def test_filter_and_concat_datasets():
cortex_dataset_1 = CortexDataset(save_path='tests/data/')
cortex_dataset_1.subsample_genes(subset_genes=np.arange(0, 3))
cortex_dataset_1.filter_cell_types(["microglia", "oligodendrocytes"])
cortex_dataset_2 = CortexDataset(save_path='tests/data/')
cortex_dataset_2.subsample_genes(subset_genes=np.arange(1, 4))
cortex_dataset_2.filter_cell_types(["endothelial-mural", "interneurons", "microglia", "oligodendrocytes"])
cortex_dataset_2.filter_cell_types([2, 0])
cortex_dataset_merged = GeneExpressionDataset.concat_datasets(cortex_dataset_1, cortex_dataset_2)
assert cortex_dataset_merged.nb_genes == 2
synthetic_dataset_1 = SyntheticDataset(n_batches=2, n_labels=5)
synthetic_dataset_2 = SyntheticDataset(n_batches=3, n_labels=3)
synthetic_merged_1 = GeneExpressionDataset.concat_datasets(synthetic_dataset_1, synthetic_dataset_2)
assert synthetic_merged_1.n_batches == 5
assert synthetic_merged_1.n_labels == 5
synthetic_merged_2 = GeneExpressionDataset.concat_datasets(synthetic_dataset_1, synthetic_dataset_2,
shared_labels=False)
assert synthetic_merged_2.n_batches == 5
assert synthetic_merged_2.n_labels == 8
synthetic_dataset_1.filter_cell_types([0, 1, 2, 3])
assert synthetic_dataset_1.n_labels == 4
synthetic_dataset_1.subsample_cells(50)
assert len(synthetic_dataset_1) == 50
synthetic_dataset_3 = SyntheticDataset(n_labels=6)
synthetic_dataset_3.cell_types = np.arange(6).astype(np.str)
synthetic_dataset_3.map_cell_types({"2": "9", ("4", "3"): "8"})
def test_filter_and_concat_datasets():
cortex_dataset_1 = CortexDataset()
cortex_dataset_1.subsample_genes(subset_genes=np.arange(0, 300))
cortex_dataset_1.filter_cell_types(["microglia", "oligodendrocytes"])
cortex_dataset_2 = CortexDataset()
cortex_dataset_2.subsample_genes(subset_genes=np.arange(100, 400))
cortex_dataset_2.filter_cell_types(
["endothelial-mural", "interneurons", "microglia", "oligodendrocytes"])
cortex_dataset_2.filter_cell_types([2, 0])
cortex_dataset_merged = GeneExpressionDataset.concat_datasets(
cortex_dataset_1, cortex_dataset_2)
assert cortex_dataset_merged.nb_genes == 200
synthetic_dataset_1 = SyntheticDataset(n_batches=2, n_labels=5)
synthetic_dataset_2 = SyntheticDataset(n_batches=3, n_labels=3)
synthetic_merged_1 = GeneExpressionDataset.concat_datasets(
synthetic_dataset_1, synthetic_dataset_2)
assert synthetic_merged_1.n_batches == 5
assert synthetic_merged_1.n_labels == 5
synthetic_merged_2 = GeneExpressionDataset.concat_datasets(
synthetic_dataset_1, synthetic_dataset_2, shared_labels=False)
assert synthetic_merged_2.n_batches == 5
assert synthetic_merged_2.n_labels == 8
synthetic_dataset_1.filter_cell_types([0, 1, 2, 3])
assert synthetic_dataset_1.n_labels == 4
synthetic_dataset_1.subsample_cells(50)
assert len(synthetic_dataset_1) == 50
