def test_leading_trailing_whitespace_column_name(self):
col1 = CategoricalMetadataColumn(
pd.Series(['foo', ' bar ', 'baz'],
name=' col ',
index=pd.Index(['a', 'b', 'c'], name='id')))
col2 = CategoricalMetadataColumn(
pd.Series(['foo', ' bar ', 'baz'],
name='col',
index=pd.Index(['a', 'b', 'c'], name='id')))
self.assertEqual(col1, col2)
def test_all_missing_data(self):
mdc = CategoricalMetadataColumn(pd.Series(
np.array([np.nan, np.nan, np.nan], dtype=object), name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
np.array([np.nan, np.nan, np.nan], dtype=object), name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
def test_all_missing_data(self):
mdc = CategoricalMetadataColumn(
pd.Series(np.array([np.nan, np.nan, np.nan], dtype=object),
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series(np.array([np.nan, np.nan, np.nan], dtype=object),
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
def test_supported_dtype(self):
series = pd.Series(['foo', np.nan, 'bar', 'foo'],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_numeric_strings_preserved_as_strings(self):
series = pd.Series(['1', np.nan, '2.5', '3.0'],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_numeric_strings_preserved_as_strings(self):
series = pd.Series(
['1', np.nan, '2.5', '3.0'], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_supported_dtype(self):
series = pd.Series(
['foo', np.nan, 'bar', 'foo'], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_leading_trailing_whitespace_value(self):
with self.assertRaisesRegex(
ValueError, "CategoricalMetadataColumn.*leading or trailing "
"whitespace characters.*Column 'col1'.*' bar '"):
CategoricalMetadataColumn(
pd.Series(['foo', ' bar ', 'baz'],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
def test_empty_str_value(self):
with self.assertRaisesRegex(
ValueError, "CategoricalMetadataColumn.*empty strings.*"
"column 'col1'"):
CategoricalMetadataColumn(
pd.Series(['foo', '', 'bar'],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
def test_unsupported_type_value(self):
with self.assertRaisesRegex(
TypeError, "CategoricalMetadataColumn.*strings or missing "
r"values.*42\.5.*float.*'col1'"):
CategoricalMetadataColumn(
pd.Series(['foo', 'bar', 42.5],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
def test_unsupported_dtype(self):
with self.assertRaisesRegex(
TypeError, "CategoricalMetadataColumn 'col1' does not support"
".*Series.*dtype.*float64"):
CategoricalMetadataColumn(
pd.Series([42.5, 42.6, 42.7],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = CategoricalMetadataColumn(pd.Series(
[np.nan, 'foo', float('nan'), None], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
[np.nan, 'foo', np.nan, np.nan], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
self.assertTrue(np.isnan(obs['d']))
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = CategoricalMetadataColumn(
pd.Series([np.nan, 'foo', float('nan'), None],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series([np.nan, 'foo', np.nan, np.nan],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
self.assertTrue(np.isnan(obs['d']))
def test_wrong_obj(self):
with self.assertRaisesRegex(
TypeError, 'NumericMetadataColumn constructor.*pandas.Series'):
NumericMetadataColumn(pd.DataFrame([[1, 2, 3]]))
with self.assertRaisesRegex(
TypeError,
'CategoricalMetadataColumn constructor.*pandas.Series'):
CategoricalMetadataColumn({})
def test_categorical_metadata_column(self):
mdc = CategoricalMetadataColumn(
pd.Series(['foo', 'bar', '42.50'],
name='categorical-column',
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
mdc.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\tcategorical-column\n"
"#q2:types\tcategorical\n"
"id1\tfoo\n"
"id2\tbar\n"
"id3\t42.50\n")
self.assertEqual(obs, exp)
def test_categorical_metadata_column(self):
mdc = CategoricalMetadataColumn(pd.Series(
['foo', 'bar', '42.50'], name='categorical-column',
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
mdc.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcategorical-column\n"
"#q2:types\tcategorical\n"
"id1\tfoo\n"
"id2\tbar\n"
"id3\t42.50\n"
)
self.assertEqual(obs, exp)
def subsample_neighbors(focal_seqs: DNAFASTAFormat,
context_seqs: DNAFASTAFormat,
percent_id: float,
samples_per_cluster: int,
locale: CategoricalMetadataColumn = None,
max_accepts: int = 10,
n_threads: int = 1,
seed: int = None) -> IDSelection:
if max_accepts < samples_per_cluster:
raise ValueError('max_accepts (%d) must be greater than or equal to '
'samples_per_cluster (%d), since it is determines '
'the largest number of samples that could be '
'obtained per cluster.' %
(max_accepts, samples_per_cluster))
context_ids = ids_from_fasta(str(context_seqs))
inclusion = pd.Series(False, index=context_ids, name='inclusion')
if locale is not None:
locale = locale.filter_ids(inclusion.index).to_series()
metadata = pd.DataFrame(locale)
else:
metadata = pd.DataFrame(index=pd.Index(inclusion.index))
metadata.index.name = 'id'
with tempfile.NamedTemporaryFile() as vsearch_out_f:
command = [
'vsearch', '--threads',
str(n_threads), '--usearch_global',
str(focal_seqs), '--id',
str(percent_id), '--db',
str(context_seqs), '--userout', vsearch_out_f.name, '--qmask',
'none', '--maxaccepts',
str(max_accepts), '--uc_allhits', '--userfields',
'query+target+mism'
]
run_command(command)
vsearch_out = pd.read_csv(
open(vsearch_out_f.name),
sep='\t',
na_values='*',
names=['focal_id', 'context_id', 'n_mismatches'])
clusters = _clusters_from_vsearch_out(vsearch_out, locale)
context_seqs_to_keep = \
_sample_clusters(clusters, samples_per_cluster, seed=seed)
inclusion[context_seqs_to_keep] = True
return IDSelection(inclusion, qiime2.Metadata(metadata),
"subsample_neighbors")
def test_type_mismatch(self):
dummy = DummyMetadataColumn(
pd.Series([1.0, 2.0, 3.0],
name='col1',
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
numeric = NumericMetadataColumn(
pd.Series([1.0, 2.0, 3.0],
name='col1',
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
categorical = CategoricalMetadataColumn(
pd.Series(['a', 'b', 'c'],
name='col1',
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
self.assertReallyNotEqual(dummy, numeric)
self.assertReallyNotEqual(dummy, categorical)
