def test_pw_distances_braycurtis(self):
actual_dm = pw_distances(self.t1, self.ids1, 'braycurtis')
self.assertEqual(actual_dm.shape, (3, 3))
npt.assert_almost_equal(actual_dm['A', 'A'], 0.0)
npt.assert_almost_equal(actual_dm['B', 'B'], 0.0)
npt.assert_almost_equal(actual_dm['C', 'C'], 0.0)
npt.assert_almost_equal(actual_dm['A', 'B'], 0.27272727)
npt.assert_almost_equal(actual_dm['B', 'A'], 0.27272727)
npt.assert_almost_equal(actual_dm['A', 'C'], 0.71428571)
npt.assert_almost_equal(actual_dm['C', 'A'], 0.71428571)
npt.assert_almost_equal(actual_dm['B', 'C'], 0.66666667)
npt.assert_almost_equal(actual_dm['C', 'B'], 0.66666667)
actual_dm = pw_distances(self.t2, self.ids2, 'braycurtis')
expected_data = [
[0., 0.78787879, 0.86666667, 0.30927835, 0.85714286, 0.81521739],
[0.78787879, 0., 0.78142077, 0.86813187, 0.75, 0.1627907],
[0.86666667, 0.78142077, 0., 0.87709497, 0.09392265, 0.71597633],
[0.30927835, 0.86813187, 0.87709497, 0., 0.87777778, 0.89285714],
[0.85714286, 0.75, 0.09392265, 0.87777778, 0., 0.68235294],
[0.81521739, 0.1627907, 0.71597633, 0.89285714, 0.68235294, 0.]]
expected_dm = DistanceMatrix(expected_data, self.ids2)
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(actual_dm[id1, id2],
expected_dm[id1, id2], 6)
def test_pw_distances_braycurtis(self):
actual_dm = pw_distances(self.t1, self.ids1, 'braycurtis')
self.assertEqual(actual_dm.shape, (3, 3))
npt.assert_almost_equal(actual_dm['A', 'A'], 0.0)
npt.assert_almost_equal(actual_dm['B', 'B'], 0.0)
npt.assert_almost_equal(actual_dm['C', 'C'], 0.0)
npt.assert_almost_equal(actual_dm['A', 'B'], 0.27272727)
npt.assert_almost_equal(actual_dm['B', 'A'], 0.27272727)
npt.assert_almost_equal(actual_dm['A', 'C'], 0.71428571)
npt.assert_almost_equal(actual_dm['C', 'A'], 0.71428571)
npt.assert_almost_equal(actual_dm['B', 'C'], 0.66666667)
npt.assert_almost_equal(actual_dm['C', 'B'], 0.66666667)
actual_dm = pw_distances(self.t2, self.ids2, 'braycurtis')
expected_data = [
[0., 0.78787879, 0.86666667, 0.30927835, 0.85714286, 0.81521739],
[0.78787879, 0., 0.78142077, 0.86813187, 0.75, 0.1627907],
[0.86666667, 0.78142077, 0., 0.87709497, 0.09392265, 0.71597633],
[0.30927835, 0.86813187, 0.87709497, 0., 0.87777778, 0.89285714],
[0.85714286, 0.75, 0.09392265, 0.87777778, 0., 0.68235294],
[0.81521739, 0.1627907, 0.71597633, 0.89285714, 0.68235294, 0.]]
expected_dm = DistanceMatrix(expected_data, self.ids2)
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(actual_dm[id1, id2],
expected_dm[id1, id2], 6)
def test_pw_distances_euclidean(self):
actual_dm = pw_distances(self.t1, self.ids1, 'euclidean')
self.assertEqual(actual_dm.shape, (3, 3))
npt.assert_almost_equal(actual_dm['A', 'A'], 0.0)
npt.assert_almost_equal(actual_dm['B', 'B'], 0.0)
npt.assert_almost_equal(actual_dm['C', 'C'], 0.0)
npt.assert_almost_equal(actual_dm['A', 'B'], 2.23606798)
npt.assert_almost_equal(actual_dm['B', 'A'], 2.23606798)
npt.assert_almost_equal(actual_dm['A', 'C'], 4.12310563)
npt.assert_almost_equal(actual_dm['C', 'A'], 4.12310563)
npt.assert_almost_equal(actual_dm['B', 'C'], 2.82842712)
npt.assert_almost_equal(actual_dm['C', 'B'], 2.82842712)
actual_dm = pw_distances(self.t2, self.ids2, 'euclidean')
expected_data = [
[0., 80.8455317, 84.0297566, 36.3042697, 86.0116271, 78.9176786],
[80.8455317, 0., 71.0844568, 74.4714710, 69.3397433, 14.422205],
[84.0297566, 71.0844568, 0., 77.2851861, 8.3066238, 60.7536007],
[36.3042697, 74.4714710, 77.2851861, 0., 78.7908624, 70.7389567],
[86.0116271, 69.3397433, 8.3066238, 78.7908624, 0., 58.4807660],
[78.9176786, 14.422205, 60.7536007, 70.7389567, 58.4807660, 0.]]
expected_dm = DistanceMatrix(expected_data, self.ids2)
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(actual_dm[id1, id2],
expected_dm[id1, id2], 6)
def test_pw_distances_euclidean(self):
actual_dm = pw_distances(self.t1, self.ids1, 'euclidean')
self.assertEqual(actual_dm.shape, (3, 3))
npt.assert_almost_equal(actual_dm['A', 'A'], 0.0)
npt.assert_almost_equal(actual_dm['B', 'B'], 0.0)
npt.assert_almost_equal(actual_dm['C', 'C'], 0.0)
npt.assert_almost_equal(actual_dm['A', 'B'], 2.23606798)
npt.assert_almost_equal(actual_dm['B', 'A'], 2.23606798)
npt.assert_almost_equal(actual_dm['A', 'C'], 4.12310563)
npt.assert_almost_equal(actual_dm['C', 'A'], 4.12310563)
npt.assert_almost_equal(actual_dm['B', 'C'], 2.82842712)
npt.assert_almost_equal(actual_dm['C', 'B'], 2.82842712)
actual_dm = pw_distances(self.t2, self.ids2, 'euclidean')
expected_data = [
[0., 80.8455317, 84.0297566, 36.3042697, 86.0116271, 78.9176786],
[80.8455317, 0., 71.0844568, 74.4714710, 69.3397433, 14.422205],
[84.0297566, 71.0844568, 0., 77.2851861, 8.3066238, 60.7536007],
[36.3042697, 74.4714710, 77.2851861, 0., 78.7908624, 70.7389567],
[86.0116271, 69.3397433, 8.3066238, 78.7908624, 0., 58.4807660],
[78.9176786, 14.422205, 60.7536007, 70.7389567, 58.4807660, 0.]]
expected_dm = DistanceMatrix(expected_data, self.ids2)
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(actual_dm[id1, id2],
expected_dm[id1, id2], 6)
def test_pw_distances_from_table_euclidean(self):
# results are equal when passed as Table or matrix
m_dm = pw_distances(self.t1, self.ids1, 'euclidean')
t_dm = npt.assert_warns(DeprecationWarning, pw_distances_from_table,
self.table1, 'euclidean')
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
m_dm = pw_distances(self.t2, self.ids2, 'euclidean')
t_dm = npt.assert_warns(DeprecationWarning, pw_distances_from_table,
self.table2, 'euclidean')
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
def test_pw_distances_from_table_braycurtis(self):
# results are equal when passed as Table or matrix
m_dm = pw_distances(self.t1, self.ids1, 'braycurtis')
t_dm = npt.assert_warns(
UserWarning, pw_distances_from_table, self.table1, 'braycurtis')
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
m_dm = pw_distances(self.t2, self.ids2, 'braycurtis')
t_dm = npt.assert_warns(
UserWarning, pw_distances_from_table, self.table2, 'braycurtis')
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
def test_pw_distances_from_table_braycurtis(self):
# results are equal when passed as Table or matrix
m_dm = pw_distances(self.t1, self.ids1, 'braycurtis')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
t_dm = pw_distances_from_table(self.table1, 'braycurtis')
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
m_dm = pw_distances(self.t2, self.ids2, 'braycurtis')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
t_dm = pw_distances_from_table(self.table2, 'braycurtis')
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
def test_pw_distances_from_table_braycurtis(self):
# results are equal when passed as Table or matrix
m_dm = pw_distances(self.t1, self.ids1, 'braycurtis')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
t_dm = pw_distances_from_table(self.table1, 'braycurtis')
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
m_dm = pw_distances(self.t2, self.ids2, 'braycurtis')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
t_dm = pw_distances_from_table(self.table2, 'braycurtis')
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
def test_pw_distances_weighted_unifrac(self):
# expected values calculated by hand
dm1 = pw_distances('weighted_unifrac', self.t1, self.ids1,
otu_ids=self.otu_ids1, tree=self.tree1)
dm2 = pw_distances(weighted_unifrac, self.t1, self.ids1,
otu_ids=self.otu_ids1, tree=self.tree1)
self.assertEqual(dm1.shape, (3, 3))
self.assertEqual(dm1, dm2)
expected_data = [
[0.0, 0.1750000, 0.12499999],
[0.1750000, 0.0, 0.3000000],
[0.12499999, 0.3000000, 0.0]]
expected_dm = DistanceMatrix(expected_data, ids=self.ids1)
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(dm1[id1, id2],
expected_dm[id1, id2], 6)
def test_pw_distances_from_table_euclidean(self):
# results are equal when passed as Table or matrix
m_dm = pw_distances(self.t1, self.ids1, 'euclidean')
t_dm = npt.assert_warns(
DeprecationWarning, pw_distances_from_table, self.table1,
'euclidean')
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
m_dm = pw_distances(self.t2, self.ids2, 'euclidean')
t_dm = npt.assert_warns(
DeprecationWarning, pw_distances_from_table, self.table2,
'euclidean')
for id1 in self.ids2:
for id2 in self.ids2:
npt.assert_almost_equal(m_dm[id1, id2], t_dm[id1, id2])
def test_pw_distances_weighted_unifrac_normalized(self):
# expected values calculated by hand
dm1 = pw_distances('weighted_unifrac', self.t1, self.ids1,
otu_ids=self.otu_ids1, tree=self.tree1,
normalized=True)
dm2 = pw_distances(weighted_unifrac, self.t1, self.ids1,
otu_ids=self.otu_ids1, tree=self.tree1,
normalized=True)
self.assertEqual(dm1.shape, (3, 3))
self.assertEqual(dm1, dm2)
expected_data = [
[0.0, 0.128834, 0.085714],
[0.128834, 0.0, 0.2142857],
[0.085714, 0.2142857, 0.0]]
expected_dm = DistanceMatrix(expected_data, ids=self.ids1)
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(dm1[id1, id2],
expected_dm[id1, id2], 6)
def get_clusters(x_original, axis='row'):
"""Performs UPGMA clustering using euclidean distances"""
x = x_original.copy()
if axis == 'column':
x = x.T
nr = x.shape[0]
row_dissims = pw_distances(x, ids=map(str, range(nr)), metric='euclidean')
# do upgma - rows
# Average in SciPy's cluster.hierarchy.linkage is UPGMA
linkage_matrix = linkage(row_dissims.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, row_dissims.ids)
return [int(tip.name) for tip in tree.tips()]
def get_clusters(x_original, axis='row'):
"""Performs UPGMA clustering using euclidean distances"""
x = x_original.copy()
if axis == 'column':
x = x.T
nr = x.shape[0]
row_dissims = pw_distances(x, ids=map(str, range(nr)), metric='euclidean')
# do upgma - rows
# Average in SciPy's cluster.hierarchy.linkage is UPGMA
linkage_matrix = linkage(row_dissims.condensed_form(), method='average')
tree = TreeNode.from_linkage_matrix(linkage_matrix, row_dissims.ids)
return [int(tip.name) for tip in tree.tips()]
def test_pw_distances_unweighted_unifrac(self):
# expected values calculated by hand
dm1 = pw_distances('unweighted_unifrac',
self.t1,
self.ids1,
otu_ids=self.otu_ids1,
tree=self.tree1)
dm2 = pw_distances(unweighted_unifrac,
self.t1,
self.ids1,
otu_ids=self.otu_ids1,
tree=self.tree1)
self.assertEqual(dm1.shape, (3, 3))
self.assertEqual(dm1, dm2)
expected_data = [[0.0, 0.0, 0.25 / 1.0], [0.0, 0.0, 0.25 / 1.0],
[0.25 / 1.0, 0.25 / 1.0, 0.0]]
expected_dm = DistanceMatrix(expected_data, ids=self.ids1)
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(dm1[id1, id2], expected_dm[id1, id2],
6)
def test_pw_distances_weighted_unifrac_normalized(self):
# expected values calculated by hand
dm1 = pw_distances('weighted_unifrac',
self.t1,
self.ids1,
otu_ids=self.otu_ids1,
tree=self.tree1,
normalized=True)
dm2 = pw_distances(weighted_unifrac,
self.t1,
self.ids1,
otu_ids=self.otu_ids1,
tree=self.tree1,
normalized=True)
self.assertEqual(dm1.shape, (3, 3))
self.assertEqual(dm1, dm2)
expected_data = [[0.0, 0.128834, 0.085714], [0.128834, 0.0, 0.2142857],
[0.085714, 0.2142857, 0.0]]
expected_dm = DistanceMatrix(expected_data, ids=self.ids1)
for id1 in self.ids1:
for id2 in self.ids1:
npt.assert_almost_equal(dm1[id1, id2], expected_dm[id1, id2],
6)
def biom_to_dm(metric, biom):
return pw_distances(metric=metric, counts=biom.T, ids=biom.columns)
#!/usr/bin/env python3
import numpy as np
import csv
from numpy import genfromtxt
from skbio.diversity.beta import pw_distances
taxonomy_tbl = np.genfromtxt("BAM_9ancient_hmp_protein.csv",
delimiter=',',
dtype=float,
skip_header=1,
usecols=range(1, 157))
taxonomy_trans = taxonomy_tbl.transpose()
with open(r'BAM_9ancient_hmp_protein.csv') as csvfile:
csv_reader = csv.reader(csvfile)
sample_ID = next(csv_reader)
sample_ID.pop(0)
print(sample_ID[1])
#jaccard_distance
j_dm = pw_distances(taxonomy_trans, sample_ID, "jaccard")
print(j_dm[0:3])
j_dm.write('jaccard__9ancient_hmp_protein.csv')
from skbio.diversity.beta import pw_distances
import numpy as np
data = [[23, 64, 14, 0, 0, 3, 1], [0, 3, 35, 42, 0, 12, 1],
[0, 5, 5, 0, 40, 40, 0], [44, 35, 9, 0, 1, 0, 0],
[0, 2, 8, 0, 35, 45, 1], [0, 0, 25, 35, 0, 19, 0]]
ids = list('ABCDEF')
# Compute Bray-Curtis distances between all pairs of samples and return a
# ``DistanceMatrix`` object:
bc_dm = pw_distances(data, ids, "braycurtis")
print(bc_dm)
# 6x6 distance matrix
# IDs:
# 'A', 'B', 'C', 'D', 'E', 'F'
# Data:
# [[ 0. 0.78787879 0.86666667 0.30927835 0.85714286 0.81521739]
# [ 0.78787879 0. 0.78142077 0.86813187 0.75 0.1627907 ]
# [ 0.86666667 0.78142077 0. 0.87709497 0.09392265 0.71597633]
# [ 0.30927835 0.86813187 0.87709497 0. 0.87777778 0.89285714]
# [ 0.85714286 0.75 0.09392265 0.87777778 0. 0.68235294]
# [ 0.81521739 0.1627907 0.71597633 0.89285714 0.68235294 0. ]]
# Compute Jaccard distances between all pairs of samples and return a
# ``DistanceMatrix`` object:
j_dm = pw_distances(data, ids, "jaccard")
print(j_dm)
# 6x6 distance matrix
# IDs:
# 'A', 'B', 'C', 'D', 'E', 'F'