def test_make_new_summary_file(self):
"""make_new_summary_file works
"""
lower_percentage, upper_percentage = None, None
#otu_table = parse_otu_table(self.otu_table, int)
#otu_table = parse_biom_table(self.otu_table)
summary, header = make_summary(
self.otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(header, ['Taxon', 's1', 's2', 's3', 's4'])
self.assertEqual(
summary, [[('Root', 'Bacteria', 'Actinobacteria'), 1, 0, 2, 4],
[('Root', 'Bacteria', 'Firmicutes'),
1, 3, 1, 1],
[('Root', 'Bacteria', 'Other'), 1, 2, 1, 0]])
# test that works with relative abundances
#otu_table = parse_otu_table(self.otu_table, float)
#otu_table = parse_biom_table(self.otu_table, float)
#otu_table = convert_otu_table_relative(otu_table)
otu_table = self.otu_table.norm(axis='sample', inplace=False)
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(header, ['Taxon', 's1', 's2', 's3', 's4'])
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Actinobacteria'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.0, 0.5, 0.8])
self.assertEqual(summary[1][0], ('Root', 'Bacteria', 'Firmicutes'))
assert_almost_equal(summary[1][1:], [1.0 / 3, 0.6, 0.25, 0.2])
self.assertEqual(summary[2][0], ('Root', 'Bacteria', 'Other'))
assert_almost_equal(summary[2][1:], [1.0 / 3, 0.4, 0.25, 0.0])
##
# testing lower triming
lower_percentage, upper_percentage = 0.3, None
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Other'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.4, 0.25, 0.0])
##
# testing upper triming
lower_percentage, upper_percentage = None, 0.4
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Actinobacteria'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.0, 0.5, 0.8])
def test_make_new_summary_file(self):
"""make_new_summary_file works
"""
lower_percentage, upper_percentage = None, None
#otu_table = parse_otu_table(self.otu_table, int)
#otu_table = parse_biom_table(self.otu_table)
summary, header = make_summary(
self.otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(header, ['Taxon', 's1', 's2', 's3', 's4'])
self.assertEqual(
summary, [[('Root', 'Bacteria', 'Actinobacteria'), 1, 0, 2, 4],
[('Root', 'Bacteria', 'Firmicutes'),
1, 3, 1, 1],
[('Root', 'Bacteria', 'Other'), 1, 2, 1, 0]])
# test that works with relative abundances
#otu_table = parse_otu_table(self.otu_table, float)
#otu_table = parse_biom_table(self.otu_table, float)
#otu_table = convert_otu_table_relative(otu_table)
otu_table = self.otu_table.norm(axis='sample', inplace=False)
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(header, ['Taxon', 's1', 's2', 's3', 's4'])
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Actinobacteria'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.0, 0.5, 0.8])
self.assertEqual(summary[1][0], ('Root', 'Bacteria', 'Firmicutes'))
assert_almost_equal(summary[1][1:], [1.0 / 3, 0.6, 0.25, 0.2])
self.assertEqual(summary[2][0], ('Root', 'Bacteria', 'Other'))
assert_almost_equal(summary[2][1:], [1.0 / 3, 0.4, 0.25, 0.0])
##
# testing lower triming
lower_percentage, upper_percentage = 0.3, None
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Other'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.4, 0.25, 0.0])
##
# testing upper triming
lower_percentage, upper_percentage = None, 0.4
summary, header = make_summary(
otu_table, 3, upper_percentage, lower_percentage)
self.assertEqual(summary[0][0], ('Root', 'Bacteria', 'Actinobacteria'))
assert_almost_equal(summary[0][1:], [1.0 / 3, 0.0, 0.5, 0.8])
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = parse_biom_table(open(otu_table_fp, 'U'))
delimiter = opts.delimiter
mapping_fp = opts.mapping
md_as_string = opts.md_as_string
md_identifier = opts.md_identifier
levels = opts.level.split(',')
suppress_classic_table_output = opts.suppress_classic_table_output
suppress_biom_table_output = opts.suppress_biom_table_output
if upper_percentage!=None and lower_percentage!=None:
raise ValueError("upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage!=None and lower_percentage!=None and mapping:
raise ValueError("upper_percentage and lower_percentage can not be using with mapping file")
if upper_percentage!=None and (upper_percentage<0 or upper_percentage>1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage!=None and (lower_percentage<0 or lower_percentage>1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path,map_fname=split(mapping_fp)
map_basename,map_fname_ext=splitext(map_fname)
else:
if suppress_classic_table_output and suppress_biom_table_output:
option_parser.error("Both classic and BIOM output formats were "
"suppressed.")
if opts.relative_abundance != '':
option_parser.error("Deprecated. Please use --absolute_abundances to disable relative abundance")
if not opts.absolute_abundance:
otu_table = otu_table.normObservationBySample()
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir,False)
output_dir_path=opts.output_dir
else:
output_dir_path='./'
# use the input OTU table to produce the output filenames
dir_path,fname=split(otu_table_fp)
basename,fname_ext=splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
#define output filename
output_fname = join(output_dir_path,
map_basename+'_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table,
mapping,
int(level),
md_as_string,
md_identifier)
write_add_taxa_summary_mapping(summary,tax_order,mapping,
header,output_fname,delimiter)
else:
# define the output filename. The extension will be added to the
# end depending on the output format
output_fname = join(output_dir_path, basename + '_L%s' % level)
summary, header = make_summary(otu_table,
int(level),
upper_percentage,
lower_percentage,
md_as_string,
md_identifier)
if not suppress_classic_table_output:
write_summarize_taxa(summary, header, output_fname + '.txt',
delimiter, opts.transposed_output,
file_format='classic')
if not suppress_biom_table_output:
write_summarize_taxa(summary, header, output_fname + '.biom',
delimiter, opts.transposed_output,
file_format='biom')
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = load_table(otu_table_fp)
delimiter = opts.delimiter
mapping_fp = opts.mapping
md_as_string = opts.md_as_string
md_identifier = opts.md_identifier
levels = opts.level.split(',')
suppress_classic_table_output = opts.suppress_classic_table_output
suppress_biom_table_output = opts.suppress_biom_table_output
if upper_percentage is not None and lower_percentage is not None:
raise ValueError(
"upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage is not None and lower_percentage is not None and \
mapping:
raise ValueError("upper_percentage and lower_percentage can not be "
"using with mapping file")
if upper_percentage is not None and \
(upper_percentage < 0 or upper_percentage > 1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage is not None and \
(lower_percentage < 0 or lower_percentage > 1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path, map_fname = split(mapping_fp)
map_basename, map_fname_ext = splitext(map_fname)
else:
if suppress_classic_table_output and suppress_biom_table_output:
option_parser.error("Both classic and BIOM output formats were "
"suppressed.")
if not opts.absolute_abundance:
otu_table = otu_table.norm(axis='sample', inplace=False)
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir, False)
output_dir_path = opts.output_dir
else:
output_dir_path = './'
# use the input OTU table to produce the output filenames
dir_path, fname = split(otu_table_fp)
basename, fname_ext = splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
# define output filename
output_fname = join(output_dir_path,
map_basename + '_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table, mapping,
int(level), md_as_string,
md_identifier)
write_add_taxa_summary_mapping(summary, tax_order, mapping, header,
output_fname, delimiter)
else:
# define the output filename. The extension will be added to the
# end depending on the output format
output_fname = join(output_dir_path, basename + '_L%s' % level)
summary, header = make_summary(otu_table, int(level),
upper_percentage, lower_percentage,
md_as_string, md_identifier)
sample_ids = header[1:]
observation_ids = []
data = []
for row in summary:
# Join taxonomic levels to create an observation ID.
observation_ids.append(delimiter.join(row[0]))
data.append(row[1:])
table = Table(np.asarray(data), observation_ids, sample_ids)
if opts.transposed_output:
table = table.transpose()
if not suppress_classic_table_output:
with open(output_fname + '.txt', 'w') as outfile:
outfile.write(table.to_tsv())
if not suppress_biom_table_output:
write_biom_table(table, output_fname + '.biom')
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = parse_otu_table(open(otu_table_fp, 'U'))
delimiter = opts.delimiter
mapping_fp = opts.mapping
levels = opts.level.split(',')
if upper_percentage!=None and lower_percentage!=None:
raise ValueError("upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage!=None and lower_percentage!=None and mapping:
raise ValueError("upper_percentage and lower_percentage can not be using with mapping file")
if upper_percentage!=None and (upper_percentage<0 or upper_percentage>1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage!=None and (lower_percentage<0 or lower_percentage>1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path,map_fname=split(mapping_fp)
map_basename,map_fname_ext=splitext(map_fname)
if opts.relative_abundance != '':
raise option_parser.error("Deprecated. Please use --absolute_abundances to disable relative abundance")
if not opts.absolute_abundance:
otu_table = convert_otu_table_relative(otu_table)
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir,False)
output_dir_path=opts.output_dir
else:
output_dir_path='./'
# use the input OTU table to produce the output filenames
dir_path,fname=split(otu_table_fp)
basename,fname_ext=splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
#define output filename
output_fname = join(output_dir_path,
map_basename+'_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table, mapping,
int(level))
write_add_taxa_summary_mapping(summary,tax_order,mapping,
header,output_fname,delimiter)
else:
#define output filename
output_fname = join(output_dir_path,basename+'_L%s.txt' % (level))
summary, header = make_summary(otu_table, int(level),
upper_percentage, lower_percentage)
write_summarize_taxa(summary, header, output_fname, delimiter)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
lower_percentage = opts.lower_percentage
upper_percentage = opts.upper_percentage
otu_table_fp = opts.otu_table_fp
otu_table = load_table(otu_table_fp)
delimiter = opts.delimiter
mapping_fp = opts.mapping
md_as_string = opts.md_as_string
md_identifier = opts.md_identifier
levels = opts.level.split(',')
suppress_classic_table_output = opts.suppress_classic_table_output
suppress_biom_table_output = opts.suppress_biom_table_output
if upper_percentage is not None and lower_percentage is not None:
raise ValueError(
"upper_percentage and lower_percentage are mutually exclusive")
if upper_percentage is not None and lower_percentage is not None and \
mapping:
raise ValueError("upper_percentage and lower_percentage can not be "
"using with mapping file")
if upper_percentage is not None and \
(upper_percentage < 0 or upper_percentage > 1.0):
raise ValueError('max_otu_percentage should be between 0.0 and 1.0')
if lower_percentage is not None and \
(lower_percentage < 0 or lower_percentage > 1.0):
raise ValueError('lower_percentage should be between 0.0 and 1.0')
if mapping_fp:
mapping_file = open(mapping_fp, 'U')
mapping, header, comments = parse_mapping_file(mapping_file)
# use the input Mapping file for producing the output filenames
map_dir_path, map_fname = split(mapping_fp)
map_basename, map_fname_ext = splitext(map_fname)
else:
if suppress_classic_table_output and suppress_biom_table_output:
option_parser.error("Both classic and BIOM output formats were "
"suppressed.")
if not opts.absolute_abundance:
otu_table = otu_table.norm(axis='sample', inplace=False)
# introduced output directory to will allow for multiple outputs
if opts.output_dir:
create_dir(opts.output_dir, False)
output_dir_path = opts.output_dir
else:
output_dir_path = './'
# use the input OTU table to produce the output filenames
dir_path, fname = split(otu_table_fp)
basename, fname_ext = splitext(fname)
# Iterate over the levels and generate a summarized taxonomy for each
for level in levels:
if mapping_fp:
# define output filename
output_fname = join(output_dir_path,
map_basename + '_L%s.txt' % (level))
summary, tax_order = add_summary_mapping(otu_table,
mapping,
int(level),
md_as_string,
md_identifier)
write_add_taxa_summary_mapping(summary, tax_order, mapping,
header, output_fname, delimiter)
else:
# define the output filename. The extension will be added to the
# end depending on the output format
output_fname = join(output_dir_path, basename + '_L%s' % level)
summary, header = make_summary(otu_table,
int(level),
upper_percentage,
lower_percentage,
md_as_string,
md_identifier)
sample_ids = header[1:]
observation_ids = []
data = []
for row in summary:
# Join taxonomic levels to create an observation ID.
observation_ids.append(delimiter.join(row[0]))
data.append(row[1:])
table = Table(np.asarray(data), observation_ids, sample_ids)
if opts.transposed_output:
table = table.transpose()
if not suppress_classic_table_output:
with open(output_fname + '.txt', 'w') as outfile:
outfile.write(table.to_tsv())
if not suppress_biom_table_output:
write_biom_table(table, output_fname + '.biom')
