def test_molecular_kernel():
molecules = [molecule('H2'), molecule('O2'), molecule('CH4')]
graphs = [Graph.from_ase(m) for m in molecules]
kernel = Tang2019MolecularKernel(starting_probability='uniform')
R = kernel(graphs)
D = np.diag(np.diag(R)**-0.5)
K = D.dot(R).dot(D)
assert (R.shape == (3, 3))
for i in range(len(molecules)):
assert (K[i, i] == pytest.approx(1, 1e-6))
R_nodal = kernel(graphs, nodal=True)
D_nodal = np.diag(np.diag(R_nodal)**-0.5)
K_nodal = D_nodal.dot(R_nodal).dot(D_nodal)
natoms = np.sum([len(m) for m in molecules])
assert (R_nodal.shape == (natoms, natoms))
for i in range(natoms):
assert (K_nodal[i, i] == pytest.approx(1, 1e-6))
kernel_nocarbon = Tang2019MolecularKernel(
starting_probability=lambda n: 0.0 if n[1]['element'] == 6 else 1.0)
R_nocarbon_nodal = kernel_nocarbon(graphs, nodal=True)
k = 0
for i, m in enumerate(molecules):
for j, a in enumerate(m):
if a.symbol == 'C':
assert (R_nocarbon_nodal[k, :].sum() == 0)
assert (R_nocarbon_nodal[:, k].sum() == 0)
k += 1
def test_mlgk_on_permuted_graph():
g = Graph.from_ase(molecule('C6H6'))
for _ in range(10):
h = g.permute(np.random.permutation(len(g.nodes)))
kernel = MarginalizedGraphKernel(
TensorProduct(element=KroneckerDelta(0.5)),
TensorProduct(length=SquareExponential(0.1)))
assert (kernel([g], [h]).item() == pytest.approx(kernel([g]).item()))
def test_molecular_kernel_custom_pstart():
molecules = [molecule('H2'), molecule('O2'), molecule('CH4')]
graphs = [Graph.from_ase(m) for m in molecules]
kernel_nocarbon = Tang2019MolecularKernel(
starting_probability=(lambda ns: np.where(ns.element == 6, 0.0, 1.0),
'n.element == 6 ? 0.f : 1.f'))
R_nocarbon_nodal = kernel_nocarbon(graphs, nodal=True)
k = 0
for i, m in enumerate(molecules):
for j, a in enumerate(m):
if a.symbol == 'C':
assert (R_nocarbon_nodal[k, :].sum() == 0)
assert (R_nocarbon_nodal[:, k].sum() == 0)
k += 1
def test_molecular_kernel():
molecules = [molecule('H2'), molecule('O2'), molecule('CH4')]
graphs = [Graph.from_ase(m) for m in molecules]
kernel = Tang2019MolecularKernel()
R = kernel(graphs)
D = np.diag(np.diag(R)**-0.5)
K = D.dot(R).dot(D)
assert (R.shape == (3, 3))
for i in range(len(molecules)):
assert (K[i, i] == pytest.approx(1, 1e-6))
R_nodal = kernel(graphs, nodal=True)
D_nodal = np.diag(np.diag(R_nodal)**-0.5)
K_nodal = D_nodal.dot(R_nodal).dot(D_nodal)
natoms = np.sum([len(m) for m in molecules])
assert (R_nodal.shape == (natoms, natoms))
for i in range(natoms):
assert (K_nodal[i, i] == pytest.approx(1, 1e-6))
import numpy as np
import pandas as pd
from ase.build import molecule, bulk
from graphdot import Graph
from graphdot.kernel.molecular import Tang2019MolecularKernel
# build sample molecules
small_title = ['H2O', 'HCl', 'NaCl']
bulk_title = ['NaCl-bulk', 'NaCl-bulk2']
bulk = [
bulk('NaCl', 'rocksalt', a=5.64),
bulk('NaCl', 'rocksalt', a=5.66),
]
molecules = [molecule(name) for name in small_title] + bulk
# convert to molecular graphs
graphs = [Graph.from_ase(m) for m in molecules]
# use pre-defined molecular kernel
kernel = Tang2019MolecularKernel(edge_length_scale=0.1)
R = kernel(graphs)
# normalize the similarity matrix
d = np.diag(R)**-0.5
K = np.diag(d).dot(R).dot(np.diag(d))
# note the difference between the NaCl variants
title = small_title + bulk_title
print(pd.DataFrame(K, columns=title, index=title))
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import numpy as np
import pytest
from ase.build import molecule
from graphdot import Graph
from graphdot.metric.maximin import MaxiMin
from graphdot.microkernel import (
KroneckerDelta,
SquareExponential,
TensorProduct,
)
from graphdot.kernel.marginalized.starting_probability import Uniform
G = [Graph.from_ase(molecule(f)) for f in ['CH3SCH3', 'CH3OCH3']]
H = [Graph.from_ase(molecule(f)) for f in ['CH4', 'NH3', 'H2O']]
def test_maximin_basic():
metric = MaxiMin(node_kernel=TensorProduct(element=KroneckerDelta(0.5)),
edge_kernel=TensorProduct(length=SquareExponential(0.1)),
q=0.01)
distance = metric(G)
assert distance.shape == (len(G), len(G))
assert np.allclose(distance.diagonal(), 0, atol=1e-3)
assert np.all(distance >= 0)
assert np.allclose(distance, distance.T, rtol=1e-14, atol=1e-14)
distance = metric(G, G)
assert distance.shape == (len(G), len(G))
assert np.allclose(distance.diagonal(), 0, atol=1e-3)