round 4

Author: TomAugspurger

doc/source/whatsnew/v1.0.0.rst

@@ -78,6 +78,8 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+- Removed ``SparseSeries`` and ``SparseDataFrame`` (:issue:``)
 - Removed the previously deprecated :meth:`Series.get_value`, :meth:`Series.set_value`, :meth:`DataFrame.get_value`, :meth:`DataFrame.set_value` (:issue:`17739`)
 - Changed the the default value of `inplace` in :meth:`DataFrame.set_index` and :meth:`Series.set_axis`. It now defaults to False (:issue:`27600`)
 - :meth:`pandas.Series.str.cat` now defaults to aligning ``others``, using ``join='left'`` (:issue:`27611`)

pandas/tests/frame/test_indexing.py

@@ -2145,13 +2145,6 @@ def test_loc_duplicates(self):
         df.loc[trange[bool_idx], "A"] += 6
         tm.assert_frame_equal(df, expected)
 
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-    def test_iloc_sparse_propegate_fill_value(self):
-        from pandas.core.sparse.api import SparseDataFrame
-
-        df = SparseDataFrame({"A": [999, 1]}, default_fill_value=999)
-        assert len(df["A"].sp_values) == len(df.iloc[:, 0].sp_values)
-
     def test_iat(self, float_frame):
 
         for i, row in enumerate(float_frame.index):

pandas/tests/io/generate_legacy_storage_files.py

@@ -53,10 +53,7 @@
     Period,
     RangeIndex,
     Series,
-    SparseDataFrame,
-    SparseSeries,
     Timestamp,
-    bdate_range,
     date_range,
     period_range,
     timedelta_range,
@@ -89,47 +86,6 @@
 _loose_version = LooseVersion(pandas.__version__)
 
 
-def _create_sp_series():
-    nan = np.nan
-
-    # nan-based
-    arr = np.arange(15, dtype=np.float64)
-    arr[7:12] = nan
-    arr[-1:] = nan
-
-    bseries = SparseSeries(arr, kind="block")
-    bseries.name = "bseries"
-    return bseries
-
-
-def _create_sp_tsseries():
-    nan = np.nan
-
-    # nan-based
-    arr = np.arange(15, dtype=np.float64)
-    arr[7:12] = nan
-    arr[-1:] = nan
-
-    date_index = bdate_range("1/1/2011", periods=len(arr))
-    bseries = SparseSeries(arr, index=date_index, kind="block")
-    bseries.name = "btsseries"
-    return bseries
-
-
-def _create_sp_frame():
-    nan = np.nan
-
-    data = {
-        "A": [nan, nan, nan, 0, 1, 2, 3, 4, 5, 6],
-        "B": [0, 1, 2, nan, nan, nan, 3, 4, 5, 6],
-        "C": np.arange(10).astype(np.int64),
-        "D": [0, 1, 2, 3, 4, 5, nan, nan, nan, nan],
-    }
-
-    dates = bdate_range("1/1/2011", periods=10)
-    return SparseDataFrame(data, index=dates)
-
-
 def create_data():
     """ create the pickle/msgpack data """
 
@@ -287,8 +243,6 @@ def create_data():
         index=index,
         scalars=scalars,
         mi=mi,
-        sp_series=dict(float=_create_sp_series(), ts=_create_sp_tsseries()),
-        sp_frame=dict(float=_create_sp_frame()),
         cat=cat,
         timestamp=timestamp,
         offsets=off,
@@ -308,8 +262,6 @@ def _u(x):
 def create_msgpack_data():
     data = create_data()
     # Not supported
-    del data["sp_series"]
-    del data["sp_frame"]
     del data["series"]["cat"]
     del data["series"]["period"]
     del data["frame"]["cat_onecol"]

pandas/tests/io/test_packers.py

@@ -585,49 +585,6 @@ def test_dataframe_duplicate_column_names(self):
         assert_frame_equal(result_3, expected_3)
 
 
-@pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-@pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
-@pytest.mark.filterwarnings("ignore:DataFrame.to_sparse:FutureWarning")
-@pytest.mark.filterwarnings("ignore:.*msgpack:FutureWarning")
-class TestSparse(TestPackers):
-    def _check_roundtrip(self, obj, comparator, **kwargs):
-
-        # currently these are not implemetned
-        # i_rec = self.encode_decode(obj)
-        # comparator(obj, i_rec, **kwargs)
-        msg = r"msgpack sparse (series|frame) is not implemented"
-        with pytest.raises(NotImplementedError, match=msg):
-            self.encode_decode(obj)
-
-    def test_sparse_series(self):
-
-        s = tm.makeStringSeries()
-        s[3:5] = np.nan
-        ss = s.to_sparse()
-        self._check_roundtrip(ss, tm.assert_series_equal, check_series_type=True)
-
-        ss2 = s.to_sparse(kind="integer")
-        self._check_roundtrip(ss2, tm.assert_series_equal, check_series_type=True)
-
-        ss3 = s.to_sparse(fill_value=0)
-        self._check_roundtrip(ss3, tm.assert_series_equal, check_series_type=True)
-
-    def test_sparse_frame(self):
-
-        s = tm.makeDataFrame()
-        s.loc[3:5, 1:3] = np.nan
-        s.loc[8:10, -2] = np.nan
-        ss = s.to_sparse()
-
-        self._check_roundtrip(ss, tm.assert_frame_equal, check_frame_type=True)
-
-        ss2 = s.to_sparse(kind="integer")
-        self._check_roundtrip(ss2, tm.assert_frame_equal, check_frame_type=True)
-
-        ss3 = s.to_sparse(fill_value=0)
-        self._check_roundtrip(ss3, tm.assert_frame_equal, check_frame_type=True)
-
-
 @pytest.mark.filterwarnings("ignore:.*msgpack:FutureWarning")
 class TestCompression(TestPackers):
     """See https://github.com/pandas-dev/pandas/pull/9783

pandas/tests/reshape/test_reshape.py

@@ -273,7 +273,7 @@ def test_dataframe_dummies_subset(self, df, sparse):
         expected[["C"]] = df[["C"]]
         if sparse:
             cols = ["from_A_a", "from_A_b"]
-            expected[cols] = expected[cols].apply(lambda x: pd.SparseSeries(x))
+            expected[cols] = expected[cols].astype(pd.SparseDtype("uint8", 0))
         assert_frame_equal(result, expected)
 
     def test_dataframe_dummies_prefix_sep(self, df, sparse):
@@ -292,7 +292,7 @@ def test_dataframe_dummies_prefix_sep(self, df, sparse):
         expected = expected[["C", "A..a", "A..b", "B..b", "B..c"]]
         if sparse:
             cols = ["A..a", "A..b", "B..b", "B..c"]
-            expected[cols] = expected[cols].apply(lambda x: pd.SparseSeries(x))
+            expected[cols] = expected[cols].astype(pd.SparseDtype("uint8", 0))
 
         assert_frame_equal(result, expected)
 
@@ -329,7 +329,7 @@ def test_dataframe_dummies_prefix_dict(self, sparse):
         columns = ["from_A_a", "from_A_b", "from_B_b", "from_B_c"]
         expected[columns] = expected[columns].astype(np.uint8)
         if sparse:
-            expected[columns] = expected[columns].apply(lambda x: pd.SparseSeries(x))
+            expected[columns] = expected[columns].astype(pd.SparseDtype("uint8", 0))
 
         assert_frame_equal(result, expected)
 
@@ -495,7 +495,7 @@ def test_dataframe_dummies_drop_first_with_categorical(self, df, sparse, dtype):
         expected = expected[["C", "A_b", "B_c", "cat_y"]]
         if sparse:
             for col in cols:
-                expected[col] = pd.SparseSeries(expected[col])
+                expected[col] = pd.SparseArray(expected[col])
         assert_frame_equal(result, expected)
 
     def test_dataframe_dummies_drop_first_with_na(self, df, sparse):
@@ -517,7 +517,7 @@ def test_dataframe_dummies_drop_first_with_na(self, df, sparse):
         expected = expected.sort_index(axis=1)
         if sparse:
             for col in cols:
-                expected[col] = pd.SparseSeries(expected[col])
+                expected[col] = pd.SparseArray(expected[col])
 
         assert_frame_equal(result, expected)
 

pandas/tests/series/test_api.py

@@ -131,12 +131,6 @@ def test_sort_index_name(self):
         result = self.ts.sort_index(ascending=False)
         assert result.name == self.ts.name
 
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-    @pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
-    def test_to_sparse_pass_name(self):
-        result = self.ts.to_sparse()
-        assert result.name == self.ts.name
-
     def test_constructor_dict(self):
         d = {"a": 0.0, "b": 1.0, "c": 2.0}
         result = self.series_klass(d)

pandas/tests/series/test_combine_concat.py

@@ -218,8 +218,6 @@ def test_combine_first_dt_tz_values(self, tz_naive_fixture):
         exp = pd.Series(exp_vals, name="ser1")
         assert_series_equal(exp, result)
 
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-    @pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
     def test_concat_empty_series_dtypes(self):
 
         # booleans
@@ -273,39 +271,6 @@ def test_concat_empty_series_dtypes(self):
             == "object"
         )
 
-        # sparse
-        # TODO: move?
-        result = pd.concat(
-            [Series(dtype="float64").to_sparse(), Series(dtype="float64").to_sparse()]
-        )
-        assert result.dtype == "Sparse[float64]"
-
-        # GH 26705 - Assert .ftype is deprecated
-        with tm.assert_produces_warning(FutureWarning):
-            assert result.ftype == "float64:sparse"
-
-        result = pd.concat(
-            [Series(dtype="float64").to_sparse(), Series(dtype="float64")]
-        )
-        # TODO: release-note: concat sparse dtype
-        expected = pd.core.sparse.api.SparseDtype(np.float64)
-        assert result.dtype == expected
-
-        # GH 26705 - Assert .ftype is deprecated
-        with tm.assert_produces_warning(FutureWarning):
-            assert result.ftype == "float64:sparse"
-
-        result = pd.concat(
-            [Series(dtype="float64").to_sparse(), Series(dtype="object")]
-        )
-        # TODO: release-note: concat sparse dtype
-        expected = pd.core.sparse.api.SparseDtype("object")
-        assert result.dtype == expected
-
-        # GH 26705 - Assert .ftype is deprecated
-        with tm.assert_produces_warning(FutureWarning):
-            assert result.ftype == "object:sparse"
-
     def test_combine_first_dt64(self):
         from pandas.core.tools.datetimes import to_datetime
 

pandas/tests/series/test_missing.py

@@ -6,7 +6,6 @@
 import pytz
 
 from pandas._libs.tslib import iNaT
-from pandas.errors import PerformanceWarning
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -992,65 +991,6 @@ def test_series_fillna_limit(self):
         expected[:3] = np.nan
         assert_series_equal(result, expected)
 
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-    @pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
-    def test_sparse_series_fillna_limit(self):
-        index = np.arange(10)
-        s = Series(np.random.randn(10), index=index)
-
-        ss = s[:2].reindex(index).to_sparse()
-        # TODO: what is this test doing? why are result an expected
-        # the same call to fillna?
-        with tm.assert_produces_warning(
-            PerformanceWarning, raise_on_extra_warnings=False
-        ):
-            # TODO: release-note fillna performance warning
-            result = ss.fillna(method="pad", limit=5)
-            expected = ss.fillna(method="pad", limit=5)
-        expected = expected.to_dense()
-        expected[-3:] = np.nan
-        expected = expected.to_sparse()
-        assert_series_equal(result, expected)
-
-        ss = s[-2:].reindex(index).to_sparse()
-        with tm.assert_produces_warning(
-            PerformanceWarning, raise_on_extra_warnings=False
-        ):
-            result = ss.fillna(method="backfill", limit=5)
-            expected = ss.fillna(method="backfill")
-        expected = expected.to_dense()
-        expected[:3] = np.nan
-        expected = expected.to_sparse()
-        assert_series_equal(result, expected)
-
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
-    @pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
-    def test_sparse_series_pad_backfill_limit(self):
-        index = np.arange(10)
-        s = Series(np.random.randn(10), index=index)
-        s = s.to_sparse()
-
-        result = s[:2].reindex(index, method="pad", limit=5)
-        with tm.assert_produces_warning(
-            PerformanceWarning, raise_on_extra_warnings=False
-        ):
-            expected = s[:2].reindex(index).fillna(method="pad")
-        expected = expected.to_dense()
-        expected[-3:] = np.nan
-        expected = expected.to_sparse()
-        assert_series_equal(result, expected)
-
-        result = s[-2:].reindex(index, method="backfill", limit=5)
-        with tm.assert_produces_warning(
-            PerformanceWarning, raise_on_extra_warnings=False
-        ):
-            expected = s[-2:].reindex(index).fillna(method="backfill")
-        expected = expected.to_dense()
-        expected[:3] = np.nan
-        expected = expected.to_sparse()
-        assert_series_equal(result, expected)
-
-    @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
     def test_series_pad_backfill_limit(self):
         index = np.arange(10)
         s = Series(np.random.randn(10), index=index)