def test_haversine_fails_high_dimensions():
data = np.array([[0., 1., 2.], [3., 4., 5.]])
cunn = cuKNN(metric='haversine', n_neighbors=2, algorithm='brute')
cunn.fit(data).kneighbors(data)
def test_neighborhood_predictions(nrows, ncols, n_neighbors, n_clusters,
datatype, algo):
if algo == "ivfpq":
pytest.xfail("""See Memory access error in IVFPQ :
https://github.com/rapidsai/cuml/issues/3318""")
if not has_scipy():
pytest.skip('Skipping test_neighborhood_predictions because ' +
'Scipy is missing')
X, y = make_blobs(n_samples=nrows,
centers=n_clusters,
n_features=ncols,
random_state=0)
if datatype == "dataframe":
X = cudf.DataFrame(X)
knn_cu = cuKNN(algorithm=algo)
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
del knn_cu
gc.collect()
if datatype == "dataframe":
assert isinstance(neigh_ind, cudf.DataFrame)
neigh_ind = neigh_ind.as_gpu_matrix().copy_to_host()
else:
assert isinstance(neigh_ind, cp.core.core.ndarray)
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_ivfpq_pred(nrows, ncols, n_neighbors, nlist, M, n_bits,
usePrecomputedTables):
algo_params = {
'nlist': nlist,
'nprobe': int(nlist * 0.2),
'M': M,
'n_bits': n_bits,
'usePrecomputedTables': usePrecomputedTables
}
X, y = make_blobs(n_samples=nrows,
centers=5,
n_features=ncols,
random_state=0)
knn_cu = cuKNN(algorithm="ivfpq", algo_params=algo_params)
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
del knn_cu
gc.collect()
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_cuml_against_sklearn(input_type, nrows, n_feats, k):
X, _ = make_blobs(n_samples=nrows, n_features=n_feats, random_state=0)
knn_sk = skKNN(metric="euclidean")
knn_sk.fit(X)
D_sk, I_sk = knn_sk.kneighbors(X, k)
if input_type == "dataframe":
X = cudf.DataFrame.from_gpu_matrix(rmm.to_device(X))
knn_cu = cuKNN()
knn_cu.fit(X)
D_cuml, I_cuml = knn_cu.kneighbors(X, k)
if input_type == "dataframe":
assert isinstance(D_cuml, cudf.DataFrame)
assert isinstance(I_cuml, cudf.DataFrame)
D_cuml_arr = D_cuml.as_gpu_matrix().copy_to_host()
I_cuml_arr = I_cuml.as_gpu_matrix().copy_to_host()
else:
assert isinstance(D_cuml, np.ndarray)
assert isinstance(I_cuml, np.ndarray)
D_cuml_arr = D_cuml
I_cuml_arr = I_cuml
assert array_equal(D_cuml_arr, D_sk, 1e-2, with_sign=True)
assert I_cuml_arr.all() == I_sk.all()
def test_neighborhood_predictions(nrows, ncols, n_neighbors, n_clusters,
datatype):
X, y = make_blobs(n_samples=nrows,
centers=n_clusters,
n_features=ncols,
random_state=0)
X = X.astype(np.float32)
if datatype == "dataframe":
X = cudf.DataFrame.from_gpu_matrix(rmm.to_device(X))
knn_cu = cuKNN()
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
if datatype == "dataframe":
assert isinstance(neigh_ind, cudf.DataFrame)
neigh_ind = neigh_ind.as_gpu_matrix().copy_to_host()
else:
assert isinstance(neigh_ind, np.ndarray)
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_ivfsq_pred(qtype, encodeResidual, nrows, ncols, n_neighbors, nlist):
algo_params = {
'nlist': nlist,
'nprobe': nlist * 0.25,
'qtype': qtype,
'encodeResidual': encodeResidual
}
X, y = make_blobs(n_samples=nrows,
centers=5,
n_features=ncols,
random_state=0)
logger.set_level(logger.level_debug)
knn_cu = cuKNN(algorithm="ivfsq", algo_params=algo_params)
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
del knn_cu
gc.collect()
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_ivfpq_pred(nrows, ncols, n_neighbors, nlist, M, n_bits,
usePrecomputedTables):
pytest.xfail("Warning: IVFPQ might be unstable in this "
"version of cuML. This is due to a known issue "
"in the FAISS release that this cuML version "
"is linked to. (see FAISS issue #1421)")
algo_params = {
'nlist': nlist,
'nprobe': int(nlist * 0.2),
'M': M,
'n_bits': n_bits,
'usePrecomputedTables': usePrecomputedTables
}
X, y = make_blobs(n_samples=nrows,
centers=5,
n_features=ncols,
random_state=0)
knn_cu = cuKNN(algorithm="ivfpq", algo_params=algo_params)
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
del knn_cu
gc.collect()
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_neighborhood_predictions(nrows, ncols, n_neighbors, n_clusters,
datatype):
if not has_scipy():
pytest.skip('Skipping test_neighborhood_predictions because ' +
'Scipy is missing')
X, y = make_blobs(n_samples=nrows,
centers=n_clusters,
n_features=ncols,
random_state=0)
X = X.astype(np.float32)
if datatype == "dataframe":
X = cudf.DataFrame(X)
knn_cu = cuKNN()
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
if datatype == "dataframe":
assert isinstance(neigh_ind, cudf.DataFrame)
neigh_ind = neigh_ind.as_gpu_matrix().copy_to_host()
else:
assert isinstance(neigh_ind, np.ndarray)
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_haversine(n_neighbors):
hoboken_nj = [40.745255, -74.034775]
port_hueneme_ca = [34.155834, -119.202789]
auburn_ny = [42.933334, -76.566666]
league_city_tx = [29.499722, -95.089722]
tallahassee_fl = [30.455000, -84.253334]
aurora_il = [41.763889, -88.29001]
data = np.array([
hoboken_nj, port_hueneme_ca, auburn_ny, league_city_tx, tallahassee_fl,
aurora_il
])
data = data * math.pi / 180
pw_dists = pairwise_distances(data, metric='haversine')
cunn = cuKNN(metric='haversine',
n_neighbors=n_neighbors,
algorithm='brute')
dists, inds = cunn.fit(data).kneighbors(data)
argsort = np.argsort(pw_dists, axis=1)
for i in range(pw_dists.shape[0]):
cpu_ordered = pw_dists[i, argsort[i]]
cp.testing.assert_allclose(cpu_ordered[:n_neighbors],
dists[i],
atol=1e-4,
rtol=1e-4)
def test_nn_downcast_fails(input_type, nrows, n_feats):
X, y = make_blobs(n_samples=nrows, n_features=n_feats, random_state=0)
knn_cu = cuKNN()
if input_type == 'dataframe':
X_pd = pd.DataFrame({'fea%d' % i: X[0:, i] for i in range(X.shape[1])})
X_cudf = cudf.DataFrame.from_pandas(X_pd)
knn_cu.fit(X_cudf, convert_dtype=True)
with pytest.raises(Exception):
knn_cu.fit(X, convert_dtype=False)
# Test fit() fails when downcast corrupted data
X = np.array([[np.finfo(np.float32).max]], dtype=np.float64)
knn_cu = cuKNN()
with pytest.raises(Exception):
knn_cu.fit(X, convert_dtype=False)
def test_nn_downcast_fails(input_type):
X = np.array([[1.0], [50.0], [51.0]], dtype=np.float64)
# Test fit() fails with double precision when should_downcast set to False
knn_cu = cuKNN()
if input_type == 'dataframe':
X = cudf.DataFrame.from_pandas(pd.DataFrame(X))
with pytest.raises(Exception):
knn_cu.fit(X, should_downcast=False)
# Test fit() fails when downcast corrupted data
X = np.array([[np.finfo(np.float32).max]], dtype=np.float64)
knn_cu = cuKNN()
if input_type == 'dataframe':
X = cudf.DataFrame.from_pandas(pd.DataFrame(X))
with pytest.raises(Exception):
knn_cu.fit(X, should_downcast=True)
def test_nonmonotonic_labels():
X = np.array([[0, 0, 1], [1, 0, 1]]).astype(np.float32)
y = np.array([15, 5]).astype(np.int32)
knn_cu = cuKNN(n_neighbors=1)
knn_cu.fit(X, y)
p = knn_cu.predict(X)
assert array_equal(p.astype(np.int32), y)
def test_self_neighboring(datatype, metric_p, nrows):
"""Test that searches using an indexed vector itself return sensible
results for that vector
For L2-derived metrics, this specifically exercises the slow high-precision
mode used to correct for approximation errors in L2 computation during NN
searches.
"""
ncols = 1000
n_clusters = 10
n_neighbors = 3
metric, p = metric_p
if not has_scipy():
pytest.skip('Skipping test_neighborhood_predictions because ' +
'Scipy is missing')
X, y = make_blobs(n_samples=nrows,
centers=n_clusters,
n_features=ncols,
random_state=0)
if datatype == "dataframe":
X = cudf.DataFrame(X)
knn_cu = cuKNN(metric=metric, n_neighbors=n_neighbors)
knn_cu.fit(X)
neigh_dist, neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=True,
two_pass_precision=True)
if datatype == 'dataframe':
assert isinstance(neigh_ind, cudf.DataFrame)
neigh_ind = neigh_ind.to_numpy()
neigh_dist = neigh_dist.to_numpy()
else:
assert isinstance(neigh_ind, cp.ndarray)
neigh_ind = neigh_ind.get()
neigh_dist = neigh_dist.get()
neigh_ind = neigh_ind[:, 0]
neigh_dist = neigh_dist[:, 0]
assert_array_equal(
neigh_ind,
np.arange(0, neigh_dist.shape[0]),
)
assert_allclose(neigh_dist,
np.zeros(neigh_dist.shape, dtype=neigh_dist.dtype),
atol=1e-4)
def test_score(nrows, ncols, n_neighbors, n_clusters, datatype):
X, y = make_blobs(n_samples=nrows, centers=n_clusters,
n_features=ncols, random_state=0,
cluster_std=0.01)
X = X.astype(np.float32)
X_train, X_test, y_train, y_test = _build_train_test_data(X, y, datatype)
knn_cu = cuKNN(n_neighbors=n_neighbors)
knn_cu.fit(X_train, y_train)
assert knn_cu.score(X_test, y_test) >= (1.0 - 0.004)
def test_tsne_knn_graph_used(dataset, type_knn_graph, method):
X = dataset.data
neigh = cuKNN(n_neighbors=DEFAULT_N_NEIGHBORS, metric="euclidean").fit(X)
knn_graph = neigh.kneighbors_graph(X, mode="distance").astype('float32')
if type_knn_graph == 'cuml':
knn_graph = cupyx.scipy.sparse.csr_matrix(knn_graph)
tsne = TSNE(random_state=1,
n_neighbors=DEFAULT_N_NEIGHBORS,
method=method,
perplexity=DEFAULT_PERPLEXITY,
learning_rate_method='none',
min_grad_norm=1e-12)
# Perform tsne with normal knn_graph
Y = tsne.fit_transform(X, True, knn_graph)
trust_normal = trustworthiness(X, Y, n_neighbors=DEFAULT_N_NEIGHBORS)
X_garbage = np.ones(X.shape)
knn_graph_garbage = neigh.kneighbors_graph(
X_garbage, mode="distance").astype('float32')
if type_knn_graph == 'cuml':
knn_graph_garbage = cupyx.scipy.sparse.csr_matrix(knn_graph_garbage)
tsne = TSNE(random_state=1,
n_neighbors=DEFAULT_N_NEIGHBORS,
method=method,
perplexity=DEFAULT_PERPLEXITY,
learning_rate_method='none',
min_grad_norm=1e-12)
# Perform tsne with garbage knn_graph
Y = tsne.fit_transform(X, True, knn_graph_garbage)
trust_garbage = trustworthiness(X, Y, n_neighbors=DEFAULT_N_NEIGHBORS)
assert (trust_normal - trust_garbage) > 0.15
Y = tsne.fit_transform(X, True, knn_graph_garbage)
trust_garbage = trustworthiness(X, Y, n_neighbors=DEFAULT_N_NEIGHBORS)
assert (trust_normal - trust_garbage) > 0.15
Y = tsne.fit_transform(X, True, knn_graph_garbage)
trust_garbage = trustworthiness(X, Y, n_neighbors=DEFAULT_N_NEIGHBORS)
assert (trust_normal - trust_garbage) > 0.15
def test_nearest_neighbors_rbc(distance, n_neighbors, nrows):
X, y = make_blobs(n_samples=nrows,
centers=25,
shuffle=True,
n_features=2,
cluster_std=3.0,
random_state=42)
knn_cu = cuKNN(metric=distance, algorithm="rbc")
knn_cu.fit(X)
query_rows = int(nrows / 2)
rbc_d, rbc_i = knn_cu.kneighbors(X[:query_rows, :],
n_neighbors=n_neighbors)
if distance == 'euclidean':
# Need to use unexpanded euclidean distance
pw_dists = cuPW(X, metric="l2")
brute_i = cp.argsort(pw_dists, axis=1)[:query_rows, :n_neighbors]
brute_d = cp.sort(pw_dists, axis=1)[:query_rows, :n_neighbors]
else:
knn_cu_brute = cuKNN(metric=distance, algorithm="brute")
knn_cu_brute.fit(X)
brute_d, brute_i = knn_cu_brute.kneighbors(X[:query_rows, :],
n_neighbors=n_neighbors)
rbc_i = cp.sort(rbc_i, axis=1)
brute_i = cp.sort(brute_i, axis=1)
# TODO: These are failing with 1 or 2 mismatched elements
# for very small values of k:
# https://github.com/rapidsai/cuml/issues/4262
assert len(brute_d[brute_d != rbc_d]) <= 1
assert len(brute_i[brute_i != rbc_i]) <= 1
def test_knn_separate_index_search(input_type, nrows, n_feats, k, metric):
X, _ = make_blobs(n_samples=nrows, n_features=n_feats, random_state=0)
X_index = X[:100]
X_search = X[101:]
p = 5 # Testing 5-norm of the minkowski metric only
knn_sk = skKNN(metric=metric, p=p) # Testing
knn_sk.fit(X_index.get())
D_sk, I_sk = knn_sk.kneighbors(X_search.get(), k)
X_orig = X_index
if input_type == "dataframe":
X_index = cudf.DataFrame(X_index)
X_search = cudf.DataFrame(X_search)
knn_cu = cuKNN(metric=metric, p=p)
knn_cu.fit(X_index)
D_cuml, I_cuml = knn_cu.kneighbors(X_search, k)
if input_type == "dataframe":
assert isinstance(D_cuml, cudf.DataFrame)
assert isinstance(I_cuml, cudf.DataFrame)
D_cuml_np = D_cuml.to_numpy()
I_cuml_np = I_cuml.to_numpy()
else:
assert isinstance(D_cuml, cp.ndarray)
assert isinstance(I_cuml, cp.ndarray)
D_cuml_np = D_cuml.get()
I_cuml_np = I_cuml.get()
with cuml.using_output_type("numpy"):
# Assert the cuml model was properly reverted
np.testing.assert_allclose(knn_cu.X_m,
X_orig.get(),
atol=1e-3,
rtol=1e-3)
if metric == 'braycurtis':
diff = D_cuml_np - D_sk
# Braycurtis has a few differences, but this is computed by FAISS.
# So long as the indices all match below, the small discrepancy
# should be okay.
assert len(diff[diff > 1e-2]) / X_search.shape[0] < 0.06
else:
np.testing.assert_allclose(D_cuml_np, D_sk, atol=1e-3, rtol=1e-3)
assert I_cuml_np.all() == I_sk.all()
def test_score(nrows, ncols, n_neighbors, n_clusters, datatype):
X, y = make_blobs(n_samples=nrows, centers=n_clusters,
n_features=ncols, random_state=0,
cluster_std=0.01)
X = X.astype(np.float32)
if datatype == "dataframe":
X = cudf.DataFrame.from_gpu_matrix(rmm.to_device(X))
y = cudf.DataFrame.from_gpu_matrix(rmm.to_device(y.reshape(nrows, 1)))
knn_cu = cuKNN(n_neighbors=n_neighbors)
knn_cu.fit(X, y)
assert knn_cu.score(X, y) >= (1.0 - 0.004)
def test_score_dtype(dtype):
# Using make_blobs here to check averages and neighborhoods
X, y = make_blobs(n_samples=1000,
centers=2,
cluster_std=0.01,
n_features=50,
random_state=0)
X = X.astype(dtype)
y = y.astype(dtype)
knn_cu = cuKNN(n_neighbors=5)
knn_cu.fit(X, y)
pred = knn_cu.predict(X)
assert pred.dtype == dtype
assert knn_cu.score(X, y) >= 0.9999
def test_knn_return_cumlarray(input_type):
n_samples = 50
n_feats = 50
k = 5
X, _ = make_blobs(n_samples=n_samples, n_features=n_feats, random_state=0)
if input_type == "dataframe":
X = cudf.DataFrame(X)
knn_cu = cuKNN()
knn_cu.fit(X)
indices, distances = knn_cu._kneighbors(X, k, _output_cumlarray=True)
assert isinstance(indices, CumlArray)
assert isinstance(distances, CumlArray)
def test_nearest_neighbors_sparse(shape,
metric,
n_neighbors,
batch_size_index,
batch_size_query):
nrows, ncols, density = shape
if nrows == 1 and n_neighbors > 1:
return
a = cp.sparse.random(nrows, ncols, format='csr', density=density,
random_state=35)
b = cp.sparse.random(nrows, ncols, format='csr', density=density,
random_state=38)
if metric == 'jaccard':
a = a.astype('bool').astype('float32')
b = b.astype('bool').astype('float32')
logger.set_level(logger.level_debug)
nn = cuKNN(metric=metric, p=2.0, n_neighbors=n_neighbors,
algorithm="brute", output_type="numpy",
verbose=logger.level_debug,
algo_params={"batch_size_index": batch_size_index,
"batch_size_query": batch_size_query})
nn.fit(a)
cuD, cuI = nn.kneighbors(b)
if metric not in sklearn.neighbors.VALID_METRICS_SPARSE['brute']:
a = a.todense()
b = b.todense()
sknn = skKNN(metric=metric, p=2.0, n_neighbors=n_neighbors,
algorithm="brute", n_jobs=-1)
sk_X = a.get()
sknn.fit(sk_X)
skD, skI = sknn.kneighbors(b.get())
cp.testing.assert_allclose(cuD, skD, atol=1e-3, rtol=1e-3)
# Jaccard & Chebyshev have a high potential for mismatched indices
# due to duplicate distances. We can ignore the indices in this case.
if metric not in ['jaccard', 'chebyshev']:
cp.testing.assert_allclose(cuI, skI, atol=1e-4, rtol=1e-4)
def test_return_dists():
n_samples = 50
n_feats = 50
k = 5
X, y = make_blobs(n_samples=n_samples, n_features=n_feats, random_state=0)
knn_cu = cuKNN()
knn_cu.fit(X)
ret = knn_cu.kneighbors(X, k, return_distance=False)
assert not isinstance(ret, tuple)
assert ret.shape == (n_samples, k)
ret = knn_cu.kneighbors(X, k, return_distance=True)
assert isinstance(ret, tuple)
assert len(ret) == 2
def test_score(nrows, ncols, n_neighbors, n_clusters, datatype):
# Using make_blobs here to check averages and neighborhoods
X, y = make_blobs(n_samples=nrows, centers=n_clusters,
cluster_std=0.01,
n_features=ncols, random_state=0)
X = X.astype(np.float32)
y = y.astype(np.float32)
if datatype == "dataframe":
X = cudf.DataFrame.from_gpu_matrix(rmm.to_device(X))
y = cudf.DataFrame.from_gpu_matrix(rmm.to_device(y.reshape(nrows, 1)))
knn_cu = cuKNN(n_neighbors=n_neighbors)
knn_cu.fit(X, y)
assert knn_cu.score(X, y) >= 0.9999
def test_kneighbors_regressor(n_samples=40,
n_features=5,
n_test_pts=10,
n_neighbors=3,
random_state=0):
# Test k-neighbors regression
rng = np.random.RandomState(random_state)
X = 2 * rng.rand(n_samples, n_features) - 1
y = np.sqrt((X ** 2).sum(1))
y /= y.max()
y_target = y[:n_test_pts]
knn = cuKNN(n_neighbors=n_neighbors)
knn.fit(X, y)
epsilon = 1E-5 * (2 * rng.rand(1, n_features) - 1)
y_pred = knn.predict(X[:n_test_pts] + epsilon)
assert np.all(abs(y_pred - y_target) < 0.3)
def test_tsne_knn_parameters_sparse(type_knn_graph, input_type):
datasets
digits = datasets.load_digits()
neigh = skKNN(n_neighbors=90) if type_knn_graph == 'sklearn' \
else cuKNN(n_neighbors=90)
digits_selection = np.random.RandomState(42).choice(
[True, False], 1797, replace=True, p=[0.60, 0.40])
selected_digits = digits.data[~digits_selection]
neigh.fit(selected_digits)
knn_graph = neigh.kneighbors_graph(selected_digits, mode="distance")
if input_type == 'cupy':
sp_prefix = cupyx.scipy.sparse
else:
sp_prefix = scipy.sparse
tsne = TSNE(2, n_neighbors=15,
random_state=1,
learning_rate=500,
angle=0.8)
new_data = sp_prefix.csr_matrix(
scipy.sparse.csr_matrix(selected_digits))
Y = tsne.fit_transform(new_data, True, knn_graph)
if input_type == 'cupy':
Y = Y.get()
check_embedding(selected_digits, Y, 0.85)
Y = tsne.fit_transform(new_data, True, knn_graph.tocoo())
if input_type == 'cupy':
Y = Y.get()
check_embedding(selected_digits, Y, 0.85)
Y = tsne.fit_transform(new_data, True, knn_graph.tocsc())
if input_type == 'cupy':
Y = Y.get()
check_embedding(selected_digits, Y, 0.85)
del Y
def test_ivfflat_pred(nrows, ncols, n_neighbors, nlist):
algo_params = {'nlist': nlist, 'nprobe': nlist * 0.25}
X, y = make_blobs(n_samples=nrows,
centers=5,
n_features=ncols,
random_state=0)
knn_cu = cuKNN(algorithm="ivfflat", algo_params=algo_params)
knn_cu.fit(X)
neigh_ind = knn_cu.kneighbors(X,
n_neighbors=n_neighbors,
return_distance=False)
del knn_cu
gc.collect()
labels, probs = predict(neigh_ind, y, n_neighbors)
assert array_equal(labels, y)
def test_ann_distances_metrics(algo, metric):
X, y = make_blobs(n_samples=500, centers=2, n_features=128, random_state=0)
cu_knn = cuKNN(algorithm=algo, metric=metric)
cu_knn.fit(X)
cu_dist, cu_ind = cu_knn.kneighbors(X,
n_neighbors=10,
return_distance=True)
del cu_knn
gc.collect()
X = X.get()
sk_knn = skKNN(metric=metric)
sk_knn.fit(X)
sk_dist, sk_ind = sk_knn.kneighbors(X,
n_neighbors=10,
return_distance=True)
return array_equal(sk_dist, cu_dist)
def test_predict_multioutput(datatype):
X = np.array([[0, 0, 1], [1, 0, 1]]).astype(np.float32)
y = np.array([[15, 2], [5, 4]]).astype(np.int32)
if datatype == "dataframe":
X = cudf.DataFrame.from_gpu_matrix(rmm.to_device(X))
y = cudf.DataFrame.from_gpu_matrix(rmm.to_device(y))
knn_cu = cuKNN(n_neighbors=1)
knn_cu.fit(X, y)
p = knn_cu.predict(X)
if datatype == "dataframe":
assert isinstance(p, cudf.DataFrame)
else:
assert isinstance(p, np.ndarray)
assert array_equal(p.astype(np.int32), y)
def test_tsne_knn_parameters_sparse(type_knn_graph, input_type, method):
digits = test_datasets["digits"].data
neigh = cuKNN(n_neighbors=DEFAULT_N_NEIGHBORS,
metric="euclidean").fit(digits)
knn_graph = neigh.kneighbors_graph(digits,
mode="distance").astype('float32')
if type_knn_graph == 'cuml':
knn_graph = cupyx.scipy.sparse.csr_matrix(knn_graph)
if input_type == 'cupy':
sp_prefix = cupyx.scipy.sparse
else:
sp_prefix = scipy.sparse
tsne = TSNE(n_components=2,
n_neighbors=DEFAULT_N_NEIGHBORS,
random_state=1,
learning_rate_method='none',
method=method,
min_grad_norm=1e-12,
perplexity=DEFAULT_PERPLEXITY)
new_data = sp_prefix.csr_matrix(scipy.sparse.csr_matrix(digits))
Y = tsne.fit_transform(new_data, True, knn_graph)
if input_type == 'cupy':
Y = Y.get()
validate_embedding(digits, Y, 0.85)
Y = tsne.fit_transform(new_data, True, knn_graph.tocoo())
if input_type == 'cupy':
Y = Y.get()
validate_embedding(digits, Y, 0.85)
Y = tsne.fit_transform(new_data, True, knn_graph.tocsc())
if input_type == 'cupy':
Y = Y.get()
validate_embedding(digits, Y, 0.85)
def test_knn_graph(input_type, mode, output_type, as_instance, nrows, n_feats,
p, k, metric):
X, _ = make_blobs(n_samples=nrows, n_features=n_feats, random_state=0)
if as_instance:
sparse_sk = sklearn.neighbors.kneighbors_graph(X.get(),
k,
mode=mode,
metric=metric,
p=p,
include_self='auto')
else:
knn_sk = skKNN(metric=metric, p=p)
knn_sk.fit(X.get())
sparse_sk = knn_sk.kneighbors_graph(X.get(), k, mode=mode)
if input_type == "dataframe":
X = cudf.DataFrame(X)
with cuml.using_output_type(output_type):
if as_instance:
sparse_cu = cuml.neighbors.kneighbors_graph(X,
k,
mode=mode,
metric=metric,
p=p,
include_self='auto')
else:
knn_cu = cuKNN(metric=metric, p=p)
knn_cu.fit(X)
sparse_cu = knn_cu.kneighbors_graph(X, k, mode=mode)
assert np.array_equal(sparse_sk.data.shape, sparse_cu.data.shape)
assert np.array_equal(sparse_sk.indices.shape, sparse_cu.indices.shape)
assert np.array_equal(sparse_sk.indptr.shape, sparse_cu.indptr.shape)
assert np.array_equal(sparse_sk.toarray().shape, sparse_cu.toarray().shape)
if output_type == 'cupy' or output_type is None:
assert cupyx.scipy.sparse.isspmatrix_csr(sparse_cu)
else:
assert isspmatrix_csr(sparse_cu)
