def test_partial_fit(nrows, ncols, n_components, density, batch_size_divider,
whiten):
X, _ = make_blobs(n_samples=nrows, n_features=ncols, random_state=10)
cu_ipca = cuIPCA(n_components=n_components, whiten=whiten)
sample_size = int(nrows / batch_size_divider)
for i in range(0, nrows, sample_size):
cu_ipca.partial_fit(X[i:i + sample_size].copy())
cu_t = cu_ipca.transform(X)
cu_inv = cu_ipca.inverse_transform(cu_t)
sk_ipca = skIPCA(n_components=n_components, whiten=whiten)
X = cp.asnumpy(X)
for i in range(0, nrows, sample_size):
sk_ipca.partial_fit(X[i:i + sample_size].copy())
sk_t = sk_ipca.transform(X)
sk_inv = sk_ipca.inverse_transform(sk_t)
assert array_equal(cu_inv, sk_inv, 5e-5, with_sign=True)
def test_fit(nrows, ncols, n_components, sparse_input, density, sparse_format,
batch_size_divider, whiten):
if sparse_format == 'csc':
pytest.skip("cupyx.scipy.sparse.csc.csc_matrix does not support"
" indexing as of cupy 7.6.0")
if sparse_input:
X = cupyx.scipy.sparse.random(nrows,
ncols,
density=density,
random_state=10,
format=sparse_format)
else:
X, _ = make_blobs(n_samples=nrows, n_features=ncols, random_state=10)
cu_ipca = cuIPCA(n_components=n_components,
whiten=whiten,
batch_size=int(nrows / batch_size_divider))
cu_ipca.fit(X)
cu_t = cu_ipca.transform(X)
cu_inv = cu_ipca.inverse_transform(cu_t)
sk_ipca = skIPCA(n_components=n_components,
whiten=whiten,
batch_size=int(nrows / batch_size_divider))
if sparse_input:
X = X.get()
else:
X = cp.asnumpy(X)
sk_ipca.fit(X)
sk_t = sk_ipca.transform(X)
sk_inv = sk_ipca.inverse_transform(sk_t)
assert array_equal(cu_inv, sk_inv, 5e-5, with_sign=True)