def train_vae(self, case_config):
model_config = self.get_model_config(case_config)
create_dir(model_config["model_dir"])
avg_valid_loss = 0.0
for k in range(0, 10):
train_dataset = Dataset.concatenate(*(self.datasets[:k] +
self.datasets[(k + 1):]))
valid_dataset = self.datasets[k]
# Start training!
vae = VAE(model_config)
if self.debug:
epochs = 2
else:
epochs = 100
vae.train(train_dataset,
epochs=epochs,
batch_size=50,
validation_dataset=valid_dataset)
fold_valid_loss = vae.evaluate(valid_dataset)
self.logger.info("{}|Fold #{} Loss = {:f}".format(
model_config["name"], k + 1, fold_valid_loss))
avg_valid_loss += fold_valid_loss
if self.debug:
break
avg_valid_loss /= 10
self.logger.info("{}|Avg Validation Loss = {:f}".format(
model_config["name"], avg_valid_loss))
self.case_counter += 1
return {
"status": STATUS_OK,
"loss": avg_valid_loss,
"name": model_config["name"],
"model_config": model_config
}
def train_final_vae(self, model_config):
model_config["name"] = model_config["name"] + "_FULL"
model_dir = self.get_model_dir(model_config["name"])
create_dir(model_dir)
model_config["model_dir"] = model_dir
n_epochs = 2 if self.debug else 100
full_dataset = Dataset.concatenate(*self.datasets)
self.logger.info("Training Final VAE: " + model_config["name"])
final_vae = VAE(model_config)
final_vae.train(full_dataset,
epochs=n_epochs,
batch_size=50,
validation_dataset=full_dataset)
loss = final_vae.evaluate(full_dataset)
self.logger.info("{}|Loss = {:f}".format(model_config["name"], loss))
self.logger.info("Creating latent represenations...")
latent_reps = final_vae.encode(full_dataset.features)
results = np.hstack((np.expand_dims(full_dataset.sample_data[0],
axis=1), latent_reps,
np.expand_dims(full_dataset.sample_data[1],
axis=1),
np.expand_dims(full_dataset.sample_data[2],
axis=1)))
header = ["cell_ids"]
for l in range(1, model_config["latent_size"] + 1):
header.append("dim{}".format(l))
header.append("cell_type")
header.append("cell_subtype")
header = np.array(header)
results = np.vstack((header, results))
self.logger.info("Saving results")
save_data_table(
results, model_config["model_dir"] + "/latent_representations.txt")
writer.writerow(r)
cell_ids, features, cell_types, cell_subtypes = load_data()
datasets = stratified_kfold(
features, cell_subtypes,
[cell_ids, cell_types, cell_subtypes],
n_folds=5, convert_labels_to_int=True)
full_dataset = Dataset.concatenate(*datasets)
n_epochs = 200
final_vae = VAE(model_config)
final_vae.train(full_dataset,
epochs=n_epochs, batch_size=model_config["batch_size"])
loss = final_vae.evaluate(full_dataset)
print(loss)
latent_reps = final_vae.encode(full_dataset.features)
results = np.hstack((
np.expand_dims(full_dataset.sample_data[0], axis=1),
latent_reps,
np.expand_dims(full_dataset.sample_data[1], axis=1),
np.expand_dims(full_dataset.sample_data[2], axis=1)
))
header = ["cell_ids"]
for l in range(1, model_config["latent_size"] + 1):
header.append("dim{}".format(l))
header.append("cell_type")
header.append("cell_subtype")