def run(self, debug=False):
cell_ids, features, cell_types, cell_subtypes = self.load_data()
self.datasets = stratified_kfold(features,
cell_subtypes,
[cell_ids, cell_types, cell_subtypes],
n_folds=10,
convert_labels_to_int=True)
trials = Trials()
search_space = self.generate_search_space()
n_evals = 1 if self.debug else 30
best = fmin(self.train_vae,
space=search_space,
algo=tpe.suggest,
max_evals=n_evals,
trials=trials)
self.logger.info("Finished hyperopt optimization")
best_model_config = self.get_model_config(
space_eval(search_space, best))
self.train_final_vae(best_model_config)
experiment_results = [["model_name", "10foldcv_loss"]]
for result in trials.results:
experiment_results.append([result["name"], result["loss"]])
save_data_table(experiment_results,
self.experiment_dir + "/experiment_results.txt")
def __init__(self, n_genes, debug=False):
super(TrainUsoskinVAE, self).__init__(debug=debug)
self.input_size = n_genes
self.setup_dir()
self.setup_logger()
self.setup_hyperopt(n_evals=N_EVALS)
cell_ids, features, cell_types, cell_subtypes = self.load_data()
self.datasets = stratified_kfold(
features, cell_subtypes, [cell_ids, cell_types, cell_subtypes],
n_folds=N_FOLDS, convert_labels_to_int=True)
self.logger.info(
"Loaded {}g Usoskin dataset".format(
self.input_size))
self.setup_cross_validation(n_folds=N_FOLDS,
datasets=self.datasets,
model_class=VAE,
epochs=MAX_EPOCHS)
def __init__(self, debug=False):
super(Experiment, self).__init__(debug)
self.experiment_name = "train_usokin-100g-2layer-vae"
if self.debug:
self.experiment_name = "DEBUG_" + self.experiment_name
self.setup_dir()
self.setup_logger()
self.setup_hyperopt(n_evals=50)
self.input_size = 100
cell_ids, features, cell_types, cell_subtypes = self.load_data()
self.datasets = stratified_kfold(
features, cell_subtypes,
[cell_ids, cell_types, cell_subtypes],
n_folds=5, convert_labels_to_int=True)
self.logger.info("Loaded 100g, standardized Usokin dataset")
self.setup_cross_validation(n_folds=5,
datasets=self.datasets,
model_class=VAE)
if root is not None:
filepath = root + "/" + filepath
delimiter = str(delimiter) if six.PY2 else delimiter
with open(filepath, "w") as f:
writer = csv.writer(
f, delimiter=delimiter, quoting=csv.QUOTE_MINIMAL)
for r in data:
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),
