FIX in randomized_svd flip sign

devashishd12 · ogrisel · commit cfa498ca6842 · 2016-02-08T16:59:44.000+01:00
Flip sign according to `u` in both cases of `transpose`.
diff --git a/sklearn/utils/extmath.py b/sklearn/utils/extmath.py
@@ -363,7 +363,12 @@ def randomized_svd(M, n_components, n_oversamples=10, n_iter=2,
     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
diff --git a/sklearn/utils/tests/test_extmath.py b/sklearn/utils/tests/test_extmath.py
@@ -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
@@ -328,6 +329,37 @@ 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
 
