Merge pull request scikit-learn#4352 from amueller/issue-4297-infinite-isotonic_bak

[MRG + 2] Adding fix for issue scikit-learn#4297, isotonic infinite loop

Author: amueller

sklearn/isotonic.py

@@ -252,8 +252,6 @@ def _build_y(self, X, y, sample_weight):
         """Build the y_ IsotonicRegression."""
         check_consistent_length(X, y, sample_weight)
         X, y = [check_array(x, ensure_2d=False) for x in [X, y]]
-        if sample_weight is not None:
-            sample_weight = check_array(sample_weight, ensure_2d=False)
 
         y = as_float_array(y)
         self._check_fit_data(X, y, sample_weight)
@@ -264,10 +262,16 @@ def _build_y(self, X, y, sample_weight):
         else:
             self.increasing_ = self.increasing
 
+        # If sample_weights is passed, removed zero-weight values and clean order
+        if sample_weight is not None:
+            sample_weight = check_array(sample_weight, ensure_2d=False)
+            mask = sample_weight > 0
+            X, y, sample_weight = X[mask], y[mask], sample_weight[mask]
+        else:
+            sample_weight = np.ones(len(y))
+
         order = np.lexsort((y, X))
         order_inv = np.argsort(order)
-        if sample_weight is None:
-            sample_weight = np.ones(len(y))
         X, y, sample_weight = [astype(array[order], np.float64, copy=False)
                                for array in [X, y, sample_weight]]
         unique_X, unique_y, unique_sample_weight = _make_unique(X, y, sample_weight)

sklearn/tests/test_isotonic.py

@@ -325,6 +325,29 @@ def test_isotonic_duplicate_min_entry():
     all_predictions_finite = np.all(np.isfinite(ir.predict(x)))
     assert_true(all_predictions_finite)
 
+
+def test_isotonic_zero_weight_loop():
+    # Test from @ogrisel's issue:
+    # https://github.com/scikit-learn/scikit-learn/issues/4297
+
+    # Get deterministic RNG with seed
+    rng = np.random.RandomState(42)
+
+    # Create regression and samples
+    regression = IsotonicRegression()
+    n_samples = 50
+    x = np.linspace(-3, 3, n_samples)
+    y = x + rng.uniform(size=n_samples)
+
+    # Get some random weights and zero out
+    w = rng.uniform(size=n_samples)
+    w[5:8] = 0
+    regression.fit(x, y, sample_weight=w)
+
+    # This will hang in failure case.
+    regression.fit(x, y, sample_weight=w)
+
+
 if __name__ == "__main__":
     import nose
     nose.run(argv=['', __file__])