def test_seed_returns_identically(self):
for A in self.test_matrices:
for seed in self.seeds:
sketch1 = clarkson_woodruff_transform(A,
self.n_sketch_rows,
seed=seed)
sketch2 = clarkson_woodruff_transform(A,
self.n_sketch_rows,
seed=seed)
if issparse(sketch1):
sketch1 = sketch1.toarray()
if issparse(sketch2):
sketch2 = sketch2.toarray()
assert_equal(sketch1, sketch2)
def test_seed_returns_identically(self):
for A in self.test_matrices:
for seed in self.seeds:
sketch1 = clarkson_woodruff_transform(
A, self.n_sketch_rows, seed=seed
)
sketch2 = clarkson_woodruff_transform(
A, self.n_sketch_rows, seed=seed
)
if issparse(sketch1):
sketch1 = sketch1.todense()
if issparse(sketch2):
sketch2 = sketch2.todense()
assert_equal(sketch1, sketch2)
def test_sketch_dimensions(self):
for A in self.test_matrices:
for seed in self.seeds:
sketch = clarkson_woodruff_transform(A,
self.n_sketch_rows,
seed=seed)
assert_(sketch.shape == (self.n_sketch_rows, self.n_cols))
def test_sketch_dimensions(self):
for A in self.test_matrices:
for seed in self.seeds:
sketch = clarkson_woodruff_transform(
A, self.n_sketch_rows, seed=seed
)
assert_(sketch.shape == (self.n_sketch_rows, self.n_cols))
def test_sketch_preserves_vector_norm(self):
n_errors = 0
n_sketch_rows = int(np.ceil(2. / (0.01 * 0.5**2)))
true_norm = np.linalg.norm(self.x)
for seed in self.seeds:
sketch = clarkson_woodruff_transform(
self.x, n_sketch_rows, seed=seed,
)
sketch_norm = np.linalg.norm(sketch)
if np.abs(true_norm - sketch_norm) > 0.5 * true_norm:
n_errors += 1
assert_(n_errors == 0)
def test_sketch_preserves_vector_norm(self):
n_errors = 0
n_sketch_rows = int(np.ceil(2. / (0.01 * 0.5**2)))
true_norm = np.linalg.norm(self.x)
for seed in self.seeds:
sketch = clarkson_woodruff_transform(
self.x, n_sketch_rows, seed=seed,
)
sketch_norm = np.linalg.norm(sketch)
if np.abs(true_norm - sketch_norm) > 0.5 * true_norm:
n_errors += 1
assert_(n_errors == 0)
def test_sketch_rows_norm(self):
# Given the probabilistic nature of the sketches
# we run the 'test' multiple times and check that
# we pass all/almost all the tries
n_errors = 0
seeds = [
1755490010, 934377150, 1391612830, 1752708722, 2008891431,
1302443994, 1521083269, 1501189312, 1126232505, 1533465685
]
for seed_ in seeds:
sketch = clarkson_woodruff_transform(self.dense_big_matrix,
self.n_sketch_rows, seed_)
# We could use other norms (like L2)
err = np.linalg.norm(
self.dense_big_matrix) - np.linalg.norm(sketch)
if err > self.threshold:
n_errors += 1
assert_(n_errors == 0)
def test_sketch_preserves_frobenius_norm(self):
# Given the probabilistic nature of the sketches
# we run the test multiple times and check that
# we pass all/almost all the tries.
n_errors = 0
for A in self.test_matrices:
if issparse(A):
true_norm = norm(A)
else:
true_norm = np.linalg.norm(A)
for seed in self.seeds:
sketch = clarkson_woodruff_transform(
A, self.n_sketch_rows, seed=seed,
)
if issparse(sketch):
sketch_norm = norm(sketch)
else:
sketch_norm = np.linalg.norm(sketch)
if np.abs(true_norm - sketch_norm) > 0.1 * true_norm:
n_errors += 1
assert_(n_errors == 0)
def test_sketch_preserves_frobenius_norm(self):
# Given the probabilistic nature of the sketches
# we run the test multiple times and check that
# we pass all/almost all the tries.
n_errors = 0
for A in self.test_matrices:
if issparse(A):
true_norm = norm(A)
else:
true_norm = np.linalg.norm(A)
for seed in self.seeds:
sketch = clarkson_woodruff_transform(
A, self.n_sketch_rows, seed=seed,
)
if issparse(sketch):
sketch_norm = norm(sketch)
else:
sketch_norm = np.linalg.norm(sketch)
if np.abs(true_norm - sketch_norm) > 0.1 * true_norm:
n_errors += 1
assert_(n_errors == 0)
def test_sketch_dimensions(self):
sketch = clarkson_woodruff_transform(self.dense_big_matrix,
self.n_sketch_rows)
assert_(sketch.shape == (self.n_sketch_rows,
self.dense_big_matrix.shape[1]))