Fix nonzero of a SparseArray (pandas-dev#21175)

Author: babky

doc/source/whatsnew/v0.24.0.rst

@@ -1438,6 +1438,7 @@ Sparse
 - Bug in ``DataFrame.groupby`` not including ``fill_value`` in the groups for non-NA ``fill_value`` when grouping by a sparse column (:issue:`5078`)
 - Bug in unary inversion operator (``~``) on a ``SparseSeries`` with boolean values. The performance of this has also been improved (:issue:`22835`)
 - Bug in :meth:`SparseArary.unique` not returning the unique values (:issue:`19595`)
+- Bug in :meth:`SparseArray.nonzero` and :meth:`SparseDataFrame.dropna` returning shifted/incorrect results (:issue:`21172`)
 
 Build Changes
 ^^^^^^^^^^^^^

pandas/tests/arrays/sparse/test_array.py

@@ -784,6 +784,23 @@ def test_fillna_overlap(self):
         exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
         tm.assert_sp_array_equal(res, exp)
 
+    def test_nonzero(self):
+        # Tests regression #21172.
+        sa = pd.SparseArray([
+            float('nan'),
+            float('nan'),
+            1, 0, 0,
+            2, 0, 0, 0,
+            3, 0, 0
+        ])
+        expected = np.array([2, 5, 9], dtype=np.int32)
+        result, = sa.nonzero()
+        tm.assert_numpy_array_equal(expected, result)
+
+        sa = pd.SparseArray([0, 0, 1, 0, 0, 2, 0, 0, 0, 3, 0, 0])
+        result, = sa.nonzero()
+        tm.assert_numpy_array_equal(expected, result)
+
 
 class TestSparseArrayAnalytics(object):
 

pandas/tests/sparse/frame/test_frame.py

@@ -1360,3 +1360,16 @@ def test_assign_with_sparse_frame(self):
 
         for column in res.columns:
             assert type(res[column]) is SparseSeries
+
+    @pytest.mark.parametrize("inplace", [True, False])
+    @pytest.mark.parametrize("how", ["all", "any"])
+    def test_dropna(self, inplace, how):
+        # Tests regression #21172.
+        expected = pd.SparseDataFrame({"F2": [0, 1]})
+        input_df = pd.SparseDataFrame(
+            {"F1": [float('nan'), float('nan')], "F2": [0, 1]}
+        )
+        result_df = input_df.dropna(axis=1, inplace=inplace, how=how)
+        if inplace:
+            result_df = input_df
+        tm.assert_sp_frame_equal(expected, result_df)