def test_linkage_matrix(self):
# Ensure matches: http://www.southampton.ac.uk/~re1u06/teaching/upgma/
id_list = ['A', 'B', 'C', 'D', 'E', 'F', 'G']
linkage = np.asarray([[1.0, 5.0, 1.0, 2.0], [0.0, 3.0, 8.0, 2.0],
[6.0, 7.0, 12.5, 3.0], [8.0, 9.0, 16.5, 5.0],
[2.0, 10.0, 29.0, 6.0], [4.0, 11.0, 34.0, 7.0]])
tree = TreeNode.from_linkage_matrix(linkage, id_list)
self.assertEquals(
"(E:17.0,(C:14.5,((A:4.0,D:4.0):4.25,(G:6.25,(B:0.5,"
"F:0.5):5.75):2.0):6.25):2.5);",
tree.to_newick(with_distances=True))
def get_clusters(x_original, axis=['row', 'column'][0]):
"""Performs UPGMA clustering using euclidean distances"""
x = x_original.copy()
if axis == 'column':
x = x.T
nr = x.shape[0]
metric_f = get_nonphylogenetic_metric('euclidean')
row_dissims = DistanceMatrix(metric_f(x), map(str, range(nr)))
# do upgma - rows
# Average in SciPy's cluster.heirarchy.linkage is UPGMA
linkage_matrix = linkage(row_dissims.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, row_dissims.ids)
row_order = [int(tip.name) for tip in tree.tips()]
return row_order
def test_linkage_matrix(self):
# Ensure matches: http://www.southampton.ac.uk/~re1u06/teaching/upgma/
id_list = ['A', 'B', 'C', 'D', 'E', 'F', 'G']
linkage = np.asarray([[1.0, 5.0, 1.0, 2.0],
[0.0, 3.0, 8.0, 2.0],
[6.0, 7.0, 12.5, 3.0],
[8.0, 9.0, 16.5, 5.0],
[2.0, 10.0, 29.0, 6.0],
[4.0, 11.0, 34.0, 7.0]])
tree = TreeNode.from_linkage_matrix(linkage, id_list)
self.assertEqual("(E:17.0,(C:14.5,((A:4.0,D:4.0):4.25,(G:6.25,(B:0.5,"
"F:0.5):5.75):2.0):6.25):2.5);",
tree.to_newick(with_distances=True))
def get_clusters(x_original, axis=['row', 'column'][0]):
"""Performs UPGMA clustering using euclidean distances"""
x = x_original.copy()
if axis == 'column':
x = x.T
nr = x.shape[0]
metric_f = get_nonphylogenetic_metric('euclidean')
row_dissims = DistanceMatrix(metric_f(x), map(str, range(nr)))
# do upgma - rows
# Average in SciPy's cluster.heirarchy.linkage is UPGMA
linkage_matrix = linkage(row_dissims.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, row_dissims.ids)
row_order = [int(tip.name) for tip in tree.tips()]
return row_order
def single_file_upgma(input_file, output_file):
# read in dist matrix
dist_mat = DistanceMatrix.from_file(input_file)
# SciPy uses average as UPGMA:
# http://docs.scipy.org/doc/scipy/reference/generated/
# scipy.cluster.hierarchy.linkage.html#scipy.cluster.hierarchy.linkage
linkage_matrix = linkage(dist_mat.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, dist_mat.ids)
# write output
f = open(output_file, 'w')
try:
f.write(tree.to_newick(with_distances=True))
except AttributeError:
if c is None:
raise RuntimeError("""input file %s did not make a UPGMA tree.
Ensure it has more than one sample present""" % (str(input_file), ))
raise
f.close()
def single_file_upgma(input_file, output_file):
# read in dist matrix
dist_mat = DistanceMatrix.from_file(input_file)
# SciPy uses average as UPGMA:
# http://docs.scipy.org/doc/scipy/reference/generated/
# scipy.cluster.hierarchy.linkage.html#scipy.cluster.hierarchy.linkage
linkage_matrix = linkage(dist_mat.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, dist_mat.ids)
# write output
f = open(output_file, 'w')
try:
f.write(tree.to_newick(with_distances=True))
except AttributeError:
if c is None:
raise RuntimeError("""input file %s did not make a UPGMA tree.
Ensure it has more than one sample present""" % (str(input_file),))
raise
f.close()
