def test_leng15():
training_data = datasets.leng15(mode='all')
if not training_data.shape == (460, 19084):
raise AssertionError()
training_data = datasets.leng15(mode='sorted')
if not training_data.shape == (247, 19084):
raise AssertionError()
training_data = datasets.leng15(mode='unsorted')
if not training_data.shape == (213, 19084):
raise AssertionError()
def test_cyclone_train_on_train():
print("")
print("")
print("## Testing correctness of cyclone()")
print("")
print("# Testing algorithm on training data")
print("")
settings.enable_fastmath = True
settings.verbosity = 4
training_data = datasets.leng15(mode='sorted')
scores = pairs.cyclone(training_data,
datasets.default_cc_marker(),
iterations=1000,
min_iter=10,
min_pairs=1)
print(scores)
test_quality = utils.evaluate_prediction(prediction=scores['max_class'],
reference=ref_prediction)
print(test_quality)
assert np.allclose(np.array(test_quality.values, dtype=float),
np.ones(shape=(4, 4)),
atol=0.1)
def test_filter_unexpressed_genes():
data = datasets.leng15(mode='sorted', gene_sub=list(range(0, 10)), sample_sub=list(range(0, 10)))
filtered, gene_names = utils.filter_unexpressed_genes(data.X, list(data.var_names))
if not filtered.shape == (10, 8):
raise AssertionError()
if not len(gene_names) == 8:
raise AssertionError()
def test_cyclone_speed():
print("")
print("")
print("## Testing speed of cyclone()")
print("")
print("# Testing algorithm on minimal data, unjitted and single core")
print("")
marker = datasets.default_cc_marker()
for p, m in marker.items():
marker[p] = m[:500]
settings.enable_jit = False
settings.n_jobs = 1
utils.benchmark_test(pairs.cyclone, {
'data': datasets.leng15(mode='sorted'),
'marker_pairs': marker
})
print("")
print("# Testing algorithm on minimal data, jitted and single core")
print("")
settings.enable_jit = True
settings.n_jobs = 1
utils.benchmark_test(pairs.cyclone, {
'data': datasets.leng15(mode='sorted'),
'marker_pairs': marker
})
print("")
print("# Testing algorithm on minimal data, jitted and multi core")
print("")
settings.enable_jit = True
settings.n_jobs = 4
utils.benchmark_test(pairs.cyclone, {
'data': datasets.leng15(mode='sorted'),
'marker_pairs': marker
})
def test_sandbag_inputs():
print("")
print("")
print("## Testing different input types for sandbag()")
settings.n_jobs = 4
settings.verbosity = 4
print("")
print("# Testing AnnData obj, including annotation")
print("")
training_data = datasets.leng15(mode='sorted', gene_sub=list(range(0, 1000)))
marker_pairs = pairs.sandbag(training_data)
assert utils.same_marker(marker_pairs, ref_markers)
print("")
print("# Testing AnnData obj, with separate annotation")
print("")
annotation = {
cat: [i for i, x in enumerate(training_data.obs['category']) if x == cat]
for cat in ["G1", "S", "G2M"]
}
marker_pairs = pairs.sandbag(training_data, annotation=annotation)
assert utils.same_marker(marker_pairs, ref_markers)
print("")
print("# Testing DataFrame obj, with separate annotation")
print("")
training_data_df = DataFrame(training_data.X)
sample_names = list(training_data.obs_names)
gene_names = list(training_data.var_names)
training_data_df.Index = sample_names
training_data_df.columns = gene_names
marker_pairs = pairs.sandbag(training_data_df, annotation=annotation)
assert utils.same_marker(marker_pairs, ref_markers)
print("")
print("# Testing DataFrame obj, with separate annotation and separate gene-/sample_names")
print("")
marker_pairs = pairs.sandbag(training_data_df, annotation, gene_names, sample_names)
assert utils.same_marker(marker_pairs, ref_markers)
print("")
print("# Testing ndarray obj, with separate annotation and separate gene-/sample_names")
print("")
training_data_np = training_data_df.values
marker_pairs = pairs.sandbag(training_data_np, annotation, gene_names, sample_names)
assert utils.same_marker(marker_pairs, ref_markers)