Skip to content

Backport 0.17.X -- FIX in randomized_svd flip sign #6375

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 1 commit into from
Feb 18, 2016
Merged

Backport 0.17.X -- FIX in randomized_svd flip sign #6375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 6 additions & 1 deletion sklearn/utils/extmath.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,7 +305,12 @@ def randomized_svd(M, n_components, n_oversamples=10, n_iter=0,
U = np.dot(Q, Uhat)

if flip_sign:
U, V = svd_flip(U, V)
if not transpose:
U, V = svd_flip(U, V)
else:
# In case of transpose u_based_decision=false
# to actually flip based on u and not v.
U, V = svd_flip(U, V, u_based_decision=False)

if transpose:
# transpose back the results according to the input convention
Expand Down
32 changes: 32 additions & 0 deletions sklearn/utils/tests/test_extmath.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
from sklearn.utils.testing import assert_array_equal
from sklearn.utils.testing import assert_array_almost_equal
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_false
from sklearn.utils.testing import assert_greater
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import skip_if_32bit
Expand Down Expand Up @@ -287,6 +288,37 @@ def test_randomized_svd_sign_flip():
assert_almost_equal(np.dot(v2.T, v2), np.eye(2))


def test_randomized_svd_sign_flip_with_transpose():
# Check if the randomized_svd sign flipping is always done based on u
# irrespective of transpose.
# See https://github.com/scikit-learn/scikit-learn/issues/5608
# for more details.
def max_loading_is_positive(u, v):
"""
returns bool tuple indicating if the values maximising np.abs
are positive across all rows for u and across all columns for v.
"""
u_based = (np.abs(u).max(axis=0) == u.max(axis=0)).all()
v_based = (np.abs(v).max(axis=1) == v.max(axis=1)).all()
return u_based, v_based

mat = np.arange(10 * 8).reshape(10, -1)

# Without transpose
u_flipped, _, v_flipped = randomized_svd(mat, 3, flip_sign=True)
u_based, v_based = max_loading_is_positive(u_flipped, v_flipped)
assert_true(u_based)
assert_false(v_based)

# With transpose
u_flipped_with_transpose, _, v_flipped_with_transpose = randomized_svd(
mat, 3, flip_sign=True, transpose=True)
u_based, v_based = max_loading_is_positive(
u_flipped_with_transpose, v_flipped_with_transpose)
assert_true(u_based)
assert_false(v_based)


def test_cartesian():
# Check if cartesian product delivers the right results

Expand Down