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 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 decoder(args, model):
latent_dim = args.latent_dim
data, charset = read_latent_data(args.data)
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.decoder.predict(data[0].reshape(1, latent_dim)).argmax(axis=2)[0]
sampled = decode_smiles_from_indexes(sampled, charset)
print(sampled)
def decoder(args, model):
latent_dim = args.latent_dim
data, charset = read_latent_data(args.data)
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.decoder.predict(data[0].reshape(
1, latent_dim)).argmax(axis=2)[0]
sampled = decode_smiles_from_indexes(sampled, charset)
print(sampled)
def interpolate(source, dest, steps, charset, model, latent_dim, width):
source_just = source.ljust(width)
dest_just = dest.ljust(width)
one_hot_encoded_fn = lambda row: map(lambda x: one_hot_array(x, len(charset)),
one_hot_index(row, charset))
source_encoded = numpy.array(map(one_hot_encoded_fn, source_just))
source_x_latent = model.encoder.predict(source_encoded.reshape(1, width, len(charset)))
dest_encoded = numpy.array(map(one_hot_encoded_fn, dest_just))
dest_x_latent = model.encoder.predict(dest_encoded.reshape(1, width, len(charset)))
step = (dest_x_latent - source_x_latent)/float(steps)
results = []
for i in range(steps):
item = source_x_latent + (step * i)
sampled = model.decoder.predict(item.reshape(1, latent_dim)).argmax(axis=2)[0]
sampled = decode_smiles_from_indexes(sampled, charset)
results.append( (i, item, sampled) )
return results
def interpolate(source, dest, steps, charset, model, latent_dim, width):
source_just = source.ljust(width)
dest_just = dest.ljust(width)
one_hot_encoded_fn = lambda row: list(map(lambda x: one_hot_array(x, len(charset)),
one_hot_index(row, charset)))
source_encoded = numpy.array(list(map(one_hot_encoded_fn, source_just)))
source_x_latent = model.encoder.predict(source_encoded.reshape(1, width, len(charset)))
dest_encoded = numpy.array(list(map(one_hot_encoded_fn, dest_just)))
dest_x_latent = model.encoder.predict(dest_encoded.reshape(1, width, len(charset)))
step = (dest_x_latent - source_x_latent)/float(steps)
results = []
for i in range(steps):
item = source_x_latent + (step * i)
sampled = model.decoder.predict(item.reshape(1, latent_dim)).argmax(axis=2)[0]
sampled = decode_smiles_from_indexes(sampled, charset)
results.append( (i, item, sampled) )
return results
