Move to internals

Author: TomAugspurger

pandas/core/arrays/categorical.py

@@ -16,11 +16,11 @@
 from pandas.core.dtypes.cast import (
     coerce_indexer_dtype, maybe_infer_to_datetimelike)
 from pandas.core.dtypes.common import (
-    ensure_int64, ensure_object, ensure_platform_int, extract_array,
-    is_categorical, is_categorical_dtype, is_datetime64_dtype, is_datetimelike,
-    is_dict_like, is_dtype_equal, is_extension_array_dtype, is_float_dtype,
-    is_integer_dtype, is_iterator, is_list_like, is_object_dtype, is_scalar,
-    is_sequence, is_timedelta64_dtype)
+    ensure_int64, ensure_object, ensure_platform_int, is_categorical,
+    is_categorical_dtype, is_datetime64_dtype, is_datetimelike, is_dict_like,
+    is_dtype_equal, is_extension_array_dtype, is_float_dtype, is_integer_dtype,
+    is_iterator, is_list_like, is_object_dtype, is_scalar, is_sequence,
+    is_timedelta64_dtype)
 from pandas.core.dtypes.dtypes import CategoricalDtype
 from pandas.core.dtypes.generic import (
     ABCCategoricalIndex, ABCIndexClass, ABCSeries)
@@ -2091,6 +2091,7 @@ def __setitem__(self, key, value):
             If (one or more) Value is not in categories or if a assigned
             `Categorical` does not have the same categories
         """
+        from pandas.core.internals.arrays import extract_array
 
         value = extract_array(value, extract_numpy=True)
 

pandas/core/arrays/numpy_.py

@@ -5,7 +5,6 @@
 from pandas._libs import lib
 from pandas.compat.numpy import function as nv
 
-from pandas.core.dtypes.common import extract_array
 from pandas.core.dtypes.dtypes import ExtensionDtype
 from pandas.core.dtypes.generic import ABCIndexClass, ABCSeries
 from pandas.core.dtypes.inference import is_list_like
@@ -210,6 +209,8 @@ def __getitem__(self, item):
         return result
 
     def __setitem__(self, key, value):
+        from pandas.core.internals.arrays import extract_array
+
         value = extract_array(value, extract_numpy=True)
 
         if not lib.is_scalar(key) and is_list_like(key):

pandas/core/dtypes/common.py

@@ -14,8 +14,8 @@
     registry)
 from pandas.core.dtypes.generic import (
     ABCCategorical, ABCCategoricalIndex, ABCDateOffset, ABCDatetimeIndex,
-    ABCIndexClass, ABCPandasArray, ABCPeriodArray, ABCPeriodIndex, ABCSeries,
-    ABCSparseArray, ABCSparseSeries)
+    ABCIndexClass, ABCPeriodArray, ABCPeriodIndex, ABCSeries, ABCSparseArray,
+    ABCSparseSeries)
 from pandas.core.dtypes.inference import (  # noqa:F401
     is_array_like, is_bool, is_complex, is_decimal, is_dict_like, is_file_like,
     is_float, is_hashable, is_integer, is_interval, is_iterator, is_list_like,
@@ -2016,54 +2016,3 @@ def pandas_dtype(dtype):
         raise TypeError("dtype '{}' not understood".format(dtype))
 
     return npdtype
-
-
-def extract_array(obj, extract_numpy=False):
-    """
-    Extract the ndarray or ExtensionArray from a Series or Index.
-
-    For all other types, `obj` is just returned as is.
-
-    Parameters
-    ----------
-    obj : object
-        For Series / Index, the underlying ExtensionArray is unboxed.
-        For Numpy-backed ExtensionArrays, the ndarray is extracted.
-
-    extract_numpy : bool, default False
-        Whether to extract the ndarray from a PandasArray
-
-    Returns
-    -------
-    arr : object
-
-    Examples
-    --------
-    >>> extract_array(pd.Series(['a', 'b', 'c'], dtype='category'))
-    [a, b, c]
-    Categories (3, object): [a, b, c]
-
-    Other objects like lists, arrays, and DataFrames are just passed through.
-
-    >>> extract_array([1, 2, 3])
-    [1, 2, 3]
-
-    For an ndarray-backed Series / Index a PandasArray is returned.
-
-    >>> extract_array(pd.Series([1, 2, 3]))
-    <PandasArray>
-    [1, 2, 3]
-    Length: 3, dtype: int64
-
-    To extract all the way down to the ndarray, pass ``extract_numpy=True``.
-
-    >>> extract_array(pd.Series([1, 2, 3]), extract_numpy=True)
-    array([1, 2, 3])
-    """
-    if isinstance(obj, (ABCIndexClass, ABCSeries)):
-        obj = obj.array
-
-    if extract_numpy and isinstance(obj, ABCPandasArray):
-        obj = obj._ndarray
-
-    return obj

pandas/core/internals/arrays.py

@@ -0,0 +1,55 @@
+"""
+Methods for cleaning, validating, and unboxing arrays.
+"""
+from pandas.core.dtypes.generic import ABCIndexClass, ABCPandasArray, ABCSeries
+
+
+def extract_array(obj, extract_numpy=False):
+    """
+    Extract the ndarray or ExtensionArray from a Series or Index.
+
+    For all other types, `obj` is just returned as is.
+
+    Parameters
+    ----------
+    obj : object
+        For Series / Index, the underlying ExtensionArray is unboxed.
+        For Numpy-backed ExtensionArrays, the ndarray is extracted.
+
+    extract_numpy : bool, default False
+        Whether to extract the ndarray from a PandasArray
+
+    Returns
+    -------
+    arr : object
+
+    Examples
+    --------
+    >>> extract_array(pd.Series(['a', 'b', 'c'], dtype='category'))
+    [a, b, c]
+    Categories (3, object): [a, b, c]
+
+    Other objects like lists, arrays, and DataFrames are just passed through.
+
+    >>> extract_array([1, 2, 3])
+    [1, 2, 3]
+
+    For an ndarray-backed Series / Index a PandasArray is returned.
+
+    >>> extract_array(pd.Series([1, 2, 3]))
+    <PandasArray>
+    [1, 2, 3]
+    Length: 3, dtype: int64
+
+    To extract all the way down to the ndarray, pass ``extract_numpy=True``.
+
+    >>> extract_array(pd.Series([1, 2, 3]), extract_numpy=True)
+    array([1, 2, 3])
+    """
+    if isinstance(obj, (ABCIndexClass, ABCSeries)):
+        obj = obj.array
+
+    if extract_numpy and isinstance(obj, ABCPandasArray):
+        obj = obj.to_numpy()
+
+    return obj

pandas/core/internals/blocks.py

@@ -18,13 +18,12 @@
     infer_dtype_from_scalar, maybe_convert_objects, maybe_downcast_to_dtype,
     maybe_infer_dtype_type, maybe_promote, maybe_upcast, soft_convert_objects)
 from pandas.core.dtypes.common import (
-    _NS_DTYPE, _TD_DTYPE, ensure_platform_int, extract_array, is_bool_dtype,
-    is_categorical, is_categorical_dtype, is_datetime64_dtype,
-    is_datetime64tz_dtype, is_dtype_equal, is_extension_array_dtype,
-    is_extension_type, is_float_dtype, is_integer, is_integer_dtype,
-    is_interval_dtype, is_list_like, is_numeric_v_string_like, is_object_dtype,
-    is_period_dtype, is_re, is_re_compilable, is_sparse, is_timedelta64_dtype,
-    pandas_dtype)
+    _NS_DTYPE, _TD_DTYPE, ensure_platform_int, is_bool_dtype, is_categorical,
+    is_categorical_dtype, is_datetime64_dtype, is_datetime64tz_dtype,
+    is_dtype_equal, is_extension_array_dtype, is_extension_type,
+    is_float_dtype, is_integer, is_integer_dtype, is_interval_dtype,
+    is_list_like, is_numeric_v_string_like, is_object_dtype, is_period_dtype,
+    is_re, is_re_compilable, is_sparse, is_timedelta64_dtype, pandas_dtype)
 import pandas.core.dtypes.concat as _concat
 from pandas.core.dtypes.dtypes import (
     CategoricalDtype, DatetimeTZDtype, ExtensionDtype, PandasExtensionDtype)
@@ -41,6 +40,7 @@
 from pandas.core.indexes.datetimes import DatetimeIndex
 from pandas.core.indexes.timedeltas import TimedeltaIndex
 from pandas.core.indexing import check_setitem_lengths
+from pandas.core.internals.arrays import extract_array
 import pandas.core.missing as missing
 
 from pandas.io.formats.printing import pprint_thing

pandas/core/reshape/reshape.py

@@ -11,9 +11,8 @@
 
 from pandas.core.dtypes.cast import maybe_promote
 from pandas.core.dtypes.common import (
-    ensure_platform_int, extract_array, is_bool_dtype,
-    is_extension_array_dtype, is_integer_dtype, is_list_like, is_object_dtype,
-    needs_i8_conversion)
+    ensure_platform_int, is_bool_dtype, is_extension_array_dtype,
+    is_integer_dtype, is_list_like, is_object_dtype, needs_i8_conversion)
 from pandas.core.dtypes.missing import notna
 
 from pandas import compat
@@ -22,6 +21,7 @@
 from pandas.core.arrays.categorical import _factorize_from_iterable
 from pandas.core.frame import DataFrame
 from pandas.core.index import Index, MultiIndex
+from pandas.core.internals.arrays import extract_array
 from pandas.core.series import Series
 from pandas.core.sorting import (
     compress_group_index, decons_obs_group_ids, get_compressed_ids,