DEPR: Deprecate Series/Dataframe.to_dense/to_sparse

pandas/core/frame.py

@@ -1889,6 +1889,8 @@ def to_sparse(self, fill_value=None, kind='block'):
  """
  Convert to SparseDataFrame.
 
+ .. deprecated:: 0.25.0
+
  Implement the sparse version of the DataFrame meaning that any data
  matching a specific value it's omitted in the representation.
  The sparse DataFrame allows for a more efficient storage.
@@ -1939,6 +1941,9 @@ def to_sparse(self, fill_value=None, kind='block'):
  >>> type(sdf) # doctest: +SKIP
  <class 'pandas.core.sparse.frame.SparseDataFrame'>
  """
+ warnings.warn("DataFrame.to_sparse is deprecated and will be removed "
+ "in a future version", FutureWarning, stacklevel=2)
+
  from pandas.core.sparse.api import SparseDataFrame
  return SparseDataFrame(self._series, index=self.index,
  columns=self.columns, default_kind=kind,
@@ -2282,7 +2287,7 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
  text_col 5 non-null object
  float_col 5 non-null float64
  dtypes: float64(1), int64(1), object(1)
- memory usage: 200.0+ bytes
+ memory usage: 248.0+ bytes
 
  Prints a summary of columns count and its dtypes but not per column
  information:
@@ -2292,7 +2297,7 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
  RangeIndex: 5 entries, 0 to 4
  Columns: 3 entries, int_col to float_col
  dtypes: float64(1), int64(1), object(1)
- memory usage: 200.0+ bytes
+ memory usage: 248.0+ bytes
 
  Pipe output of DataFrame.info to buffer instead of sys.stdout, get
  buffer content and writes to a text file:
@@ -2494,7 +2499,7 @@ def memory_usage(self, index=True, deep=False):
  4 1 1.0 1.0+0.0j 1 True
 
  >>> df.memory_usage()
- Index  80
+ Index 128
  int64 40000
  float64 40000
  complex128 80000
@@ -2513,7 +2518,7 @@ def memory_usage(self, index=True, deep=False):
  The memory footprint of `object` dtype columns is ignored by default:
 
  >>> df.memory_usage(deep=True)
- Index  80
+ Index 128
  int64 40000
  float64 40000
  complex128 80000
@@ -2525,7 +2530,7 @@ def memory_usage(self, index=True, deep=False):
  many repeated values.
 
  >>> df['object'].astype('category').memory_usage(deep=True)
- 5168
+ 5216
  """
  result = Series([c.memory_usage(index=False, deep=deep)
  for col, c in self.iteritems()], index=self.columns)

pandas/core/generic.py

@@ -1964,11 +1964,16 @@ def to_dense(self):
  """
  Return dense representation of NDFrame (as opposed to sparse).
 
+ .. deprecated:: 0.25.0
+
  Returns
  -------
  %(klass)s
  Dense %(klass)s.
  """
+ warnings.warn("NDFrame.to_dense is deprecated "
+ "and will be removed in a future version",
+ FutureWarning, stacklevel=2)
  # compat
  return self
 

pandas/core/groupby/ops.py

@@ -630,9 +630,9 @@ def _aggregate_series_fast(self, obj, func):
  group_index, _, ngroups = self.group_info
 
  # avoids object / Series creation overhead
- dummy = obj._get_values(slice(None, 0)).to_dense()
+ dummy = obj._get_values(slice(None, 0))
  indexer = get_group_index_sorter(group_index, ngroups)
- obj = obj._take(indexer).to_dense()
+ obj = obj._take(indexer)
  group_index = algorithms.take_nd(
  group_index, indexer, allow_fill=False)
  grouper = reduction.SeriesGrouper(obj, func, group_index, ngroups,
@@ -879,7 +879,7 @@ def apply(self, f):
 class SeriesSplitter(DataSplitter):
 
  def _chop(self, sdata, slice_obj):
- return sdata._get_values(slice_obj).to_dense()
+ return sdata._get_values(slice_obj)
 
 
 class FrameSplitter(DataSplitter):

pandas/core/series.py

@@ -1575,6 +1575,8 @@ def to_sparse(self, kind='block', fill_value=None):
  """
  Convert Series to SparseSeries.
 
+ .. deprecated:: 0.25.0
+
  Parameters
  ----------
  kind : {'block', 'integer'}, default 'block'
@@ -1586,6 +1588,9 @@ def to_sparse(self, kind='block', fill_value=None):
  SparseSeries
  Sparse representation of the Series.
  """
+
+ warnings.warn("Series.to_sparse is deprecated and will be removed "
+ "in a future version", FutureWarning, stacklevel=2)
  from pandas.core.sparse.series import SparseSeries
 
  values = SparseArray(self, kind=kind, fill_value=fill_value)
@@ -4010,7 +4015,7 @@ def memory_usage(self, index=True, deep=False):
  --------
  >>> s = pd.Series(range(3))
  >>> s.memory_usage()
- 104
+ 152
 
  Not including the index gives the size of the rest of the data, which
  is necessarily smaller:
@@ -4024,9 +4029,9 @@ def memory_usage(self, index=True, deep=False):
  >>> s.values
  array(['a', 'b'], dtype=object)
  >>> s.memory_usage()
- 96
+ 144
  >>> s.memory_usage(deep=True)
- 212
+ 260
  """
  v = super().memory_usage(deep=deep)
  if index:

pandas/core/sparse/frame.py

@@ -242,6 +242,11 @@ def _init_spmatrix(self, data, index, columns, dtype=None,
  def to_coo(self):
  return SparseFrameAccessor(self).to_coo()
 
+ def __repr__(self):
+ with warnings.catch_warnings():
+ warnings.filterwarnings("ignore", "Sparse")
+ return super().__repr__()
+
  def __getstate__(self):
  # pickling
  return dict(_typ=self._typ, _subtyp=self._subtyp, _data=self._data,
@@ -277,6 +282,21 @@ def _unpickle_sparse_frame_compat(self, state):
 
  @Appender(SparseFrameAccessor.to_dense.__doc__)
  def to_dense(self):
+ """
+ .. deprecated:: 0.25.0
+ Use Dataframe.sparse.to_dense() instead
+ """
+
+ warning_message = """\
+SparseDataFrame.to_dense is deprecated and will be removed in a future version
+
+ Use Dataframe.sparse.to_dense() instead
+
+ >>> df = pd.DataFrame({"A": pd.SparseArray([0, 1, 0])})
+ >>> df.sparse.to_dense()
+ """
+ warnings.warn(warning_message, FutureWarning, stacklevel=2)
+
  return SparseFrameAccessor(self).to_dense()
 
  def _apply_columns(self, func):

pandas/core/sparse/series.py

@@ -214,10 +214,12 @@ def as_sparse_array(self, kind=None, fill_value=None, copy=False):
  fill_value=fill_value, kind=kind, copy=copy)
 
  def __repr__(self):
- series_rep = Series.__repr__(self)
- rep = '{series}\n{index!r}'.format(series=series_rep,
- index=self.sp_index)
- return rep
+ with warnings.catch_warnings():
+ warnings.filterwarnings("ignore", "Sparse")
+ series_rep = Series.__repr__(self)
+ rep = '{series}\n{index!r}'.format(series=series_rep,
+ index=self.sp_index)
+ return rep
 
  def _reduce(self, op, name, axis=0, skipna=True, numeric_only=None,
  filter_type=None, **kwds):
@@ -429,11 +431,15 @@ def _set_values(self, key, value):
  def to_dense(self):
  """
  Convert SparseSeries to a Series.
-
+ .. deprecated:: 0.25.0
  Returns
  -------
  s : Series
  """
+ warnings.warn("SparseSeries.to_dense is deprecated "
+ "and will be removed in a future version",
+ FutureWarning, stacklevel=2)
+
  return Series(self.values.to_dense(), index=self.index,
  name=self.name)
 

pandas/tests/arrays/sparse/test_arithmetics.py

@@ -9,6 +9,7 @@
 
 
 @pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
+@pytest.mark.filterwarnings("ignore:Series.to_sparse:FutureWarning")
 class TestSparseArrayArithmetics:
 
  _base = np.array

pandas/tests/frame/test_deprecations.py

@@ -0,0 +1,17 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.util import testing as tm
+
+
+@pytest.mark.filterwarnings("ignore:Sparse:FutureWarning")
+def test_deprecated_to_sparse():
+ df = pd.DataFrame({"A": [1, np.nan, 3]})
+ sparse_df = pd.SparseDataFrame({"A": [1, np.nan, 3]})
+
+ # Deprecated 0.25.0
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ result = df.to_sparse()
+ tm.assert_frame_equal(result, sparse_df)

pandas/tests/generic/test_generic.py

@@ -918,3 +918,16 @@ def test_axis_classmethods(self, box):
  assert obj._get_axis_name(v) == box._get_axis_name(v)
  assert obj._get_block_manager_axis(v) == \
  box._get_block_manager_axis(v)
+
+ def test_deprecated_to_dense(self):
+ # Deprecated 0.25.0
+
+ df = pd.DataFrame({"A": [1, 2, 3]})
+ with tm.assert_produces_warning(FutureWarning):
+ result = df.to_dense()
+ tm.assert_frame_equal(result, df)
+
+ ser = pd.Series([1, 2, 3])
+ with tm.assert_produces_warning(FutureWarning):
+ result = ser.to_dense()
+ tm.assert_series_equal(result, ser)

pandas/tests/io/json/test_pandas.py

@@ -1018,13 +1018,19 @@ def test_sparse(self):
  df = pd.DataFrame(np.random.randn(10, 4))
  df.loc[:8] = np.nan
 
- sdf = df.to_sparse()
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ sdf = df.to_sparse()
  expected = df.to_json()
  assert expected == sdf.to_json()
 
  s = pd.Series(np.random.randn(10))
  s.loc[:8] = np.nan
- ss = s.to_sparse()
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ ss = s.to_sparse()
 
  expected = s.to_json()
  assert expected == ss.to_json()

pandas/tests/io/test_packers.py

@@ -566,15 +566,24 @@ def test_sparse_series(self):
 
  s = tm.makeStringSeries()
  s[3:5] = np.nan
- ss = s.to_sparse()
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ ss = s.to_sparse()
  self._check_roundtrip(ss, tm.assert_series_equal,
  check_series_type=True)
 
- ss2 = s.to_sparse(kind='integer')
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ 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)
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ ss3 = s.to_sparse(fill_value=0)
  self._check_roundtrip(ss3, tm.assert_series_equal,
  check_series_type=True)
 
@@ -583,16 +592,25 @@ 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()
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ ss = s.to_sparse()
 
  self._check_roundtrip(ss, tm.assert_frame_equal,
  check_frame_type=True)
 
- ss2 = s.to_sparse(kind='integer')
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ 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)
+ # GH 26557: DEPR
+ with tm.assert_produces_warning(FutureWarning,
+ check_stacklevel=False):
+ ss3 = s.to_sparse(fill_value=0)
  self._check_roundtrip(ss3, tm.assert_frame_equal,
  check_frame_type=True)