def setUp(self):
eigvals = pd.Series(np.array([0.50, 0.25, 0.25]),
index=['PC1', 'PC2', 'PC3'])
samples = np.array([[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]])
proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=['PC1', 'PC2', 'PC3'])
samples_df = pd.DataFrame(samples,
index=['A', 'B', 'C', 'D'],
columns=['PC1', 'PC2', 'PC3'])
self.pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
samples_df = pd.DataFrame(samples + 1.01,
index=['A', 'B', 'C', 'D'],
columns=['PC1', 'PC2', 'PC3'])
self.other = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals.copy(),
samples_df,
proportion_explained=proportion_explained.copy())
self.metadata = qiime2.Metadata(
pd.DataFrame(
{
'val1': ['1.0', '2.0', '3.0', '4.0'],
'val2': ['3.3', '3.5', '3.6', '3.9']
},
index=pd.Index(['A', 'B', 'C', 'D'], name='id')))
def setUp(self):
axes = ['PC1', 'PC2', 'PC3', 'PC4', 'PC5', 'PC6']
eigvals = pd.Series(np.array([1.5, 0.75, 0.3, 0.15, 0.15, 0.15]),
index=axes)
samples = np.array([[0, 3, 4, 4, 0, 0], [1, 2, 1, 4, 3, 3],
[2, 3, 1, 0, 0, 1], [0, 3, 2, 4, 3, 0]])
proportion_explained = pd.Series([0.50, 0.25, 0.10, 0.05, 0.05, 0.05],
index=axes)
samples_df = pd.DataFrame(samples,
index=['A', 'B', 'C', 'D'],
columns=axes)
self.reference = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
samples = np.array([[0.7, 3.7, 4.7, 4.7, 0.7, 0.7],
[1.7, 2.7, 1.7, 4.7, 3.7, 3.7],
[2.7, 3.7, 1.7, 0.7, 0.7, 1.7],
[30, 3.7, 2.7, 4.7, 3.7, 0.7]])
samples_df = pd.DataFrame(samples,
index=['A', 'B', 'C', 'D'],
columns=axes)
self.other = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals.copy(),
samples_df.copy(),
proportion_explained=proportion_explained.copy())
S = [[-0.1358036, 0.0452679, 0.3621430, 0.1810715, -0.2716072],
[0.0452679, -0.1358036, -0.1810715, 0.1810715, 0.2716072],
[0.2263394, 0.0452679, -0.1810715, -0.5432145, -0.2716072],
[-0.1358036, 0.0452679, 0.0000000, 0.1810715, 0.2716072]]
samples_df = pd.DataFrame(np.array(S),
index=['A', 'B', 'C', 'D'],
columns=axes[:5])
self.expected_ref = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals[:5].copy(),
samples_df.copy(),
proportion_explained=proportion_explained[:5].copy())
S = [[0.0482731, -0.0324317, 0.0494312, -0.0316828, -0.1584374],
[0.0803620, -0.0718115, -0.0112234, -0.0171011, -0.1101209],
[0.0527554, -0.0042753, -0.0126739, -0.0969602, -0.0964822],
[-0.1813905, 0.1085184, -0.0255339, 0.1457440, 0.3650405]]
samples_df = pd.DataFrame(np.array(S),
index=['A', 'B', 'C', 'D'],
columns=axes[:5])
self.expected_other = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals[:5].copy(),
samples_df.copy(),
proportion_explained=proportion_explained[:5].copy())
def rpca(
table: biom.Table,
rank: int = 3,
min_sample_count: int = 500,
min_feature_count: int = 10,
iterations: int = 5
) -> (skbio.OrdinationResults, skbio.DistanceMatrix):
""" Runs RPCA with an rclr preprocessing step"""
# filter sample to min depth
def sample_filter(val, id_, md):
return sum(val) > min_sample_count
table = table.filter(sample_filter, axis='sample')
table = table.to_dataframe().T.drop_duplicates()
table = table.T[table.sum() > min_feature_count].T
# rclr preprocessing and OptSpace (RPCA)
opt = OptSpace(rank=rank, iteration=iterations).fit(rclr().fit_transform(
table.copy()))
rename_cols = {i - 1: 'PC' + str(i) for i in range(1, rank + 1)}
# Feature Loadings
feature_loading = pd.DataFrame(opt.feature_weights, index=table.columns)
feature_loading = feature_loading.rename(columns=rename_cols)
feature_loading.sort_values('PC1', inplace=True, ascending=True)
# Sample Loadings
sample_loading = pd.DataFrame(opt.sample_weights, index=table.index)
sample_loading = sample_loading.rename(columns=rename_cols)
# % var explained
proportion_explained = pd.Series(opt.explained_variance_ratio,
index=list(rename_cols.values()))
# eigan-vals
eigvals = pd.Series(opt.eigenvalues, index=list(rename_cols.values()))
# if the rank is two add PC3 of zeros
if rank == 2:
feature_loading['PC3'] = [0] * len(feature_loading.index)
sample_loading['PC3'] = [0] * len(sample_loading.index)
eigvals.loc['PC3'] = 0
proportion_explained.loc['PC3'] = 0
# save ordination results
short_method_name = 'rpca_biplot'
long_method_name = '(Robust Aitchison) RPCA Biplot'
ord_res = skbio.OrdinationResults(
short_method_name,
long_method_name,
eigvals.copy(),
samples=sample_loading.copy(),
features=feature_loading.copy(),
proportion_explained=proportion_explained.copy())
# save distance matrix
dist_res = skbio.stats.distance.DistanceMatrix(opt.distance,
ids=sample_loading.index)
return ord_res, dist_res
def test_remove_empty_nothing_to_remove_with_ordination(self, mock_stdout):
good_pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
self.eigvals,
self.samples_df.drop(labels="Sample4", axis="index"),
features=self.features_df.drop(labels="e", axis="index"),
proportion_explained=self.proportion_explained)
ft, fsm = remove_empty_samples_and_features(self.table_ef, self.sm_ef,
good_pcoa)
self.assertEqual(ft, self.table_ef)
assert_frame_equal(fsm, self.sm_ef)
self.assertEqual(mock_stdout.getvalue(), "")
def test_remove_empty_with_empty_feature_in_ordination(self):
bad_feature_pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
self.eigvals,
self.samples_df.drop(labels="Sample4", axis="index"),
features=self.features_df,
proportion_explained=self.proportion_explained)
with self.assertRaisesRegex(
ValueError,
(r"The ordination contains features that are empty \(i.e. all "
r"0s\) in the table. Problematic feature IDs: e")):
remove_empty_samples_and_features(self.table, self.sm,
bad_feature_pcoa)
def setUp(self):
eigvals = np.array([0.50, 0.25, 0.25])
samples = np.array([[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]])
proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=['PC1', 'PC2', 'PC3'])
samples_df = pd.DataFrame(samples, ['A', 'B', 'C', 'D'],
['PC1', 'PC2', 'PC3'])
self.pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
self.metadata = qiime2.Metadata(
pd.DataFrame({'val1': ['1.0', '2.0', '3.0', '4.0']},
index=['A', 'B', 'C', 'D']))
def test_remove_empty_with_empty_sample_and_feature_in_ordination(self):
# Checks behavior when both an empty sample and an empty feature are in
# the ordination. Currently the code is structured so that empty sample
# errors take precedence over empty feature errors -- I imagine this
# will be the more common of the two scenarios, which is partially why
# I went with this. But this is probably a rare edge case anyway.
extremely_funky_pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
self.eigvals,
self.samples_df,
features=self.features_df,
proportion_explained=self.proportion_explained)
with self.assertRaisesRegex(
ValueError,
(r"The ordination contains samples that are empty \(i.e. all "
r"0s\) in the table. Problematic sample IDs: Sample4")):
remove_empty_samples_and_features(self.table, self.sm,
extremely_funky_pcoa)
def setUp(self):
self.table = biom.Table(
np.array([[1, 2, 0, 4], [8, 7, 0, 5], [1, 0, 0, 0], [0, 0, 0,
0]]).T,
list('abed'), ['Sample1', 'Sample2', 'Sample3', 'Sample4'])
# After filtering out empty samples/features:
self.table_ef = biom.Table(
np.array([[1, 2, 4], [8, 7, 5], [1, 0, 0]]).T, ['a', 'b', 'd'],
['Sample1', 'Sample2', 'Sample3'])
self.sm = pd.DataFrame(
{
"Metadata1": [0, 0, 0, 1],
"Metadata2": [0, 0, 0, 0],
"Metadata3": [1, 2, 3, 4],
"Metadata4": ["abc", "def", "ghi", "jkl"]
},
index=list(self.table.ids()))
# After filtering out empty samples/features:
# (Note that we only care about "emptiness" from the table's
# perspective. We don't consider a sample with 0 for all of its
# metadata, or a metadata field with 0 for all samples, to be empty.)
self.sm_ef = pd.DataFrame(
{
"Metadata1": [0, 0, 0],
"Metadata2": [0, 0, 0],
"Metadata3": [1, 2, 3],
"Metadata4": ["abc", "def", "ghi"]
},
index=self.table_ef.ids().copy())
self.sid2idx = {"Sample1": 0, "Sample2": 1, "Sample3": 2}
self.tm = pd.DataFrame(
{
"Level 1": ["k__Bacteria", "k__Bacteria"],
"Level 2": ["p__Bacteroidetes", "p__Bacteroidetes"],
"Level 3": ["c__Bacteroidia", "c__Bacteroidia"],
"Level 4": ["o__Bacteroidales", "o__Bacteroidales"],
"Level 5": ["f__Bacteroidaceae", "f__Bacteroidaceae"],
"Level 6": ["g__Bacteroides", "g__Bacteroides"],
"Level 7": ["s__", "s__uniformis"],
"Confidence": [0.95, 0]
},
index=["e", "a"])
self.im = pd.DataFrame(
{
"Level 1": ["k__Bacteria", "k__Archaea"],
"Level 2": ["p__Proteobacteria", "Unspecified"],
"Level 3": ["c__Gammaproteobacteria", "Unspecified"],
"Level 4": ["o__Pasteurellales", "Unspecified"],
"Level 5": ["f__Pasteurellaceae", "Unspecified"],
"Level 6": ["g__", "Unspecified"],
"Level 7": ["s__", "Unspecified"],
"Confidence": [0.8, 1]
},
index=["h", "m"])
self.exp_fm_cols = [
"Level 1", "Level 2", "Level 3", "Level 4", "Level 5", "Level 6",
"Level 7", "Confidence"
]
self.exp_ctm = {
"e": [
"k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia",
"o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides",
"s__", "0.95"
],
# The ".0" in "a"'s Confidence value is due to the 0 being treated
# as numeric by Pandas, since this was a numeric column in the DF.
# We can *try* to prevent this sort of thing from happening, but I
# doubt this will make a difference to anyone -- and also it's kind
# of dependent on whatever tool is reading the metadata in the
# first place (if it was all read with dtype=str, then this
# shouldn't be a problem). So, more of a QIIME 2 problem.
"a": [
"k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia",
"o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides",
"s__uniformis", "0.0"
]
}
self.exp_cim = {
"h": [
"k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria",
"o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__", "0.8"
],
"m": [
"k__Archaea", "Unspecified", "Unspecified", "Unspecified",
"Unspecified", "Unspecified", "Unspecified", "1.0"
]
}
# Ordination info (for testing inputs to remove_empty...())
self.eigvals = pd.Series(np.array([0.50, 0.25, 0.25]),
index=["PC1", "PC2", "PC3"])
samples = np.array([[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]])
self.proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=["PC1", "PC2", "PC3"])
self.samples_df = pd.DataFrame(
samples,
index=["Sample1", "Sample2", "Sample3", "Sample4"],
columns=["PC1", "PC2", "PC3"])
features = np.array([[0.9, 0.8, 0.7], [0.6, 0.5, 0.4], [0.3, 0.2, 0.1],
[0.0, 0.2, 0.4]])
self.features_df = pd.DataFrame(features,
index=["a", "b", "e", "d"],
columns=["PC1", "PC2", "PC3"])
# self.pcoa is problematic by default, because it contains Sample4
self.pcoa = skbio.OrdinationResults(
"PCoA",
"Principal Coordinate Analysis",
self.eigvals,
self.samples_df,
proportion_explained=self.proportion_explained)
def setUp(self):
self.tree = parse_newick('(((a:1,e:2):1,b:2)g:1,(:1,d:3)h:2):1;')
self.pruned_tree = TreeNode.read(
StringIO('(((a:1)EmpressNode0:1,b:2)g:1,(d:3)h:2)EmpressNode1:1;'))
# Test table/metadata (mostly) adapted from Qurro:
self.table = biom.Table(
np.array([[1, 2, 0, 4], [8, 7, 0, 5], [1, 0, 0, 0], [0, 0, 1,
0]]).T,
list('abed'), ['Sample1', 'Sample2', 'Sample3', 'Sample4'])
self.unrelated_table = biom.Table(
np.array([[5, 2, 0, 2], [2, 3, 0, 1], [5, 2, 0, 0], [4, 5, 0,
4]]).T,
list("hijk"), ['Sample1', 'Sample2', 'Sample3', 'Sample4'])
self.sample_metadata = pd.DataFrame(
{
"Metadata1": [0, 0, 0, 1],
"Metadata2": [0, 0, 0, 0],
"Metadata3": [1, 2, 3, 4],
"Metadata4": ["abc", "def", "ghi", "jkl"]
},
index=list(self.table.ids()))
self.feature_metadata = pd.DataFrame(
{
"fmdcol1": ["asdf", "ghjk"],
"fmdcol2": ["qwer", "tyui"]
},
index=["a", "h"])
self.filtered_table = biom.Table(
np.array([[1, 2, 4], [8, 7, 5], [1, 0, 0]]).T, ['a', 'b', 'd'],
['Sample1', 'Sample2', 'Sample3'])
self.filtered_sample_metadata = pd.DataFrame(
{
"Metadata1": [0, 0, 0],
"Metadata2": [0, 0, 0],
"Metadata3": [1, 2, 3],
"Metadata4": ["abc", "def", "ghi"]
},
index=["Sample1", "Sample2", "Sample3"])
eigvals = pd.Series(np.array([0.50, 0.25, 0.25]),
index=['PC1', 'PC2', 'PC3'])
samples = np.array([[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]])
proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=['PC1', 'PC2', 'PC3'])
samples_df = pd.DataFrame(
samples,
index=['Sample1', 'Sample2', 'Sample3', 'Sample4'],
columns=['PC1', 'PC2', 'PC3'])
self.pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
features = np.abs(samples_df.copy() / 2.0).iloc[:2, :]
features.index = 'f.' + features.index
self.biplot_no_matches = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
features=features,
proportion_explained=proportion_explained)
features = np.abs(samples_df / 2.0).iloc[:2, :]
features.index = pd.Index(['a', 'h'])
self.biplot = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
features=features,
proportion_explained=proportion_explained)
self.biplot_tree = parse_newick(
'(((y:1,z:2):1,b:2)g:1,(:1,d:3)h:2):1;')
self.biplot_table = biom.Table(
np.array([[1, 2], [8, 7], [1, 0], [0, 3]]).T, ['y', 'z'],
['Sample1', 'Sample2', 'Sample3', 'Sample4'])
self.files_to_remove = []
self.maxDiff = None
def rpca(
table: biom.Table,
n_components: int = DEFAULT_RANK,
min_sample_count: int = DEFAULT_MSC,
min_feature_count: int = DEFAULT_MFC,
max_iterations: int = DEFAULT_ITERATIONS
) -> (skbio.OrdinationResults, skbio.DistanceMatrix):
"""Runs RPCA with an rclr preprocessing step.
This code will be run by both the standalone and QIIME 2 versions of
DEICODE.
"""
# filter sample to min depth
def sample_filter(val, id_, md):
return sum(val) > min_sample_count
def observation_filter(val, id_, md):
return sum(val) > min_feature_count
# filter and import table
table = table.filter(observation_filter, axis='observation')
table = table.filter(sample_filter, axis='sample')
table = table.to_dataframe().T
if len(table.index) != len(set(table.index)):
raise ValueError('Data-table contains duplicate indices')
if len(table.columns) != len(set(table.columns)):
raise ValueError('Data-table contains duplicate columns')
# rclr preprocessing and OptSpace (RPCA)
opt = MatrixCompletion(n_components=n_components,
max_iterations=max_iterations).fit(rclr(table))
rename_cols = ['PC' + str(i + 1) for i in range(n_components)]
X = opt.sample_weights @ opt.s @ opt.feature_weights.T
X = X - X.mean(axis=0)
X = X - X.mean(axis=1).reshape(-1, 1)
u, s, v = svd(X)
u = u[:, :n_components]
v = v.T[:, :n_components]
p = s**2 / np.sum(s**2)
p = p[:n_components]
s = s[:n_components]
feature_loading = pd.DataFrame(v, index=table.columns, columns=rename_cols)
sample_loading = pd.DataFrame(u, index=table.index, columns=rename_cols)
# % var explained
proportion_explained = pd.Series(p, index=rename_cols)
# get eigenvalues
eigvals = pd.Series(s, index=rename_cols)
# if the n_components is two add PC3 of zeros
# this is referenced as in issue in
# <https://github.com/biocore/emperor/commit
# /a93f029548c421cb0ba365b4294f7a5a6b0209ce>
# discussed in DEICODE -- PR#29
if n_components == 2:
feature_loading['PC3'] = [0] * len(feature_loading.index)
sample_loading['PC3'] = [0] * len(sample_loading.index)
eigvals.loc['PC3'] = 0
proportion_explained.loc['PC3'] = 0
# save ordination results
short_method_name = 'rpca_biplot'
long_method_name = '(Robust Aitchison) RPCA Biplot'
ord_res = skbio.OrdinationResults(
short_method_name,
long_method_name,
eigvals.copy(),
samples=sample_loading.copy(),
features=feature_loading.copy(),
proportion_explained=proportion_explained.copy())
# save distance matrix
dist_res = skbio.stats.distance.DistanceMatrix(opt.distance,
ids=sample_loading.index)
return ord_res, dist_res
def rpca(
table: biom.Table,
n_components: Union[int, str] = DEFAULT_COMP,
min_sample_count: int = DEFAULT_MSC,
min_feature_count: int = DEFAULT_MFC,
min_feature_frequency: float = DEFAULT_MFF,
max_iterations: int = DEFAULT_OPTSPACE_ITERATIONS
) -> (skbio.OrdinationResults, skbio.DistanceMatrix):
"""Runs RPCA with an matrix_rclr preprocessing step.
This code will be run by both the standalone and QIIME 2 versions of
gemelli.
"""
# get shape of table
n_features, n_samples = table.shape
# filter sample to min seq. depth
def sample_filter(val, id_, md):
return sum(val) > min_sample_count
# filter features to min total counts
def observation_filter(val, id_, md):
return sum(val) > min_feature_count
# filter features by N samples presence
def frequency_filter(val, id_, md):
return (np.sum(val > 0) / n_samples) > (min_feature_frequency / 100)
# filter and import table for each filter above
table = table.filter(observation_filter, axis='observation')
table = table.filter(frequency_filter, axis='observation')
table = table.filter(sample_filter, axis='sample')
# table to dataframe
table = pd.DataFrame(table.matrix_data.toarray(), table.ids('observation'),
table.ids('sample')).T
# check the table after filtering
if len(table.index) != len(set(table.index)):
raise ValueError('Data-table contains duplicate indices')
if len(table.columns) != len(set(table.columns)):
raise ValueError('Data-table contains duplicate columns')
# Robust-clt (matrix_rclr) preprocessing and OptSpace (RPCA)
opt = MatrixCompletion(n_components=n_components,
max_iterations=max_iterations).fit(
matrix_rclr(table))
# get new n-comp when applicable
n_components = opt.s.shape[0]
# get PC column labels for the skbio OrdinationResults
rename_cols = ['PC' + str(i + 1) for i in range(n_components)]
# get completed matrix for centering
X = opt.sample_weights @ opt.s @ opt.feature_weights.T
# center again around zero after completion
X = X - X.mean(axis=0)
X = X - X.mean(axis=1).reshape(-1, 1)
# re-factor the data
u, s, v = svd(X)
# only take n-components
u = u[:, :n_components]
v = v.T[:, :n_components]
# calc. the new variance using projection
p = s**2 / np.sum(s**2)
p = p[:n_components]
s = s[:n_components]
# save the loadings
feature_loading = pd.DataFrame(v, index=table.columns, columns=rename_cols)
sample_loading = pd.DataFrame(u, index=table.index, columns=rename_cols)
# % var explained
proportion_explained = pd.Series(p, index=rename_cols)
# get eigenvalues
eigvals = pd.Series(s, index=rename_cols)
# if the n_components is two add PC3 of zeros
# this is referenced as in issue in
# <https://github.com/biocore/emperor/commit
# /a93f029548c421cb0ba365b4294f7a5a6b0209ce>
# discussed in gemelli -- PR#29
if n_components == 2:
feature_loading['PC3'] = [0] * len(feature_loading.index)
sample_loading['PC3'] = [0] * len(sample_loading.index)
eigvals.loc['PC3'] = 0
proportion_explained.loc['PC3'] = 0
# save ordination results
short_method_name = 'rpca_biplot'
long_method_name = '(Robust Aitchison) RPCA Biplot'
ord_res = skbio.OrdinationResults(
short_method_name,
long_method_name,
eigvals.copy(),
samples=sample_loading.copy(),
features=feature_loading.copy(),
proportion_explained=proportion_explained.copy())
# save distance matrix
dist_res = skbio.stats.distance.DistanceMatrix(opt.distance,
ids=sample_loading.index)
return ord_res, dist_res
def setUp(self):
self.tree = parse_newick('(((a:1,e:2):1,b:2)g:1,(:1,d:3)h:2):1;')
self.pruned_tree = TreeNode.read(
StringIO('(((a:1)EmpressNode0:1,b:2)g:1,(d:3)h:2)EmpressNode1:1;'))
# Test table/metadata (mostly) adapted from Qurro:
# the table is transposed to match QIIME2's expectation
self.table = pd.DataFrame(
{
"Sample1": [1, 2, 0, 4],
"Sample2": [8, 7, 0, 5],
"Sample3": [1, 0, 0, 0],
"Sample4": [0, 0, 0, 0]
},
index=["a", "b", "e", "d"]).T
self.unrelated_table = pd.DataFrame(
{
"Sample1": [5, 2, 0, 2],
"Sample2": [2, 3, 0, 1],
"Sample3": [5, 2, 0, 0],
"Sample4": [4, 5, 0, 4]
},
index=["h", "i", "j", "k"]).T
self.sample_metadata = pd.DataFrame(
{
"Metadata1": [0, 0, 0, 1],
"Metadata2": [0, 0, 0, 0],
"Metadata3": [1, 2, 3, 4],
"Metadata4": ["abc", "def", "ghi", "jkl"]
},
index=list(self.table.index))
self.feature_metadata = pd.DataFrame(
{
"fmdcol1": ["asdf", "ghjk"],
"fmdcol2": ["qwer", "tyui"]
},
index=["a", "h"])
self.filtered_table = pd.DataFrame(
{
"Sample1": [1, 2, 4],
"Sample2": [8, 7, 5],
"Sample3": [1, 0, 0],
"Sample4": [0, 0, 0]
},
index=["a", "b", "d"]).T
eigvals = pd.Series(np.array([0.50, 0.25, 0.25]),
index=['PC1', 'PC2', 'PC3'])
samples = np.array([[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]])
proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=['PC1', 'PC2', 'PC3'])
samples_df = pd.DataFrame(
samples,
index=['Sample1', 'Sample2', 'Sample3', 'Sample4'],
columns=['PC1', 'PC2', 'PC3'])
self.pcoa = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
self.files_to_remove = []
self.maxDiff = None
def setUp(self):
axes = ['PC1', 'PC2', 'PC3', 'PC4', 'PC5', 'PC6']
eigvals = pd.Series(np.array([1.5, 0.75, 0.3, 0.15, 0.15, 0.15]),
index=axes)
samples = np.array([[0, 3, 4, 4, 0, 0], [1, 2, 1, 4, 3, 3],
[2, 3, 1, 0, 0, 1], [0, 3, 2, 4, 3, 0]])
proportion_explained = pd.Series([0.50, 0.25, 0.10, 0.05, 0.05, 0.05],
index=axes)
samples_df = pd.DataFrame(samples,
index=['A', 'B', 'C', 'D'],
columns=axes)
self.reference = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
samples = np.array([[0.7, 3.7, 4.7, 4.7, 0.7, 0.7],
[1.7, 2.7, 1.7, 4.7, 3.7, 3.7],
[2.7, 3.7, 1.7, 0.7, 0.7, 1.7],
[30, 3.7, 2.7, 4.7, 3.7, 0.7]])
samples_df = pd.DataFrame(samples,
index=['A', 'B', 'C', 'D'],
columns=axes)
self.other = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals.copy(),
samples_df.copy(),
proportion_explained=proportion_explained.copy())
S = [[-0.1358036, 0.0452679, 0.3621430, 0.1810715, -0.2716072],
[0.0452679, -0.1358036, -0.1810715, 0.1810715, 0.2716072],
[0.2263394, 0.0452679, -0.1810715, -0.5432145, -0.2716072],
[-0.1358036, 0.0452679, 0.0000000, 0.1810715, 0.2716072]]
samples_df = pd.DataFrame(np.array(S),
index=['A', 'B', 'C', 'D'],
columns=axes[:5])
self.expected_ref = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals[:5].copy(),
samples_df.copy(),
proportion_explained=proportion_explained[:5].copy())
S = [[0.0482731, -0.0324317, 0.0494312, -0.0316828, -0.1584374],
[0.0803620, -0.0718115, -0.0112234, -0.0171011, -0.1101209],
[0.0527554, -0.0042753, -0.0126739, -0.0969602, -0.0964822],
[-0.1813905, 0.1085184, -0.0255339, 0.1457440, 0.3650405]]
samples_df = pd.DataFrame(np.array(S),
index=['A', 'B', 'C', 'D'],
columns=axes[:5])
self.expected_other = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals[:5].copy(),
samples_df.copy(),
proportion_explained=proportion_explained[:5].copy())
noise = [
[0.04988341, -0.03234447, 0.03177641, -0.03507789, -0.13564394],
[0.09117347, -0.08318546, -0.02249053, -0.01597601, -0.10901541],
[0.05077765, -0.003994, -0.00984688, -0.09356729, -0.09648388],
[-0.19183453, 0.11952393, 0.000561, 0.14462118, 0.34114323]
]
samples_df = pd.DataFrame(np.array(noise),
index=['A', 'B', 'C', 'D'],
columns=axes[:5])
self.expected_noise = skbio.OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals[:5].copy(),
samples_df.copy(),
proportion_explained=proportion_explained[:5].copy())
self.expected_m2 = 0.72240956
self.expected_p = 0.5