def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def main():
np.random.seed(RANDOM_SEED)
data_train, data_test, charset = load_dataset('data/processed.h5')
print("Charset", charset)
model = MoleculeVAE()
model.create(charset, latent_rep_size=292)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
checkpointer = ModelCheckpoint(filepath='model.h5',
verbose=1,
save_best_only=True)
history = model.autoencoder.fit(data_train[:1000],
data_train[:1000],
shuffle=True,
nb_epoch=NUM_EPOCHS,
batch_size=100,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test[:1000],
data_test[:1000]))
with open('trainHistoryDict', 'wb') as file_pi:
pickle.dump(history.history, file_pi)
def main():
args = get_arguments()
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def decoder(model):
latent_dim = 292
data_train, data_test, charset = load_dataset('data/processed.h5')
#Here we directly raise exceptions for non-existent model
if os.path.isfile('model.h5'):
model.load(charset, 'model.h5', latent_rep_size=latent_dim)
print("model loaded")
else:
raise ValueError("Model file doesn't exist")
samples_all = []
with open('encoded_vec.csv', 'r') as csvfile: #good dataset/data2.csv
reader = csv.reader(csvfile)
rows = [row for row in reader]
data = np.array(rows, dtype=float)
for ix in range(len(data)):
sampled = model.decoder.predict(data[ix].reshape(
-1, 292)).argmax(axis=2)[0]
#sampled=data_test[ix].argmax(axis=1)
print(sampled)
#print(np.shape(sampled))
sampled = decode_smiles_from_indexes(sampled, charset)
print(np.shape(sampled))
samples_all.append(sampled)
print(sampled)
with open('decoded_vec.csv', 'w') as f:
writer = csv.writer(f)
writer.writerows(np.array(samples_all))
def encoder(model):
#latent_dim = args.latent_dim
latent_dim = 292
data_train, data_test, charset = load_dataset('data/processed.h5')
print(np.shape(data_train))
if os.path.isfile('model.h5'):
model.load(charset, 'model.h5', latent_rep_size=latent_dim)
else:
raise ValueError("Model file doesn't exist")
print(model.encoder.predict(data_train[0:2]))
m = model.encoder.predict(data_train[0:100])
print(np.shape(m))
with open('encoded_vec.csv', 'w') as f:
writer = csv.writer(f)
writer.writerows(m)
'''true_pred_gen = (((mat, weight, model.encoder.predict(mat))
for (mat, _, weight) in train_gen))
h5f = h5py.File('encoded.h5', 'w')
h5f.create_dataset('charset', data = charset)
h5f.create_dataset('latent_vectors', (NUM_SAMPLED, 120, latent_dim))
for ix in range(NUM_SAMPLED):
_, _, x_latent = true_pred_gen.next()
print(x_latent[0])
h5f['latent_vectors'][ix] = x_latent[0]
h5f.close()'''
'''else:
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
model.create(charset, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit(
data_train,
data_train,
shuffle = True,
nb_epoch = args.epochs,
batch_size = args.batch_size,
callbacks = [checkpointer, reduce_lr],
validation_data = (data_test, data_test)
)
def visualize_model(args):
model = MoleculeVAE()
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
plot(model.autoencoder, to_file = args.outfile)
def visualize_model(args):
model = MoleculeVAE()
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
plot(model.autoencoder, to_file = args.outfile)
def autoencoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
sampled = model.autoencoder.predict(data[0].reshape(1, 120, len(charset))).argmax(axis=2)[0]
mol = decode_smiles_from_indexes(map(from_one_hot_array, data[0]), charset)
sampled = decode_smiles_from_indexes(sampled, charset)
print(mol)
print(sampled)
def autoencoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split=False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
sampled = model.autoencoder.predict(data[0].reshape(
1, 120, len(charset))).argmax(axis=2)[0]
mol = decode_smiles_from_indexes(map(from_one_hot_array, data[0]), charset)
sampled = decode_smiles_from_indexes(sampled, charset)
print(mol)
print(sampled)
def encoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split=False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if args.save_h5:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data=charset)
h5f.create_dataset('latent_vectors', data=x_latent)
h5f.close()
else:
np.savetxt(sys.stdout, x_latent, delimiter='\t')
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE, SimpleMoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
if args.num_cores != -1:
config = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1, \
allow_soft_placement=True, device_count = {'CPU': args.num_cores})
session = tf.Session(config=config)
K.set_session(session)
data_train, data_test, charset = load_dataset(args.data)
if args.simple:
model = SimpleMoleculeVAE()
else:
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
# plot_model(model, to_file='model.png')
history = model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
with open('history.p', 'wb') as f:
cPickle.dump(history.history, f)
def encoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if args.save_h5:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data = charset)
h5f.create_dataset('latent_vectors', data = x_latent)
h5f.close()
else:
np.savetxt(sys.stdout, x_latent, delimiter = '\t')
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if not args.visualize:
if not args.save_h5:
np.savetxt(sys.stdout, x_latent, delimiter = '\t')
else:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data = charset)
h5f.create_dataset('latent_vectors', data = x_latent)
h5f.close()
else:
visualize_latent_rep(args, model, x_latent)
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if not args.visualize:
if not args.save_h5:
np.savetxt(sys.stdout, x_latent, delimiter='\t')
else:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data=charset)
h5f.create_dataset('latent_vectors', data=x_latent)
h5f.close()
else:
visualize_latent_rep(args, model, x_latent)
os.environ['KERAS_BACKEND'] = 'tensorflow'
import h5py
import numpy as np
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
NUM_EPOCHS = 100
BATCH_SIZE = 10
LATENT_DIM = 128
RANDOM_SEED = 123
np.random.seed(RANDOM_SEED) #args.random_seed)
data_train, data_test, charset = load_dataset('./data/processed.h5')
model = MoleculeVAE()
#model.load(charset, args.model, latent_rep_size = args.latent_dim)
model.create(charset, latent_rep_size=LATENT_DIM)
checkpointer = ModelCheckpoint(
filepath='./test_models/weights.{epoch:02d}-{val_loss:.2f}.hdf5',
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
data_train = data_train[:1]
