def test_gradient_sort_error(self):
# Makes sure that the tree is sorted according
# a pre-set ordering
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
x = pd.Series({'f': 'x', 'g': 'y', 'h': 'z', 'a': 'u', 'b': 'dz'})
with self.assertRaises(ValueError):
gradient_sort(tree, x)
def test_gradient_sort_error(self):
# Makes sure that the tree is sorted according
# a pre-set ordering
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
x = pd.Series({'f': 'x', 'g': 'y', 'h': 'z', 'a': 'u', 'b': 'dz'})
with self.assertRaises(ValueError):
gradient_sort(tree, x)
def gradient_clustering(table: pd.DataFrame,
gradient: NumericMetadataColumn,
weighted: bool = True) -> skbio.TreeNode:
""" Builds a tree for features based on a gradient.
Parameters
----------
table : pd.DataFrame
Contingency table where rows are samples and columns are features.
gradient : qiime2.NumericMetadataColumn
Continuous vector of measurements corresponding to samples.
weighted : bool
Specifies if abundance or presence/absence information
should be used to perform the clustering.
Returns
-------
skbio.TreeNode
Represents the partitioning of features with respect to the gradient.
"""
c = gradient.to_series()
if not weighted:
table = (table > 0).astype(np.float)
table, c = match(table, c)
t = gradient_linkage(table, c, method='average')
mean_g = mean_niche_estimator(table, c)
mean_g = pd.Series(mean_g, index=table.columns)
mean_g = mean_g.sort_values()
t = gradient_sort(t, mean_g)
return t
def test_gradient_sort_descending(self):
# Makes sure that the tree is sorted according
# a pre-set ordering in descending order
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
exp = '((b,a)c,(f,(h,g)e)d)r;\n'
x = pd.Series({'f': 3, 'g': 1, 'h': 2, 'a': 4, 'b': 5})
res = str(gradient_sort(tree, x, ascending=False))
self.assertEqual(exp, res)
def test_gradient_sort(self):
# Makes sure that the tree is sorted according
# a pre-set ordering
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
exp = '(((g,h)e,f)d,(a,b)c)r;\n'
x = pd.Series({'f': 3, 'g': 1, 'h': 2, 'a': 4, 'b': 5})
res = str(gradient_sort(tree, x))
self.assertEqual(exp, res)
def test_gradient_sort_descending(self):
# Makes sure that the tree is sorted according
# a pre-set ordering in descending order
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
exp = '((b,a)c,(f,(h,g)e)d)r;\n'
x = pd.Series({'f': 3, 'g': 1, 'h': 2, 'a': 4, 'b': 5})
res = str(gradient_sort(tree, x, ascending=False))
self.assertEqual(exp, res)
def test_gradient_sort(self):
# Makes sure that the tree is sorted according
# a pre-set ordering
tree = TreeNode.read([u'((a,b)c, ((g,h)e,f)d)r;'])
exp = '(((g,h)e,f)d,(a,b)c)r;\n'
x = pd.Series({'f': 3, 'g': 1, 'h': 2, 'a': 4, 'b': 5})
res = str(gradient_sort(tree, x))
self.assertEqual(exp, res)
def gradient_clustering(table: pd.DataFrame,
gradient: NumericMetadataColumn,
ignore_missing_samples: bool = False,
weighted: bool = True) -> skbio.TreeNode:
""" Builds a tree for features based on a gradient.
Parameters
----------
table : pd.DataFrame
Contingency table where rows are samples and columns are features.
gradient : qiime2.NumericMetadataColumn
Continuous vector of measurements corresponding to samples.
ignore_missing_samples: bool
Whether to except or ignore when there are samples present in the table
that are not present in the gradient metadata.
weighted : bool
Specifies if abundance or presence/absence information
should be used to perform the clustering.
Returns
-------
skbio.TreeNode
Represents the partitioning of features with respect to the gradient.
"""
c = gradient.to_series()
if not ignore_missing_samples:
difference = set(table.index) - set(c.index)
if difference:
raise KeyError("There are samples present in the table not "
"present in the gradient metadata column. Override "
"this error by using the `ignore_missing_samples` "
"argument. Offending samples: %r" %
', '.join(sorted([str(i) for i in difference])))
if not weighted:
table = (table > 0).astype(float)
table, c = match(table, c)
t = gradient_linkage(table, c, method='average')
mean_g = mean_niche_estimator(table, c)
mean_g = pd.Series(mean_g, index=table.columns)
mean_g = mean_g.sort_values()
t = gradient_sort(t, mean_g)
return t
