def unifrac_tasks_from_matrix(u, env_names, modes=UNIFRAC_DEFAULT_MODES):
"""Returns the UniFrac matrix, PCoA, and/or cluster from the matrix."""
result = {}
if UNIFRAC_DIST_MATRIX in modes:
result[UNIFRAC_DIST_MATRIX] = (u, env_names)
if UNIFRAC_PCOA in modes:
point_matrix, eigvals = principal_coordinates_analysis(u)
result[UNIFRAC_PCOA] = output_pca(point_matrix, eigvals, env_names)
if UNIFRAC_CLUST_ENVS in modes:
nodes = map(PhyloNode, env_names)
BIG = 1e305
U = u.copy()
for i in range(len(U)):
U[i, i] = BIG
c = UPGMA_cluster(U, nodes, BIG)
result[UNIFRAC_CLUST_ENVS] = c
if UNIFRAC_NJ_ENVS in modes:
c = nj(dists_to_nj(u, env_names))
result[UNIFRAC_NJ_ENVS] = c
return result
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 = metric_f(x)
# do upgma - rows
BIG = 1e305
row_nodes = map(PhyloNode, map(str,range(nr)))
for i in range(len(row_dissims)):
row_dissims[i,i] = BIG
row_tree = UPGMA_cluster(row_dissims, row_nodes, BIG)
row_order = [int(tip.Name) for tip in row_tree.iterTips()]
return row_order
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 = metric_f(x)
# do upgma - rows
BIG = 1e305
row_nodes = map(PhyloNode, map(str, range(nr)))
for i in range(len(row_dissims)):
row_dissims[i, i] = BIG
row_tree = UPGMA_cluster(row_dissims, row_nodes, BIG)
row_order = [int(tip.Name) for tip in row_tree.iterTips()]
return row_order
def test_upgma_cluster(self):
"""UPGMA_cluster clusters nodes based on info in a matrix with UPGMA
"""
matrix = self.matrix
node_order = self.node_order
large_number = 9999999999
tree = UPGMA_cluster(matrix, node_order, large_number)
self.assertEqual(str(tree), \
'(((a:0.5,b:0.5):1.75,c:2.25):5.875,(d:1.0,e:1.0):7.125);')
def single_file_upgma(input_file, output_file):
# read in dist matrix
f = open(input_file, 'U')
headers, data = parse_distmat(f)
f.close()
# do upgma
nodes = map(PhyloNode, headers)
BIG = 1e305
U = data.copy()
for i in range(len(U)):
U[i,i] = BIG
c = UPGMA_cluster(U, nodes, BIG)
# write output
f = open(output_file,'w')
f.write(c.getNewick(with_distances=True))
f.close()
def test_UPGMA_cluster_diag(self):
"""UPGMA_cluster works when the diagonal has intermediate values
"""
#test that checking the diagonal works
matrix = self.matrix_five
node_order = self.node_order
large_number = 9999999999
tree = UPGMA_cluster(matrix, node_order, large_number)
self.assertEqual(str(tree), \
'(((a:0.5,b:0.5):1.75,c:2.25):5.875,(d:1.0,e:1.0):7.125);')
def single_file_upgma(input_file, output_file):
# read in dist matrix
f = open(input_file, 'U')
headers, data = parse_distmat(f)
f.close()
# do upgma
nodes = map(PhyloNode, headers)
BIG = 1e305
U = data.copy()
for i in range(len(U)):
U[i,i] = BIG
c = UPGMA_cluster(U, nodes, BIG)
# write output
f = open(output_file,'w')
try:
f.write(c.getNewick(with_distances=True))
except AttributeError:
if c == 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
f = open(input_file, 'U')
headers, data = parse_distmat(f)
f.close()
# do upgma
nodes = map(PhyloNode, headers)
BIG = 1e305
U = data.copy()
for i in range(len(U)):
U[i, i] = BIG
c = UPGMA_cluster(U, nodes, BIG)
# write output
f = open(output_file, 'w')
try:
f.write(c.getNewick(with_distances=True))
except AttributeError:
if c == 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()