def test_safe_md5(self):
"""Make sure we have the expected md5 with varied input types
This method is ported from PyCogent (http://www.pycogent.org). PyCogent
is a GPL project, but we obtained permission from the authors of this
method to port it to the BIOM Format project (and keep it under BIOM's
BSD license).
"""
exp = 'd3b07384d113edec49eaa6238ad5ff00'
tmp_f = NamedTemporaryFile(
mode='w',
prefix='test_safe_md5',
suffix='txt')
tmp_f.write('foo\n')
tmp_f.flush()
obs = safe_md5(open(tmp_f.name, 'U'))
self.assertEqual(obs, exp)
obs = safe_md5(['foo\n'])
self.assertEqual(obs, exp)
# unsupported type raises TypeError
self.assertRaises(TypeError, safe_md5, 42)
def test_safe_md5(self):
"""Make sure we have the expected md5 with varied input types
This method is ported from PyCogent (http://www.pycogent.org). PyCogent
is a GPL project, but we obtained permission from the authors of this
method to port it to the BIOM Format project (and keep it under BIOM's
BSD license).
"""
exp = 'd3b07384d113edec49eaa6238ad5ff00'
tmp_f = NamedTemporaryFile(
mode='w',
prefix='test_safe_md5',
suffix='txt')
tmp_f.write('foo\n')
tmp_f.flush()
obs = safe_md5(open(tmp_f.name, 'U'))
self.assertEqual(obs, exp)
obs = safe_md5(['foo\n'])
self.assertEqual(obs, exp)
# unsupported type raises TypeError
self.assertRaises(TypeError, safe_md5, 42)
def test_safe_md5(self):
"""Make sure we have the expected md5 with varied input types
Modified from PyCogent (www.pycogent.org).
"""
exp = 'd3b07384d113edec49eaa6238ad5ff00'
tmp_f = NamedTemporaryFile(mode='w',prefix='test_safe_md5', suffix='txt')
tmp_f.write('foo\n')
tmp_f.flush()
obs = safe_md5(open(tmp_f.name, 'U'))
self.assertEqual(obs,exp)
obs = safe_md5(['foo\n'])
self.assertEqual(obs,exp)
# unsupported type raises TypeError
self.assertRaises(TypeError,safe_md5,42)
def test_safe_md5(self):
"""Make sure we have the expected md5
Modified from PyCogent (www.pycogent.org).
"""
exp = "d3b07384d113edec49eaa6238ad5ff00"
tmp_f = NamedTemporaryFile(mode="w", prefix="test_safe_md5", suffix="txt")
tmp_f.write("foo\n")
tmp_f.flush()
obs = safe_md5(open(tmp_f.name, "U"))
self.assertEqual(obs, exp)
def run(self, **kwargs):
"""
table: two-element tuple containing the biom table to summarize and
the file(-like) object containing the original table data. The
second element of the tuple (the file(-like) object) may be
None. If this is the case, the MD5 sum will *not* be computed
qualitative: counts are presented as number of unique observation
ids per sample, rather than total observation count per
sample
suppress_md5: if ``True``, the MD5 sum of the table file contents will
not be computed. This parameter is ignored if
``table[1] is None``
"""
result = {}
qualitative = kwargs['qualitative']
table, table_lines = kwargs['table']
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.ObservationIds)
suppress_md5 = (table_lines is None) or kwargs['suppress_md5']
counts_per_sample_values = counts_per_sample.values()
if table.SampleMetadata is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.SampleMetadata[0].keys()
if table.ObservationMetadata is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.ObservationMetadata[0].keys()
lines = []
num_samples = len(counts_per_sample)
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' % \
table.getTableDensity())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(table_lines))
lines.append('')
if qualitative:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
lines.append(' Sample Metadata Categories: %s' % '; '.join(sample_md_keys))
lines.append(' Observation Metadata Categories: %s' % '; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
sorted_counts_per_sample = [(v,k) for k,v in counts_per_sample.items()]
sorted_counts_per_sample.sort()
for v,k in sorted_counts_per_sample:
lines.append(' %s: %r' % (k,v))
result['biom-summary'] = lines
return result
def run(self, **kwargs):
result = {}
qualitative = kwargs['qualitative']
table, table_lines = kwargs['table']
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, qualitative)
num_observations = len(table.observation_ids)
suppress_md5 = (table_lines is None) or kwargs['suppress_md5']
counts_per_sample_values = counts_per_sample.values()
if table.sample_metadata is None:
sample_md_keys = ["None provided"]
else:
sample_md_keys = table.sample_metadata[0].keys()
if table.observation_metadata is None:
observation_md_keys = ["None provided"]
else:
observation_md_keys = table.observation_metadata[0].keys()
lines = []
num_samples = len(table.sample_ids)
lines.append('Num samples: %d' % num_samples)
lines.append('Num observations: %d' % num_observations)
if not qualitative:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %d' % total_count)
lines.append('Table density (fraction of non-zero values): %1.3f' %
table.get_table_density())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(table_lines))
lines.append('')
if qualitative:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %r' % min_counts)
lines.append(' Max: %r' % max_counts)
lines.append(' Median: %1.3f' % median_counts)
lines.append(' Mean: %1.3f' % mean_counts)
lines.append(' Std. dev.: %1.3f' % std(counts_per_sample_values))
lines.append(
' Sample Metadata Categories: %s' %
'; '.join(sample_md_keys))
lines.append(
' Observation Metadata Categories: %s' %
'; '.join(observation_md_keys))
lines.append('')
if qualitative:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
for k, v in sorted(counts_per_sample.items(), key=itemgetter(1)):
lines.append(' %s: %r' % (k, v))
result['biom_summary'] = lines
return result
def main():
opts,args = parser.parse_args()
if opts.input_fp is None:
parser.print_help()
parser.error('Must specify an input file!')
input_fp = opts.input_fp
output_fp = opts.output_fp
table = parse_biom_table(biom_open(input_fp,'U'))
min_counts, max_counts, median_counts, mean_counts, counts_per_sample =\
compute_counts_per_sample_stats(table, opts.num_observations)
num_observations = len(table.ObservationIds)
suppress_md5 = opts.suppress_md5
counts_per_sample_values = counts_per_sample.values()
try:
sample_md_keys = table.SampleMetadata[0].keys()
except TypeError:
sample_md_keys = ["None provided"]
try:
observation_md_keys = table.ObservationMetadata[0].keys()
except TypeError:
observation_md_keys = ["None provided"]
lines = []
num_samples = len(counts_per_sample)
lines.append('Num samples: %s' % str(num_samples))
lines.append('Num observations: %s' % str(num_observations))
if not opts.num_observations:
total_count = sum(counts_per_sample_values)
lines.append('Total count: %s' % str(total_count))
lines.append('Table density (fraction of non-zero values): %1.4f' % \
table.getTableDensity())
if not suppress_md5:
lines.append('Table md5 (unzipped): %s' % safe_md5(biom_open(input_fp,'U')))
lines.append('')
if opts.num_observations:
lines.append('Observations/sample summary:')
else:
lines.append('Counts/sample summary:')
lines.append(' Min: %s' % str(min_counts))
lines.append(' Max: %s' % str(max_counts))
lines.append(' Median: %s' % str(median_counts))
lines.append(' Mean: %s' % str(mean_counts))
lines.append(' Std. dev.: %s' % (str(std(counts_per_sample_values))))
lines.append(' Sample Metadata Categories: %s' % '; '.join(sample_md_keys))
lines.append(' Observation Metadata Categories: %s' % '; '.join(observation_md_keys))
lines.append('')
if opts.num_observations:
lines.append('Observations/sample detail:')
else:
lines.append('Counts/sample detail:')
sorted_counts_per_sample = [(v,k) for k,v in counts_per_sample.items()]
sorted_counts_per_sample.sort()
for v,k in sorted_counts_per_sample:
lines.append(' %s: %s' % (k,str(v)))
if output_fp != None:
open(output_fp,'w').write('\n'.join(lines))
else:
print '\n'.join(lines)