CLN: Assorted cleanups (#28563)

Author: jbrockmendel

pandas/core/algorithms.py

@@ -39,7 +39,6 @@
     is_period_dtype,
     is_scalar,
     is_signed_integer_dtype,
-    is_sparse,
     is_timedelta64_dtype,
     is_unsigned_integer_dtype,
     needs_i8_conversion,
@@ -743,7 +742,7 @@ def value_counts(
 
     else:
 
-        if is_extension_array_dtype(values) or is_sparse(values):
+        if is_extension_array_dtype(values):
 
             # handle Categorical and sparse,
             result = Series(values)._values.value_counts(dropna=dropna)
@@ -1623,7 +1622,7 @@ def take_nd(
     out : ndarray or None, default None
         Optional output array, must be appropriate type to hold input and
         fill_value together, if indexer has any -1 value entries; call
-        _maybe_promote to determine this type for any fill_value
+        maybe_promote to determine this type for any fill_value
     fill_value : any, default np.nan
         Fill value to replace -1 values with
     mask_info : tuple of (ndarray, boolean)
@@ -1644,9 +1643,7 @@ def take_nd(
     if is_extension_array_dtype(arr):
         return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
 
-    if is_sparse(arr):
-        arr = arr.to_dense()
-    elif isinstance(arr, (ABCIndexClass, ABCSeries)):
+    if isinstance(arr, (ABCIndexClass, ABCSeries)):
         arr = arr._values
 
     arr = np.asarray(arr)

pandas/core/construction.py

@@ -9,7 +9,7 @@
 import numpy as np
 import numpy.ma as ma
 
-from pandas._libs import lib, tslibs
+from pandas._libs import lib
 from pandas._libs.tslibs import IncompatibleFrequency, OutOfBoundsDatetime
 
 from pandas.core.dtypes.cast import (
@@ -36,7 +36,7 @@
     is_timedelta64_ns_dtype,
     pandas_dtype,
 )
-from pandas.core.dtypes.dtypes import ExtensionDtype, registry
+from pandas.core.dtypes.dtypes import CategoricalDtype, ExtensionDtype, registry
 from pandas.core.dtypes.generic import (
     ABCExtensionArray,
     ABCIndexClass,
@@ -275,7 +275,7 @@ def array(
         if inferred_dtype == "period":
             try:
                 return period_array(data, copy=copy)
-            except tslibs.IncompatibleFrequency:
+            except IncompatibleFrequency:
                 # We may have a mixture of frequencies.
                 # We choose to return an ndarray, rather than raising.
                 pass
@@ -365,7 +365,9 @@ def extract_array(obj, extract_numpy=False):
     return obj
 
 
-def sanitize_array(data, index, dtype=None, copy=False, raise_cast_failure=False):
+def sanitize_array(
+    data, index, dtype=None, copy: bool = False, raise_cast_failure: bool = False
+):
     """
     Sanitize input data to an ndarray, copy if specified, coerce to the
     dtype if specified.
@@ -486,13 +488,19 @@ def sanitize_array(data, index, dtype=None, copy=False, raise_cast_failure=False
     return subarr
 
 
-def _try_cast(arr, dtype, copy, raise_cast_failure):
+def _try_cast(
+    arr,
+    dtype: Optional[Union[np.dtype, "ExtensionDtype"]],
+    copy: bool,
+    raise_cast_failure: bool,
+):
     """
     Convert input to numpy ndarray and optionally cast to a given dtype.
 
     Parameters
     ----------
-    arr : array-like
+    arr : ndarray, list, tuple, iterator (catchall)
+        Excludes: ExtensionArray, Series, Index.
     dtype : np.dtype, ExtensionDtype or None
     copy : bool
         If False, don't copy the data if not needed.
@@ -528,11 +536,13 @@ def _try_cast(arr, dtype, copy, raise_cast_failure):
         if is_categorical_dtype(dtype):
             # We *do* allow casting to categorical, since we know
             # that Categorical is the only array type for 'category'.
+            dtype = cast(CategoricalDtype, dtype)
             subarr = dtype.construct_array_type()(
                 arr, dtype.categories, ordered=dtype._ordered
             )
         elif is_extension_array_dtype(dtype):
             # create an extension array from its dtype
+            dtype = cast(ExtensionDtype, dtype)
             array_type = dtype.construct_array_type()._from_sequence
             subarr = array_type(arr, dtype=dtype, copy=copy)
         elif dtype is not None and raise_cast_failure:

pandas/core/dtypes/cast.py

@@ -1311,9 +1311,8 @@ def construct_1d_ndarray_preserving_na(values, dtype=None, copy=False):
     >>> np.array([1.0, 2.0, None], dtype='str')
     array(['1.0', '2.0', 'None'], dtype='<U4')
 
-    >>> construct_1d_ndarray_preserving_na([1.0, 2.0, None], dtype='str')
-
-
+    >>> construct_1d_ndarray_preserving_na([1.0, 2.0, None], dtype=np.dtype('str'))
+    array(['1.0', '2.0', None], dtype=object)
     """
     subarr = np.array(values, dtype=dtype, copy=copy)
 

pandas/core/dtypes/common.py

@@ -888,7 +888,8 @@ def is_dtype_equal(source, target):
 
 
 def is_any_int_dtype(arr_or_dtype) -> bool:
-    """Check whether the provided array or dtype is of an integer dtype.
+    """
+    Check whether the provided array or dtype is of an integer dtype.
 
     In this function, timedelta64 instances are also considered "any-integer"
     type objects and will return True.

pandas/core/internals/blocks.py

@@ -2128,7 +2128,8 @@ def _can_hold_na(self):
         return True
 
     def _maybe_coerce_values(self, values):
-        """Input validation for values passed to __init__. Ensure that
+        """
+        Input validation for values passed to __init__. Ensure that
         we have datetime64ns, coercing if necessary.
 
         Parameters