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 PCA as daskPCA
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)
cupca = daskPCA(n_components=20, whiten=True)
cupca.fit_transform(X_cudf)
if owns_cluster:
client.close()
cluster.close()
def test_pca_fit(nrows, ncols, n_parts, input_type, cluster):
client = Client(cluster)
try:
from cuml.dask.decomposition import PCA as daskPCA
from sklearn.decomposition import PCA
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())
try:
cupca = daskPCA(n_components=5, whiten=True)
cupca.fit(X_train)
except Exception as e:
print(str(e))
skpca = PCA(n_components=5, whiten=True, svd_solver="full")
skpca.fit(X_cpu)
from cuml.test.utils import array_equal
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(cupca, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(skpca, attr)
assert array_equal(cuml_res, skl_res, 1e-1, with_sign=with_sign)
finally:
client.close()
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 PCA as daskPCA
from sklearn.decomposition import PCA
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
cupca = daskPCA(n_components=5, whiten=True)
cupca.fit(X_cudf)
skpca = PCA(n_components=5, whiten=True, svd_solver="full")
skpca.fit(X)
from cuml.test.utils import array_equal
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(cupca, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(skpca, attr)
assert array_equal(cuml_res, skl_res, 1e-3, with_sign=with_sign)
def test_pca_fit_transform_fp64(nrows, ncols, n_parts, client):
from cuml.dask.decomposition import PCA as daskPCA
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.float64)
cupca = daskPCA(n_components=30, whiten=False)
res = cupca.fit_transform(X_cudf)
res = res.compute()
assert res.shape[0] == nrows and res.shape[1] == 30
def test_pca_fit_transform_fp32_noncomponents(nrows, ncols, n_parts, client):
# Tests the case when n_components is not passed for MG scenarios
from cuml.dask.decomposition import PCA as daskPCA
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)
cupca = daskPCA(whiten=False)
res = cupca.fit_transform(X_cudf)
res = res.compute()
assert res.shape[0] == nrows and res.shape[1] == 20
def test_pca_fit(nrows, ncols, n_parts, cluster):
client = Client(cluster)
try:
from cuml.dask.decomposition import PCA as daskPCA
from sklearn.decomposition import PCA
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)
print(str(X_cudf.head(3)))
try:
cupca = daskPCA(n_components=5, whiten=True)
cupca.fit(X_cudf)
except Exception as e:
print(str(e))
X = X_cudf.compute().to_pandas().values
skpca = PCA(n_components=5, whiten=True, svd_solver="full")
skpca.fit(X)
from cuml.test.utils import array_equal
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(cupca, attr))
if type(cuml_res) == np.ndarray:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(skpca, attr)
assert array_equal(cuml_res, skl_res, 1e-3, with_sign=with_sign)
finally:
client.close()
def test_pca_fit_transform_fp32(nrows, ncols, n_parts, cluster):
client = Client(cluster)
try:
from cuml.dask.decomposition import PCA as daskPCA
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)
cupca = daskPCA(n_components=20, whiten=True)
cupca.fit_transform(X_cudf)
finally:
client.close()
def test_pca_fit_transform_fp64(nrows, ncols, n_parts, cluster):
client = Client(cluster)
try:
from cuml.dask.decomposition import PCA as daskPCA
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.float64)
wait(X_cudf)
cupca = daskPCA(n_components=30, whiten=False)
cupca.fit_transform(X_cudf)
finally:
client.close()
