Merge pull request #1 from mdhaber/gh16238

MAINT: stats._contains_nan: only detect numeric np.nan, not string 'nan'

Author: AtsushiSakai

scipy/stats/_stats_py.py

@@ -103,7 +103,12 @@ def _contains_nan(a, nan_policy='propagate'):
             try:
                 # This can happen when attempting to check nan with np.isnan
                 # for string array (e.g. as in the function `rankdata`).
-                contains_nan = np.any(a == "nan")
+                contains_nan = False
+                for el in a.ravel():
+                    # isnan doesn't work on elements of string arrays
+                    if np.issubdtype(type(el), np.number) and np.isnan(el):
+                        contains_nan = True
+                        break
             except TypeError:
                 # Don't know what to do. Fall back to omitting nan values and
                 # issue a warning.

scipy/stats/tests/test_stats.py

@@ -7550,8 +7550,11 @@ def test_contains_nan_1d(self):
         data3 = np.array([np.nan, 2, 3, np.nan])
         assert _contains_nan(data3)[0]
 
-        data4 = np.array([1, 2, "3", np.nan])
-        assert _contains_nan(data4)[0]
+        data4 = np.array([1, 2, "3", np.nan])  # converted to string "nan"
+        assert not _contains_nan(data4)[0]
+
+        data5 = np.array([1, 2, "3", np.nan], dtype='object')
+        assert _contains_nan(data5)[0]
 
     def test_contains_nan_2d(self):
         data1 = np.array([[1, 2], [3, 4]])
@@ -7560,5 +7563,8 @@ def test_contains_nan_2d(self):
         data2 = np.array([[1, 2], [3, np.nan]])
         assert _contains_nan(data2)[0]
 
-        data3 = np.array([["1", 2], [3, np.nan]])
-        assert _contains_nan(data3)[0]
+        data3 = np.array([["1", 2], [3, np.nan]])  # converted to string "nan"
+        assert not _contains_nan(data3)[0]
+
+        data4 = np.array([["1", 2], [3, np.nan]], dtype='object')
+        assert _contains_nan(data4)[0]