CLN: more assorted cleanups (pandas-dev#27555)

Author: jbrockmendel

pandas/_libs/missing.pyx

@@ -80,11 +80,8 @@ cpdef bint checknull_old(object val):
 
 
 cdef inline bint _check_none_nan_inf_neginf(object val):
-    try:
-        return val is None or (isinstance(val, float) and
-                               (val != val or val == INF or val == NEGINF))
-    except ValueError:
-        return False
+    return val is None or (isinstance(val, float) and
+                           (val != val or val == INF or val == NEGINF))
 
 
 @cython.wraparound(False)

pandas/core/arrays/categorical.py

@@ -38,12 +38,7 @@
     is_timedelta64_dtype,
 )
 from pandas.core.dtypes.dtypes import CategoricalDtype
-from pandas.core.dtypes.generic import (
-    ABCCategoricalIndex,
-    ABCDataFrame,
-    ABCIndexClass,
-    ABCSeries,
-)
+from pandas.core.dtypes.generic import ABCDataFrame, ABCIndexClass, ABCSeries
 from pandas.core.dtypes.inference import is_hashable
 from pandas.core.dtypes.missing import isna, notna
 
@@ -166,19 +161,6 @@ def f(self, other):
     return f
 
 
-def _maybe_to_categorical(array):
-    """
-    Coerce to a categorical if a series is given.
-
-    Internal use ONLY.
-    """
-    if isinstance(array, (ABCSeries, ABCCategoricalIndex)):
-        return array._values
-    elif isinstance(array, np.ndarray):
-        return Categorical(array)
-    return array
-
-
 def contains(cat, key, container):
     """
     Helper for membership check for ``key`` in ``cat``.
@@ -1988,23 +1970,6 @@ def take_nd(self, indexer, allow_fill=None, fill_value=None):
 
     take = take_nd
 
-    def _slice(self, slicer):
-        """
-        Return a slice of myself.
-
-        For internal compatibility with numpy arrays.
-        """
-
-        # only allow 1 dimensional slicing, but can
-        # in a 2-d case be passd (slice(None),....)
-        if isinstance(slicer, tuple) and len(slicer) == 2:
-            if not com.is_null_slice(slicer[0]):
-                raise AssertionError("invalid slicing for a 1-ndim " "categorical")
-            slicer = slicer[1]
-
-        codes = self._codes[slicer]
-        return self._constructor(values=codes, dtype=self.dtype, fastpath=True)
-
     def __len__(self):
         """
         The length of this Categorical.

pandas/core/arrays/sparse.py

@@ -601,10 +601,6 @@ def __init__(
         dtype=None,
         copy=False,
     ):
-        from pandas.core.internals import SingleBlockManager
-
-        if isinstance(data, SingleBlockManager):
-            data = data.internal_values()
 
         if fill_value is None and isinstance(dtype, SparseDtype):
             fill_value = dtype.fill_value
@@ -1859,15 +1855,6 @@ def _formatter(self, boxed=False):
 SparseArray._add_unary_ops()
 
 
-def _maybe_to_dense(obj):
-    """
-    try to convert to dense
-    """
-    if hasattr(obj, "to_dense"):
-        return obj.to_dense()
-    return obj
-
-
 def make_sparse(arr, kind="block", fill_value=None, dtype=None, copy=False):
     """
     Convert ndarray to sparse format

pandas/core/generic.py

@@ -4892,12 +4892,12 @@ def sample(
         if weights is not None:
 
             # If a series, align with frame
-            if isinstance(weights, pd.Series):
+            if isinstance(weights, ABCSeries):
                 weights = weights.reindex(self.axes[axis])
 
             # Strings acceptable if a dataframe and axis = 0
             if isinstance(weights, str):
-                if isinstance(self, pd.DataFrame):
+                if isinstance(self, ABCDataFrame):
                     if axis == 0:
                         try:
                             weights = self[weights]
@@ -6628,7 +6628,7 @@ def replace(
                 to_replace = [to_replace]
 
             if isinstance(to_replace, (tuple, list)):
-                if isinstance(self, pd.DataFrame):
+                if isinstance(self, ABCDataFrame):
                     return self.apply(
                         _single_replace, args=(to_replace, method, inplace, limit)
                     )
@@ -7421,7 +7421,7 @@ def _clip_with_one_bound(self, threshold, method, axis, inplace):
         # be transformed to NDFrame from other array like structure.
         if (not isinstance(threshold, ABCSeries)) and is_list_like(threshold):
             if isinstance(self, ABCSeries):
-                threshold = pd.Series(threshold, index=self.index)
+                threshold = self._constructor(threshold, index=self.index)
             else:
                 threshold = _align_method_FRAME(self, threshold, axis)
         return self.where(subset, threshold, axis=axis, inplace=inplace)
@@ -7510,9 +7510,9 @@ def clip(self, lower=None, upper=None, axis=None, inplace=False, *args, **kwargs
         # so ignore
         # GH 19992
         # numpy doesn't drop a list-like bound containing NaN
-        if not is_list_like(lower) and np.any(pd.isnull(lower)):
+        if not is_list_like(lower) and np.any(isna(lower)):
             lower = None
-        if not is_list_like(upper) and np.any(pd.isnull(upper)):
+        if not is_list_like(upper) and np.any(isna(upper)):
             upper = None
 
         # GH 2747 (arguments were reversed)
@@ -8985,7 +8985,7 @@ def _where(
 
         msg = "Boolean array expected for the condition, not {dtype}"
 
-        if not isinstance(cond, pd.DataFrame):
+        if not isinstance(cond, ABCDataFrame):
             # This is a single-dimensional object.
             if not is_bool_dtype(cond):
                 raise ValueError(msg.format(dtype=cond.dtype))

pandas/core/groupby/generic.py

@@ -35,7 +35,7 @@
     is_object_dtype,
     is_scalar,
 )
-from pandas.core.dtypes.missing import isna, notna
+from pandas.core.dtypes.missing import _isna_ndarraylike, isna, notna
 
 from pandas._typing import FrameOrSeries
 import pandas.core.algorithms as algorithms
@@ -44,8 +44,13 @@
 from pandas.core.frame import DataFrame
 from pandas.core.generic import ABCDataFrame, ABCSeries, NDFrame, _shared_docs
 from pandas.core.groupby import base
-from pandas.core.groupby.groupby import GroupBy, _apply_docs, _transform_template
-from pandas.core.index import Index, MultiIndex
+from pandas.core.groupby.groupby import (
+    GroupBy,
+    _apply_docs,
+    _transform_template,
+    groupby,
+)
+from pandas.core.index import Index, MultiIndex, _all_indexes_same
 import pandas.core.indexes.base as ibase
 from pandas.core.internals import BlockManager, make_block
 from pandas.core.series import Series
@@ -162,8 +167,6 @@ def _cython_agg_blocks(self, how, alt=None, numeric_only=True, min_count=-1):
                     continue
 
                 # call our grouper again with only this block
-                from pandas.core.groupby.groupby import groupby
-
                 obj = self.obj[data.items[locs]]
                 s = groupby(obj, self.grouper)
                 try:
@@ -348,8 +351,6 @@ def _decide_output_index(self, output, labels):
         return output_keys
 
     def _wrap_applied_output(self, keys, values, not_indexed_same=False):
-        from pandas.core.index import _all_indexes_same
-
         if len(keys) == 0:
             return DataFrame(index=keys)
 
@@ -1590,13 +1591,14 @@ def count(self):
         DataFrame
             Count of values within each group.
         """
-        from pandas.core.dtypes.missing import _isna_ndarraylike as _isna
-
         data, _ = self._get_data_to_aggregate()
         ids, _, ngroups = self.grouper.group_info
         mask = ids != -1
 
-        val = ((mask & ~_isna(np.atleast_2d(blk.get_values()))) for blk in data.blocks)
+        val = (
+            (mask & ~_isna_ndarraylike(np.atleast_2d(blk.get_values())))
+            for blk in data.blocks
+        )
         loc = (blk.mgr_locs for blk in data.blocks)
 
         counter = partial(lib.count_level_2d, labels=ids, max_bin=ngroups, axis=1)

pandas/core/internals/blocks.py

@@ -3074,10 +3074,10 @@ class CategoricalBlock(ExtensionBlock):
     _concatenator = staticmethod(concat_categorical)
 
     def __init__(self, values, placement, ndim=None):
-        from pandas.core.arrays.categorical import _maybe_to_categorical
-
         # coerce to categorical if we can
-        super().__init__(_maybe_to_categorical(values), placement=placement, ndim=ndim)
+        values = extract_array(values)
+        assert isinstance(values, Categorical), type(values)
+        super().__init__(values, placement=placement, ndim=ndim)
 
     @property
     def _holder(self):

pandas/core/reshape/pivot.py

@@ -127,8 +127,6 @@ def pivot_table(
         table = agged.unstack(to_unstack)
 
     if not dropna:
-        from pandas import MultiIndex
-
         if table.index.nlevels > 1:
             m = MultiIndex.from_arrays(
                 cartesian_product(table.index.levels), names=table.index.names

pandas/core/sorting.py

@@ -202,19 +202,19 @@ def lexsort_indexer(keys, orders=None, na_position="last"):
 
         # we are already a Categorical
         if is_categorical_dtype(key):
-            c = key
+            cat = key
 
         # create the Categorical
         else:
-            c = Categorical(key, ordered=True)
+            cat = Categorical(key, ordered=True)
 
         if na_position not in ["last", "first"]:
             raise ValueError("invalid na_position: {!r}".format(na_position))
 
-        n = len(c.categories)
-        codes = c.codes.copy()
+        n = len(cat.categories)
+        codes = cat.codes.copy()
 
-        mask = c.codes == -1
+        mask = cat.codes == -1
         if order:  # ascending
             if na_position == "last":
                 codes = np.where(mask, n, codes)

pandas/core/sparse/series.py

@@ -114,6 +114,11 @@ def __init__(
         elif is_scalar(data) and index is not None:
             data = np.full(len(index), fill_value=data)
 
+        if isinstance(data, SingleBlockManager):
+            # SparseArray doesn't accept SingleBlockManager
+            index = data.index
+            data = data.blocks[0].values
+
         super().__init__(
             SparseArray(
                 data,

pandas/core/window.py

@@ -40,6 +40,7 @@
 import pandas.core.common as com
 from pandas.core.generic import _shared_docs
 from pandas.core.groupby.base import GroupByMixin
+from pandas.core.index import Index, MultiIndex, ensure_index
 
 _shared_docs = dict(**_shared_docs)
 _doc_template = """
@@ -281,7 +282,6 @@ def _wrap_results(self, results, blocks, obj, exclude=None) -> FrameOrSeries:
         """
 
         from pandas import Series, concat
-        from pandas.core.index import ensure_index
 
         final = []
         for result, block in zip(results, blocks):
@@ -1691,8 +1691,6 @@ def _on(self):
         if self.on is None:
             return self.obj.index
         elif isinstance(self.obj, ABCDataFrame) and self.on in self.obj.columns:
-            from pandas import Index
-
             return Index(self.obj[self.on])
         else:
             raise ValueError(
@@ -2670,7 +2668,7 @@ def dataframe_from_int_dict(data, frame_template):
                                 *_prep_binary(arg1.iloc[:, i], arg2.iloc[:, j])
                             )
 
-                from pandas import MultiIndex, concat
+                from pandas import concat
 
                 result_index = arg1.index.union(arg2.index)
                 if len(result_index):