def test_wilcoxon_tie_correction(reference):
pbmc = pbmc68k_reduced()
groups = ['CD14+ Monocyte', 'Dendritic']
groupby = 'bulk_labels'
_, groups_masks = select_groups(pbmc, groups, groupby)
X = pbmc.raw.X[groups_masks[0]].toarray()
mask_rest = groups_masks[1] if reference else ~groups_masks[0]
Y = pbmc.raw.X[mask_rest].toarray()
n_genes = X.shape[1]
pvals = np.zeros(n_genes)
for i in range(n_genes):
try:
_, pvals[i] = mannwhitneyu(X[:, i], Y[:, i], False, 'two-sided')
except ValueError:
pvals[i] = 1
if reference:
ref = groups[1]
else:
ref = 'rest'
groups = groups[:1]
test_obj = _RankGenes(pbmc, groups, groupby, reference=ref)
test_obj.compute_statistics('wilcoxon', tie_correct=True)
assert np.allclose(test_obj.stats[groups[0]]['pvals'], pvals)
def test_wilcoxon_symmetry():
pbmc = pbmc68k_reduced()
rank_genes_groups(
pbmc,
groupby="bulk_labels",
groups=["CD14+ Monocyte", "Dendritic"],
reference="Dendritic",
method='wilcoxon',
rankby_abs=True,
)
stats_mono = (rank_genes_groups_df(
pbmc, group="CD14+ Monocyte").drop(columns="names").to_numpy())
rank_genes_groups(
pbmc,
groupby="bulk_labels",
groups=["CD14+ Monocyte", "Dendritic"],
reference="CD14+ Monocyte",
method='wilcoxon',
rankby_abs=True,
)
stats_dend = (rank_genes_groups_df(
pbmc, group="Dendritic").drop(columns="names").to_numpy())
assert np.allclose(np.abs(stats_mono), np.abs(stats_dend))
def test_emptycat():
pbmc = pbmc68k_reduced()
pbmc.obs['louvain'] = pbmc.obs['louvain'].cat.add_categories(['11'])
with pytest.raises(ValueError,
match=rf"Could not calculate statistics.*{'11'}"):
rank_genes_groups(pbmc, groupby='louvain')
def test_py2rpy2_numpy_pbmc68k():
"""This has some weird metadata"""
from scanpy.datasets import pbmc68k_reduced
try:
anndata2ri.activate()
with catch_warnings(record=True) as logs: # type: List[WarningMessage]
simplefilter("ignore", DeprecationWarning)
globalenv["adata"] = pbmc68k_reduced()
assert len(logs) == 0, [m.message for m in logs]
finally:
anndata2ri.deactivate()
def test_py2rpy2_numpy_pbmc68k():
"""This has some weird metadata"""
from scanpy.datasets import pbmc68k_reduced
try:
anndata2ri.activate()
with catch_warnings(record=True) as logs: # type: List[WarningMessage]
simplefilter("ignore", DeprecationWarning)
globalenv["adata"] = pbmc68k_reduced()
assert len(logs) == 1, [m.message for m in logs]
assert logs[0].category is NotConvertedWarning
assert "scipy.sparse.csr.csr_matrix" in str(logs[0].message)
finally:
anndata2ri.deactivate()
def test_wilcoxon_tie_correction(reference):
pbmc = pbmc68k_reduced()
groups = ['CD14+ Monocyte', 'Dendritic']
groupby = 'bulk_labels'
_, groups_masks = select_groups(pbmc, groups, groupby)
X = pbmc.raw.X[groups_masks[0]].toarray()
mask_rest = groups_masks[1] if reference else ~groups_masks[0]
Y = pbmc.raw.X[mask_rest].toarray()
# Handle scipy versions
if version.parse(scipy.__version__) >= version.parse("1.7.0"):
pvals = mannwhitneyu(X,
Y,
use_continuity=False,
alternative='two-sided').pvalue
pvals[np.isnan(pvals)] = 1.0
else:
# Backwards compat, to drop once we drop scipy < 1.7
n_genes = X.shape[1]
pvals = np.zeros(n_genes)
for i in range(n_genes):
try:
_, pvals[i] = mannwhitneyu(X[:, i],
Y[:, i],
use_continuity=False,
alternative='two-sided')
except ValueError:
pvals[i] = 1
if reference:
ref = groups[1]
else:
ref = 'rest'
groups = groups[:1]
test_obj = _RankGenes(pbmc, groups, groupby, reference=ref)
test_obj.compute_statistics('wilcoxon', tie_correct=True)
np.testing.assert_allclose(test_obj.stats[groups[0]]['pvals'], pvals)
def test_filter_rank_genes_groups():
adata = pbmc68k_reduced()
# fix filter defaults
args = {
'adata': adata,
'key_added': 'rank_genes_groups_filtered',
'min_in_group_fraction': 0.25,
'min_fold_change': 1,
'max_out_group_fraction': 0.5,
}
rank_genes_groups(adata,
'bulk_labels',
reference='Dendritic',
method='wilcoxon',
n_genes=5)
filter_rank_genes_groups(**args)
assert np.array_equal(
names_reference,
np.array(adata.uns['rank_genes_groups_filtered']['names'].tolist()),
)
rank_genes_groups(adata, 'bulk_labels', method='wilcoxon', n_genes=5)
filter_rank_genes_groups(**args)
assert np.array_equal(
names_no_reference,
np.array(adata.uns['rank_genes_groups_filtered']['names'].tolist()),
)
rank_genes_groups(adata,
'bulk_labels',
method='wilcoxon',
pts=True,
n_genes=5)
filter_rank_genes_groups(**args)
assert np.array_equal(
names_no_reference,
np.array(adata.uns['rank_genes_groups_filtered']['names'].tolist()),
)