def test_pca_fit_transform_fp32(nrows, ncols, n_parts, client=None):
owns_cluster = False
if client is None:
owns_cluster = True
cluster = LocalCUDACluster(threads_per_worker=1)
client = Client(cluster)
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from cuml.dask.datasets import make_blobs
X_cudf, _ = make_blobs(nrows,
ncols,
1,
n_parts,
cluster_std=1.5,
verbose=False,
random_state=10,
dtype=np.float32)
wait(X_cudf)
cutsvd = daskTPCA(n_components=20)
cutsvd.fit_transform(X_cudf)
if owns_cluster:
client.close()
cluster.close()
def test_pca_fit(data_info, input_type, client):
nrows, ncols, n_parts = data_info
if nrows == int(9e6) and pytest.max_gpu_memory < 48:
if pytest.adapt_stress_test:
nrows = nrows * pytest.max_gpu_memory // 256
ncols = ncols * pytest.max_gpu_memory // 256
else:
pytest.skip("Insufficient GPU memory for this test."
"Re-run with 'CUML_ADAPT_STRESS_TESTS=True'")
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from sklearn.decomposition import TruncatedSVD
from cuml.dask.datasets import make_blobs
X, _ = make_blobs(n_samples=nrows,
n_features=ncols,
centers=1,
n_parts=n_parts,
cluster_std=0.5,
random_state=10,
dtype=np.float32)
if input_type == "dataframe":
X_train = to_dask_cudf(X)
X_cpu = X_train.compute().to_pandas().values
elif input_type == "array":
X_train = X
X_cpu = cp.asnumpy(X_train.compute())
cutsvd = daskTPCA(n_components=5)
cutsvd.fit(X_train)
sktsvd = TruncatedSVD(n_components=5, algorithm="arpack")
sktsvd.fit(X_cpu)
all_attr = [
'singular_values_', 'components_', 'explained_variance_',
'explained_variance_ratio_'
]
for attr in all_attr:
with_sign = False if attr in ['components_'] else True
cuml_res = (getattr(cutsvd, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.to_numpy()
skl_res = getattr(sktsvd, attr)
if attr == 'singular_values_':
assert array_equal(cuml_res, skl_res, 1, with_sign=with_sign)
else:
assert array_equal(cuml_res, skl_res, 1e-1, with_sign=with_sign)
def test_pca_fit(data_info, input_type, cluster):
client = Client(cluster)
nrows, ncols, n_parts = data_info
try:
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from sklearn.decomposition import TruncatedSVD
from cuml.dask.datasets import make_blobs
X, _ = make_blobs(n_samples=nrows,
n_features=ncols,
centers=1,
n_parts=n_parts,
cluster_std=0.5,
random_state=10,
dtype=np.float32)
wait(X)
if input_type == "dataframe":
X_train = to_dask_cudf(X)
X_cpu = X_train.compute().to_pandas().values
elif input_type == "array":
X_train = X
X_cpu = cp.asnumpy(X_train.compute())
cutsvd = daskTPCA(n_components=5)
cutsvd.fit(X_train)
sktsvd = TruncatedSVD(n_components=5, algorithm="arpack")
sktsvd.fit(X_cpu)
all_attr = [
'singular_values_', 'components_', 'explained_variance_',
'explained_variance_ratio_'
]
finally:
client.close()
for attr in all_attr:
with_sign = False if attr in ['components_'] else True
cuml_res = (getattr(cutsvd, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(sktsvd, attr)
if attr == 'singular_values_':
assert array_equal(cuml_res, skl_res, 1, with_sign=with_sign)
else:
assert array_equal(cuml_res, skl_res, 1e-1, with_sign=with_sign)
def test_pca_fit(nrows, ncols, n_parts, client=None):
owns_cluster = False
if client is None:
owns_cluster = True
cluster = LocalCUDACluster(threads_per_worker=1)
client = Client(cluster)
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from sklearn.decomposition import TruncatedSVD
from cuml.dask.datasets import make_blobs
X_cudf, _ = make_blobs(nrows,
ncols,
1,
n_parts,
cluster_std=0.5,
verbose=False,
random_state=10,
dtype=np.float32)
wait(X_cudf)
X = X_cudf.compute().to_pandas().values
cutsvd = daskTPCA(n_components=5)
cutsvd.fit(X_cudf)
sktsvd = TruncatedSVD(n_components=5, algorithm="arpack")
sktsvd.fit(X)
all_attr = [
'singular_values_', 'components_', 'explained_variance_',
'explained_variance_ratio_'
]
if owns_cluster:
client.close()
cluster.close()
for attr in all_attr:
with_sign = False if attr in ['components_'] else True
cuml_res = (getattr(cutsvd, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(sktsvd, attr)
if attr == 'singular_values_':
assert array_equal(cuml_res, skl_res, 1, with_sign=with_sign)
else:
assert array_equal(cuml_res, skl_res, 1e-1, with_sign=with_sign)
def test_pca_fit_transform_fp32(data_info, client):
nrows, ncols, n_parts = data_info
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from cuml.dask.datasets import make_blobs
X_cudf, _ = make_blobs(n_samples=nrows,
n_features=ncols,
centers=1,
n_parts=n_parts,
cluster_std=1.5,
random_state=10,
dtype=np.float32)
cutsvd = daskTPCA(n_components=20)
cutsvd.fit_transform(X_cudf)
def test_pca_fit_transform_fp32(nrows, ncols, n_parts, cluster):
client = Client(cluster)
try:
from cuml.dask.decomposition import TruncatedSVD as daskTPCA
from cuml.dask.datasets import make_blobs
X_cudf, _ = make_blobs(n_samples=nrows,
n_features=ncols,
centers=1,
n_parts=n_parts,
cluster_std=1.5, verbose=False,
random_state=10, dtype=np.float32)
wait(X_cudf)
cutsvd = daskTPCA(n_components=20)
cutsvd.fit_transform(X_cudf)
finally:
client.close()