10000 TST Extend tests for `scipy.sparse/*array` in `sklearn/ensemble/tests/test_iforest` by Charlie-XIAO · Pull Request #27218 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

TST Extend tests for scipy.sparse/*array in sklearn/ensemble/tests/test_iforest #27218

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

Merged
merged 5 commits into from
Sep 13, 2023
Merged

TST Extend tests for scipy.sparse/*array in sklearn/ensemble/tests/test_iforest #27218

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
483c8aa
TST Extend tests for scipy.sparse/*array in sklearn/ensemble/tests/te…
Charlie-XIAO Aug 30, 2023
9832312
Resolve conversation: parametrize instead of loop
Charlie-XIAO Sep 1, 2023
1aa53d2
Merge remote-tracking branch 'upstream/main' into tst_sp_iforest
Charlie-XIAO Sep 1, 2023
d431542
prefer concatenation over unpacking
Charlie-XIAO Sep 13, 2023
f2444bd
Merge remote-tracking branch 'upstream/main' into tst_sp_iforest
Charlie-XIAO Sep 13, 2023
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
39 changes: 20 additions & 19 deletions sklearn/ensemble/tests/test_iforest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@

import numpy as np
import pytest
from scipy.sparse import csc_matrix, csr_matrix

from sklearn.datasets import load_diabetes, load_iris, make_classification
from sklearn.ensemble import IsolationForest
Expand All @@ -25,6 +24,7 @@
assert_array_equal,
ignore_warnings,
)
from sklearn.utils.fixes import CSC_CONTAINERS, CSR_CONTAINERS

# load iris & diabetes dataset
iris = load_iris()
Expand All @@ -47,30 +47,30 @@ def test_iforest(global_random_seed):
).predict(X_test)


def test_iforest_sparse(global_random_seed):
@pytest.mark.parametrize("sparse_container", CSC_CONTAINERS + CSR_CONTAINERS)
def test_iforest_sparse(global_random_seed, sparse_container):
"""Check IForest for various parameter settings on sparse input."""
rng = check_random_state(global_random_seed)
X_train, X_test = train_test_split(diabetes.data[:50], random_state=rng)
grid = ParameterGrid({"max_samples": [0.5, 1.0], "bootstrap": [True, False]})

for sparse_format in [csc_matrix, csr_matrix]:
X_train_sparse = sparse_format(X_train)
X_test_sparse = sparse_format(X_test)
X_train_sparse = sparse_container(X_train)
X_test_sparse = sparse_container(X_test)

for params in grid:
# Trained on sparse format
sparse_classifier = IsolationForest(
n_estimators=10, random_state=global_random_seed, **params
).fit(X_train_sparse)
sparse_results = sparse_classifier.predict(X_test_sparse)
for params in grid:
# Trained on sparse format
sparse_classifier = IsolationForest(
n_estimators=10, random_state=global_random_seed, **params
).fit(X_train_sparse)
sparse_results = sparse_classifier.predict(X_test_sparse)

# Trained on dense format
dense_classifier = IsolationForest(
n_estimators=10, random_state=global_random_seed, **params
).fit(X_train)
dense_results = dense_classifier.predict(X_test)
# Trained on dense format
dense_classifier = IsolationForest(
n_estimators=10, random_state=global_random_seed, **params
).fit(X_train)
dense_results = dense_classifier.predict(X_test)

assert_array_equal(sparse_results, dense_results)
assert_array_equal(sparse_results, dense_results)


def test_iforest_error():
Expand Down Expand Up @@ -314,13 +314,14 @@ def test_iforest_with_uniform_data():
assert all(iforest.predict(np.ones((100, 10))) == 1)


def test_iforest_with_n_jobs_does_not_segfault():
@pytest.mark.parametrize("csc_container", CSC_CONTAINERS)
def test_iforest_with_n_jobs_does_not_segfault(csc_container):
"""Check that Isolation Forest does not segfault with n_jobs=2

Non-regression test for #23252
"""
X, _ = make_classification(n_samples=85_000, n_features=100, random_state=0)
X = csc_matrix(X)
X = csc_container(X)
IsolationForest(n_estimators=10, max_samples=256, n_jobs=2).fit(X)


Expand Down
0