def test_sine_coulomb_matrix(self):
# flat
scm = SineCoulombMatrix(flatten=True)
df = pd.DataFrame({"s": [self.sc, self.ni3al]})
with self.assertRaises(NotFittedError):
df = scm.featurize_dataframe(df, "s")
df = scm.fit_featurize_dataframe(df, "s")
labels = scm.feature_labels()
self.assertEqual(labels[0], "sine coulomb matrix eig 0")
self.assertArrayAlmostEqual(df[labels].iloc[0],
[235.740418, 0.0, 0.0, 0.0],
decimal=5)
self.assertArrayAlmostEqual(
df[labels].iloc[1],
[232.578562, 1656.288171, 1403.106576, 1403.106576],
decimal=5)
# matrix
scm = SineCoulombMatrix(flatten=False)
sin_mat = scm.featurize(self.diamond)
mtarget = [[36.8581, 6.147068], [6.147068, 36.8581]]
self.assertAlmostEqual(np.linalg.norm(sin_mat - np.array(mtarget)),
0.0,
places=4)
scm = SineCoulombMatrix(diag_elems=False, flatten=False)
sin_mat = scm.featurize(self.diamond)[0]
self.assertEqual(sin_mat[0][0], 0)
self.assertEqual(sin_mat[1][1], 0)
def test_sine_coulomb_matrix(self):
# flat
scm = SineCoulombMatrix(flatten=True)
df = pd.DataFrame({"s": [self.sc, self.ni3al]})
with self.assertRaises(NotFittedError):
df = scm.featurize_dataframe(df, "s")
df = scm.fit_featurize_dataframe(df, "s")
labels = scm.feature_labels()
self.assertEqual(labels[0], "sine coulomb matrix eig 0")
self.assertArrayAlmostEqual(
df[labels].iloc[0],
[235.740418, 0.0, 0.0, 0.0],
decimal=5)
self.assertArrayAlmostEqual(
df[labels].iloc[1],
[232.578562, 1656.288171, 1403.106576, 1403.106576],
decimal=5)
# matrix
scm = SineCoulombMatrix(flatten=False)
sin_mat = scm.featurize(self.diamond)
mtarget = [[36.8581, 6.147068], [6.147068, 36.8581]]
self.assertAlmostEqual(
np.linalg.norm(sin_mat - np.array(mtarget)), 0.0, places=4)
scm = SineCoulombMatrix(diag_elems=False, flatten=False)
sin_mat = scm.featurize(self.diamond)[0]
self.assertEqual(sin_mat[0][0], 0)
self.assertEqual(sin_mat[1][1], 0)
return sklearn.metrics.r2_score(y_true, y_pred)
def length(self, vec):
return vec[vec != 0].shape[0]
# SCM evaluation
DIAG = True
print("DIAG ELEMS", DIAG)
# Featurize dataframe with sine coulomb matrix and time it
start = time.monotonic()
scm = SineCoulombMatrix(diag_elems=DIAG, flatten=True)
# Set the number of jobs for parallelization
scm.set_n_jobs(NJOBS)
df = scm.fit_featurize_dataframe(df, 'structure')
# Take the eigenvalues of the SCMs to form vector descriptors
# df['sine coulomb matrix'] = pd.Series([np.sort(np.linalg.eigvals(s))[::-1]
# for s in df['sine coulomb matrix']],
# df.index)
finish = time.monotonic()
print("TIME TO FEATURIZE SCM %f SECONDS" % (finish - start))
print()
# Set up KRR model
krr = KrrScm()
print(krr.get_params().keys())
# Initialize hyperparameter grid search
hpsel = GridSearchCV(krr,
params['sine coulomb matrix'],