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/_libs/parsers.pyx

@@ -51,7 +51,7 @@ from pandas.core.dtypes.common import (
     is_bool_dtype, is_object_dtype,
     is_datetime64_dtype,
     pandas_dtype)
-from pandas.core.arrays import Categorical
+from pandas.core.arrays.categorical import Categorical
 from pandas.core.dtypes.concat import union_categoricals
 import pandas.io.common as icom
 

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'):
@@ -130,8 +138,13 @@ class Unpickler(pkl._Unpickler):
 
         def find_class(self, module, name):
             # override superclass
+            print(module)
+            print(name)
             key = (module, name)
             module, name = _class_locations_map.get(key, key)
+            print(module)
+            print(name)
+            print("---")
             return super(Unpickler, self).find_class(module, name)
 
 else:

pandas/core/api.py

@@ -6,7 +6,7 @@
 
 from pandas.core.algorithms import factorize, unique, value_counts
 from pandas.core.dtypes.missing import isna, isnull, notna, notnull
-from pandas.core.arrays import Categorical
+from pandas.core.arrays.categorical import Categorical
 from pandas.core.groupby import Grouper
 from pandas.io.formats.format import set_eng_float_format
 from pandas.core.index import (Index, CategoricalIndex, Int64Index,

pandas/core/arrays/__init__.py

@@ -1,10 +0,0 @@
-from .base import (ExtensionArray,    # noqa
-                   ExtensionOpsMixin,
-                   ExtensionScalarOpsMixin)
-from .categorical import Categorical  # noqa
-from .datetimes import DatetimeArrayMixin  # noqa
-from .interval import IntervalArray  # noqa
-from .period import PeriodArrayMixin  # noqa
-from .timedeltas import TimedeltaArrayMixin  # noqa
-from .integer import (  # noqa
-    IntegerArray, integer_array)

pandas/core/arrays/datetimelike.py

@@ -715,7 +715,7 @@ def __rsub__(self, other):
                 # we need to wrap in DatetimeArray/Index and flip the operation
                 if not isinstance(other, DatetimeLikeArrayMixin):
                     # Avoid down-casting DatetimeIndex
-                    from pandas.core.arrays import DatetimeArrayMixin
+                    from pandas.core.arrays.datetimes import DatetimeArrayMixin
                     other = DatetimeArrayMixin(other)
                 return other - self
             elif (is_datetime64_any_dtype(self) and hasattr(other, 'dtype') and

pandas/core/arrays/datetimes.py

@@ -34,7 +34,7 @@
 from pandas.tseries.frequencies import to_offset, get_period_alias
 from pandas.tseries.offsets import Tick, generate_range
 
-from pandas.core.arrays import datetimelike as dtl
+import pandas.core.arrays.datetimelike as dtl
 
 
 _midnight = time(0, 0)

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.base 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 +23,8 @@
 from pandas.util._decorators import Appender
 from pandas.util._doctools import _WritableDoc
 
-from . import ExtensionArray, Categorical
+from pandas.core.arrays.base import ExtensionArray
+from pandas.core.arrays.categorical import Categorical
 
 _VALID_CLOSED = {'left', 'right', 'both', 'neither'}
 _interval_shared_docs = {}

pandas/core/arrays/period.py

@@ -27,7 +27,7 @@
 from pandas.tseries import frequencies
 from pandas.tseries.offsets import Tick, DateOffset
 
-from pandas.core.arrays import datetimelike as dtl
+import pandas.core.arrays.datetimelike as dtl
 from pandas.core.arrays.datetimelike import DatetimeLikeArrayMixin
 
 

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

@@ -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/scipy_sparse.py → pandas/core/arrays/sparse/scipy_sparse.py

@@ -1,6 +1,5 @@
 """
 Interaction with scipy.sparse matrices.
-
 Currently only includes SparseSeries.to_coo helpers.
 """
 from pandas.core.index import MultiIndex, Index

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/arrays/timedeltas.py

@@ -230,7 +230,7 @@ def _add_delta(self, delta):
 
     def _add_datelike(self, other):
         # adding a timedeltaindex to a datetimelike
-        from pandas.core.arrays import DatetimeArrayMixin
+        from pandas.core.arrays.datetimes import DatetimeArrayMixin
         if isinstance(other, (DatetimeArrayMixin, np.ndarray)):
             # if other is an ndarray, we assume it is datetime64-dtype
             # defer to implementation in DatetimeIndex

pandas/core/categorical.py

@@ -4,5 +4,5 @@
 warnings.warn("'pandas.core' is private. Use 'pandas.Categorical'",
               FutureWarning, stacklevel=2)
 
-from pandas.core.arrays import Categorical  # noqa
+from pandas.core.arrays.categorical import Categorical  # noqa
 from pandas.core.dtypes.dtypes import CategoricalDtype  # noqa

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,
@@ -22,7 +20,7 @@
     is_dict_like, is_scalar, is_string_like, is_list_like, is_number,
     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)
-
+from pandas.core.arrays.sparse.dtype import SparseDtype
 
 _POSSIBLY_CAST_DTYPES = {np.dtype(t).name
                          for t in ['O', 'int8', 'uint8', 'int16', 'uint16',
@@ -181,7 +179,7 @@ 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)

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
 
@@ -523,7 +523,7 @@ def _concat_index_asobject(to_concat, name=None):
     PeriodIndex are converted to object dtype before concatenation
     """
     from pandas import Index
-    from pandas.core.arrays import ExtensionArray
+    from pandas.core.arrays.base import ExtensionArray
 
     klasses = (ABCDatetimeIndex, ABCTimedeltaIndex, ABCPeriodIndex,
                ExtensionArray)
@@ -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/dtypes/dtypes.py

@@ -776,7 +776,7 @@ def construct_array_type(cls):
         -------
         type
         """
-        from pandas.core.arrays import IntervalArray
+        from pandas.core.arrays.interval import IntervalArray
         return IntervalArray
 
     @classmethod

pandas/core/frame.py

@@ -80,7 +80,8 @@
 from pandas.core import nanops
 from pandas.core import ops
 from pandas.core.accessor import CachedAccessor
-from pandas.core.arrays import Categorical, ExtensionArray
+from pandas.core.arrays.categorical import Categorical
+from pandas.core.arrays.base import ExtensionArray
 from pandas.core.config import get_option
 from pandas.core.generic import NDFrame, _shared_docs
 from pandas.core.index import (Index, MultiIndex, ensure_index,
@@ -1761,9 +1762,9 @@ 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/grouper.py

@@ -12,7 +12,8 @@
 from pandas.compat import zip, callable
 
 from pandas.core.dtypes.generic import ABCSeries
-from pandas.core.arrays import ExtensionArray, Categorical
+from pandas.core.arrays.base import ExtensionArray
+from pandas.core.arrays.categorical import Categorical
 from pandas.core.index import (
     Index, MultiIndex, CategoricalIndex)
 from pandas.core.dtypes.common import (

pandas/core/indexes/base.py

@@ -14,7 +14,7 @@
 from pandas import compat
 
 from pandas.core.accessor import CachedAccessor
-from pandas.core.arrays import ExtensionArray
+from pandas.core.arrays.base import ExtensionArray
 from pandas.core.dtypes.generic import (
     ABCSeries, ABCDataFrame,
     ABCMultiIndex,

pandas/core/indexes/datetimes.py

@@ -30,7 +30,7 @@
 
 import pandas.core.dtypes.concat as _concat
 from pandas.core.arrays.datetimes import DatetimeArrayMixin, _to_m8
-from pandas.core.arrays import datetimelike as dtl
+import pandas.core.arrays.datetimelike as dtl
 
 from pandas.core.indexes.base import Index, _index_shared_docs
 from pandas.core.indexes.numeric import Int64Index

pandas/core/indexes/multi.py

@@ -1858,7 +1858,7 @@ def _get_labels_for_sorting(self):
         for sorting, where we need to disambiguate that -1 is not
         a valid valid
         """
-        from pandas.core.arrays import Categorical
+        from pandas.core.arrays.categorical import Categorical
 
         def cats(label):
             return np.arange(np.array(label).max() + 1 if len(label) else 0,

pandas/core/indexes/period.py

@@ -31,7 +31,7 @@
 from pandas._libs.tslibs import resolution, period
 
 from pandas.core.algorithms import unique1d
-from pandas.core.arrays import datetimelike as dtl
+import pandas.core.arrays.datetimelike as dtl
 from pandas.core.arrays.period import PeriodArrayMixin, dt64arr_to_periodarr
 from pandas.core.base import _shared_docs
 from pandas.core.indexes.base import _index_shared_docs, ensure_index