# of the scope of this library.
if __name__ == '__main__':
elements = ['Fe', 'H', 'H', 'H', 'H', 'H', 'H']
coords = np.array([
[0., 0., 0.],
[1.46, 0., 0.],
[0., 1.46, 0.],
[0., 0., 1.46],
[-1.46, 0., 0.],
[0., -1.46, 0.],
[0., 0., -1.46],
])
feat = Connectivity(depth=2)
# Notice the warning about missing elements.
print(feat.fit_transform([(elements, coords)]))
# 1) Modify the values in the constants module before your script.
BOND_LENGTHS['Fe'] = {'1': 1.32}
print(feat.fit_transform([(elements, coords)]))
del BOND_LENGTHS['Fe']
# 2) Include connectivity information in your data. The other instances
# where constants are used (electronegativity, element symbols, atomic
# numbers).
connections = {
0: {1: '1', 2: '1', 3: '1', 4: '1', 5: '1', 6: '1'},
1: {0: '1'},
2: {0: '1'},
3: {0: '1'},
4: {0: '1'},
feat = Connectivity(n_jobs=-1)
alpha = 0.1
gamma = 1
for fold in range(4):
train_folds = [x for x in range(4) if x != fold]
train_idxs = np.ravel(train_validation[train_folds])
test_idxs = np.ravel(train_validation[fold])
Xin_train = list(zip(train_anum[train_idxs], train_coor[train_idxs]))
Xin_test = list(zip(train_anum[test_idxs], train_coor[test_idxs]))
y_train = train_energy[train_idxs]
y_test = train_energy[test_idxs]
#for feat in feats:
X_train = feat.fit_transform(Xin_train)
X_test = feat.transform(Xin_test)
clf = KernelRidge(alpha=alpha, gamma=gamma, kernel="rbf")
clf.fit(X_train, y_train)
train_error_temp[fold] = MAE(clf.predict(X_train), y_train)
test_error_temp[fold] = MAE(clf.predict(X_test), y_test)
with open('ANI1_KRR.txt', 'a') as f:
print('\n', feat)
print("alpha: %.4f gamma: %6f" % (alpha, gamma))
print(
"Avg Train MAE: %.6f Avg Test MAE: %.6f" %
(statistics.mean(train_error_temp), statistics.mean(test_error_temp)))
print()
#caluate standard deviation
#feat2s = [(Connectivity(n_jobs = -1, depth = 2)),
#EncodedBond(n_jobs = -1, max_depth = 1)]
feat1 = Connectivity(n_jobs=1)
featLC = EncodedBond(n_jobs=-1, smoothing='expit', max_depth=1)
featNP = EncodedBond(n_jobs=-1, smoothing='norm', max_depth=2)
#feat1b = (Connectivity(n_jobs = 1, use_coordination = True))
#loop to test each fold
for x in range(5):
# Fit and transform test and train set
Xin_train, Xin_test, y_train, y_test = load_qm7(x)
#for feat in featNP:
#X_train = feat1.fit_transform(Xin_train)
#X_test = feat1.transform(Xin_test)
#for feat2 in feats2:
X_train1 = feat1.fit_transform(Xin_train)
X_test1 = feat1.transform(Xin_test)
#X_train2b = feat2b.fit_transform(Xin_train)
#X_test2b = feat2b.transform(Xin_test)
#for feat in featsNP:
X_trainLC = featLC.fit_transform(Xin_train)
X_testLC = featLC.transform(Xin_test)
X_train = np.concatenate((X_train1, X_trainLC), axis=1)
X_test = np.concatenate((X_test1, X_testLC), axis=1)
# Use Ridge linear regression
clf = Ridge(alpha=0.01)
clf.fit(X_trainLC, y_train)
# Calculate train and test MAE
train_error_temp[x] = MAE(clf.predict(X_trainLC), y_train)
test_error_temp[x] = MAE(clf.predict(X_testLC), y_test)
# of the scope of this library.
if __name__ == '__main__':
elements = ['Fe', 'H', 'H', 'H', 'H', 'H', 'H']
coords = np.array([
[0., 0., 0.],
[1.46, 0., 0.],
[0., 1.46, 0.],
[0., 0., 1.46],
[-1.46, 0., 0.],
[0., -1.46, 0.],
[0., 0., -1.46],
])
feat = Connectivity(depth=2)
# Notice the warning about missing elements.
print(feat.fit_transform([(elements, coords)]))
# 1) Modify the values in the constants module before your script.
BOND_LENGTHS['Fe'] = {'1': 1.32}
print(feat.fit_transform([(elements, coords)]))
del BOND_LENGTHS['Fe']
# 2) Include connectivity information in your data. The other instances
# where constants are used (electronegativity, element symbols, atomic
# numbers).
connections = {
0: {
1: '1',
2: '1',
3: '1',
4: '1',