def test_rarefy_depth_error(self):
t = Table(np.array([[0, 1, 3], [1, 1, 2]]),
['O1', 'O2'],
['S1', 'S2', 'S3'])
with self.assertRaisesRegex(ValueError, 'shallow enough'):
rarefy(t, 50)
def test_rarefy_depth_error(self):
t = Table(np.array([[0, 1, 3], [1, 1, 2]]),
['O1', 'O2'],
['S1', 'S2', 'S3'])
with self.assertRaisesRegex(ValueError, 'shallow enough'):
rarefy(t, 50)
def test_rarefy_replacement(self):
t = Table(np.array([[0, 1, 3], [1, 1, 2]]), ['O1', 'O2'],
['S1', 'S2', 'S3'])
rt = rarefy(t, 3, with_replacement=True)
self.assertEqual(rt.shape, (2, 3))
for n_draws in range(5, 100, 5):
rt = rarefy(t, n_draws, with_replacement=True)
npt.assert_array_equal(rt.sum('sample'), np.array([n_draws] * 3))
def rarefy_wrapper(state: PipelineState, target_count: int) -> PipelineState:
table = Artifact.import_data("FeatureTable[Frequency]", state.df) \
.view(biom.Table)
table = rarefy(table, target_count)
df = Artifact.import_data("FeatureTable[Frequency]", table) \
.view(pd.DataFrame)
return state.update_df(df)
def test_rarefy(self):
t = Table(np.array([[0, 1, 3], [1, 1, 2]]), ['O1', 'O2'],
['S1', 'S2', 'S3'])
a = rarefy(t, 2)
self.assertEqual(a.shape, (2, 2))
self.assertEqual(set(a.ids(axis='sample')), set(['S2', 'S3']))
self.assertEqual(set(a.ids(axis='observation')), set(['O1', 'O2']))
npt.assert_array_equal(a.sum(axis='sample'), np.array([2., 2.]))
def _get_multiple_rarefaction(beta_func, metric, iterations, table,
sampling_depth):
distance_matrices = []
for _ in range(iterations):
rarefied_table = q2_feature_table.rarefy(table, sampling_depth)
distance_matrix = beta_func(table=rarefied_table, metric=metric)
distance_matrices.append(distance_matrix)
return distance_matrices
def _get_multiple_rarefaction(beta_func, metric, iterations, table,
sampling_depth):
distance_matrices = []
for _ in range(iterations):
rarefied_table = q2_feature_table.rarefy(table, sampling_depth)
distance_matrix = beta_func(table=rarefied_table, metric=metric)
distance_matrices.append(distance_matrix)
return distance_matrices
def test_rarefy(self):
t = Table(np.array([[0, 1, 3], [1, 1, 2]]),
['O1', 'O2'],
['S1', 'S2', 'S3'])
a = rarefy(t, 2)
self.assertEqual(a.shape, (2, 2))
self.assertEqual(set(a.ids(axis='sample')), set(['S2', 'S3']))
self.assertEqual(set(a.ids(axis='observation')), set(['O1', 'O2']))
npt.assert_array_equal(a.sum(axis='sample'), np.array([2., 2.]))
def core_metrics(table: biom.Table, phylogeny: skbio.TreeNode,
sampling_depth: int) -> (pd.Series,
pd.Series,
pd.Series,
pd.Series,
skbio.DistanceMatrix,
skbio.DistanceMatrix,
skbio.DistanceMatrix,
skbio.DistanceMatrix,
skbio.OrdinationResults,
skbio.OrdinationResults,
skbio.OrdinationResults,
skbio.OrdinationResults):
rarefied_table = rarefy(table=table, sampling_depth=sampling_depth)
faith_pd_vector = alpha_phylogenetic(
table=rarefied_table, phylogeny=phylogeny, metric='faith_pd')
observed_otus_vector = alpha(table=rarefied_table, metric='observed_otus')
shannon_vector = alpha(table=rarefied_table, metric='shannon')
evenness_vector = alpha(table=rarefied_table, metric='pielou_e')
unweighted_unifrac_distance_matrix = beta_phylogenetic(
table=rarefied_table, phylogeny=phylogeny, metric='unweighted_unifrac')
weighted_unifrac_distance_matrix = beta_phylogenetic(
table=rarefied_table, phylogeny=phylogeny, metric='weighted_unifrac')
jaccard_distance_matrix = beta(table=rarefied_table, metric='jaccard')
bray_curtis_distance_matrix = beta(
table=rarefied_table, metric='braycurtis')
unweighted_unifrac_pcoa_results = pcoa(
distance_matrix=unweighted_unifrac_distance_matrix)
weighted_unifrac_pcoa_results = pcoa(
distance_matrix=weighted_unifrac_distance_matrix)
jaccard_pcoa_results = pcoa(distance_matrix=jaccard_distance_matrix)
bray_curtis_pcoa_results = pcoa(
distance_matrix=bray_curtis_distance_matrix)
return (
faith_pd_vector, observed_otus_vector, shannon_vector, evenness_vector,
unweighted_unifrac_distance_matrix, weighted_unifrac_distance_matrix,
jaccard_distance_matrix, bray_curtis_distance_matrix,
unweighted_unifrac_pcoa_results, weighted_unifrac_pcoa_results,
jaccard_pcoa_results, bray_curtis_pcoa_results
)
def _compute_rarefaction_data(feature_table, min_depth, max_depth, steps,
iterations, phylogeny, metrics):
depth_range = np.linspace(min_depth, max_depth, num=steps, dtype=int)
iter_range = range(1, iterations + 1)
rows = feature_table.ids(axis='sample')
cols = pd.MultiIndex.from_product(
[list(depth_range), list(iter_range)], names=['depth', 'iter'])
data = {k: pd.DataFrame(np.NaN, index=rows, columns=cols) for k in metrics}
for d, i in itertools.product(depth_range, iter_range):
rt = rarefy(feature_table, d)
for m in metrics:
if m in phylogenetic_metrics():
vector = alpha_phylogenetic(table=rt,
metric=m,
phylogeny=phylogeny)
else:
vector = alpha(table=rt, metric=m)
data[m][(d, i)] = vector
return data
def _compute_rarefaction_data(feature_table, min_depth, max_depth, steps,
iterations, phylogeny, metrics):
depth_range = np.linspace(min_depth, max_depth, num=steps, dtype=int)
iter_range = range(1, iterations + 1)
rows = feature_table.ids(axis='sample')
cols = pd.MultiIndex.from_product([list(depth_range), list(iter_range)],
names=['depth', 'iter'])
data = {k: pd.DataFrame(np.NaN, index=rows, columns=cols)
for k in metrics}
for d, i in itertools.product(depth_range, iter_range):
rt = rarefy(feature_table, d)
for m in metrics:
if m in phylogenetic_metrics():
vector = alpha_phylogenetic(table=rt, metric=m,
phylogeny=phylogeny)
else:
vector = alpha(table=rt, metric=m)
data[m][(d, i)] = vector
return data
def core_metrics(
table: biom.Table, phylogeny: skbio.TreeNode, sampling_depth: int
) -> (pd.Series, pd.Series, pd.Series, pd.Series, skbio.DistanceMatrix,
skbio.DistanceMatrix, skbio.DistanceMatrix, skbio.DistanceMatrix,
skbio.OrdinationResults, skbio.OrdinationResults,
skbio.OrdinationResults, skbio.OrdinationResults):
rarefied_table = rarefy(table=table, sampling_depth=sampling_depth)
faith_pd_vector = alpha_phylogenetic(table=rarefied_table,
phylogeny=phylogeny,
metric='faith_pd')
observed_otus_vector = alpha(table=rarefied_table, metric='observed_otus')
shannon_vector = alpha(table=rarefied_table, metric='shannon')
evenness_vector = alpha(table=rarefied_table, metric='pielou_e')
unweighted_unifrac_distance_matrix = beta_phylogenetic(
table=rarefied_table, phylogeny=phylogeny, metric='unweighted_unifrac')
weighted_unifrac_distance_matrix = beta_phylogenetic(
table=rarefied_table, phylogeny=phylogeny, metric='weighted_unifrac')
jaccard_distance_matrix = beta(table=rarefied_table, metric='jaccard')
bray_curtis_distance_matrix = beta(table=rarefied_table,
metric='braycurtis')
unweighted_unifrac_pcoa_results = pcoa(
distance_matrix=unweighted_unifrac_distance_matrix)
weighted_unifrac_pcoa_results = pcoa(
distance_matrix=weighted_unifrac_distance_matrix)
jaccard_pcoa_results = pcoa(distance_matrix=jaccard_distance_matrix)
bray_curtis_pcoa_results = pcoa(
distance_matrix=bray_curtis_distance_matrix)
return (faith_pd_vector, observed_otus_vector, shannon_vector,
evenness_vector, unweighted_unifrac_distance_matrix,
weighted_unifrac_distance_matrix, jaccard_distance_matrix,
bray_curtis_distance_matrix, unweighted_unifrac_pcoa_results,
weighted_unifrac_pcoa_results, jaccard_pcoa_results,
bray_curtis_pcoa_results)
