def test_output_type_context_mgr(global_output_type, context_type):
dataset = get_small_dataset('numba')
test_type = 'cupy' if global_output_type != 'cupy' else 'numpy'
cuml.set_global_output_type(test_type)
# use cuml context manager
with cuml.using_output_type(context_type):
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
if context_type == 'numba':
assert is_cuda_array(res)
else:
assert isinstance(res, test_output_types[context_type])
# use cuml again outside the context manager
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
assert isinstance(res, test_output_types[test_type])
def test_default_global_output_type(input_type):
dataset = get_small_dataset(input_type)
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
if input_type == 'numba':
assert is_cuda_array(res)
else:
assert isinstance(res, test_output_types[input_type])
def run_gpu(X, eps, min_samples):
# Transfer inputs to GPU
X = cp.array(X)
# Begin computation
t0 = time.time()
mean = cp.mean(X, axis=0)
std = cp.std(X, axis=0)
cp.subtract(X, mean, out=X)
cp.divide(X, std, out=X)
print('Preprocessing:', time.time() - t0)
# Run DBSCAN
db = cuml.DBSCAN(eps=eps, min_samples=min_samples)
db = db.fit(X)
labels = db.labels_
# Transfer outputs to CPU
# labels = labels.to_pandas().to_numpy()
labels = cp.asnumpy(labels)
return labels
solver_models = dict(CD=cuml.CD(), SGD=cuml.SGD(eta0=0.005))
cluster_models = dict(KMeans=cuml.KMeans())
decomposition_models = dict(
PCA=cuml.PCA(),
TruncatedSVD=cuml.TruncatedSVD(),
)
decomposition_models_xfail = dict(
GaussianRandomProjection=cuml.GaussianRandomProjection(),
SparseRandomProjection=cuml.SparseRandomProjection())
neighbor_models = dict(NearestNeighbors=cuml.NearestNeighbors())
dbscan_model = dict(DBSCAN=cuml.DBSCAN())
umap_model = dict(UMAP=cuml.UMAP())
def unit_param(*args, **kwargs):
return pytest.param(*args, **kwargs, marks=pytest.mark.unit)
def quality_param(*args, **kwargs):
return pytest.param(*args, **kwargs, marks=pytest.mark.quality)
def stress_param(*args, **kwargs):
return pytest.param(*args, **kwargs, marks=pytest.mark.stress)
cluster_models = {"KMeans": lambda: cuml.KMeans()}
decomposition_models = {
"PCA": lambda: cuml.PCA(),
"TruncatedSVD": lambda: cuml.TruncatedSVD(),
}
decomposition_models_xfail = {
"GaussianRandomProjection": lambda: cuml.GaussianRandomProjection(),
"SparseRandomProjection": lambda: cuml.SparseRandomProjection()
}
neighbor_models = {"NearestNeighbors": lambda: cuml.NearestNeighbors()}
dbscan_model = {"DBSCAN": lambda: cuml.DBSCAN()}
umap_model = {"UMAP": lambda: cuml.UMAP()}
rf_models = {
"rfc": lambda: cuml.RandomForestClassifier(),
"rfr": lambda: cuml.RandomForestRegressor()
}
all_models = {
**regression_models,
**solver_models,
**cluster_models,
**decomposition_models,
**decomposition_models_xfail,
**neighbor_models,
"""Load a dataset into GPU memory"""
import cudf
import io, requests
# download CSV file from github
url = "https://github.com/plotly/datasets/raw/master/tips.csv"
content = requests.get(url).content.decode('utf-8')
# read CSV from memory
tips_df = cudf.read_csv(io.StringIO(content))
tips_df['tip_percentage'] = tips_df['tip']/tips_df['total_bill']*100
# display average tip by dining party size
print(tips_df.groupby('size').tip_percentage.mean())
import cuml
# Create and populate a GPU DataFrame
df_float = cudf.DataFrame()
df_float['0'] = [1.0, 2.0, 5.0]
df_float['1'] = [4.0, 2.0, 1.0]
df_float['2'] = [4.0, 2.0, 1.0]
# Setup and fit clusters
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(df_float)
print(dbscan_float.labels_)
decomposition_models = {
"PCA": lambda: cuml.PCA(),
"TruncatedSVD": lambda: cuml.TruncatedSVD(),
}
decomposition_models_xfail = {
"GaussianRandomProjection": lambda: cuml.GaussianRandomProjection(),
"SparseRandomProjection": lambda: cuml.SparseRandomProjection()
}
neighbor_models = {
"NearestNeighbors": lambda: cuml.NearestNeighbors()
}
dbscan_model = {
"DBSCAN": lambda: cuml.DBSCAN()
}
umap_model = {
"UMAP": lambda: cuml.UMAP()
}
rf_classification_model = {
"rfc": lambda: cuml.RandomForestClassifier()
}
rf_regression_model = {
"rfr": lambda: cuml.RandomForestRegressor()
}