From fe28eafd0af6dc0aace878f59988835bfcaa6338 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pavlin=20Poli=C4=8Dar?= <pavlin.g.p@gmail.com>
Date: Fri, 15 Feb 2019 10:21:04 +0100
Subject: [PATCH] OwLouvain: Properly compare new data with old without
 warnings

---
 Orange/statistics/util.py                     | 17 +++++++++++++++
 Orange/tests/test_statistics.py               | 21 ++++++++++++++++++-
 .../unsupervised/owlouvainclustering.py       |  4 ++--
 3 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/Orange/statistics/util.py b/Orange/statistics/util.py
index f4b44b1e4ea..94207b2ec62 100644
--- a/Orange/statistics/util.py
+++ b/Orange/statistics/util.py
@@ -13,6 +13,23 @@
 from sklearn.utils.sparsefuncs import mean_variance_axis
 
 
+def sparse_array_equal(x1, x2):
+    """Check if two sparse arrays are equal."""
+    if not sp.issparse(x1):
+        raise TypeError("`x1` must be sparse.")
+    if not sp.issparse(x2):
+        raise TypeError("`x2` must be sparse.")
+
+    return x1.shape == x2.shape and (x1 != x2).nnz == 0
+
+
+def array_equal(x1, x2):
+    """Equivalent of np.array_equal that properly handles sparse matrices."""
+    if sp.issparse(x1) and sp.issparse(x2):
+        return sparse_array_equal(x1, x2)
+    return np.array_equal(x1, x2)
+
+
 def _count_nans_per_row_sparse(X, weights, dtype=None):
     """ Count the number of nans (undefined) values per row. """
     if weights is not None:
diff --git a/Orange/tests/test_statistics.py b/Orange/tests/test_statistics.py
index 99be289556e..722025774d3 100644
--- a/Orange/tests/test_statistics.py
+++ b/Orange/tests/test_statistics.py
@@ -9,7 +9,7 @@
 
 from Orange.statistics.util import bincount, countnans, contingency, digitize, \
     mean, nanmax, nanmean, nanmedian, nanmin, nansum, nanunique, stats, std, \
-    unique, var, nanstd, nanvar, nanmode
+    unique, var, nanstd, nanvar, nanmode, array_equal
 from sklearn.utils import check_random_state
 
 
@@ -590,6 +590,25 @@ def test_nanunique_ignores_nans_in_counts(self, array):
         np.testing.assert_equal(nanunique(x, return_counts=True)[1], expected)
 
 
+class TestArrayEqual(unittest.TestCase):
+    @dense_sparse
+    def test_same_matrices(self, array):
+        x = array([0, 1, 0, 0, 2])
+        self.assertTrue(array_equal(x, x))
+
+    @dense_sparse
+    def test_with_different_shapes(self, array):
+        x = array(np.eye(4))
+        y = array(np.eye(5))
+        self.assertFalse(array_equal(x, y))
+
+    @dense_sparse
+    def test_with_different_values(self, array):
+        x = array([0, 1, 0, 0, 2])
+        y = array([0, 3, 0, 0, 2])
+        self.assertFalse(array_equal(x, y))
+
+
 class TestNanModeAppVeyor(unittest.TestCase):
     def test_appveyour_still_not_onscipy_1_2_0(self):
         import scipy
diff --git a/Orange/widgets/unsupervised/owlouvainclustering.py b/Orange/widgets/unsupervised/owlouvainclustering.py
index 3e6f1cecf9c..f1509c55829 100644
--- a/Orange/widgets/unsupervised/owlouvainclustering.py
+++ b/Orange/widgets/unsupervised/owlouvainclustering.py
@@ -19,6 +19,7 @@
 from Orange.data.util import get_unique_names
 from Orange import preprocess
 from Orange.projection import PCA
+from Orange.statistics import util as ut
 from Orange.widgets import widget, gui, report
 from Orange.widgets.settings import DomainContextHandler, ContextSetting, \
     Setting
@@ -407,8 +408,7 @@ def set_data(self, data):
         # Make sure to properly enable/disable slider based on `apply_pca` setting
         self.controls.pca_components.setEnabled(self.apply_pca)
 
-        # If X hasn't changed, there's no reason to recompute clusters
-        if prev_data and self.data and np.array_equal(self.data.X, prev_data.X):
+        if prev_data and self.data and ut.array_equal(prev_data.X, self.data.X):
             if self.auto_commit:
                 self._send_data()
             return