Merge pull request #1585 from nikicc/fix-stats

[FIX] Stats: Fix counting of missing values for non-numeric data

Author: astaric

Orange/statistics/util.py

@@ -195,7 +195,7 @@ def stats(X, weights=None, compute_variance=False):
             X.shape[1] - non_zero,
             non_zero))
     else:
-        nans = ~X.astype(bool).sum(axis=0) if X.size else np.zeros(X.shape[1])
+        nans = (~X.astype(bool)).sum(axis=0) if X.size else np.zeros(X.shape[1])
         return np.column_stack((
             np.tile(np.inf, X.shape[1]),
             np.tile(-np.inf, X.shape[1]),

Orange/tests/test_statistics.py

@@ -69,3 +69,13 @@ def test_stats_weights_sparse(self):
         weights = np.array([1, 3])
         np.testing.assert_equal(stats(X, weights), [[0, 2, 1.5, 0, 1, 1],
                                                     [1, 3, 2.5, 0, 0, 2]])
+
+    def test_stats_non_numeric(self):
+        X = np.array([
+            ['', 'a', 'b'],
+            ['a', '', 'b'],
+            ['a', 'b', ''],
+        ], dtype=object)
+        np.testing.assert_equal(stats(X), [[np.inf, -np.inf, 0, 0, 1, 2],
+                                           [np.inf, -np.inf, 0, 0, 1, 2],
+                                           [np.inf, -np.inf, 0, 0, 1, 2]])