def test_gaussian_kernel():
np.random.seed(666)
n_train = 25
n_test = 20
# List of dummy representations
X = np.random.rand(n_train, 1000)
Xs = np.random.rand(n_test, 1000)
sigma = 100.0
Ktest = np.zeros((n_train, n_test))
for i in range(n_train):
for j in range(n_test):
Ktest[i, j] = np.exp(
np.sum(np.square(X[i] - Xs[j])) / (-2.0 * sigma**2))
K = gaussian_kernel(X, Xs, sigma)
# Compare two implementations:
assert np.allclose(K, Ktest), "Error in Gaussian kernel"
Ksymm = gaussian_kernel(X, X, sigma)
# Check for symmetry:
assert np.allclose(Ksymm, Ksymm.T), "Error in Gaussian kernel"
def do_qml_gaussian_kernel(self):
#K is also a np array, create kernel matrix
K = gaussian_kernel(self.x_training, self.x_training, self.sigma)
#add small lambda to the diagonal of the kernel matrix
K[np.diag_indices_from(K)] += self.lamda
#use the built in Cholesky-decomposition to solve
alpha = cho_solve(K, self.y_training)
#predict new, calculate kernel matrix between test and training
Ks = gaussian_kernel(self.x_test, self.x_training, self.sigma)
#make prediction
Y_predicted = np.dot(Ks, alpha)
# Calculate mean-absolute-error (MAE):
self.mae = np.mean(np.abs(Y_predicted - self.y_test))
self.test_predicted_results = Y_predicted
def test_kernels():
import sys
import numpy as np
import qml
from qml.kernels import laplacian_kernel
from qml.kernels import gaussian_kernel
n_train = 25
n_test = 20
# List of dummy representations
X = np.random.rand(n_train, 1000)
Xs = np.random.rand(n_test, 1000)
sigma = 100.0
Gtest = np.zeros((n_train, n_test))
Ltest = np.zeros((n_train, n_test))
for i in range(n_train):
for j in range(n_test):
Gtest[i,j] = np.exp( np.sum(np.square(X[i] - Xs[j])) / (-2.0 * sigma**2))
Ltest[i,j] = np.exp( np.sum(np.abs(X[i] - Xs[j])) / (-1.0 * sigma))
G = gaussian_kernel(X, Xs, sigma)
L = laplacian_kernel(X, Xs, sigma)
# Compare two implementations:
assert np.allclose(G, Gtest), "Error in Gaussian kernel"
assert np.allclose(L, Ltest), "Error in Laplacian kernel"
Gsymm = gaussian_kernel(X, X, sigma)
Lsymm = laplacian_kernel(X, X, sigma)
# Check for symmetry:
assert np.allclose(Gsymm, Gsymm.T), "Error in Gaussian kernel"
assert np.allclose(Lsymm, Lsymm.T), "Error in Laplacian kernel"
for mol in compounds:
mol.generate_coulomb_matrix(size=23, sorting="row-norm")
# mol.generate_bob(size=23, asize={"O":3, "C":7, "N":3, "H":16, "S":1})
# Make a big 2D array with all the representations
X = np.array([mol.representation for mol in compounds])
# X = np.array([mol.bob for mol in compounds])
# Print all representations
print("Representations:")
print(X)
# Assign 1000 first molecules to the training set
X_training = X[:1000]
Y_training = energy_pbe0[:1000]
sigma = 4000.0
K = gaussian_kernel(X_training, X_training, sigma)
print("Gaussian kernel:")
print(K)
# Add a small lambda to the diagonal of the kernel matrix
K[np.diag_indices_from(K)] += 1e-8
# Use the built-in Cholesky-decomposition to solve
alpha = cho_solve(K, Y_training)
print("Alphas:")
print(alpha)
print(energy_pbe0)
# Assign 1000 first molecules to the training set
X_training = X[:1000]
Y_training = energy_pbe0[:1000]
# Y_training = energy_delta[:1000]
# Assign 1000 first molecules to the training set
X_test = X[-1000:]
Y_test = energy_pbe0[-1000:]
# Y_test = energy_delta[-1000:]
# Calculate the Gaussian kernel
sigma = 700.0
K = gaussian_kernel(X_training, X_training, sigma)
print(K)
# Add a small lambda to the diagonal of the kernel matrix
K[np.diag_indices_from(K)] += 1e-8
# Use the built-in Cholesky-decomposition to solve
alpha = cho_solve(K, Y_training)
print(alpha)
# Assign 1000 last molecules to the test set
X_test = X[-1000:]
Y_test = energy_pbe0[-1000:]
# calculate a kernel matrix between test and training data, using the same sigma
Yprime = np.asarray([mol.properties for mol in mols])
Ytest = np.asarray([mol.properties for mol in mols_test])
"""np.save("data/krr/trainingFCHL", X)
np.save("data/krr/testFCHL", X_test)"""
print("\n -> calculating kernels")
random.seed(667)
"""
Calculating kernel functions and crossvalidation.
"""
print("\n -> calculating cross validation and predictions")
for j in tqdm(range(len(sigmas))):
K = gaussian_kernel(X, X, sigmas[j])
K_test = gaussian_kernel(X, X_test, sigmas[j])
for train in N:
test = total - train
maes = []
for i in range(nModels):
split = list(range(total))
random.shuffle(split)
training_index = split[:train]
test_index = split[-test:]
Y = Yprime[training_index]
Ys = Yprime[test_index]
def __init__(self, wds, ia1, ia2, coeff=1.0, llambda=1.e-4):
"""
ia1, ia2 -- atomic index, starting from 0,
"""
s1 = SLATM(wds, 'out', regexp='', properties='AE', M='slatm', \
local=True, igroup=False, ow=False, nproc=1, istart=0, \
slatm_params = { 'nbody':3, 'dgrids': [0.03,0.03], 'sigmas':[0.05,0.05],\
'rcut':4.8, 'rpower2':6, 'ws':[1.,1.,1.], \
'rpower3': 3, 'isf':0, 'kernel':'g', 'intc':3 }, \
iY=False)
fs = s1.fs
coords = s1.coords
iast2 = s1.nas.cumsum()
iast1 = np.array([
0,
] + list(kas2[:-1]))
objs = []
ds = []
for i, f in enumerate(fs):
obj = wfn(f)
obj.get_dm()
objs.append(obj)
if i < self.nm - 1:
ds.append(ssd.cdist(coords[i], coords[self.nm - 1]))
## specify target atom pairs!!
#ia1, ia2 = 0, 1
#coeff = 1.0; llambda = 1e-6
cia1 = coords[-1][ia1]
cia2 = coords[-1][ia2]
xs = []
ys = []
nhass = []
for i, f in enumerate(fs):
dsi = ds[i]
jas = np.arange(dsi.shape[0])
filt1 = (dsi[:, ia1] <= 0.01)
filt2 = (dsi[:, ia2] <= 0.01)
if np.any(filt1) and np.any(filt2):
nhass.append(s1.nhass[i])
obj = objs[i]
ja1 = jas[filt1]
ja2 = jas[filt2]
p, q, r, s = obj.ibs1[ja1], obj.ibs2[ja1], obj.ibs1[
ja2], obj.ibs2[ja2]
dmij = obj.dm[p:q, r:s].ravel()
ys.append(dmij)
iat1 = iast1[i] + ja1
iat2 = iast1[i] + ja2
x1 = s1.X[iat1]
x2 = s1.X[iat2]
xs.append(np.concatenate((x1, x2), axis=0))
nprop = len(dmij)
nt = len(nhass)
nhass = np.array(nhass)
tidxs = np.arange(nt)
nhass_u = np.unique(nhass)
nu = len(nhass_u)
xs = np.array(xs)
ys = np.array(ys)
xs2 = np.array([xs[-1]])
ys2 = np.array([ys[-1]])
for j in range(nu):
jdxs = tidxs[nhass <= nhass_u[j]]
xs1 = xs[jdxs, :]
ys1 = ys[jdxs, :]
ds1 = qd.l2_distance(X1, X1) # ssd.pdist(x1, metric='euclidean')
dmax = max(ds1.ravel())
sigma = coeff * dmax / np.sqrt(2.0 * np.log(2.0))
K1 = qk.gaussian_kernel(xs1, xs1, sigma)
assert np.allclose(K1,
K1.T), "Error in local Gaussian kernel symmetry"
K1[np.diag_indices_from(K1)] += llambda
alpha = np.array([cho_solve(K1, ys1)]).T
K2 = qk.gaussian_kernel(xs2, xs1, sigma)
ys2_est = np.dot(K2, alpha)
error = np.squeeze(ys2_est) - ys2
mae = np.sum(np.abs(error)) / nprop
rmse = np.sqrt(np.sum(error**2) / nprop)
print('%4d %12.8f %12.8f' % (len(xs1), mae, rmse))
def compute_kernel_qml(X_i, X_j, sigma=1e3):
return gaussian_kernel(X_i, X_j, sigma)
from tutorial_data import compounds
from qml.kernels import gaussian_kernel
# For every compound generate a coulomb matrix or BoB
for mol in compounds:
mol.generate_coulomb_matrix(size=23, sorting="row-norm")
# mol.generate_bob(size=23, asize={"O":3, "C":7, "N":3, "H":16, "S":1})
# Make a big 2D array with all the representations
X = np.array([mol.representation for mol in compounds])
# X = np.array([mol.bob for mol in compounds])
# Print all representations
print("Representations:")
print(X)
# Run on only a subset of the first 100 (for speed)
X = X[:100]
# Define the kernel width
sigma = 1000.0
# K is also a Numpy array
K = gaussian_kernel(X, X, sigma)
# Print the kernel
print("Gaussian kernel:")
print(K)
Y = np.array([mol.properties for mol in training])
Ys = np.array([mol.properties for mol in test])
# List of representations
mbtypes = get_slatm_mbtypes(np.array([mol.nuclear_charges
for mol in mols]))
for i, mol in enumerate(training):
mol.generate_slatm(mbtypes, local=False, rpower=6)
for i, mol in enumerate(test):
mol.generate_slatm(mbtypes, local=False, rpower=6)
X = np.array([mol.representation for mol in training])
Xs = np.array([mol.representation for mol in test])
# Generate training Kernel
K = gaussian_kernel(X, X, sigma)
Ks = gaussian_kernel(X, Xs, sigma)
K[np.diag_indices_from(K)] += llambda
alpha = cho_solve(K, Y)
# Calculate prediction kernel
Yss = np.dot(Ks.transpose(), alpha)
mae = np.mean(np.abs(Ys - Yss))
print mae
exit()
# sigma = 0.1
# llambda = 1e-9