def test_tensor_input():
X = np.random.normal(size=(100, 5, 5))
mds = ClassicalMDS(n_components=3, dissimilarity="euclidean")
mds.fit(X)
assert_equal(mds.dissimilarity_matrix_.shape, (100, 100))
X_transformed = mds.fit_transform(X)
assert_equal(X_transformed.shape, (100, 3))
def use_fit_transform():
A = np.ones((4, 4)) - np.identity(4)
mds = ClassicalMDS(n_components=3, dissimilarity="precomputed")
B = mds.fit_transform(A)
Ahat = _compute_dissimilarity(B)
# Checks up to 7 decimal points
assert_almost_equal(A, Ahat)
def use_fit():
A = np.ones((4, 4)) - np.identity(4)
mds = ClassicalMDS(n_components=3, dissimilarity="precomputed")
mds.fit(A)
B = np.dot(mds.components_, np.diag(mds.singular_values_))
Ahat = _compute_dissimilarity(B)
# Checks up to 7 decimal points
assert_almost_equal(A, Ahat)
def use_euclidean():
A = np.array([
[-7.62291243e-17, 6.12372436e-01, 4.95031815e-16],
[-4.97243701e-01, -2.04124145e-01, -2.93397401e-01],
[5.02711453e-01, -2.04124145e-01, -2.83926977e-01],
[-5.46775198e-03, -2.04124145e-01, 5.77324378e-01],
])
mds = ClassicalMDS(dissimilarity="euclidean")
B = mds.fit_transform(A)
target = np.ones((4, 4)) - np.identity(4)
assert_almost_equal(mds.dissimilarity_matrix_, target)
def _omni_embed(pop_array, atlas, graph_path_list, ID,
subgraph_name="all_nodes", n_components=None, norm=1):
"""
Omnibus embedding of arbitrary number of input graphs with matched vertex
sets.
Given :math:`A_1, A_2, ..., A_m` a collection of (possibly weighted)
adjacency matrices of a collection :math:`m` undirected graphs with
matched vertices.
Then the :math:`(mn \times mn)` omnibus matrix, :math:`M`, has the
subgraph where :math:`M_{ij} = \frac{1}{2}(A_i + A_j)`. The omnibus
matrix is then embedded using adjacency spectral embedding.
Parameters
----------
pop_array : list of nx.Graph or ndarray, or ndarray
If list of nx.Graph, each Graph must contain same number of nodes.
If list of ndarray, each array must have shape (n_vertices,
n_vertices).
If ndarray, then array must have shape (n_graphs, n_vertices,
n_vertices).
atlas : str
The name of an atlas (indicating the node definition).
graph_pathlist : list
List of file paths to graphs in pop_array.
ID : str
An arbitrary subject identifier.
subgraph_name : str
Returns
-------
out_path : str
File path to .npy file containing omni embedding tensor.
References
----------
.. [1] Levin, K., Athreya, A., Tang, M., Lyzinski, V., & Priebe, C. E.
(2017, November). A central limit theorem for an omnibus embedding of
multiple random dot product graphs. In Data Mining Workshops (ICDMW),
2017 IEEE International Conference on (pp. 964-967). IEEE.
.. [2] Chung, J., Pedigo, B. D., Bridgeford, E. W., Varjavand, B. K.,
Helm, H. S., & Vogelstein, J. T. (2019). Graspy: Graph statistics in
python. Journal of Machine Learning Research.
"""
import os
import networkx as nx
import numpy as np
from pynets.core.utils import flatten
from graspologic.embed.omni import OmnibusEmbed
from graspologic.embed.mds import ClassicalMDS
from joblib import dump
from pynets.stats.netstats import CleanGraphs
dir_path = str(Path(os.path.dirname(graph_path_list[0])).parent)
namer_dir = f"{dir_path}/embeddings"
if os.path.isdir(namer_dir) is False:
os.makedirs(namer_dir, exist_ok=True)
clean_mats = []
i = 0
for graph_path in graph_path_list:
cg = CleanGraphs(None, None, graph_path, 0, norm)
if float(norm) >= 1:
G = cg.normalize_graph()
mat_clean = nx.to_numpy_array(G)
else:
mat_clean = pop_array[i]
mat_clean[np.where(np.isnan(mat_clean) | np.isinf(mat_clean))] = 0
if np.isnan(np.sum(mat_clean)) == False:
clean_mats.append(mat_clean)
i += 1
clean_mats = [i for i in clean_mats if np.isfinite(i).all()]
if len(clean_mats) > 0:
# Omnibus embedding
print(
f"{'Embedding unimodal omnetome for atlas: '}{atlas} and "
f"{subgraph_name}{'...'}"
)
omni = OmnibusEmbed(n_components=n_components, check_lcc=False)
mds = ClassicalMDS(n_components=n_components)
omni_fit = omni.fit_transform(clean_mats)
# Transform omnibus tensor into dissimilarity feature
mds_fit = mds.fit_transform(omni_fit.reshape(omni_fit.shape[1],
omni_fit.shape[2],
omni_fit.shape[0]))
out_path = (
f"{namer_dir}/gradient-OMNI_{atlas}_{subgraph_name}_"
f"{os.path.basename(graph_path_list[0]).split('_thrtype')[0]}.npy"
)
# out_path_est_omni = f"{namer_dir}/gradient-OMNI_{atlas}_" \
# f"{subgraph_name}_" \
# f"{os.path.basename(graph_path).split(
# '_thrtype')[0]}" \
# f"_MDS.joblib"
# out_path_est_mds = f"{namer_dir}/gradient-OMNI_{atlas}_" \
# f"{subgraph_name}_" \
# f"{os.path.basename(graph_path).split(
# '_thrtype')[0]}" \
# f"_MDS.joblib"
# dump(omni, out_path_est_omni)
# dump(omni, out_path_est_mds)
print("Saving...")
np.save(out_path, mds_fit)
del mds, mds_fit, omni, omni_fit
else:
# Add a null tmp file to prevent pool from breaking
out_path = f"{namer_dir}/gradient-OMNI" \
f"_{atlas}_{subgraph_name}_" \
f"{os.path.basename(graph_path_list[0])}_NULL"
if not os.path.exists(out_path):
os.mknod(out_path)
return out_path
def test_input():
X = np.random.normal(0, 1, size=(10, 3))
# X cannot be tensor when precomputed dissimilarity
with pytest.raises(ValueError):
tensor = np.random.normal(0, 1, size=(10, 3, 3))
mds = ClassicalMDS(n_components=3, dissimilarity="precomputed")
mds.fit(tensor)
with pytest.raises(ValueError):
one_dimensional = np.random.normal(size=10)
mds = ClassicalMDS(n_components=2, dissimilarity="euclidean")
mds.fit(one_dimensional)
# n_components > n_samples
with pytest.raises(ValueError):
mds = ClassicalMDS(n_components=100)
mds.fit(X)
# Invalid n_components
with pytest.raises(ValueError):
mds = ClassicalMDS(n_components=-2)
with pytest.raises(TypeError):
mds = ClassicalMDS(n_components="1")
# Invalid dissimilarity
with pytest.raises(ValueError):
mds = ClassicalMDS(dissimilarity="abc")
# Invalid input for fit function
with pytest.raises(ValueError):
mds = ClassicalMDS(n_components=3, dissimilarity="precomputed")
mds.fit(X="bad_input")
# Must be square and symmetric matrix if precomputed dissimilarity
with pytest.raises(ValueError):
mds = ClassicalMDS(n_components=3, dissimilarity="precomputed")
mds.fit(X)
def test_sklearn_conventions(self):
check_estimator(ClassicalMDS())