def test_umap_transform_embedding_stability():
"""Test that transforming data does not alter the learned embeddings
Issue #217 describes how using transform to embed new data using a
trained UMAP transformer causes the fitting embedding matrix to change
in cases when the new data has the same number of rows as the original
training data.
"""
data = iris.data[iris_selection]
fitter = UMAP(n_neighbors=10, min_dist=0.01, random_state=42).fit(data)
original_embedding = fitter.embedding_.copy()
# The important point is that the new data has the same number of rows
# as the original fit data
new_data = np.random.random(data.shape)
embedding = fitter.transform(new_data)
assert_array_equal(
original_embedding,
fitter.embedding_,
"Transforming new data changed the original embeddings",
)
# Example from issue #217
a = np.random.random((1000, 10))
b = np.random.random((1000, 5))
umap = UMAP()
u1 = umap.fit_transform(a[:, :5])
u1_orig = u1.copy()
assert_array_equal(u1_orig, umap.embedding_)
u2 = umap.transform(b)
assert_array_equal(u1_orig, umap.embedding_)
def test_umap_transform_on_iris():
data = iris.data[iris_selection]
fitter = UMAP(n_neighbors=10, min_dist=0.01, random_state=42).fit(data)
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, 10)
assert (
trust >= 0.89
), "Insufficiently trustworthy transform for iris dataset: {}".format(trust)
def test_umap_transform_on_iris_modified_dtype():
data = iris.data[iris_selection]
fitter = UMAP(n_neighbors=10, min_dist=0.01, random_state=42).fit(data)
fitter.embedding_ = fitter.embedding_.astype(np.float64)
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, 10)
assert_greater_equal(
trust,
0.89,
"Insufficiently trustworthy transform for" "iris dataset: {}".format(trust),
)
def test_umap_sparse_transform_on_iris():
data = sparse.csr_matrix(iris.data[iris_selection])
assert sparse.issparse(data)
fitter = UMAP(
n_neighbors=10,
min_dist=0.01,
random_state=42,
n_epochs=100,
force_approximation_algorithm=True,
).fit(data)
new_data = sparse.csr_matrix(iris.data[~iris_selection])
assert sparse.issparse(new_data)
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, 10)
assert_greater_equal(
trust,
0.85,
"Insufficiently trustworthy transform for" "iris dataset: {}".format(trust),
)
