From 4bc01a16aa7bd65342132b994cb07eea903d4ed7 Mon Sep 17 00:00:00 2001 From: keitakurita Date: Sat, 29 Apr 2017 14:31:41 +0900 Subject: [PATCH] BUG: Made SparseDataFrame.fillna() fill all NaNs --- pandas/core/sparse/array.py | 14 ++++++-------- pandas/tests/sparse/test_frame.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 8 deletions(-) diff --git a/pandas/core/sparse/array.py b/pandas/core/sparse/array.py index 5c1cf8c773501..9025f248e26b6 100644 --- a/pandas/core/sparse/array.py +++ b/pandas/core/sparse/array.py @@ -595,14 +595,12 @@ def fillna(self, value, downcast=None): if issubclass(self.dtype.type, np.floating): value = float(value) - if self._null_fill_value: - return self._simple_new(self.sp_values, self.sp_index, - fill_value=value) - else: - new_values = self.sp_values.copy() - new_values[isnull(new_values)] = value - return self._simple_new(new_values, self.sp_index, - fill_value=self.fill_value) + new_values = self.sp_values.copy() + new_values[isnull(new_values)] = value + fill_value = value if isnull(self.fill_value) else self.fill_value + + return self._simple_new(new_values, self.sp_index, + fill_value=fill_value) def sum(self, axis=0, *args, **kwargs): """ diff --git a/pandas/tests/sparse/test_frame.py b/pandas/tests/sparse/test_frame.py index 654d12b782f37..5d75616464fa1 100644 --- a/pandas/tests/sparse/test_frame.py +++ b/pandas/tests/sparse/test_frame.py @@ -1252,6 +1252,7 @@ def test_from_scipy_correct_ordering(spmatrix): tm.skip_if_no_package('scipy') arr = np.arange(1, 5).reshape(2, 2) + try: spm = spmatrix(arr) assert spm.dtype == arr.dtype @@ -1267,6 +1268,33 @@ def test_from_scipy_correct_ordering(spmatrix): tm.assert_frame_equal(sdf.to_dense(), expected.to_dense()) +def test_from_scipy_object_fillna(spmatrix): + # GH 16112 + tm.skip_if_no_package('scipy', max_version='0.19.0') + + arr = np.eye(3) + arr[1:, 0] = np.nan + + try: + spm = spmatrix(arr) + assert spm.dtype == arr.dtype + except (TypeError, AssertionError): + # If conversion to sparse fails for this spmatrix type and arr.dtype, + # then the combination is not currently supported in NumPy, so we + # can just skip testing it thoroughly + return + + sdf = pd.SparseDataFrame(spm).fillna(-1.0) + + # Returning frame should fill all nan values with -1.0 + expected = pd.SparseDataFrame({0: {0: 1.0, 1: np.nan, 2: np.nan}, + 1: {0: np.nan, 1: 1.0, 2: np.nan}, + 2: {0: np.nan, 1: np.nan, 2: 1.0}} + ).fillna(-1.0) + + tm.assert_frame_equal(sdf.to_dense(), expected.to_dense()) + + class TestSparseDataFrameArithmetic(object): def test_numeric_op_scalar(self):