def test_scanvi(save_path):
adata = synthetic_iid(run_setup_anndata=False)
SCANVI.setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
)
model = SCANVI(adata, "label_0", n_latent=10)
model.train(1, train_size=0.5, check_val_every_n_epoch=1)
logged_keys = model.history.keys()
assert "elbo_validation" in logged_keys
assert "reconstruction_loss_validation" in logged_keys
assert "kl_local_validation" in logged_keys
assert "elbo_train" in logged_keys
assert "reconstruction_loss_train" in logged_keys
assert "kl_local_train" in logged_keys
assert "classification_loss_validation" in logged_keys
adata2 = synthetic_iid()
predictions = model.predict(adata2, indices=[1, 2, 3])
assert len(predictions) == 3
model.predict()
df = model.predict(adata2, soft=True)
assert isinstance(df, pd.DataFrame)
model.predict(adata2, soft=True, indices=[1, 2, 3])
model.get_normalized_expression(adata2)
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels",
group1="label_1",
group2="label_2")
# test that all data labeled runs
unknown_label = "asdf"
a = scvi.data.synthetic_iid()
scvi.model.SCANVI.setup_anndata(a, batch_key="batch", labels_key="labels")
m = scvi.model.SCANVI(a, unknown_label)
m.train(1)
# test mix of labeled and unlabeled data
unknown_label = "label_0"
a = scvi.data.synthetic_iid()
scvi.model.SCANVI.setup_anndata(a, batch_key="batch", labels_key="labels")
m = scvi.model.SCANVI(a, unknown_label)
m.train(1, train_size=0.9)
# test from_scvi_model
a = scvi.data.synthetic_iid()
m = scvi.model.SCVI(a, use_observed_lib_size=False)
a2 = scvi.data.synthetic_iid()
scanvi_model = scvi.model.SCANVI.from_scvi_model(m, "label_0", adata=a2)
scanvi_model = scvi.model.SCANVI.from_scvi_model(m,
"label_0",
use_labels_groups=False)
scanvi_model.train(1)
def test_scanvi():
adata = synthetic_iid()
model = SCANVI(adata, "undefined_0", n_latent=10)
model.train(1)
adata2 = synthetic_iid()
predictions = model.predict(adata2, indices=[1, 2, 3])
assert len(predictions) == 3
model.predict()
model.predict(adata2, soft=True)
model.predict(adata2, soft=True, indices=[1, 2, 3])
model.get_normalized_expression(adata2)
model.differential_expression(groupby="labels", group1="undefined_1")
model.differential_expression(groupby="labels",
group1="undefined_1",
group2="undefined_2")
def test_scanvi():
adata = synthetic_iid()
model = SCANVI(adata, "label_0", n_latent=10)
model.train(1, train_size=0.5, frequency=1)
assert len(model.history["unsupervised_trainer_history"]) == 2
assert len(model.history["semisupervised_trainer_history"]) == 7
adata2 = synthetic_iid()
predictions = model.predict(adata2, indices=[1, 2, 3])
assert len(predictions) == 3
model.predict()
model.predict(adata2, soft=True)
model.predict(adata2, soft=True, indices=[1, 2, 3])
model.get_normalized_expression(adata2)
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels", group1="label_1", group2="label_2")
def test_scanvi(save_path):
adata = synthetic_iid()
model = SCANVI(adata, "label_0", n_latent=10)
model.train(1, train_size=0.5, check_val_every_n_epoch=1)
logged_keys = model.history.keys()
assert "elbo_validation" in logged_keys
assert "reconstruction_loss_validation" in logged_keys
assert "kl_local_validation" in logged_keys
assert "elbo_train" in logged_keys
assert "reconstruction_loss_train" in logged_keys
assert "kl_local_train" in logged_keys
adata2 = synthetic_iid()
predictions = model.predict(adata2, indices=[1, 2, 3])
assert len(predictions) == 3
model.predict()
model.predict(adata2, soft=True)
model.predict(adata2, soft=True, indices=[1, 2, 3])
model.get_normalized_expression(adata2)
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels", group1="label_1", group2="label_2")
# test that all data labeled runs
unknown_label = "asdf"
a = scvi.data.synthetic_iid()
scvi.data.setup_anndata(a, batch_key="batch", labels_key="labels")
m = scvi.model.SCANVI(a, unknown_label)
m.train(1)
# check the number of indices
n_train_idx = len(m.train_indices)
n_validation_idx = len(m.validation_indices)
n_test_idx = len(m.test_indices)
assert n_train_idx + n_validation_idx + n_test_idx == a.n_obs
assert np.isclose(n_train_idx / a.n_obs, 0.9)
assert np.isclose(n_validation_idx / a.n_obs, 0.1)
assert np.isclose(n_test_idx / a.n_obs, 0)
# test mix of labeled and unlabeled data
unknown_label = "label_0"
a = scvi.data.synthetic_iid()
scvi.data.setup_anndata(a, batch_key="batch", labels_key="labels")
m = scvi.model.SCANVI(a, unknown_label)
m.train(1, train_size=0.9)
# check the number of indices
n_train_idx = len(m.train_indices)
n_validation_idx = len(m.validation_indices)
n_test_idx = len(m.test_indices)
assert n_train_idx + n_validation_idx + n_test_idx == a.n_obs
assert np.isclose(n_train_idx / a.n_obs, 0.9, rtol=0.05)
assert np.isclose(n_validation_idx / a.n_obs, 0.1, rtol=0.05)
assert np.isclose(n_test_idx / a.n_obs, 0, rtol=0.05)
# check that training indices have proper mix of labeled and unlabeled data
labelled_idx = np.where(a.obs["labels"] != unknown_label)[0]
unlabelled_idx = np.where(a.obs["labels"] == unknown_label)[0]
# labeled training idx
labeled_train_idx = [i for i in m.train_indices if i in labelled_idx]
# unlabeled training idx
unlabeled_train_idx = [i for i in m.train_indices if i in unlabelled_idx]
n_labeled_idx = len(m._labeled_indices)
n_unlabeled_idx = len(m._unlabeled_indices)
# labeled vs unlabeled ratio in adata
adata_ratio = n_unlabeled_idx / n_labeled_idx
# labeled vs unlabeled ratio in train set
train_ratio = len(unlabeled_train_idx) / len(labeled_train_idx)
assert np.isclose(adata_ratio, train_ratio, atol=0.05)
def test_scanvi(save_path):
adata = synthetic_iid()
SCANVI.setup_anndata(
adata,
"label_0",
batch_key="batch",
labels_key="labels",
)
model = SCANVI(adata, n_latent=10)
model.train(1, train_size=0.5, check_val_every_n_epoch=1)
logged_keys = model.history.keys()
assert "elbo_validation" in logged_keys
assert "reconstruction_loss_validation" in logged_keys
assert "kl_local_validation" in logged_keys
assert "elbo_train" in logged_keys
assert "reconstruction_loss_train" in logged_keys
assert "kl_local_train" in logged_keys
assert "classification_loss_validation" in logged_keys
adata2 = synthetic_iid()
predictions = model.predict(adata2, indices=[1, 2, 3])
assert len(predictions) == 3
model.predict()
df = model.predict(adata2, soft=True)
assert isinstance(df, pd.DataFrame)
model.predict(adata2, soft=True, indices=[1, 2, 3])
model.get_normalized_expression(adata2)
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels",
group1="label_1",
group2="label_2")
# test that all data labeled runs
unknown_label = "asdf"
a = scvi.data.synthetic_iid()
scvi.model.SCANVI.setup_anndata(a,
unknown_label,
batch_key="batch",
labels_key="labels")
m = scvi.model.SCANVI(a)
m.train(1)
# test mix of labeled and unlabeled data
unknown_label = "label_0"
a = scvi.data.synthetic_iid()
scvi.model.SCANVI.setup_anndata(a,
unknown_label,
batch_key="batch",
labels_key="labels")
m = scvi.model.SCANVI(a)
m.train(1, train_size=0.9)
# test from_scvi_model
a = scvi.data.synthetic_iid()
SCVI.setup_anndata(
a,
batch_key="batch",
labels_key="labels",
)
m = SCVI(a, use_observed_lib_size=False)
a2 = scvi.data.synthetic_iid()
scanvi_model = scvi.model.SCANVI.from_scvi_model(m, "label_0", adata=a2)
# make sure the state_dicts are different objects for the two models
assert scanvi_model.module.state_dict() is not m.module.state_dict()
scanvi_pxr = scanvi_model.module.state_dict().get("px_r", None)
scvi_pxr = m.module.state_dict().get("px_r", None)
assert scanvi_pxr is not None and scvi_pxr is not None
assert scanvi_pxr is not scvi_pxr
scanvi_model.train(1)
# Test without label groups
scanvi_model = scvi.model.SCANVI.from_scvi_model(m,
"label_0",
use_labels_groups=False)
scanvi_model.train(1)
# test from_scvi_model with size_factor
a = scvi.data.synthetic_iid()
a.obs["size_factor"] = np.random.randint(1, 5, size=(a.shape[0], ))
SCVI.setup_anndata(a,
batch_key="batch",
labels_key="labels",
size_factor_key="size_factor")
m = SCVI(a, use_observed_lib_size=False)
a2 = scvi.data.synthetic_iid()
a2.obs["size_factor"] = np.random.randint(1, 5, size=(a2.shape[0], ))
scanvi_model = scvi.model.SCANVI.from_scvi_model(m, "label_0", adata=a2)
scanvi_model.train(1)