def test_projection_without_pipeline(self):
# accomodate scaling, values are in (0,1), but will be scaled slightly
atol = 0.1
mapper = KeplerMapper(verbose=1)
data = np.random.rand(100, 5)
lens = mapper.project(data, projection=[0, 1])
np.testing.assert_allclose(lens, data[:, :2], atol=atol)
lens = mapper.project(data, projection=[0])
np.testing.assert_allclose(lens, data[:, :1], atol=atol)
def test_logging_in_project(self, capsys):
mapper = KeplerMapper(verbose=2)
data = np.random.rand(100, 2)
lens = mapper.project(data)
captured = capsys.readouterr()
assert "Projecting on" in captured[0]
def test_tuple_projection_fit(self):
mapper = KeplerMapper()
data = np.random.rand(100, 5)
y = np.random.rand(100, 1)
lens = mapper.project(data, projection=(Lasso(), data, y), scaler=None)
# hard to test this, at least it doesn't fail
assert lens.shape == (100, 1)
def test_project_sklearn_class(self):
mapper = KeplerMapper()
data = np.random.rand(100, 5)
lens = mapper.project(data, projection=PCA(n_components=1), scaler=None)
pca = PCA(n_components=1)
lens_confirm = pca.fit_transform(data)
assert lens.shape == (100, 1)
np.testing.assert_array_equal(lens, lens_confirm)
def test_tuple_projection(self):
mapper = KeplerMapper()
data = np.random.rand(100, 5)
y = np.random.rand(100, 1)
lasso = Lasso()
lasso.fit(data, y)
lens = mapper.project(data, projection=(lasso, data), scaler=None)
# hard to test this, at least it doesn't fail
assert lens.shape == (100, 1)
np.testing.assert_array_equal(lens, lasso.predict(data).reshape((100, 1)))
def test_knn_distance(self):
mapper = KeplerMapper()
data = np.random.rand(100, 5)
lens = mapper.project(data, projection="knn_distance_4", scaler=None)
nn = neighbors.NearestNeighbors(n_neighbors=4)
nn.fit(data)
lens_confirm = np.sum(
nn.kneighbors(data, n_neighbors=4, return_distance=True)[0], axis=1
).reshape((-1, 1))
assert lens.shape == (100, 1)
np.testing.assert_array_equal(lens, lens_confirm)
def test_remove_duplicates_argument(self, capsys):
mapper = KeplerMapper(verbose=1)
X = np.random.rand(100, 5)
lens = mapper.project(X)
graph = mapper.map(
lens,
X=X,
cover=Cover(n_cubes=2, perc_overlap=1),
clusterer=cluster.DBSCAN(metric="euclidean", min_samples=3),
remove_duplicate_nodes=True,
)
captured = capsys.readouterr()
assert "duplicate nodes" in captured[0]