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,
functions=['DBSCAN'],
times=[time],
metrics=[acc],
metric_type='davies_bouldin_score',
data=[X],
alg_instance=dbscan)
init=X_init,
max_samples_per_batch=params.samples_per_batch)
alg.fit(X)
return alg
# Time fit
fit_time, kmeans = measure_function_time(kmeans_fit, X_train, params=params)
train_predict = kmeans.predict(X_train)
# Time predict
predict_time, test_predict = measure_function_time(kmeans.predict,
X_test,
params=params)
X_train_host = convert_to_numpy(X_train)
train_predict_host = convert_to_numpy(train_predict)
acc_train = davies_bouldin_score(X_train_host, train_predict_host)
X_test_host = convert_to_numpy(X_test)
test_predict_host = convert_to_numpy(test_predict)
acc_test = davies_bouldin_score(X_test_host, test_predict_host)
print_output(library='cuml',
algorithm='kmeans',
stages=['training', 'prediction'],
columns=columns,
params=params,
functions=['KMeans.fit', 'KMeans.predict'],
times=[fit_time, predict_time],
params = parse_args(parser)
# Load generated data
X, _, _, _ = load_data(params)
# Create our clustering object
dbscan = DBSCAN(eps=params.eps, min_samples=params.min_samples)
columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size',
'n_clusters', 'time')
# Time fit
time, _ = measure_function_time(dbscan.fit, X, params=params)
labels = dbscan.labels_
X_host = convert_to_numpy(X)
labels_host = 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)
print_output(library='cuml',
algorithm='dbscan',
stages=['training'],
columns=columns,
params=params,
functions=['DBSCAN'],
times=[time],
accuracies=[acc],
accuracy_type='davies_bouldin_score',
data=[X],