def test_make_union(self):
svd = SparkTruncatedSVD()
mock = TransfT()
fu = make_sparkunion(svd, mock)
names, transformers = list(zip(*fu.transformer_list))
assert_equal(names, ("sparktruncatedsvd", "transft"))
assert_equal(transformers, (svd, mock))
def test_same_fit_transforms(self):
X, X_rdd = self.make_dense_rdd((1e3, 12))
n_components = 4
random_state = 42
tol = 1e-7
local = TruncatedSVD(n_components, n_iter=5, tol=tol,
random_state=random_state)
dist = SparkTruncatedSVD(n_components, n_iter=50, tol=tol,
random_state=random_state)
Z_local = local.fit_transform(X)
Z_dist = dist.fit_transform(X_rdd).toarray()
tol = 1e-1
assert_array_equal(Z_local.shape, Z_dist.shape)
assert(np.allclose(+Z_dist[:, 0], Z_local[:, 0], atol=tol) |
np.allclose(-Z_dist[:, 0], Z_local[:, 0], atol=tol))
def test_same_fit_transforms(self):
X, X_rdd = self.make_dense_rdd((1e3, 12))
n_components = 4
random_state = 42
tol = 1e-7
local = TruncatedSVD(n_components, n_iter=5, tol=tol,
random_state=random_state)
dist = SparkTruncatedSVD(n_components, n_iter=50, tol=tol,
random_state=random_state)
Z_local = local.fit_transform(X)
Z_dist = dist.fit_transform(X_rdd)
Z_collected = Z_dist.toarray()
assert_true(check_rdd_dtype(Z_dist, (np.ndarray,)))
tol = 1e-1
assert_array_equal(Z_local.shape, Z_collected.shape)
assert(np.allclose(+Z_collected[:, 0], Z_local[:, 0], atol=tol) |
np.allclose(-Z_collected[:, 0], Z_local[:, 0], atol=tol))
def test_same_components(self):
X, X_rdd = self.make_dense_rdd((1e3, 10))
n_components = 2
random_state = 42
tol = 1e-7
local = TruncatedSVD(n_components, n_iter=5, tol=tol,
random_state=random_state)
dist = SparkTruncatedSVD(n_components, n_iter=50, tol=tol,
random_state=random_state)
local.fit(X)
dist.fit(X_rdd)
v_true = local.components_
v = dist.components_
tol = 1e-1
assert(np.allclose(+v[0], v_true[0, :], atol=tol) |
np.allclose(-v[0], v_true[0, :], atol=tol))
def test_same_components(self):
X, X_rdd = self.make_dense_rdd((1e3, 10))
n_components = 2
random_state = 42
tol = 1e-7
local = TruncatedSVD(n_components, n_iter=5, tol=tol,
random_state=random_state)
dist = SparkTruncatedSVD(n_components, n_iter=50, tol=tol,
random_state=random_state)
local.fit(X)
dist.fit(X_rdd)
v_true = local.components_
v = dist.components_
tol = 1e-1
assert(np.allclose(+v[0], v_true[0, :], atol=tol) |
np.allclose(-v[0], v_true[0, :], atol=tol))
