def load_datasets(dataset_name, save_path="data/", url=None):
if dataset_name == "synthetic":
gene_dataset = SyntheticDataset()
elif dataset_name == "cortex":
gene_dataset = CortexDataset()
elif dataset_name == "brain_large":
gene_dataset = BrainLargeDataset(save_path=save_path)
elif dataset_name == "retina":
gene_dataset = RetinaDataset(save_path=save_path)
elif dataset_name == "cbmc":
gene_dataset = CbmcDataset(save_path=save_path)
elif dataset_name == "brain_small":
gene_dataset = BrainSmallDataset(save_path=save_path)
elif dataset_name == "hemato":
gene_dataset = HematoDataset(save_path="data/HEMATO/")
elif dataset_name == "pbmc":
gene_dataset = PbmcDataset(save_path=save_path)
elif dataset_name[-5:] == ".loom":
gene_dataset = LoomDataset(filename=dataset_name, save_path=save_path, url=url)
elif dataset_name[-5:] == ".h5ad":
gene_dataset = AnnDataset(dataset_name, save_path=save_path, url=url)
elif ".csv" in dataset_name:
gene_dataset = CsvDataset(dataset_name, save_path=save_path)
else:
raise Exception("No such dataset available")
return gene_dataset
def load_datasets(dataset_name, save_path='data/', url=None):
if dataset_name == 'synthetic':
gene_dataset = SyntheticDataset()
elif dataset_name == 'cortex':
gene_dataset = CortexDataset()
elif dataset_name == 'brain_large':
gene_dataset = BrainLargeDataset(save_path=save_path)
elif dataset_name == 'retina':
gene_dataset = RetinaDataset(save_path=save_path)
elif dataset_name == 'cbmc':
gene_dataset = CbmcDataset(save_path=save_path)
elif dataset_name == 'brain_small':
gene_dataset = BrainSmallDataset(save_path=save_path)
elif dataset_name == 'hemato':
gene_dataset = HematoDataset(save_path='data/HEMATO/')
elif dataset_name == 'pbmc':
gene_dataset = PbmcDataset(save_path=save_path)
elif dataset_name[-5:] == ".loom":
gene_dataset = LoomDataset(filename=dataset_name,
save_path=save_path,
url=url)
elif dataset_name[-5:] == ".h5ad":
gene_dataset = AnnDataset(dataset_name, save_path=save_path, url=url)
elif ".csv" in dataset_name:
gene_dataset = CsvDataset(dataset_name, save_path=save_path)
else:
raise "No such dataset available"
return gene_dataset
def test_brain_small():
brain_small_dataset = BrainSmallDataset(save_path='tests/data/')
base_benchmark(brain_small_dataset)
def test_brain_small(save_path):
brain_small_dataset = BrainSmallDataset(save_path=save_path)
base_benchmark(brain_small_dataset)
(70000, -1)).numpy())
mnist_labels = (torch.cat(
[mnist_train.dataset.targets, mnist_test.dataset.targets], axis=0).reshape(
(70000, -1)).numpy())
np.savez(f'{data_dir}/MNIST.npz', features=mnist_features, labels=mnist_labels)
del mnist_train, mnist_test, mnist_features, mnist_labels
# %% how to load data from npz
# data = np.load(f'{data_dir}/MNIST.npz')
# %% BrainSmall
os.chdir(data_dir)
brain_small_dataset = BrainSmallDataset(
save_path=f'{data_dir}/BrainSmall/',
save_path_10X=f'{data_dir}/BrainSmall/')
brain_small_features = brain_small_dataset.X.toarray()
brain_small_labels = brain_small_dataset.labels
np.savez(f'{data_dir}/BrainSmall.npz',
features=brain_small_features,
labels=brain_small_labels)
del brain_small_dataset, brain_small_features, brain_small_labels
# %%
dataset_objects = [
BrainLargeDataset, CortexDataset, PbmcDataset, RetinaDataset,
HematoDataset, CbmcDataset, BrainSmallDataset, SmfishDataset
]
