def test_n_init_cluster_consistency(random_state):
nclusters = 8
X, y = get_data_consistency_test()
cuml_kmeans = cuml.KMeans(verbose=0,
init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
initial_clusters = cuml_kmeans.cluster_centers_
cuml_kmeans = cuml.KMeans(verbose=0,
init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
assert array_equal(initial_clusters, cuml_kmeans.cluster_centers_)
def test_n_init_cluster_consistency(random_state):
cluster_std = 1.0
nrows = 100000
ncols = 100
nclusters = 8
X, y = make_blobs(nrows,
ncols,
nclusters,
cluster_std=cluster_std,
shuffle=False,
random_state=0)
cuml_kmeans = cuml.KMeans(verbose=0,
init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
initial_clusters = cuml_kmeans.cluster_centers_
cuml_kmeans = cuml.KMeans(verbose=0,
init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
assert array_equal(initial_clusters, cuml_kmeans.cluster_centers_)
def test_score(nrows, ncols, nclusters):
X, y = make_blobs(nrows,
ncols,
nclusters,
cluster_std=0.01,
random_state=10)
cuml_kmeans = cuml.KMeans(verbose=1,
init="k-means||",
n_clusters=nclusters,
random_state=10)
cuml_kmeans.fit(X)
actual_score = cuml_kmeans.score(X)
predictions = cuml_kmeans.predict(X)
centers = cp.array(cuml_kmeans.cluster_centers_.as_gpu_matrix())
expected_score = 0
for idx, label in enumerate(predictions):
x = X[idx]
y = centers[label]
dist = np.sqrt(np.sum((x - y)**2))
expected_score += dist**2
assert actual_score + SCORE_EPS \
>= (-1*expected_score) \
>= actual_score - SCORE_EPS
def test_rand_index_score(name, nrows):
default_base = {
'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3
}
pat = get_pattern(name, nrows)
params = default_base.copy()
params.update(pat[1])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'])
X, y = pat[0]
X = StandardScaler().fit_transform(X)
cu_y_pred, _ = fit_predict(cuml_kmeans, 'cuml_Kmeans', X)
cu_score = cu_ars(y, cu_y_pred)
cu_score_using_sk = sk_ars(y, cu_y_pred)
assert array_equal(cu_score, cu_score_using_sk)
def test_weighted_kmeans(nrows, ncols, nclusters, max_weight, random_state):
# Using fairly high variance between points in clusters
cluster_std = 1.0
np.random.seed(random_state)
# set weight per sample to be from 1 to max_weight
wt = np.random.randint(1, high=max_weight, size=nrows)
X, y = make_blobs(nrows,
ncols,
nclusters,
cluster_std=cluster_std,
shuffle=False,
random_state=0)
cuml_kmeans = cuml.KMeans(init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X, sample_weight=wt)
cu_score = cuml_kmeans.score(X)
sk_kmeans = cluster.KMeans(random_state=random_state, n_clusters=nclusters)
sk_kmeans.fit(cp.asnumpy(X), sample_weight=wt)
sk_score = sk_kmeans.score(cp.asnumpy(X))
assert abs(cu_score - sk_score) <= cluster_std * 1.5
def test_kmeans_sequential_plus_plus_init(nrows, ncols, nclusters,
random_state):
# Using fairly high variance between points in clusters
cluster_std = 1.0
X, y = make_blobs(nrows,
ncols,
nclusters,
cluster_std=cluster_std,
shuffle=False,
random_state=0)
cuml_kmeans = cuml.KMeans(verbose=0,
init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
cu_score = cuml_kmeans.score(X)
kmeans = cluster.KMeans(random_state=random_state, n_clusters=nclusters)
kmeans.fit(X.copy_to_host())
sk_score = kmeans.score(X.copy_to_host())
assert abs(cu_score - sk_score) <= cluster_std * 1.5
def test_kmeans_sklearn_comparison_default(name, nrows):
default_base = {
'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3
}
pat = get_pattern(name, nrows)
params = default_base.copy()
params.update(pat[1])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'],
random_state=12,
n_init=10,
output_type='numpy')
X, y = pat[0]
X = StandardScaler().fit_transform(X)
cu_y_pred = cuml_kmeans.fit_predict(X)
cu_score = adjusted_rand_score(cu_y_pred, y)
kmeans = cluster.KMeans(random_state=12, n_clusters=params['n_clusters'])
sk_y_pred = kmeans.fit_predict(X)
sk_score = adjusted_rand_score(sk_y_pred, y)
assert sk_score - 1e-2 <= cu_score <= sk_score + 1e-2
def test_score(nrows, ncols, nclusters):
X, y = make_blobs(int(nrows),
ncols,
nclusters,
cluster_std=0.01,
shuffle=False,
random_state=10)
cuml_kmeans = cuml.KMeans(init="k-means||",
n_clusters=nclusters,
random_state=10,
output_type='numpy')
cuml_kmeans.fit(X)
actual_score = cuml_kmeans.score(X)
predictions = cuml_kmeans.predict(X)
centers = cuml_kmeans.cluster_centers_
expected_score = 0
for idx, label in enumerate(predictions):
x = X[idx]
y = cp.array(centers[label])
dist = cp.sqrt(cp.sum((x - y)**2))
expected_score += dist**2
assert actual_score + SCORE_EPS \
>= (-1*expected_score) \
>= actual_score - SCORE_EPS
def test_traditional_kmeans_plus_plus_init(nrows, ncols, nclusters,
random_state):
# Using fairly high variance between points in clusters
cluster_std = 1.0
X, y = make_blobs(int(nrows),
ncols,
nclusters,
cluster_std=cluster_std,
shuffle=False,
random_state=0)
cuml_kmeans = cuml.KMeans(init="k-means++",
n_clusters=nclusters,
n_init=10,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
cu_score = cuml_kmeans.score(X)
kmeans = cluster.KMeans(random_state=random_state, n_clusters=nclusters)
kmeans.fit(cp.asnumpy(X))
sk_score = kmeans.score(cp.asnumpy(X))
assert abs(cu_score - sk_score) <= cluster_std * 1.5
def test_kmeans_sklearn_comparison_default(name, nrows):
default_base = {'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3}
pat = get_pattern(name, nrows)
params = default_base.copy()
params.update(pat[1])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'])
X, y = pat[0]
X = StandardScaler().fit_transform(X)
cu_y_pred = cuml_kmeans.fit_predict(X)
cu_score = adjusted_rand_score(cu_y_pred, y)
kmeans = cluster.KMeans(random_state=12, n_clusters=params['n_clusters'])
sk_y_pred = kmeans.fit_predict(X)
sk_score = adjusted_rand_score(sk_y_pred, y)
# cuML score should be in a close neighborhood around scikit-learn's
assert sk_score - 0.03 <= cu_score <= sk_score + 0.03
def test_score(nrows, ncols, nclusters, random_state):
X, y = make_blobs(int(nrows),
ncols,
nclusters,
cluster_std=1.0,
shuffle=False,
random_state=0)
cuml_kmeans = cuml.KMeans(init="k-means||",
n_clusters=nclusters,
random_state=random_state,
output_type='numpy')
cuml_kmeans.fit(X)
actual_score = cuml_kmeans.score(X)
predictions = cuml_kmeans.predict(X)
centers = cuml_kmeans.cluster_centers_
expected_score = 0.0
for idx, label in enumerate(predictions):
x = X[idx, :]
y = cp.array(centers[label, :], dtype=cp.float32)
sq_euc_dist = cp.sum(cp.square((x - y)))
expected_score += sq_euc_dist
expected_score *= -1
cp.testing.assert_allclose(actual_score,
expected_score,
atol=0.1,
rtol=1e-5)
def re_cluster(self, gdf, new_figerprints=None, new_chembl_ids=None):
if gdf.shape[0] == 0:
return None
# Before reclustering remove all columns that may interfere
ids = gdf['id']
chembl_ids = gdf['chembl_id']
gdf.drop(['x', 'y', 'cluster', 'id', 'chembl_id'], axis=1, inplace=True)
if new_figerprints is not None and new_chembl_ids is not None:
# Add new figerprints and chEmblIds before reclustering
if self.pca:
new_figerprints = self.pca.transform(new_figerprints)
if self.enable_gpu:
fp_df = cudf.DataFrame(new_figerprints, \
index=[idx for idx in range(self.orig_df.shape[0], self.orig_df.shape[0] + len(new_figerprints))],
columns=gdf.columns)
else:
fp_df = pandas.DataFrame(new_figerprints, \
index=[idx for idx in range(self.orig_df.shape[0], self.orig_df.shape[0] + len(new_figerprints))],
columns=gdf.columns)
gdf = gdf.append(fp_df, ignore_index=True)
# Update original dataframe for it to work on reload
fp_df['id'] = fp_df.index
self.orig_df = self.orig_df.append(fp_df, ignore_index=True)
chembl_ids = chembl_ids.append(
cudf.Series(new_chembl_ids), ignore_index=True)
ids = ids.append(fp_df['id'], ignore_index=True)
self.chembl_ids.extend(new_chembl_ids)
del fp_df
if self.enable_gpu:
kmeans_float = cuml.KMeans(n_clusters=self.n_clusters)
else:
kmeans_float = sklearn.cluster.KMeans(n_clusters=self.n_clusters)
kmeans_float.fit(gdf)
Xt = self.umap.fit_transform(gdf)
# Add back the column required for plotting and to correlating data
# between re-clustering
if self.enable_gpu:
gdf.add_column('x', Xt[0].to_array())
gdf.add_column('y', Xt[1].to_array())
gdf.add_column('cluster', kmeans_float.labels_.to_gpu_array())
gdf.add_column('chembl_id', chembl_ids)
gdf.add_column('id', ids)
else:
gdf['x'] = Xt[:,0]
gdf['y'] = Xt[:,1]
gdf['cluster'] = kmeans_float.labels_
gdf['chembl_id'] = chembl_ids
gdf['id'] = ids
return gdf
def KMeans(data, cluster):
warnings.filterwarnings('ignore')
data_pack = torch.utils.dlpack.to_dlpack(data)
data_df = cudf.from_dlpack(data_pack)
model = cuml.KMeans(n_clusters=cluster)
result = model.fit(data_df)
labels = torch.utils.dlpack.from_dlpack(result.labels_.to_dlpack())
warnings.filterwarnings('once')
return labels
def test_kmeans_sklearn_comparison(name, nrows):
default_base = {
'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3
}
pat = get_pattern(name, nrows)
params = default_base.copy()
params.update(pat[1])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'])
X, y = pat[0]
X = StandardScaler().fit_transform(X)
cu_y_pred = cuml_kmeans.fit_predict(X).to_array()
if nrows < 500000:
kmeans = cluster.KMeans(n_clusters=params['n_clusters'])
sk_y_pred = kmeans.fit_predict(X)
# Noisy circles clusters are rotated in the results,
# since we are comparing 2 we just need to compare that both clusters
# have approximately the same number of points.
calculation = (np.sum(sk_y_pred) - np.sum(cu_y_pred)) / len(sk_y_pred)
score_test = (cuml_kmeans.score(X) - kmeans.score(X)) < 2e-3
if name == 'noisy_circles':
assert (calculation < 4e-3) and score_test
else:
if name == 'aniso':
# aniso dataset border points tend to differ in the frontier
# between clusters when compared to sklearn
tol = 2e-2
else:
# We allow up to 5 points to be different for the other
# datasets to be robust to small behavior changes
# between library versions/ small changes. Visually it is
# very clear that the algorithm work. Will add option
# to plot if desired in a future version.
tol = 1e-2
assert (clusters_equal(
sk_y_pred, cu_y_pred, params['n_clusters'],
tol=tol)) and score_test
def _query8(self):
self._loadTables('query8')
train = {}
for i in range(12):
train['c{}'.format(i)] = np.random.rand(1000)
train = cudf.DataFrame(train)
kmeans = cuml.KMeans(n_clusters=8)
kmeans.fit(train)
rideIndex = self._createIndex(
self.rideTable,
'ride.start',
)
locationFilter = self.locationTable[
self.locationTable['loc.locationId'] == 0]
locationPolygon = self._createBox(
locationFilter,
'loc.bounds',
)
startTime = time.time()
(joinRide,
numbaTime) = self._spatialJoinDist(self.rideTable, locationFilter,
'ride.start', 'loc.bounds',
rideIndex, locationPolygon, 0.0)
featureName = [
'ride.c0', 'ride.c1', 'ride.c2', 'ride.c3', 'ride.c4', 'ride.c5',
'ride.c6', 'ride.c7', 'ride.c8', 'ride.c9', 'ride.c10', 'ride.c11'
]
join0 = joinRide.merge(self.riderTable,
left_on='ride.riderId',
right_on='rider.riderId')
groupRider = join0.groupby(['rider.riderId'], )[featureName].mean()
groupRider['cluster'] = kmeans.predict(groupRider)
endTime = time.time()
groupRider.to_csv(
'query8_gpu.csv',
index=False,
)
return endTime - startTime - numbaTime
def test_all_kmeans_params(n_rows, n_clusters, max_iter, init,
oversampling_factor, max_samples_per_batch):
np.random.seed(0)
X = np.random.rand(1000, 10)
if init == 'preset':
init = np.random.rand(n_clusters, 10)
cuml_kmeans = cuml.KMeans(n_clusters=n_clusters,
max_iter=max_iter,
init=init,
oversampling_factor=oversampling_factor,
max_samples_per_batch=max_samples_per_batch)
cuml_kmeans.fit_predict(X)
def test_kmeans_clusters_blobs(nrows, ncols, nclusters,
random_state, cluster_std):
X, y = make_blobs(int(nrows), ncols, nclusters,
cluster_std=cluster_std,
shuffle=False,
random_state=random_state,)
cuml_kmeans = cuml.KMeans(init="k-means||",
n_clusters=nclusters,
random_state=random_state,
output_type='numpy')
preds = cuml_kmeans.fit_predict(X)
assert adjusted_rand_score(cp.asnumpy(preds), cp.asnumpy(y)) >= 0.99
def test_all_kmeans_params(n_clusters, max_iter, init, oversampling_factor,
max_samples_per_batch, random_state):
np.random.seed(0)
X = np.random.rand(1000, 10)
if init == 'preset':
init = np.random.rand(n_clusters, 10)
cuml_kmeans = cuml.KMeans(n_clusters=n_clusters,
max_iter=max_iter,
init=init,
random_state=random_state,
oversampling_factor=oversampling_factor,
max_samples_per_batch=max_samples_per_batch,
output_type='cupy')
cuml_kmeans.fit_predict(X)
def test_kmeans_sklearn_comparison(name):
default_base = {
'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3
}
pat = get_pattern(name, 10000)
params = default_base.copy()
params.update(pat[1])
kmeans = cluster.KMeans(n_clusters=params['n_clusters'])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'])
X, y = pat[0]
X = StandardScaler().fit_transform(X)
clustering_algorithms = (
('sk_Kmeans', kmeans),
('cuml_Kmeans', cuml_kmeans),
)
sk_y_pred, _ = fit_predict(clustering_algorithms[0][1],
clustering_algorithms[0][0], X)
cu_y_pred, _ = fit_predict(clustering_algorithms[1][1],
clustering_algorithms[1][0], X)
# Noisy circles clusters are rotated in the results,
# since we are comparing 2 we just need to compare that both clusters
# have approximately the same number of points.
if name == 'noisy_circles':
assert (np.sum(sk_y_pred) - np.sum(cu_y_pred)) / len(sk_y_pred) < 2e-3
else:
assert clusters_equal(sk_y_pred, cu_y_pred, params['n_clusters'])
def test_kmeans_sklearn_comparison(name, nrows):
default_base = {
'quantile': .3,
'eps': .3,
'damping': .9,
'preference': -200,
'n_neighbors': 10,
'n_clusters': 3
}
pat = get_pattern(name, nrows)
params = default_base.copy()
params.update(pat[1])
cuml_kmeans = cuml.KMeans(n_clusters=params['n_clusters'])
X, y = pat[0]
X = StandardScaler().fit_transform(X)
cu_y_pred, _ = fit_predict(cuml_kmeans, 'cuml_Kmeans', X)
if nrows < 500000:
kmeans = cluster.KMeans(n_clusters=params['n_clusters'])
sk_y_pred, _ = fit_predict(kmeans, 'sk_Kmeans', X)
# Noisy circles clusters are rotated in the results,
# since we are comparing 2 we just need to compare that both clusters
# have approximately the same number of points.
calculation = (np.sum(sk_y_pred) - np.sum(cu_y_pred)) / len(sk_y_pred)
print(cuml_kmeans.score(X), kmeans.score(X))
score_test = (cuml_kmeans.score(X) - kmeans.score(X)) < 2e-3
if name == 'noisy_circles':
assert (calculation < 2e-3) and score_test
else:
assert (clusters_equal(sk_y_pred, cu_y_pred,
params['n_clusters'])) and score_test
import cuml
from cuml.test.utils import array_equal
import numpy as np
from sklearn.datasets import load_iris
from sklearn.datasets import make_regression
import pickle
from sklearn.manifold.t_sne import trustworthiness
regression_models = dict(LinearRegression=cuml.LinearRegression(),
Lasso=cuml.Lasso(),
Ridge=cuml.Ridge(),
ElasticNet=cuml.ElasticNet())
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())
fit_intercept),
"Lasso":
lambda fit_intercept=True: cuml.Lasso(fit_intercept=fit_intercept),
"Ridge":
lambda fit_intercept=True: cuml.Ridge(fit_intercept=fit_intercept),
"ElasticNet":
lambda fit_intercept=True: cuml.ElasticNet(fit_intercept=fit_intercept)
}
solver_models = {
"CD": lambda: cuml.CD(),
"SGD": lambda: cuml.SGD(eta0=0.005),
"QN": lambda: cuml.QN(loss="softmax")
}
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()}
if enable_gpu:
pca = cuml.PCA(n_components=pca_components)
else:
pca = sklearn.decomposition.PCA(n_components=pca_components)
df_fingerprints = pca.fit_transform(df_fingerprints)
print('Runtime PCA time (hh:mm:ss.ms) {}'.format(datetime.now() -
task_start_time))
else:
pca = False
print('PCA has been skipped')
task_start_time = datetime.now()
n_clusters = 7
if enable_gpu:
kmeans_float = cuml.KMeans(n_clusters=n_clusters)
else:
kmeans_float = sklearn.cluster.KMeans(n_clusters=n_clusters)
kmeans_float.fit(df_fingerprints)
print('Runtime Kmeans time (hh:mm:ss.ms) {}'.format(datetime.now() -
task_start_time))
# UMAP
task_start_time = datetime.now()
if enable_gpu:
umap = cuml.UMAP(n_neighbors=100, a=1.0, b=1.0, learning_rate=1.0)
else:
umap = umap.UMAP()
Xt = umap.fit_transform(df_fingerprints)
print('Runtime UMAP time (hh:mm:ss.ms) {}'.format(datetime.now() -
def _cluster(self, embedding, n_pca):
"""
Generates UMAP transformation on Kmeans labels generated from
molecular fingerprints.
"""
if hasattr(embedding, 'compute'):
embedding = embedding.compute()
embedding = embedding.reset_index()
# Before reclustering remove all columns that may interfere
embedding, prop_series = self._remove_non_numerics(embedding)
self.n_molecules, n_obs = embedding.shape
if self.context.is_benchmark:
molecular_embedding_sample, spearman_index = self._random_sample_from_arrays(
embedding, n_samples=self.n_spearman)
if n_pca and n_obs > n_pca:
with MetricsLogger('pca', self.n_molecules) as ml:
if self.pca == None:
self.pca = cuml.PCA(n_components=n_pca)
self.pca.fit(embedding)
embedding = self.pca.transform(embedding)
with MetricsLogger('kmeans', self.n_molecules) as ml:
if self.n_molecules < MIN_RECLUSTER_SIZE:
raise Exception(
'Reclustering less than %d molecules is not supported.' %
MIN_RECLUSTER_SIZE)
kmeans_cuml = cuml.KMeans(n_clusters=self.n_clusters)
kmeans_cuml.fit(embedding)
kmeans_labels = kmeans_cuml.predict(embedding)
ml.metric_name = 'silhouette_score'
ml.metric_func = batched_silhouette_scores
ml.metric_func_kwargs = {}
ml.metric_func_args = (None, None)
if self.context.is_benchmark:
(embedding_sample,
kmeans_labels_sample), _ = self._random_sample_from_arrays(
embedding, kmeans_labels, n_samples=self.n_silhouette)
ml.metric_func_args = (embedding_sample, kmeans_labels_sample)
with MetricsLogger('umap', self.n_molecules) as ml:
umap = cuml.manifold.UMAP()
Xt = umap.fit_transform(embedding)
ml.metric_name = 'spearman_rho'
ml.metric_func = self._compute_spearman_rho
ml.metric_func_args = (None, None)
if self.context.is_benchmark:
X_train_sample, _ = self._random_sample_from_arrays(
embedding, index=spearman_index)
ml.metric_func_args = (molecular_embedding_sample,
X_train_sample)
# Add back the column required for plotting and to correlating data
# between re-clustering
embedding['cluster'] = kmeans_labels
embedding['x'] = Xt[0]
embedding['y'] = Xt[1]
# Add back the prop columns
for col in prop_series.keys():
embedding[col] = prop_series[col]
return embedding
regression_models = {
"LinearRegression": lambda: cuml.LinearRegression(),
"Lasso": lambda: cuml.Lasso(),
"Ridge": lambda: cuml.Ridge(),
"ElasticNet": lambda: cuml.ElasticNet()
}
solver_models = {
"CD": lambda: cuml.CD(),
"SGD": lambda: cuml.SGD(eta0=0.005)
}
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()
}