def test_make_circles():
factor = 0.3
for (n_samples, n_outer, n_inner) in [(7, 3, 4), (8, 4, 4)]:
# Testing odd and even case, because in the past make_circles always
# created an even number of samples.
X, y = make_circles(n_samples,
shuffle=False,
noise=None,
factor=factor)
assert X.shape == (n_samples, 2), "X shape mismatch"
assert y.shape == (n_samples, ), "y shape mismatch"
center = [0.0, 0.0]
for x, label in zip(X, y):
dist_sqr = ((x - center)**2).sum()
dist_exp = 1.0 if label == 0 else factor**2
assert_almost_equal(dist_sqr,
dist_exp,
err_msg="Point is not on expected circle")
assert X[y == 0].shape == (n_outer, 2), (
"Samples not correctly distributed across circles.")
assert X[y == 1].shape == (n_inner, 2), (
"Samples not correctly distributed across circles.")
with pytest.raises(ValueError):
make_circles(factor=-0.01)
with pytest.raises(ValueError):
make_circles(factor=1.)
def test_gridsearch_pipeline():
# Test if we can do a grid-search to find parameters to separate
# circles with a perceptron model.
X, y = make_circles(n_samples=400, factor=.3, noise=.05, random_state=0)
kpca = KernelPCA(kernel="rbf", n_components=2)
pipeline = Pipeline([("kernel_pca", kpca),
("Perceptron", Perceptron(max_iter=5))])
param_grid = dict(kernel_pca__gamma=2.**np.arange(-2, 2))
grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
grid_search.fit(X, y)
assert grid_search.best_score_ == 1
def test_random_trees_dense_type():
# Test that the `sparse_output` parameter of RandomTreesEmbedding
# works by returning a dense array.
# Create the RTE with sparse=False
hasher = RandomTreesEmbedding(n_estimators=10, sparse_output=False)
X, y = datasets.make_circles(factor=0.5)
X_transformed = hasher.fit_transform(X)
# Assert that type is ndarray, not scipy.sparse.csr.csr_matrix
assert type(X_transformed) == np.ndarray
def test_single_linkage_clustering():
# Check that we get the correct result in two emblematic cases
moons, moon_labels = make_moons(noise=0.05, random_state=42)
clustering = AgglomerativeClustering(n_clusters=2, linkage='single')
clustering.fit(moons)
assert_almost_equal(normalized_mutual_info_score(clustering.labels_,
moon_labels), 1)
circles, circle_labels = make_circles(factor=0.5, noise=0.025,
random_state=42)
clustering = AgglomerativeClustering(n_clusters=2, linkage='single')
clustering.fit(circles)
assert_almost_equal(normalized_mutual_info_score(clustering.labels_,
circle_labels), 1)
def test_random_trees_dense_equal():
# Test that the `sparse_output` parameter of RandomTreesEmbedding
# works by returning the same array for both argument values.
# Create the RTEs
hasher_dense = RandomTreesEmbedding(n_estimators=10,
sparse_output=False,
random_state=0)
hasher_sparse = RandomTreesEmbedding(n_estimators=10,
sparse_output=True,
random_state=0)
X, y = datasets.make_circles(factor=0.5)
X_transformed_dense = hasher_dense.fit_transform(X)
X_transformed_sparse = hasher_sparse.fit_transform(X)
# Assert that dense and sparse hashers have same array.
assert_array_equal(X_transformed_sparse.toarray(), X_transformed_dense)
def test_nested_circles():
# Test the linear separability of the first 2D KPCA transform
X, y = make_circles(n_samples=400, factor=.3, noise=.05, random_state=0)
# 2D nested circles are not linearly separable
train_score = Perceptron(max_iter=5).fit(X, y).score(X, y)
assert train_score < 0.8
# Project the circles data into the first 2 components of a RBF Kernel
# PCA model.
# Note that the gamma value is data dependent. If this test breaks
# and the gamma value has to be updated, the Kernel PCA example will
# have to be updated too.
kpca = KernelPCA(kernel="rbf",
n_components=2,
fit_inverse_transform=True,
gamma=2.)
X_kpca = kpca.fit_transform(X)
# The data is perfectly linearly separable in that space
train_score = Perceptron(max_iter=5).fit(X_kpca, y).score(X_kpca, y)
assert train_score == 1.0
def test_random_hasher():
# test random forest hashing on circles dataset
# make sure that it is linearly separable.
# even after projected to two SVD dimensions
# Note: Not all random_states produce perfect results.
hasher = RandomTreesEmbedding(n_estimators=30, random_state=1)
X, y = datasets.make_circles(factor=0.5)
X_transformed = hasher.fit_transform(X)
# test fit and transform:
hasher = RandomTreesEmbedding(n_estimators=30, random_state=1)
assert_array_equal(
hasher.fit(X).transform(X).toarray(), X_transformed.toarray())
# one leaf active per data point per forest
assert X_transformed.shape[0] == X.shape[0]
assert_array_equal(X_transformed.sum(axis=1), hasher.n_estimators)
svd = TruncatedSVD(n_components=2)
X_reduced = svd.fit_transform(X_transformed)
linear_clf = LinearSVC()
linear_clf.fit(X_reduced, y)
assert linear_clf.score(X_reduced, y) == 1.