def compositional_variable_features(max_changing, fold_change, reps, intervals,
n_species, library_size, asymmetry,
fold_balance, n_contaminants, lam,
template_biom, template_sample_name,
output_dir):
if template_biom is not None:
templ = load_table(template_biom)
template = templ.data(id=template_sample_name, axis='sample')
else:
template = None
gen = compositional_variable_features_generator(
max_changing=max_changing,
fold_change=fold_change,
library_size=library_size,
reps=reps,
intervals=intervals,
n_species=n_species,
n_contaminants=n_contaminants,
lam=lam,
template=template,
asymmetry=asymmetry,
fold_balance=fold_balance)
os.mkdir(output_dir)
for i, g in enumerate(gen):
table, groups, truth = g
output_table = "%s/table.%d.biom" % (output_dir, i)
output_groups = "%s/metadata.%d.txt" % (output_dir, i)
output_truth = "%s/truth.%d.csv" % (output_dir, i)
deposit(table, groups, truth, output_table, output_groups,
output_truth)
def test_composition_variable_features_template(self):
# test template
np.random.seed(0)
gen = compositional_variable_features_generator(
max_changing=2, fold_change=2, reps=5,
intervals=2, n_species=5,
fold_balance=False,
n_contaminants=2, lam=0.1,
template=np.array([7.0, 3.0, 1.0, 1.0, 2.0, 4.0, 6.0, 1.0, 10.0]))
table, metadata, truth = next(gen)
table, metadata, truth = next(gen)
exp_table = pd.DataFrame([
[0.062500, 0.125000, 0.031250, 0.109375,
0.171875, 0.499977, 0.000023],
[0.062500, 0.125000, 0.031250, 0.109375,
0.171875, 0.499977, 0.000023],
[0.062500, 0.125000, 0.031250, 0.109375,
0.171875, 0.499977, 0.000023],
[0.062500, 0.125000, 0.031250, 0.109375,
0.171875, 0.499977, 0.000023],
[0.062500, 0.125000, 0.031250, 0.109375,
0.171875, 0.499977, 0.000023],
[0.022727, 0.045455, 0.022727, 0.159091,
0.250000, 0.499977, 0.000023],
[0.022727, 0.045455, 0.022727, 0.159091,
0.250000, 0.499977, 0.000023],
[0.022727, 0.045455, 0.022727, 0.159091,
0.250000, 0.499977, 0.000023],
[0.022727, 0.045455, 0.022727, 0.159091,
0.250000, 0.499977, 0.000023],
[0.022727, 0.045455, 0.022727, 0.159091,
0.250000, 0.499977, 0.000023]],
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
columns = ['F0', 'F1', 'F2', 'F3', 'F4', 'X0', 'X1']
)
npt.assert_allclose(table.values, exp_table.values, atol=1e-3, rtol=1e-3)
exp_metadata = pd.DataFrame(
{'group': [0] * 5 + [1] * 5,
'n_diff': [4] * 10,
'effect_size': [2] * 10,
'library_size': [10000] * 10
},
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
)
metadata = metadata.reindex_axis(sorted(metadata.columns), axis=1)
exp_metadata = exp_metadata.reindex_axis(sorted(exp_metadata.columns), axis=1)
pdt.assert_frame_equal(metadata, exp_metadata)
exp_truth = ['F0', 'F1', 'F3', 'F4']
self.assertListEqual(truth, exp_truth)
def test_composition_variable_features(self):
gen = compositional_variable_features_generator(
max_changing=2, fold_change=2, reps=5,
intervals=2, n_species=5,
fold_balance=False,
n_contaminants=2, lam=0.1)
table, metadata, truth = next(gen)
table, metadata, truth = next(gen)
exp_table = pd.DataFrame(
closure(
np.vstack((
np.array([0.142857]*2 + [0.071429]*3 +
[0.499977, 0.00002269]),
np.array([0.142857]*2 + [0.071429]*3 +
[0.499977, 0.00002269]),
np.array([0.142857]*2 + [0.071429]*3 +
[0.499977, 0.00002269]),
np.array([0.142857]*2 + [0.071429]*3 +
[0.499977, 0.00002269]),
np.array([0.142857]*2 + [0.071429]*3 +
[0.499977, 0.00002269]),
np.array([0.071429]*3 + [0.142857]*2 +
[0.499977, 0.00002269]),
np.array([0.071429]*3 + [0.142857]*2 +
[0.499977, 0.00002269]),
np.array([0.071429]*3 + [0.142857] *2+
[0.499977, 0.00002269]),
np.array([0.071429]*3 + [0.142857]*2 +
[0.499977, 0.00002269]),
np.array([0.071429]*3 + [0.142857]*2 +
[0.499977, 0.00002269])
))),
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
columns = ['F0', 'F1', 'F2', 'F3', 'F4', 'X0', 'X1']
)
pdt.assert_frame_equal(table, exp_table, check_less_precise=True)
exp_metadata = pd.DataFrame(
{'group': [0] * 5 + [1] * 5,
'n_diff': [4] * 10,
'effect_size': [2] * 10,
'library_size': [10000] * 10
},
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
)
metadata = metadata.reindex_axis(sorted(metadata.columns), axis=1)
exp_metadata = exp_metadata.reindex_axis(sorted(exp_metadata.columns), axis=1)
pdt.assert_frame_equal(metadata, exp_metadata)
exp_truth = ['F0', 'F1', 'F3', 'F4']
self.assertListEqual(truth, exp_truth)
def test_composition_variable_features_balanced(self):
gen = compositional_variable_features_generator(
max_changing=2, fold_change=2, reps=5,
intervals=2, n_species=5,
fold_balance=True,
n_contaminants=2, lam=0.1)
table, metadata, truth = next(gen)
table, metadata, truth = next(gen)
exp_table = pd.DataFrame(
[[0.100000, 0.100000, 0.100000, 0.100000,
0.100000, 0.499977, 0.000023],
[0.100000, 0.100000, 0.100000, 0.100000,
0.100000, 0.499977, 0.000023],
[0.100000, 0.100000, 0.100000, 0.100000,
0.100000, 0.499977, 0.000023],
[0.100000, 0.100000, 0.100000, 0.100000,
0.100000, 0.499977, 0.000023],
[0.100000, 0.100000, 0.100000, 0.100000,
0.100000, 0.499977, 0.000023],
[0.041667, 0.041667, 0.083333, 0.166667,
0.166667, 0.499977, 0.000023],
[0.041667, 0.041667, 0.083333, 0.166667,
0.166667, 0.499977, 0.000023],
[0.041667, 0.041667, 0.083333, 0.166667,
0.166667, 0.499977, 0.000023],
[0.041667, 0.041667, 0.083333, 0.166667,
0.166667, 0.499977, 0.000023],
[0.041667, 0.041667, 0.083333, 0.166667,
0.166667, 0.499977, 0.000023]],
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
columns = ['F0', 'F1', 'F2', 'F3', 'F4', 'X0', 'X1']
)
npt.assert_allclose(table.values, exp_table.values, atol=1e-3, rtol=1e-3)
exp_metadata = pd.DataFrame(
{'group': [0] * 5 + [1] * 5,
'n_diff': [4] * 10,
'effect_size': [2] * 10,
'library_size': [10000] * 10
},
index = ['S0', 'S1', 'S2', 'S3', 'S4',
'S5', 'S6', 'S7', 'S8', 'S9'],
)
metadata = metadata.reindex_axis(sorted(metadata.columns), axis=1)
exp_metadata = exp_metadata.reindex_axis(sorted(exp_metadata.columns), axis=1)
pdt.assert_frame_equal(metadata, exp_metadata)
exp_truth = ['F0', 'F1', 'F3', 'F4']
self.assertListEqual(truth, exp_truth)
def compositional_variable_features(max_changing, fold_change, reps, intervals,
n_species, asymmetry, n_contaminants, lam,
output_dir):
gen = compositional_variable_features_generator(max_changing, fold_change,
reps, intervals, n_species,
asymmetry, n_contaminants,
lam)
os.mkdir(output_dir)
for i, g in enumerate(gen):
table, groups, truth = g
output_table = "%s/table.%d.biom" % (output_dir, i)
output_groups = "%s/metadata.%d.txt" % (output_dir, i)
output_truth = "%s/truth.%d.csv" % (output_dir, i)
deposit(table, groups, truth, output_table, output_groups,
output_truth)
