CLN GH23123 Move SparseArray to arrays

pandas/__init__.py

@@ -40,7 +40,7 @@
 import pandas.core.config_init
 
 from pandas.core.api import *
-from pandas.core.sparse.api import *
+from pandas.core.arrays.sparse.api import *
 from pandas.tseries.api import *
 from pandas.core.computation.api import *
 from pandas.core.reshape.api import *

pandas/api/extensions/__init__.py

@@ -3,7 +3,7 @@
                                   register_index_accessor,
                                   register_series_accessor)
 from pandas.core.algorithms import take  # noqa
-from pandas.core.arrays.base import (ExtensionArray,    # noqa
+from pandas.core.arrays import (ExtensionArray,    # noqa
                                      ExtensionScalarOpsMixin)
 from pandas.core.dtypes.dtypes import (  # noqa
     ExtensionDtype, register_extension_dtype

pandas/compat/numpy/function.py

@@ -19,7 +19,8 @@
 """
 
 from numpy import ndarray
-from pandas.util._validators import (validate_args, validate_kwargs,
+from pandas.util._validators import (validate_args,
+                                     validate_kwargs,
                                      validate_args_and_kwargs)
 from pandas.errors import UnsupportedFunctionCall
 from pandas.core.dtypes.common import is_integer, is_bool

pandas/compat/pickle_compat.py

@@ -57,6 +57,14 @@ def load_reduce(self):
 # If classes are moved, provide compat here.
 _class_locations_map = {
 
+    # 23123, fix sparse mapping
+    ('pandas.core.sparse.array', 'SparseArray'):
+        ('pandas.core.arrays.sparse.series', 'SparseArray'),
+    ('pandas.core.sparse.series', 'SparseSeries'):
+        ('pandas.core.arrays.sparse.series', 'SparseSeries'),
+    ('pandas.core.sparse.frame', 'SparseDataFrame'):
+        ('pandas.core.arrays.sparse.frame', 'SparseDataFrame'),
+
     # 15477
     ('pandas.core.base', 'FrozenNDArray'):
         ('pandas.core.indexes.frozen', 'FrozenNDArray'),
@@ -67,7 +75,7 @@ def load_reduce(self):
     ('pandas.core.series', 'TimeSeries'):
         ('pandas.core.series', 'Series'),
     ('pandas.sparse.series', 'SparseTimeSeries'):
-        ('pandas.core.sparse.series', 'SparseSeries'),
+        ('pandas.core.arrays.sparse.series', 'SparseSeries'),
 
     # 12588, extensions moving
     ('pandas._sparse', 'BlockIndex'):
@@ -88,11 +96,11 @@ def load_reduce(self):
 
     # 15998 top-level dirs moving
     ('pandas.sparse.array', 'SparseArray'):
-        ('pandas.core.sparse.array', 'SparseArray'),
+        ('pandas.core.arrays.sparse.array', 'SparseArray'),
     ('pandas.sparse.series', 'SparseSeries'):
-        ('pandas.core.sparse.series', 'SparseSeries'),
+        ('pandas.core.arrays.sparse.series', 'SparseSeries'),
     ('pandas.sparse.frame', 'SparseDataFrame'):
-        ('pandas.core.sparse.frame', 'SparseDataFrame'),
+        ('pandas.core.arrays.sparse.frame', 'SparseDataFrame'),
     ('pandas.indexes.base', '_new_Index'):
         ('pandas.core.indexes.base', '_new_Index'),
     ('pandas.indexes.base', 'Index'):
@@ -112,7 +120,7 @@ def load_reduce(self):
 
     # 19269, arrays moving
     ('pandas.core.categorical', 'Categorical'):
-        ('pandas.core.arrays', 'Categorical'),
+        ('pandas.core.arrays.categorical', 'Categorical'),
 
     # 19939, add timedeltaindex, float64index compat from 15998 move
     ('pandas.tseries.tdi', 'TimedeltaIndex'):

pandas/core/arrays/datetimes.py

@@ -523,7 +523,7 @@ def _add_delta(self, delta):
         The result's name is set outside of _add_delta by the calling
         method (__add__ or __sub__)
         """
-        from pandas.core.arrays.timedeltas import TimedeltaArrayMixin
+        from pandas.core.arrays import TimedeltaArrayMixin
 
         if isinstance(delta, (Tick, timedelta, np.timedelta64)):
             new_values = self._add_delta_td(delta)
@@ -818,7 +818,7 @@ def to_period(self, freq=None):
         pandas.PeriodIndex: Immutable ndarray holding ordinal values
         pandas.DatetimeIndex.to_pydatetime: Return DatetimeIndex as object
         """
-        from pandas.core.arrays.period import PeriodArrayMixin
+        from pandas.core.arrays import PeriodArrayMixin
 
         if self.tz is not None:
             warnings.warn("Converting to PeriodArray/Index representation "

pandas/core/arrays/integer.py

@@ -18,7 +18,8 @@
     is_integer_dtype,
     is_object_dtype,
     is_list_like)
-from pandas.core.arrays import ExtensionArray, ExtensionOpsMixin
+from pandas.core.arrays import (ExtensionArray,
+                                ExtensionOpsMixin)
 from pandas.core.dtypes.base import ExtensionDtype
 from pandas.core.dtypes.dtypes import register_extension_dtype
 from pandas.core.dtypes.missing import isna, notna

pandas/core/arrays/interval.py

@@ -23,7 +23,7 @@
 from pandas.util._decorators import Appender
 from pandas.util._doctools import _WritableDoc
 
-from . import ExtensionArray, Categorical
+from pandas.core.arrays import ExtensionArray, Categorical
 
 _VALID_CLOSED = {'left', 'right', 'both', 'neither'}
 _interval_shared_docs = {}

pandas/core/arrays/period.py

@@ -301,7 +301,7 @@ def to_timestamp(self, freq=None, how='start'):
         -------
         DatetimeArray/Index
         """
-        from pandas.core.arrays.datetimes import DatetimeArrayMixin
+        from pandas.core.arrays import DatetimeArrayMixin
 
         how = libperiod._validate_end_alias(how)
 

pandas/core/arrays/sparse/api.py

@@ -0,0 +1,6 @@
+# pylint: disable=W0611
+# flake8: noqa
+from pandas.core.arrays.sparse.array import SparseArray
+from pandas.core.arrays.sparse.series import SparseSeries
+from pandas.core.arrays.sparse.frame import SparseDataFrame
+from pandas.core.arrays.sparse.dtype import SparseDtype

pandas/core/sparse/array.py → pandas/core/arrays/sparse/array.py

@@ -16,7 +16,7 @@
 from pandas.errors import PerformanceWarning
 from pandas.compat.numpy import function as nv
 
-from pandas.core.arrays.base import ExtensionArray, ExtensionOpsMixin
+from pandas.core.arrays import ExtensionArray, ExtensionOpsMixin
 import pandas.core.common as com
 from pandas.core.dtypes.generic import (
     ABCSparseSeries, ABCSeries, ABCIndexClass
@@ -45,7 +45,7 @@
 import pandas.core.algorithms as algos
 import pandas.io.formats.printing as printing
 
-from pandas.core.sparse.dtype import SparseDtype
+from pandas.core.arrays.sparse.dtype import SparseDtype
 
 
 _sparray_doc_kwargs = dict(klass='SparseArray')

pandas/core/sparse/frame.py → pandas/core/arrays/sparse/frame.py

@@ -22,8 +22,8 @@
 from pandas.core.internals import (BlockManager,
                                    create_block_manager_from_arrays)
 import pandas.core.generic as generic
-from pandas.core.sparse.series import SparseSeries, SparseArray
-from pandas.core.sparse.dtype import SparseDtype
+from pandas.core.arrays.sparse.series import SparseSeries, SparseArray
+from pandas.core.arrays.sparse.dtype import SparseDtype
 from pandas._libs.sparse import BlockIndex, get_blocks
 from pandas.util._decorators import Appender
 import pandas.core.ops as ops

pandas/core/sparse/series.py → pandas/core/arrays/sparse/series.py

@@ -24,13 +24,13 @@
 import pandas._libs.index as libindex
 from pandas.util._decorators import Appender, Substitution
 
-from pandas.core.sparse.array import (
+from pandas.core.arrays.sparse.array import (
     SparseArray,
 )
 from pandas._libs.sparse import BlockIndex, IntIndex
 import pandas._libs.sparse as splib
 
-from pandas.core.sparse.scipy_sparse import (
+from pandas.core.arrays.sparse.scipy_sparse import (
     _sparse_series_to_coo,
     _coo_to_sparse_series)
 
@@ -205,7 +205,7 @@ def _constructor(self):
 
     @property
     def _constructor_expanddim(self):
-        from pandas.core.sparse.api import SparseDataFrame
+        from pandas.core.arrays.sparse.api import SparseDataFrame
         return SparseDataFrame
 
     @property

pandas/core/dtypes/common.py

@@ -1,5 +1,4 @@
 """ common type operations """
-
 import numpy as np
 from pandas.compat import (string_types, text_type, binary_type,
                            PY3, PY36)
@@ -12,7 +11,6 @@
     PeriodDtype, IntervalDtype,
     PandasExtensionDtype, ExtensionDtype,
     _pandas_registry)
-from pandas.core.sparse.dtype import SparseDtype
 from pandas.core.dtypes.generic import (
     ABCCategorical, ABCPeriodIndex, ABCDatetimeIndex, ABCSeries,
     ABCSparseArray, ABCSparseSeries, ABCCategoricalIndex, ABCIndexClass,
@@ -23,7 +21,6 @@
     is_file_like, is_re, is_re_compilable, is_sequence, is_nested_list_like,
     is_named_tuple, is_array_like, is_decimal, is_complex, is_interval)
 
-
 _POSSIBLY_CAST_DTYPES = {np.dtype(t).name
                          for t in ['O', 'int8', 'uint8', 'int16', 'uint16',
                                    'int32', 'uint32', 'int64', 'uint64']}
@@ -181,7 +178,7 @@ def is_sparse(arr):
     >>> is_sparse(bsr_matrix([1, 2, 3]))
     False
     """
-    from pandas.core.sparse.dtype import SparseDtype
+    from pandas.core.arrays.sparse.dtype import SparseDtype
 
     dtype = getattr(arr, 'dtype', arr)
     return isinstance(dtype, SparseDtype)
@@ -1928,10 +1925,13 @@ def _get_dtype_type(arr_or_dtype):
         elif is_interval_dtype(arr_or_dtype):
             return Interval
         return _get_dtype_type(np.dtype(arr_or_dtype))
-    elif isinstance(arr_or_dtype, (ABCSparseSeries, ABCSparseArray,
-                                   SparseDtype)):
-        dtype = getattr(arr_or_dtype, 'dtype', arr_or_dtype)
-        return dtype.type
+    else:
+        from pandas.core.arrays.sparse.dtype import SparseDtype
+        if isinstance(arr_or_dtype, (ABCSparseSeries,
+                                     ABCSparseArray,
+                                     SparseDtype)):
+            dtype = getattr(arr_or_dtype, 'dtype', arr_or_dtype)
+            return dtype.type
     try:
         return arr_or_dtype.dtype.type
     except AttributeError:

pandas/core/dtypes/concat.py

@@ -76,15 +76,15 @@ def _get_series_result_type(result, objs=None):
     if isinstance(result, dict):
         # concat Series with axis 1
         if all(is_sparse(c) for c in compat.itervalues(result)):
-            from pandas.core.sparse.api import SparseDataFrame
+            from pandas.core.arrays.sparse.api import SparseDataFrame
             return SparseDataFrame
         else:
             from pandas.core.frame import DataFrame
             return DataFrame
 
     # otherwise it is a SingleBlockManager (axis = 0)
     if result._block.is_sparse:
-        from pandas.core.sparse.api import SparseSeries
+        from pandas.core.arrays.sparse.api import SparseSeries
         return SparseSeries
     else:
         return objs[0]._constructor
@@ -100,7 +100,7 @@ def _get_frame_result_type(result, objs):
     if (result.blocks and (
             all(is_sparse(b) for b in result.blocks) or
             all(isinstance(obj, ABCSparseDataFrame) for obj in objs))):
-        from pandas.core.sparse.api import SparseDataFrame
+        from pandas.core.arrays.sparse.api import SparseDataFrame
         return SparseDataFrame
     else:
         return next(obj for obj in objs if not isinstance(obj,
@@ -123,7 +123,7 @@ def _get_sliced_frame_result_type(data, obj):
     Series or SparseSeries
     """
     if is_sparse(data):
-        from pandas.core.sparse.api import SparseSeries
+        from pandas.core.arrays.sparse.api import SparseSeries
         return SparseSeries
     return obj._constructor_sliced
 
@@ -556,7 +556,7 @@ def _concat_sparse(to_concat, axis=0, typs=None):
     a single array, preserving the combined dtypes
     """
 
-    from pandas.core.sparse.array import SparseArray
+    from pandas.core.arrays.sparse.array import SparseArray
 
     fill_values = [x.fill_value for x in to_concat
                    if isinstance(x, SparseArray)]

pandas/core/frame.py

@@ -1761,9 +1761,9 @@ def to_sparse(self, fill_value=None, kind='block'):
         1  1.0  NaN
         2  NaN  1.0
         >>> type(sdf)
-        <class 'pandas.core.sparse.frame.SparseDataFrame'>
+        <class 'pandas.core.arrays.sparse.frame.SparseDataFrame'>
         """
-        from pandas.core.sparse.frame import SparseDataFrame
+        from pandas.core.arrays.sparse.frame import SparseDataFrame
         return SparseDataFrame(self._series, index=self.index,
                                columns=self.columns, default_kind=kind,
                                default_fill_value=fill_value)

pandas/core/groupby/generic.py

@@ -44,7 +44,7 @@
 from pandas.core.dtypes.cast import maybe_downcast_to_dtype
 from pandas.core.base import SpecificationError, DataError
 from pandas.core.index import Index, MultiIndex, CategoricalIndex
-from pandas.core.arrays.categorical import Categorical
+from pandas.core.arrays import Categorical
 from pandas.core.internals import BlockManager, make_block
 from pandas.compat.numpy import _np_version_under1p13
 

pandas/core/internals/managers.py

@@ -29,7 +29,7 @@
 
 from pandas.core.base import PandasObject
 import pandas.core.algorithms as algos
-from pandas.core.sparse.array import _maybe_to_sparse
+from pandas.core.arrays.sparse.array import _maybe_to_sparse
 
 from pandas.core.index import Index, MultiIndex, ensure_index
 from pandas.core.indexing import maybe_convert_indices

pandas/core/ops.py

@@ -2066,7 +2066,7 @@ def _cast_sparse_series_op(left, right, opname):
     left : SparseArray
     right : SparseArray
     """
-    from pandas.core.sparse.api import SparseDtype
+    from pandas.core.arrays.sparse.api import SparseDtype
 
     opname = opname.strip('_')
 
@@ -2116,7 +2116,7 @@ def _sparse_series_op(left, right, op, name):
     new_index = left.index
     new_name = get_op_result_name(left, right)
 
-    from pandas.core.sparse.array import _sparse_array_op
+    from pandas.core.arrays.sparse.array import _sparse_array_op
     lvalues, rvalues = _cast_sparse_series_op(left.values, right.values, name)
     result = _sparse_array_op(lvalues, rvalues, op, name)
     return left._constructor(result, index=new_index, name=new_name)
@@ -2130,7 +2130,7 @@ def _arith_method_SPARSE_ARRAY(cls, op, special):
     op_name = _get_op_name(op, special)
 
     def wrapper(self, other):
-        from pandas.core.sparse.array import (
+        from pandas.core.arrays.sparse.array import (
             SparseArray, _sparse_array_op, _wrap_result, _get_fill)
         if isinstance(other, np.ndarray):
             if len(self) != len(other):

pandas/core/reshape/reshape.py

@@ -18,8 +18,8 @@
 from pandas.core.series import Series
 from pandas.core.frame import DataFrame
 
-from pandas.core.sparse.api import SparseDataFrame, SparseSeries
-from pandas.core.sparse.array import SparseArray
+from pandas.core.arrays.sparse.api import SparseDataFrame, SparseSeries
+from pandas.core.arrays.sparse.array import SparseArray
 from pandas._libs.sparse import IntIndex
 
 from pandas.core.arrays import Categorical

pandas/core/series.py

@@ -344,7 +344,7 @@ def from_array(cls, arr, index=None, name=None, dtype=None, copy=False,
                       "future version. Please use the pd.Series(..) "
                       "constructor instead.", FutureWarning, stacklevel=2)
         if isinstance(arr, ABCSparseArray):
-            from pandas.core.sparse.series import SparseSeries
+            from pandas.core.arrays.sparse.series import SparseSeries
             cls = SparseSeries
         return cls(arr, index=index, name=name, dtype=dtype,
                    copy=copy, fastpath=fastpath)
@@ -1383,8 +1383,8 @@ def to_sparse(self, kind='block', fill_value=None):
         sp : SparseSeries
         """
         # TODO: deprecate
-        from pandas.core.sparse.series import SparseSeries
-        from pandas.core.sparse.array import SparseArray
+        from pandas.core.arrays.sparse.series import SparseSeries
+        from pandas.core.arrays.sparse.array import SparseArray
 
         values = SparseArray(self, kind=kind, fill_value=fill_value)
         return SparseSeries(

pandas/core/util/hashing.py

@@ -2,7 +2,6 @@
 data hash pandas / numpy objects
 """
 import itertools
-
 import numpy as np
 from pandas._libs import hashing, tslibs
 from pandas.core.dtypes.generic import (

pandas/io/packers.py

@@ -69,8 +69,8 @@
 from pandas.core.arrays import IntervalArray
 from pandas.core.generic import NDFrame
 from pandas.core.internals import BlockManager, make_block, _safe_reshape
-from pandas.core.sparse.api import SparseSeries, SparseDataFrame
-from pandas.core.sparse.array import BlockIndex, IntIndex
+from pandas.core.arrays.sparse.api import SparseSeries, SparseDataFrame
+from pandas.core.arrays.sparse.array import BlockIndex, IntIndex
 from pandas.io.common import get_filepath_or_buffer, _stringify_path
 from pandas.io.msgpack import Unpacker as _Unpacker, Packer as _Packer, ExtType
 

pandas/io/pytables.py

@@ -50,7 +50,7 @@
 from pandas.core.internals import (BlockManager, make_block,
                                    _block2d_to_blocknd,
                                    _factor_indexer, _block_shape)
-from pandas.core.sparse.array import BlockIndex, IntIndex
+from pandas.core.arrays.sparse.array import BlockIndex, IntIndex
 
 from pandas.io.common import _stringify_path
 from pandas.io.formats.printing import adjoin, pprint_thing