Skip to content

[MRG] Fix numpy.int overflow in make_classification #10811

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 7 commits into from
Oct 2, 2018
Merged

[MRG] Fix numpy.int overflow in make_classification #10811

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
55f6bc5
FIX numpy.int overflow in make_classification
VarIr Mar 14, 2018
7458604
Using log2
VarIr Mar 16, 2018
19f2d8b
TST make_classification() with numpy.int
VarIr Mar 16, 2018
bf1f296
Comment on log2
VarIr Mar 19, 2018
f108543
Lower hypercube center precision
VarIr Mar 19, 2018
54432a7
fix pyflakes issue
VarIr Mar 19, 2018
d3396e4
Simplification and consistency
VarIr Aug 8, 2018
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
3 changes: 2 additions & 1 deletion sklearn/datasets/samples_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,8 @@ def make_classification(n_samples=100, n_features=20, n_informative=2,
raise ValueError("Number of informative, redundant and repeated "
"features must sum to less than the number of total"
" features")
if 2 ** n_informative < n_classes * n_clusters_per_class:
# Use log2 to avoid overflow errors
if n_informative < np.log2(n_classes * n_clusters_per_class):
raise ValueError("n_classes * n_clusters_per_class must"
" be smaller or equal 2 ** n_informative")
if weights and len(weights) not in [n_classes, n_classes - 1]:
Expand Down
17 changes: 9 additions & 8 deletions sklearn/datasets/tests/test_samples_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,8 @@ def test_make_classification_informative_features():
(2, [1/4] * 4, 1),
(2, [1/2] * 2, 2),
(2, [3/4, 1/4], 2),
(10, [1/3] * 3, 10)
(10, [1/3] * 3, 10),
(np.int(64), [1], 1)
]:
n_classes = len(weights)
n_clusters = n_classes * n_clusters_per_class
Expand Down Expand Up @@ -128,19 +129,19 @@ def test_make_classification_informative_features():
for cluster in range(len(unique_signs)):
centroid = X[cluster_index == cluster].mean(axis=0)
if hypercube:
assert_array_almost_equal(np.abs(centroid),
[class_sep] * n_informative,
decimal=0,
assert_array_almost_equal(np.abs(centroid) / class_sep,
np.ones(n_informative),
decimal=5,
err_msg="Clusters are not "
"centered on hypercube "
"vertices")
else:
assert_raises(AssertionError,
assert_array_almost_equal,
np.abs(centroid),
[class_sep] * n_informative,
decimal=0,
err_msg="Clusters should not be cenetered "
np.abs(centroid) / class_sep,
np.ones(n_informative),
decimal=5,
err_msg="Clusters should not be centered "
"on hypercube vertices")

assert_raises(ValueError, make, n_features=2, n_informative=2, n_classes=5,
Expand Down