Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[REVIEW] Speeding up MNMG KNN Cl&Re testing #3052

Merged
merged 4 commits into from
Nov 2, 2020
Merged

[REVIEW] Speeding up MNMG KNN Cl&Re testing #3052

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
31c1019
Speeding up MNMG KNN Cl&Re testing
viclafargue Oct 23, 2020
e6eeb36
Update changelog
viclafargue Oct 23, 2020
8e1e880
Testing with extreme values
viclafargue Oct 26, 2020
2a82867
Merge branch-0.17
viclafargue Oct 30, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
- PR #3004: Remove Single Process Multi GPU (SPMG) code
- PR #3044: Move leftover `linalg` and `stats` to RAFT namespaces
- PR #3074: Reducing dask coordinate descent test runtime
- PR #3052: Speeding up MNMG KNN Cl&Re testing

## Bug Fixes
- PR #3072: Fusing metrics and score directories in src_prims
Expand Down
3 changes: 2 additions & 1 deletion cpp/src_prims/selection/knn.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -471,7 +471,8 @@ void class_probs(std::vector<float *> &out, const int64_t *knn_indices,
* Build array of class probability arrays from
* knn_indices and labels
*/
device_buffer<int> y_normalized(allocator, stream, n_index_rows);
device_buffer<int> y_normalized(allocator, stream,
n_index_rows + n_unique_labels);

/*
* Appending the array of unique labels to the original labels array
Expand Down
24 changes: 12 additions & 12 deletions python/cuml/test/dask/test_kneighbors_classifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,11 +69,11 @@ def dataset(request):
if len(new_x) >= request.param['n_samples']:
break
X = X[new_x]
noise = np.random.normal(0, 1.2, X.shape)
noise = np.random.normal(0, 5., X.shape)
X += noise
y = np.array(new_y)

return train_test_split(X, y, test_size=0.1)
return train_test_split(X, y, test_size=0.3)


def exact_match(output1, output2):
Expand Down Expand Up @@ -108,11 +108,11 @@ def check_probabilities(l_probas, d_probas):


@pytest.mark.parametrize("datatype", ['dask_array', 'dask_cudf'])
@pytest.mark.parametrize("n_neighbors", [1, 3, 8])
@pytest.mark.parametrize("n_parts", [2, 4, 12])
@pytest.mark.parametrize("batch_size", [128, 1024])
def test_predict_and_score(dataset, datatype, n_neighbors,
n_parts, batch_size, client):
@pytest.mark.parametrize("parameters", [(1, 3, 256),
(8, 8, 256),
(9, 3, 128)])
def test_predict_and_score(dataset, datatype, parameters, client):
n_neighbors, n_parts, batch_size = parameters
X_train, X_test, y_train, y_test = dataset
np_y_test = y_test

Expand Down Expand Up @@ -165,11 +165,11 @@ def test_predict_and_score(dataset, datatype, n_neighbors,


@pytest.mark.parametrize("datatype", ['dask_array', 'dask_cudf'])
@pytest.mark.parametrize("n_neighbors", [1, 3, 8])
@pytest.mark.parametrize("n_parts", [2, 4, 12])
@pytest.mark.parametrize("batch_size", [128, 1024])
def test_predict_proba(dataset, datatype, n_neighbors,
n_parts, batch_size, client):
@pytest.mark.parametrize("parameters", [(1, 3, 256),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good!

(8, 8, 256),
(9, 3, 128)])
def test_predict_proba(dataset, datatype, parameters, client):
n_neighbors, n_parts, batch_size = parameters
X_train, X_test, y_train, y_test = dataset

l_model = lKNNClf(n_neighbors=n_neighbors)
Expand Down
14 changes: 7 additions & 7 deletions python/cuml/test/dask/test_kneighbors_regressor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,11 +70,11 @@ def dataset(request):
if len(new_x) >= request.param['n_samples']:
break
X = X[new_x]
noise = np.random.normal(0, 1.2, X.shape)
noise = np.random.normal(0, 5., X.shape)
X += noise
y = np.array(new_y, dtype=np.float32)

return train_test_split(X, y, test_size=0.1)
return train_test_split(X, y, test_size=0.3)


def exact_match(output1, output2):
Expand Down Expand Up @@ -102,11 +102,11 @@ def exact_match(output1, output2):


@pytest.mark.parametrize("datatype", ['dask_array', 'dask_cudf'])
@pytest.mark.parametrize("n_neighbors", [1, 3, 8])
@pytest.mark.parametrize("n_parts", [2, 4, 12])
@pytest.mark.parametrize("batch_size", [128, 1024])
def test_predict_and_score(dataset, datatype, n_neighbors,
n_parts, batch_size, client):
@pytest.mark.parametrize("parameters", [(1, 3, 256),
(8, 8, 256),
(9, 3, 128)])
def test_predict_and_score(dataset, datatype, parameters, client):
n_neighbors, n_parts, batch_size = parameters
X_train, X_test, y_train, y_test = dataset
np_y_test = y_test

Expand Down