def test_umap_transform_on_iris():
iris = datasets.load_iris()
iris_selection = np.random.choice(
[True, False], 150, replace=True, p=[0.75, 0.25])
data = iris.data[iris_selection]
fitter = UMAP(n_neighbors=10, min_dist=0.01, verbose=True)
fitter.fit(data)
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, 10)
assert trust >= 0.90
def test_umap_downcast_fails(input_type):
X = np.array([[1.0, 1.0], [50.0, 1.0], [51.0, 1.0]], dtype=np.float64)
# Test fit() fails with double precision when should_downcast set to False
umap = UMAP(should_downcast=False, verbose=True)
if input_type == 'dataframe':
X = cudf.DataFrame.from_pandas(pd.DataFrame(X))
with pytest.raises(Exception):
umap.fit(X, should_downcast=False)
# Test fit() fails when downcast corrupted data
X = np.array([[np.finfo(np.float32).max]], dtype=np.float64)
umap = UMAP(should_downcast=True)
if input_type == 'dataframe':
X = cudf.DataFrame.from_pandas(pd.DataFrame(X))
with pytest.raises(Exception):
umap.fit(X, should_downcast=True)