_v1, full_v1)
# full tree run:
if "full_tree" in str(metric).lower():
continue
# do it by rows with full tree
for i in range(len(sams)):
if sams[i] in missing_sams:
continue
rows = sams[i]
row_outname = output_dir + "/ft/" + metric + "_" + in_fname
if use_metric_list:
single_file_beta(input_path, [metric], tree_path, output_dir + "/ft/", rowids=rows, full_tree=True)
else:
single_file_beta(input_path, metric, tree_path, output_dir + "/ft/", rowids=rows, full_tree=True)
col_sams, row_sams, row_dmtx = parse_matrix(open(row_outname))
self.assertEqual(row_dmtx.shape, (len(rows.split(",")), len(sams)))
# make sure rows same as full
for j in range(len(rows.split(","))):
for k in range(len(sams)):
row_v1 = row_dmtx[j, k]
full_v1 = dmtx[sams.index(row_sams[j]), sams.index(col_sams[k])]
npt.assert_almost_equal(row_v1, full_v1)
# do it with full tree
if use_metric_list:
single_file_beta(input_path, [metric], tree_path, output_dir + "/ft/", rowids=None, full_tree=True)
else:
single_file_beta(input_path, metric, tree_path, output_dir + "/ft/", rowids=None, full_tree=True)
sams_ft, dmtx_ft = parse_distmat(open(output_dir + "/ft/" + metric + "_" + in_fname))
self.assertEqual(sams_ft, sams)
npt.assert_almost_equal(dmtx_ft, dmtx)