def test_vmap_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 VMAP 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 = VMAP(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))
vmap = VMAP()
u1 = vmap.fit_transform(a[:, :5])
u1_orig = u1.copy()
assert_array_equal(u1_orig, vmap.embedding_)
u2 = vmap.transform(b)
assert_array_equal(u1_orig, vmap.embedding_)
def test_vmap_transform_on_iris():
data = iris.data[iris_selection]
fitter = VMAP(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_greater_equal(
trust,
0.89,
"Insufficiently trustworthy transform for"
"iris dataset: {}".format(trust),
)
