def run_test(feat1, output_file, alpha, feat2=None, Gmax=0):
feats = {
"1": Connectivity(n_jobs=-1),
"1c": Connectivity(n_jobs=-1, use_coordination=True, depth=1),
"2": Connectivity(n_jobs=-1, depth=2),
"2b": Connectivity(n_jobs=-1, depth=2, use_bond_order=True),
"2NP": EncodedBond(n_jobs=-1, smoothing='norm', max_depth=Gmax),
"2NC": EncodedBond(n_jobs=-1, smoothing='norm_cdf', max_depth=Gmax),
"2LP": EncodedBond(n_jobs=-1, smoothing='expit_pdf', max_depth=Gmax),
"2LC": EncodedBond(n_jobs=-1, smoothing='expit', max_depth=Gmax),
"2SP": EncodedBond(n_jobs=-1, smoothing='spike', max_depth=Gmax),
"2SC": EncodedBond(n_jobs=-1, smoothing='zero_one', max_depth=Gmax)
}
Xin_train_final = list(zip(train_anum, train_coor))
Xin_test_final = list(zip(test_anum, test_coor))
y_train_final = train_energy
y_test_final = test_energy
X_train1 = feats[feat1].fit_transform(Xin_train_final)
X_test1 = feats[feat1].transform(Xin_test_final)
if feat2 != None:
X_train2 = feats[feat2].fit_transform(Xin_train_final)
X_test2 = feats[feat2].transform(Xin_test_final)
X_train_final = np.concatenate((X_train1, X_train2), axis=1)
X_test_final = np.concatenate((X_test1, X_test2), axis=1)
else:
X_train_final = X_train1
X_test_final = X_test1
clf = Ridge(alpha=alpha)
clf.fit(X_train_final, y_train_final)
train_error = MAE(clf.predict(X_train_final), y_train_final) * 627.509
test_error = MAE(clf.predict(X_test_final), y_test_final) * 627.509
with open(output_file, 'a') as f:
print("Test set", file=f)
print(feat1, file=f)
if (feat2 != None):
print(feat2, file=f)
print("Gmax: %d" % Gmax)
print("Train MAE: %.6f Test MAE: %.6f" % (train_error, test_error),
file=f)
def run_trial(feat1, output_file, feat2=None, Gmax=0):
#%%
feats = {
"1": Connectivity(n_jobs=-1),
"1c": Connectivity(n_jobs=-1, use_coordination=True, depth=1),
"2": Connectivity(n_jobs=-1, depth=2),
"2b": Connectivity(n_jobs=-1, depth=2, use_bond_order=True),
"2NP": EncodedBond(n_jobs=-1, smoothing='norm', max_depth=Gmax),
"2NC": EncodedBond(n_jobs=-1, smoothing='norm_cdf', max_depth=Gmax),
"2LP": EncodedBond(n_jobs=-1, smoothing='expit_pdf', max_depth=Gmax),
"2LC": EncodedBond(n_jobs=-1, smoothing='expit', max_depth=Gmax),
"2SP": EncodedBond(n_jobs=-1, smoothing='spike', max_depth=Gmax),
"2SC": EncodedBond(n_jobs=-1, smoothing='zero_one', max_depth=Gmax)
}
#cross validation list
train_validation = ()
train_validation = np.arange(0, train_set_size,
dtype=int).reshape(4, int(train_set_size / 4))
np.random.shuffle(train_validation)
for i in range(4):
np.random.shuffle(train_validation[i])
train_error_temp = [None] * 4
test_error_temp = [None] * 4
alpha_range = [1, 0, 0.1, 0.01, 0.001, 0.0001]
# Perform k-fold validation. Can be made into a function
for i, alpha in enumerate(alpha_range):
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]
X_train1 = feats[feat1].fit_transform(Xin_train)
X_test1 = feats[feat1].transform(Xin_test)
if feat2 != None:
X_train2 = feats[feat2].fit_transform(Xin_train)
X_test2 = feats[feat2].transform(Xin_test)
# concatenate feature vectors for combined features
X_train = np.concatenate((X_train1, X_train2), axis=1)
X_test = np.concatenate((X_test1, X_test2), axis=1)
else:
X_train = X_train1
X_test = X_test1
# LRR
clf = Ridge(alpha=alpha)
clf.fit(X_train, y_train)
train_error_temp[fold] = MAE(clf.predict(X_train),
y_train) * 627.509
test_error_temp[fold] = MAE(clf.predict(X_test), y_test) * 627.509
# Output the result to file
with open(output_file, 'a') as f:
print(feat1, file=f)
if feat2 != None:
print(feat2, file=f)
print("Gmax = %d" % Gmax, file=f)
print("alpha: %.4f" % alpha, file=f)
print("Avg Train MAE: %.6f Avg Test MAE: %.6f" %
(statistics.mean(train_error_temp),
statistics.mean(test_error_temp)),
file=f)
print()
#caluate standard deviation
print(
"Train Standard Deviation: %.4f, Test Standard Deviation: %.4f"
% (statistics.pstdev(train_error_temp),
statistics.pstdev(test_error_temp)),
file=f)
# complex (iron is not in the constants).
# Maybe at some point, molml will include more constants, but it seems outside
# 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'},
if __name__ == "__main__":
# This is just boiler plate code to load the data
Xin_train, Xin_test, y_train, y_test = load_qm7()
# Change this to make the tranformations parallel
# Values less than 1 will set to the number of cores the CPU has
N_JOBS = 1
# Just a few examples of different features
tfs = [
EncodedBond(n_jobs=N_JOBS),
EncodedBond(spacing="inverse", n_jobs=N_JOBS),
BagOfBonds(n_jobs=N_JOBS),
CoulombMatrix(n_jobs=N_JOBS),
Connectivity(depth=1, n_jobs=N_JOBS),
Connectivity(depth=2, use_bond_order=True, n_jobs=N_JOBS),
Connectivity(depth=3, use_coordination=True, n_jobs=N_JOBS),
]
for tf in tfs:
print(tf)
X_train = tf.fit_transform(Xin_train)
X_test = tf.transform(Xin_test)
# We will not do a hyperparmeter search for simplicity
clf = Ridge()
clf.fit(X_train, y_train)
train_error = MAE(clf.predict(X_train), y_train)
test_error = MAE(clf.predict(X_test), y_test)
print("Train MAE: %.4f Test MAE: %.4f" % (train_error, test_error))
from sklearn.metrics import mean_absolute_error as MAE
from molml.features import Connectivity, EncodedBond
import statistics
import numpy as np
from utils import load_qm7
if __name__ == "__main__":
train_error = 0
test_error = 0
train_error_temp = [None] * 5
test_error_temp = [None] * 5
#feat = CoulombMatrix(n_jobs = -1)
#feats2 = [Connectivity(n_jobs = -1, depth = 2, use_bond_order = True),
#EncodedBond(n_jobs = -1, smoothing = 'expit_pdf',max_depth = 1)]
#feat2 = Connectivity(n_jobs = -1, depth = 2)
feat2b = Connectivity(n_jobs=-1, depth=2, use_bond_order=True)
#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:
from sklearn.linear_model import Ridge
from sklearn.kernel_ridge import KernelRidge
from sklearn.metrics import mean_absolute_error as MAE
from sklearn.pipeline import FeatureUnion
from molml.features import EncodedBond, Connectivity
from utils import load_qm7
if __name__ == "__main__":
# This is just boiler plate code to load the data
Xin_train, Xin_test, y_train, y_test = load_qm7()
feats = [
("encoded_bond", EncodedBond(n_jobs=-1, max_depth=3)),
("atom_count", Connectivity(depth=1, n_jobs=-1)),
("angle_count", Connectivity(depth=3, use_coordination=True,
n_jobs=-1)),
]
full_feat = FeatureUnion(feats)
X_train = full_feat.fit_transform(Xin_train)
X_test = full_feat.transform(Xin_test)
clfs = [
Ridge(alpha=0.01),
KernelRidge(alpha=1e-9, gamma=1e-5, kernel="rbf"),
]
for clf in clfs:
print(clf)
clf.fit(X_train, y_train)
from molml.features import Connectivity#, EncodedBond, CoulombMatrix
import statistics
from utils import load_qm7
if __name__ == "__main__":
train_error = 0
test_error= 0
train_error_temp = [None] * 5
test_error_temp = [None] * 5
gamma = 1e-3
alpha = 1e-7
#kern = AtomKernel(gamma=gamma,transformer = Connectivity(n_jobs = -1), n_jobs=-1)
#feat = CoulombMatrix(n_jobs = 1)
#feats = [Connectivity(n_jobs = -1, depth = 3),
#EncodedBond(n_jobs = -1)]
feat = (Connectivity(n_jobs = 1))
#feat = (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 feats:
#K_train = kern.fit_transform(Xin_train)
#K_test = kern.transform(Xin_test)
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_validation = np.arange(0, train_set_size,
dtype=int).reshape(4, int(train_set_size / 4))
np.random.shuffle(train_validation)
for i in range(4):
np.random.shuffle(train_validation[i])
#train_validation = train_validation.tolist()
train_error = 0
test_error = 0
train_error_temp = [None] * 4
test_error_temp = [None] * 4
#feats = [Connectivity(n_jobs = -1, depth = 2, use_bond_order = True),
#EncodedBond(n_jobs = -1, smoothing = 'expit_pdf',max_depth = 1)]
#feat = Connectivity(n_jobs = -1, depth = 2, use_bond_order = True)
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)
# complex (iron is not in the constants).
# Maybe at some point, molml will include more constants, but it seems outside
# 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',