def test_write_summarize_taxa_transposed_output(self):
"""write_summarize_taxa_transposed_output functions as expected"""
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp1, transposed_output=True)
obs = open(self.tmp_fp1).read()
exp = '\n'.join(['SampleID\ta;b;c\td;e;f',
'foo\t0\t3\nbar\t1\t4',
'foobar\t2\t5\n'])
self.assertEqual(obs,exp)
self.files_to_remove.append(self.tmp_fp1)
def test_write_summarize_taxa(self):
"""write_summarize_taxa functions as expected"""
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp1)
obs = open(self.tmp_fp1).read()
exp = '\n'.join(['Taxon\tfoo\tbar\tfoobar',
'a;b;c\t0\t1\t2',
'd;e;f\t3\t4\t5\n'])
self.assertEqual(obs,exp)
self.files_to_remove.append(self.tmp_fp1)
def test_write_summarize_taxa(self):
"""write_summarize_taxa functions as expected"""
# Classic format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp1)
obs = open(self.tmp_fp1).read()
exp = "\n".join(["Taxon\tfoo\tbar\tfoobar", "a;b;c\t0\t1\t2", "d;e;f\t3\t4\t5\n"])
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp1)
# BIOM format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp2, file_format="biom")
exp = parse_classic_table_to_rich_table(exp.split("\n"), None, None, None, SparseTaxonTable)
obs = open(self.tmp_fp2).read()
obs = parse_biom_table(obs)
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp2)
def test_write_summarize_taxa_transposed_output(self):
"""write_summarize_taxa_transposed_output functions as expected"""
# Classic format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp1, transposed_output=True)
obs = open(self.tmp_fp1).read()
exp = "\n".join(["SampleID\ta;b;c\td;e;f", "foo\t0\t3\nbar\t1\t4", "foobar\t2\t5\n"])
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp1)
# BIOM format.
write_summarize_taxa(
self.taxa_summary, self.taxa_header, self.tmp_fp2, transposed_output=True, file_format="biom"
)
exp = parse_classic_table_to_rich_table(exp.split("\n"), None, None, None, SparseTaxonTable)
obs = open(self.tmp_fp2).read()
obs = parse_biom_table(obs)
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp2)
def test_write_summarize_taxa(self):
"""write_summarize_taxa functions as expected"""
# Classic format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp1)
obs = open(self.tmp_fp1).read()
exp = '\n'.join(['Taxon\tfoo\tbar\tfoobar',
'a;b;c\t0\t1\t2',
'd;e;f\t3\t4\t5\n'])
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp1)
# BIOM format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp2,
file_format='biom')
exp = parse_classic_table_to_rich_table(exp.split('\n'), None, None,
None, SparseTaxonTable)
obs = open(self.tmp_fp2).read()
obs = parse_biom_table(obs)
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp2)
def test_write_summarize_taxa_transposed_output(self):
"""write_summarize_taxa_transposed_output functions as expected"""
# Classic format.
write_summarize_taxa(
self.taxa_summary,
self.taxa_header,
self.tmp_fp1,
transposed_output=True)
obs = open(self.tmp_fp1).read()
exp = '\n'.join(['SampleID\ta;b;c\td;e;f',
'foo\t0\t3\nbar\t1\t4',
'foobar\t2\t5\n'])
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp1)
# BIOM format.
write_summarize_taxa(self.taxa_summary, self.taxa_header, self.tmp_fp2,
transposed_output=True, file_format='biom')
exp = parse_classic_table_to_rich_table(exp.split('\n'), None, None,
None, SparseTaxonTable)
obs = open(self.tmp_fp2).read()
obs = parse_biom_table(obs)
self.assertEqual(obs, exp)
self.files_to_remove.append(self.tmp_fp2)
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 = 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)