BUG: Index.get_indexer_non_unique misbehaves when index contains mult…

…iple nan (pandas-dev#35392)
alexhlim · Jul 31, 2020 · d041117 · d041117
1 parent 04e9e0a
commit d041117
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 1 deletion.
diff --git a/pandas/_libs/index.pyx b/pandas/_libs/index.pyx
@@ -270,7 +270,15 @@ cdef class IndexEngine:
             Py_ssize_t i, j, n, n_t, n_alloc
 
         self._ensure_mapping_populated()
-        values = np.array(self._get_index_values(), copy=False)
+        #  GH #35392  Index.get_indexer_non_unique misbehaves when index contains multiple nan
+        if any([checknull(t) for t in targets]):
+            new_targets = [0 if checknull(t) else t for t in targets]
+            new_values = [0 if checknull(v) else v for v in self._get_index_values()]
+            targets = np.array(new_targets, dtype=object)
+            values = np.array(new_values, dtype=object)
+        else:
+            values = np.array(self._get_index_values(), copy=False)
+
         stargets = set(targets)
         n = len(values)
         n_t = len(targets)
@@ -304,6 +312,7 @@ cdef class IndexEngine:
             for i in range(n):
                 val = values[i]
                 if val in stargets:
+                    print(val, "in stargets")
                     if val not in d:
                         d[val] = []
                     d[val].append(i)

diff --git a/pandas/tests/base/test_misc.py b/pandas/tests/base/test_misc.py
@@ -201,3 +201,22 @@ def test_get_indexer_non_unique_dtype_mismatch():
     indexes, missing = pd.Index(["A", "B"]).get_indexer_non_unique(pd.Index([0]))
     tm.assert_numpy_array_equal(np.array([-1], dtype=np.intp), indexes)
     tm.assert_numpy_array_equal(np.array([0], dtype=np.int64), missing)
+
+
+@pytest.mark.parametrize(
+    "idx, target, expected",
+    [
+        ([np.nan, "var1", np.nan], [np.nan], np.array([0, 2], dtype=np.int64)),
+        (
+            [np.nan, "var1", np.nan],
+            [np.nan, "var1"],
+            np.array([0, 2, 1], dtype=np.int64),
+        ),
+    ],
+)
+def test_get_indexer_non_unique_multiple_nans(idx, target, expected):
+    # GH 35392
+    axis = pd.Index(idx)
+    actual = axis.get_indexer_for(target)
+
+    tm.assert_numpy_array_equal(actual, expected)