def test_yield_subset_biom_str_yields_string_pieces_from_valid_input(self):
"""yield_subset_biom_str yields components of a biom string containing only a subset of ids, given a valid biom str"""
biom_str = otu_table1_with_metadata
ids_to_load = ['GG_OTU_1', 'GG_OTU_2']
axis = 'observations'
idxs, new_axis_md = get_axis_indices(biom_str, ids_to_load, axis)
new_data = direct_slice_data(biom_str, idxs, axis)
#NOTE: this will fail currently due to a known bug in the BIOM direct_parse_key
#as soon as that is updated this should pass, however
obs = [
part for part in yield_subset_biom_str(biom_str, new_data,
new_axis_md, axis)
]
exp = ['{', '"id": "GG_OTU_1"', ',',\
'"format": "Biological Observation Matrix v0.9"', ',',\
'"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html"', ',',\
'"type": "OTU table"', ',',\
# '"generated_by": "QIIME 1.4.0-dev, svn revision 2753', ',',\
'"generated_by": "QIIME 1.4.0-dev', ',',\
'"date": "2012-02-22T20:50:05.024661"', ',',\
'"matrix_type": "sparse"', ',',\
'"matrix_element_type": "float"', ',',\
'"data": [[0,0,1.0],[0,1,2.0],[0,2,3.0],[0,3,5.0],[1,0,5.0],[1,1,1.0],[1,3,2.0]], "shape": [2, 4]',',',\
'"rows": [{"id": "GG_OTU_1", "metadata": null}, {"id": "GG_OTU_2", "metadata": null}]', ',',\
'"columns": [{"id": "Sample1", "metadata": {"pH":7.0}}, {"id": "Sample2", "metadata": {"pH":8.0}}, {"id": "Sample3", "metadata": {"pH":7.0}}, {"id": "Sample4", "metadata": null}]', '}']
#For now be aware that commas in generated_by
#strings won't parse correnctly
for i, piece in enumerate(exp):
self.assertEqual(obs[i], piece)
def test_yield_subset_biom_str_yields_string_pieces_from_valid_input(self):
"""yield_subset_biom_str yields components of a biom string containing only a subset of ids, given a valid biom str"""
biom_str = otu_table1_with_metadata
ids_to_load = ['GG_OTU_1','GG_OTU_2']
axis = 'observation'
idxs, new_axis_md = get_axis_indices(biom_str,ids_to_load, axis)
new_data = direct_slice_data(biom_str,idxs, axis)
#NOTE: this will fail currently due to a known bug in the BIOM direct_parse_key
#as soon as that is updated this should pass, however
obs = [part for part in yield_subset_biom_str(biom_str,new_data,new_axis_md,axis)]
exp = ['{', '"id": "GG_OTU_1"', ',',\
'"format": "Biological Observation Matrix v0.9"', ',',\
'"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html"', ',',\
'"type": "Gene table"', ',',\
# '"generated_by": "QIIME 1.4.0-dev, svn revision 2753', ',',\
'"generated_by": "QIIME 1.4.0-dev', ',',\
'"date": "2012-02-22T20:50:05.024661"', ',',\
'"matrix_type": "sparse"', ',',\
'"matrix_element_type": "float"', ',',\
'"data": [[0,0,1.0],[0,1,2.0],[0,2,3.0],[0,3,5.0],[1,0,5.0],[1,1,1.0],[1,3,2.0]], "shape": [2, 4]',',',\
'"rows": [{"id": "GG_OTU_1", "metadata": null}, {"id": "GG_OTU_2", "metadata": null}]', ',',\
'"columns": [{"id": "Sample1", "metadata": {"pH":7.0}}, {"id": "Sample2", "metadata": {"pH":8.0}}, {"id": "Sample3", "metadata": {"pH":7.0}}, {"id": "Sample4", "metadata": null}]', '}']
#For now be aware that commas in generated_by
#strings won't parse correnctly
for i,piece in enumerate(exp):
self.assertEqual(obs[i],piece)
def run(self, **kwargs):
json_table_str = kwargs['json_table_str']
hdf5_biom = kwargs['hdf5_table']
axis = kwargs['axis']
ids = kwargs['ids']
if axis not in self.Axes:
raise CommandError("Invalid axis '%s'. Must be either %s." % (
axis,
' or '.join(map(lambda e: "'%s'" % e, self.Axes))))
if hdf5_biom is None and json_table_str is None:
raise CommandError("Must specify an input table")
elif hdf5_biom is not None and json_table_str is not None:
raise CommandError("Can only specify one input table")
if json_table_str is not None:
idxs, new_axis_md = get_axis_indices(json_table_str, ids, axis)
new_data = direct_slice_data(json_table_str, idxs, axis)
# multiple walks over the string. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
def subset_generator():
yield "{"
yield direct_parse_key(json_table_str, "id")
yield ","
yield direct_parse_key(json_table_str, "format")
yield ","
yield direct_parse_key(json_table_str, "format_url")
yield ","
yield direct_parse_key(json_table_str, "type")
yield ","
yield direct_parse_key(json_table_str, "generated_by")
yield ","
yield direct_parse_key(json_table_str, "date")
yield ","
yield direct_parse_key(json_table_str, "matrix_type")
yield ","
yield direct_parse_key(json_table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observation":
yield direct_parse_key(json_table_str, "columns")
else:
yield direct_parse_key(json_table_str, "rows")
yield "}"
format_ = 'json'
table = subset_generator()
else:
with biom_open(hdf5_biom) as f:
table = Table.from_hdf5(f, ids=ids, axis=axis)
format_ = 'hdf5'
return {'subsetted_table': (table, format_)}
def run(self, **kwargs):
json_table_str = kwargs['json_table_str']
hdf5_biom = kwargs['hdf5_table']
axis = kwargs['axis']
ids = kwargs['ids']
if axis not in self.Axes:
raise CommandError(
"Invalid axis '%s'. Must be either %s." %
(axis, ' or '.join(map(lambda e: "'%s'" % e, self.Axes))))
if hdf5_biom is None and json_table_str is None:
raise CommandError("Must specify an input table")
elif hdf5_biom is not None and json_table_str is not None:
raise CommandError("Can only specify one input table")
if json_table_str is not None:
idxs, new_axis_md = get_axis_indices(json_table_str, ids, axis)
new_data = direct_slice_data(json_table_str, idxs, axis)
# multiple walks over the string. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
def subset_generator():
yield "{"
yield direct_parse_key(json_table_str, "id")
yield ","
yield direct_parse_key(json_table_str, "format")
yield ","
yield direct_parse_key(json_table_str, "format_url")
yield ","
yield direct_parse_key(json_table_str, "type")
yield ","
yield direct_parse_key(json_table_str, "generated_by")
yield ","
yield direct_parse_key(json_table_str, "date")
yield ","
yield direct_parse_key(json_table_str, "matrix_type")
yield ","
yield direct_parse_key(json_table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observation":
yield direct_parse_key(json_table_str, "columns")
else:
yield direct_parse_key(json_table_str, "rows")
yield "}"
format_ = 'json'
table = subset_generator()
else:
with biom_open(hdf5_biom) as f:
table = Table.from_hdf5(f, ids=ids, axis=axis)
format_ = 'hdf5'
return {'subsetted_table': (table, format_)}
def _subset_table(hdf5_biom, json_table_str, axis, ids):
if axis not in ['sample', 'observation']:
raise ValueError("Invalid axis '%s'. Must be either 'sample' or "
"'observation'." % axis)
if hdf5_biom is None and json_table_str is None:
raise ValueError("Must specify an input table")
elif hdf5_biom is not None and json_table_str is not None:
raise ValueError("Can only specify one input table")
if json_table_str is not None:
idxs, new_axis_md = get_axis_indices(json_table_str, ids, axis)
new_data = direct_slice_data(json_table_str, idxs, axis)
# multiple walks over the string. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
def subset_generator():
yield "{"
yield direct_parse_key(json_table_str, "id")
yield ","
yield direct_parse_key(json_table_str, "format")
yield ","
yield direct_parse_key(json_table_str, "format_url")
yield ","
yield direct_parse_key(json_table_str, "type")
yield ","
yield direct_parse_key(json_table_str, "generated_by")
yield ","
yield direct_parse_key(json_table_str, "date")
yield ","
yield direct_parse_key(json_table_str, "matrix_type")
yield ","
yield direct_parse_key(json_table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observation":
yield direct_parse_key(json_table_str, "columns")
else:
yield direct_parse_key(json_table_str, "rows")
yield "}"
format_ = 'json'
table = subset_generator()
else:
with biom_open(hdf5_biom) as f:
table = Table.from_hdf5(f, ids=ids, axis=axis)
format_ = 'hdf5'
return table, format_
def _subset_table(hdf5_biom, json_table_str, axis, ids):
if axis not in ['sample', 'observation']:
raise ValueError("Invalid axis '%s'. Must be either 'sample' or "
"'observation'." % axis)
if hdf5_biom is None and json_table_str is None:
raise ValueError("Must specify an input table")
elif hdf5_biom is not None and json_table_str is not None:
raise ValueError("Can only specify one input table")
if json_table_str is not None:
idxs, new_axis_md = get_axis_indices(json_table_str, ids, axis)
new_data = direct_slice_data(json_table_str, idxs, axis)
# multiple walks over the string. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
def subset_generator():
yield "{"
yield direct_parse_key(json_table_str, "id")
yield ","
yield direct_parse_key(json_table_str, "format")
yield ","
yield direct_parse_key(json_table_str, "format_url")
yield ","
yield direct_parse_key(json_table_str, "type")
yield ","
yield direct_parse_key(json_table_str, "generated_by")
yield ","
yield direct_parse_key(json_table_str, "date")
yield ","
yield direct_parse_key(json_table_str, "matrix_type")
yield ","
yield direct_parse_key(json_table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observation":
yield direct_parse_key(json_table_str, "columns")
else:
yield direct_parse_key(json_table_str, "rows")
yield "}"
format_ = 'json'
table = subset_generator()
else:
with biom_open(hdf5_biom) as f:
table = Table.from_hdf5(f, ids=ids, axis=axis)
format_ = 'hdf5'
return table, format_
def load_subset_from_biom_str(biom_str, ids_to_load, axis="samples"):
"""Load a biom table containing subset of samples or observations from a BIOM format JSON string"""
if axis not in ['samples', 'observations']:
raise InputError(\
'load_subset_from_biom_str axis parameter must be either "samples" or "observations"')
ids = map(str, [l.strip() for l in ids_to_load])
idxs, new_axis_md = get_axis_indices(biom_str, ids, axis)
new_data = direct_slice_data(biom_str, idxs, axis)
new_table_pieces = yield_subset_biom_str(biom_str, new_data, new_axis_md,
axis)
subset_biom_str = ''.join(new_table_pieces)
return parse_biom_table(subset_biom_str)
def load_subset_from_biom_str(biom_str,ids_to_load,axis="samples"):
"""Load a biom table containing subset of samples or observations from a BIOM format JSON string"""
if axis not in ['samples','observations']:
raise InputError(\
'load_subset_from_biom_str axis parameter must be either "samples" or "observations"')
ids = map(str,[l.strip() for l in ids_to_load])
idxs, new_axis_md = get_axis_indices(biom_str, ids, axis)
new_data = direct_slice_data(biom_str, idxs, axis)
new_table_pieces = yield_subset_biom_str(biom_str,new_data,new_axis_md,axis)
subset_biom_str = ''.join(new_table_pieces)
return parse_biom_table(subset_biom_str)
def run(self, **kwargs):
table_str = kwargs['table_str']
axis = kwargs['axis']
ids = kwargs['ids']
if axis not in self.Axes:
raise CommandError("Invalid axis '%s'. Must be either %s." % (
axis,
' or '.join(map(lambda e: "'%s'" % e, self.Axes))))
idxs, new_axis_md = get_axis_indices(table_str, ids, axis)
new_data = direct_slice_data(table_str, idxs, axis)
# multiple walks over the string. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
def subset_generator():
yield "{"
yield direct_parse_key(table_str, "id")
yield ","
yield direct_parse_key(table_str, "format")
yield ","
yield direct_parse_key(table_str, "format_url")
yield ","
yield direct_parse_key(table_str, "type")
yield ","
yield direct_parse_key(table_str, "generated_by")
yield ","
yield direct_parse_key(table_str, "date")
yield ","
yield direct_parse_key(table_str, "matrix_type")
yield ","
yield direct_parse_key(table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observations":
yield direct_parse_key(table_str, "columns")
else:
yield direct_parse_key(table_str, "rows")
yield "}"
return {'subset_generator': subset_generator()}
help="A file to write the result to")
]
if __name__ == '__main__':
if cogent_cl_parsing:
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
else:
parser = OptionParser(option_list=options)
opts, args = parser.parse_args()
ids = [l.strip() for l in open(opts.ids_fp)]
biom_str = open(opts.biom_fp).read()
idxs, new_axis_md = get_axis_indices(biom_str, ids, opts.axis)
new_data = direct_slice_data(biom_str, idxs, opts.axis)
output = open(opts.output_fp,'w')
# multiple walks over the file. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
output.write('{')
output.write(direct_parse_key(biom_str, "id"))
output.write(",")
output.write(direct_parse_key(biom_str, "format"))
output.write(",")
output.write(direct_parse_key(biom_str, "format_url"))
output.write(",")
output.write(direct_parse_key(biom_str, "type"))
output.write(",")
output.write(direct_parse_key(biom_str, "generated_by"))
output.write(",")
