def test_dbscan():
import cudf
from cuml import DBSCAN
# Create and populate a GPU DataFrame
gdf_float = cudf.DataFrame()
gdf_float['0'] = [1.0, 2.0, 5.0]
gdf_float['1'] = [4.0, 2.0, 1.0]
gdf_float['2'] = [4.0, 2.0, 1.0]
# Setup and fit clusters
dbscan_float = DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(gdf_float)
actualOutput = str(dbscan_float.labels_)
expectedOutput = """0 0
1 1
2 2
dtype: int32"""
assert actualOutput == expectedOutput
def cluster(gdf, eps, minSamples):
# cpu clustering
# clusterer = hdbscan.HDBSCAN(min_cluster_size=15, metric='euclidean', cluster_selection_method='eom')
# clusterer.fit(data)
logging.info("cuml.SCANDB Clustering - eps=%0.3f, samples=%d", eps, minSamples)
# GPU clustering
result = DBSCAN(eps=eps,
min_samples=minSamples,
verbose=False,
calc_core_sample_indices=True,
output_type='cudf').fit(gdf)
metric1 = result.labels_.max()
metric2 = len(result.core_sample_indices_)
mlflow.log_metric('labels', metric1)
mlflow.log_metric('core_samples', metric2)
gpu_mem(0)
logging.debug("cuml.DBSCAN - dims: %d, max distance: %0.3f, min samples: %d, labels: %d, core_samples: %d",
ndims, eps, minSamples, metric1, metric2)
type=float,
default=10.,
help='Radius of neighborhood of a point')
parser.add_argument('-m',
'--min-samples',
default=5,
type=int,
help='The minimum number of samples required in a '
'neighborhood to consider a point a core point')
params = bench.parse_args(parser)
# Load generated data
X, _, _, _ = bench.load_data(params)
# Create our clustering object
dbscan = DBSCAN(eps=params.eps, min_samples=params.min_samples)
# Time fit
time, _ = bench.measure_function_time(dbscan.fit, X, params=params)
labels = dbscan.labels_
X_host = bench.convert_to_numpy(X)
labels_host = bench.convert_to_numpy(labels)
acc = davies_bouldin_score(X_host, labels_host)
params.n_clusters = len(set(labels_host)) - (1 if -1 in labels_host else 0)
bench.print_output(library='cuml',
algorithm='dbscan',
stages=['training'],
params=params,