def test_clusters_b(self):
root = mtree.create_tree([[[0, [1, 2]], [3, [4, 5, 6]]],7])
root = center_and_sort_tree(root)
clusters = get_clusters(root)
observed = set(frozenset(x) for x in clusters)
expected = set(frozenset(x) for x in [[1,2],[0,1,2],[4,5,6],[0,1,2,7],[3,4,5,6]])
self.assertEqual(expected, observed)
def test_dendrogram_imager(self):
filename = 'dendrogram-test.png'
root = mtree.create_tree([[0, [1, 2]], 3, [4, 5, 6]])
imager = DendrogramImager(root)
fout = open(filename, 'wb')
imager.im.save(fout)
fout.close()
def test_dendrogram(self):
root = mtree.create_tree([[0, [1, 2]], 3, [4, 5, 6]])
# make a tall tree
observed_tall_art = str(AsciiArt(root, draw_tall_dendrogram))
self.assertEqual(observed_tall_art, g_expected_tall_art)
# make a short tree
observed_short_art = str(AsciiArt(root))
self.assertEqual(observed_short_art, g_expected_short_art)
def test_heatmap_with_dendrogram(self):
root = mtree.create_tree([[0, [1, 2]], 3, [4, 5, 6]])
M = np.random.random((7, 7))
R = np.corrcoef(M)
# draw the correlation heatmap
filename = 'r-test.png'
f = gradient.correlation_to_rgb
get_heatmap_with_dendrogram(R, root, f, filename)
# draw the squared correlation heatmap
filename = 'rr-test.png'
RoR = R*R
f = gradient.squared_correlation_to_rgb
get_heatmap_with_dendrogram(RoR, root, f, filename)
import mtree example_hash_list = [ "aa", "bb", "cc", "dd", "ee", "11", "22", "33", "44", "55" "66" ] print(mtree.create_tree(example_hash_list))
def test_center_and_sort_tree(self):
root = mtree.create_tree([[[0, [1, 2]], 3, [4, 5, 6]],7])
root = center_and_sort_tree(root)
expected = set(frozenset(x) for x in [[0,1,2],[3],[7],[4,5,6]])
observed = set(frozenset(get_label_set(c)) for c in root.children)
self.assertEqual(expected, observed)
def test_id_to_nlabels(self):
root = mtree.create_tree([[[0, [1, 2]], 3, [4, 5, 6]],7])
id_to_nlabels = build_id_to_nlabels(root, {})
self.assertEqual(id_to_nlabels[id(root)], 8)
child_nlabels = [id_to_nlabels[id(child)] for child in root.children]
self.assertEqual(sum(child_nlabels), 8)
def build_tree_helper(boxed_U_in, S_in, ordered_labels, tree_data):
"""
Get the root of an mtree reconstructed from the transformed data.
The input matrix U will be freed (deleted) by this function.
@param boxed_U_in: part of the laplacian sqrt obtained by svd
@param S_in: another part of the laplacian sqrt obtained by svd
@param ordered_labels: a list of labels conformant with rows of U
@param tree_data: state whose scope is the construction of the tree
@return: an mtree rooted at a degree 2 vertex unless the input matrix has 3 rows
"""
# take U_in out of the box
if len(boxed_U_in) != 1:
raise ValueError('expected a 2d array as the only element of a list')
U_in = boxed_U_in[0]
shape = U_in.shape
if len(shape) != 2:
raise valueError('expected a 2d array as the only element of a list')
p, n = shape
if p < 3 or n < 3:
raise ValueError('expected the input matrix to have at least three rows and columns')
# look for an informative split
index_split = None
if p > 3:
# the signs of v match the signs of the fiedler vector
v = khorr.get_fiedler_vector(U_in, S_in)
index_split = splitbuilder.eigenvector_to_split(v)
# if the split is degenerate then don't use it
if min(len(x) for x in index_split) < 2:
index_split = None
# if no informative split was found then create a degenerate tree
if not index_split:
root = mtree.create_tree(ordered_labels)
for node in root.preorder():
if node.has_label():
tree_data.add_node(node)
return root
# get the indices defined by the split
a, b = tuple(list(sorted(x)) for x in index_split)
# Create two new matrices.
# Be somewhat careful to not create lots of intermediate matrices
A = np.zeros((len(a)+1, n))
B = np.zeros((len(b)+1, n))
for i, index in enumerate(a):
A[i] = U_in[index] * S_in
for i, index in enumerate(b):
B[i] = U_in[index] * S_in
A_outgroup = np.sum(B, 0)
B_outgroup = np.sum(A, 0)
A[-1] = A_outgroup
B[-1] = B_outgroup
# delete the two references to the old matrix
del U_in
del boxed_U_in[0]
# recursively construct the subtrees
subtrees = []
stack = [[b,a,B], [a,b,A]]
# delete non-stack references to partial matrices
del A
del B
# process the partial matrices
while stack:
selection, complement, summed_L_sqrt = stack.pop()
# record the outgroup label for this subtree
outgroup_label = tree_data.decrement_outgroup_label()
# create the ordered list of labels corresponding to leaves of the subtree
next_ordered_labels = [ordered_labels[i] for i in selection]
next_ordered_labels.append(outgroup_label)
# get the criterion matrix for the next iteration
U, S, VT = np.linalg.svd(summed_L_sqrt, full_matrices=0)
del VT
# delete matrices that are no longer useful
del summed_L_sqrt
# build the tree recursively
boxed_U = [U]
del U
root = build_tree_helper(boxed_U, S, next_ordered_labels, tree_data)
# if the root is degree 2 then remove the root node
if root.degree() == 2:
root = root.remove()
# root the tree at the outgroup node
root = tree_data.label_to_node[outgroup_label]
root.reroot()
# we don't need the outgroup label anymore
tree_data.remove_node(root)
# we can also remove the label from the outgroup node itself
root.label = None
# save the properly rooted subtree
subtrees.append(root)
# connect the two subtrees at their roots
left_root, right_root = subtrees
right_root = right_root.remove()
left_root.add_child(right_root)
return left_root