From 0583e981fb930983e12a3c56fe47f881feda516f Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Sat, 22 Apr 2023 07:20:55 -0700
Subject: [PATCH 1/4] REF: avoid is_scalar

---
 pandas/core/algorithms.py           |  5 ++---
 pandas/core/array_algos/replace.py  |  4 ++--
 pandas/core/arrays/sparse/array.py  |  2 --
 pandas/core/dtypes/cast.py          |  2 --
 pandas/core/frame.py                |  2 +-
 pandas/core/generic.py              |  4 +---
 pandas/core/indexes/base.py         | 11 ++++++-----
 pandas/core/nanops.py               | 17 +++++++++--------
 pandas/core/strings/base.py         |  3 ++-
 pandas/core/strings/object_array.py | 19 ++++++++++++-------
 pandas/core/tools/datetimes.py      |  4 +---
 pandas/io/parsers/base_parser.py    | 28 +++++++++++-----------------
 12 files changed, 47 insertions(+), 54 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 4f771b3c80791..eac0b73d75ad8 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -50,7 +50,6 @@
     is_integer_dtype,
     is_list_like,
     is_object_dtype,
-    is_scalar,
     is_signed_integer_dtype,
     needs_i8_conversion,
 )
@@ -1324,7 +1323,7 @@ def searchsorted(
         # Before searching below, we therefore try to give `value` the
         # same dtype as `arr`, while guarding against integer overflows.
         iinfo = np.iinfo(arr.dtype.type)
-        value_arr = np.array([value]) if is_scalar(value) else np.array(value)
+        value_arr = np.array([value]) if is_integer(value) else np.array(value)
         if (value_arr >= iinfo.min).all() and (value_arr <= iinfo.max).all():
             # value within bounds, so no overflow, so can convert value dtype
             # to dtype of arr
@@ -1332,7 +1331,7 @@ def searchsorted(
         else:
             dtype = value_arr.dtype
 
-        if is_scalar(value):
+        if is_integer(value):
             # We know that value is int
             value = cast(int, dtype.type(value))
         else:
diff --git a/pandas/core/array_algos/replace.py b/pandas/core/array_algos/replace.py
index af01a692bc0ce..85d1f7ccf2e88 100644
--- a/pandas/core/array_algos/replace.py
+++ b/pandas/core/array_algos/replace.py
@@ -14,9 +14,9 @@
 import numpy as np
 
 from pandas.core.dtypes.common import (
+    is_bool,
     is_re,
     is_re_compilable,
-    is_scalar,
 )
 from pandas.core.dtypes.missing import isna
 
@@ -72,7 +72,7 @@ def _check_comparison_types(
         Raises an error if the two arrays (a,b) cannot be compared.
         Otherwise, returns the comparison result as expected.
         """
-        if is_scalar(result) and isinstance(a, np.ndarray):
+        if is_bool(result) and isinstance(a, np.ndarray):
             type_names = [type(a).__name__, type(b).__name__]
 
             type_names[0] = f"ndarray(dtype={a.dtype})"
diff --git a/pandas/core/arrays/sparse/array.py b/pandas/core/arrays/sparse/array.py
index 18a1fc248f7b5..4c32be4849706 100644
--- a/pandas/core/arrays/sparse/array.py
+++ b/pandas/core/arrays/sparse/array.py
@@ -1120,8 +1120,6 @@ def searchsorted(
     ) -> npt.NDArray[np.intp] | np.intp:
         msg = "searchsorted requires high memory usage."
         warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
-        if not is_scalar(v):
-            v = np.asarray(v)
         v = np.asarray(v)
         return np.asarray(self, dtype=self.dtype.subtype).searchsorted(v, side, sorter)
 
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index fd8c651fe73dc..5ceabf11b743c 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -455,8 +455,6 @@ def maybe_cast_pointwise_result(
         result maybe casted to the dtype.
     """
 
-    assert not is_scalar(result)
-
     if isinstance(dtype, ExtensionDtype):
         if not isinstance(dtype, (CategoricalDtype, DatetimeTZDtype)):
             # TODO: avoid this special-casing
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 04c1b18cb1af1..89be1c1da34f4 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -3914,7 +3914,7 @@ def isetitem(self, loc, value) -> None:
         ``frame[frame.columns[i]] = value``.
         """
         if isinstance(value, DataFrame):
-            if is_scalar(loc):
+            if is_integer(loc):
                 loc = [loc]
 
             if len(loc) != len(value.columns):
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index e01d3c44172c2..b6d862ba2180c 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -8346,9 +8346,7 @@ def clip(
             lower, upper = min(lower, upper), max(lower, upper)
 
         # fast-path for scalars
-        if (lower is None or (is_scalar(lower) and is_number(lower))) and (
-            upper is None or (is_scalar(upper) and is_number(upper))
-        ):
+        if (lower is None or is_number(lower)) and (upper is None or is_number(upper)):
             return self._clip_with_scalar(lower, upper, inplace=inplace)
 
         result = self
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
index 75320a28eb16b..8e3fd72acd8e1 100644
--- a/pandas/core/indexes/base.py
+++ b/pandas/core/indexes/base.py
@@ -916,6 +916,9 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str_t, *inputs, **kwargs):
         if ufunc.nout == 2:
             # i.e. np.divmod, np.modf, np.frexp
             return tuple(self.__array_wrap__(x) for x in result)
+        elif method == "reduce":
+            result = lib.item_from_zerodim(result)
+            return result
 
         if result.dtype == np.float16:
             result = result.astype(np.float32)
@@ -928,11 +931,9 @@ def __array_wrap__(self, result, context=None):
         Gets called after a ufunc and other functions e.g. np.split.
         """
         result = lib.item_from_zerodim(result)
-        if (
-            (not isinstance(result, Index) and is_bool_dtype(result.dtype))
-            or lib.is_scalar(result)
-            or np.ndim(result) > 1
-        ):
+        if (not isinstance(result, Index) and is_bool_dtype(result.dtype)) or np.ndim(
+            result
+        ) > 1:
             # exclude Index to avoid warning from is_bool_dtype deprecation;
             #  in the Index case it doesn't matter which path we go down.
             # reached in plotting tests with e.g. np.nonzero(index)
diff --git a/pandas/core/nanops.py b/pandas/core/nanops.py
index 8fddc8461dfbe..b405447239a7a 100644
--- a/pandas/core/nanops.py
+++ b/pandas/core/nanops.py
@@ -40,7 +40,6 @@
     is_integer,
     is_numeric_dtype,
     is_object_dtype,
-    is_scalar,
     needs_i8_conversion,
     pandas_dtype,
 )
@@ -291,7 +290,6 @@ def _get_values(
     # In _get_values is only called from within nanops, and in all cases
     #  with scalar fill_value.  This guarantee is important for the
     #  np.where call below
-    assert is_scalar(fill_value)
 
     mask = _maybe_get_mask(values, skipna, mask)
 
@@ -876,12 +874,15 @@ def _get_counts_nanvar(
     d = count - dtype.type(ddof)
 
     # always return NaN, never inf
-    if is_scalar(count):
+    if is_float(count):
         if count <= ddof:
-            count = np.nan
+            # error: Incompatible types in assignment (expression has type
+            # "float", variable has type "Union[floating[Any], ndarray[Any,
+            # dtype[floating[Any]]]]")
+            count = np.nan  # type: ignore[assignment]
             d = np.nan
     else:
-        # count is not narrowed by is_scalar check
+        # count is not narrowed by is_float check
         count = cast(np.ndarray, count)
         mask = count <= ddof
         if mask.any():
@@ -1444,8 +1445,8 @@ def _get_counts(
     values_shape: Shape,
     mask: npt.NDArray[np.bool_] | None,
     axis: AxisInt | None,
-    dtype: np.dtype = np.dtype(np.float64),
-) -> float | np.ndarray:
+    dtype: np.dtype[np.floating] = np.dtype(np.float64),
+) -> np.floating | npt.NDArray[np.floating]:
     """
     Get the count of non-null values along an axis
 
@@ -1476,7 +1477,7 @@ def _get_counts(
     else:
         count = values_shape[axis]
 
-    if is_scalar(count):
+    if is_integer(count):
         return dtype.type(count)
     return count.astype(dtype, copy=False)
 
diff --git a/pandas/core/strings/base.py b/pandas/core/strings/base.py
index 2672d22935d72..44b311ad96387 100644
--- a/pandas/core/strings/base.py
+++ b/pandas/core/strings/base.py
@@ -5,6 +5,7 @@
     TYPE_CHECKING,
     Callable,
     Literal,
+    Sequence,
 )
 
 import numpy as np
@@ -79,7 +80,7 @@ def _str_replace(
         pass
 
     @abc.abstractmethod
-    def _str_repeat(self, repeats):
+    def _str_repeat(self, repeats: int | Sequence[int]):
         pass
 
     @abc.abstractmethod
diff --git a/pandas/core/strings/object_array.py b/pandas/core/strings/object_array.py
index 294bd0ebe356b..87cc6e71b8672 100644
--- a/pandas/core/strings/object_array.py
+++ b/pandas/core/strings/object_array.py
@@ -8,6 +8,8 @@
     TYPE_CHECKING,
     Callable,
     Literal,
+    Sequence,
+    cast,
 )
 import unicodedata
 
@@ -17,7 +19,6 @@
 import pandas._libs.missing as libmissing
 import pandas._libs.ops as libops
 
-from pandas.core.dtypes.common import is_scalar
 from pandas.core.dtypes.missing import isna
 
 from pandas.core.strings.base import BaseStringArrayMethods
@@ -177,14 +178,15 @@ def _str_replace(
 
         return self._str_map(f, dtype=str)
 
-    def _str_repeat(self, repeats):
-        if is_scalar(repeats):
+    def _str_repeat(self, repeats: int | Sequence[int]):
+        if lib.is_integer(repeats):
+            rint = cast(int, repeats)
 
             def scalar_rep(x):
                 try:
-                    return bytes.__mul__(x, repeats)
+                    return bytes.__mul__(x, rint)
                 except TypeError:
-                    return str.__mul__(x, repeats)
+                    return str.__mul__(x, rint)
 
             return self._str_map(scalar_rep, dtype=str)
         else:
@@ -198,8 +200,11 @@ def rep(x, r):
                 except TypeError:
                     return str.__mul__(x, r)
 
-            repeats = np.asarray(repeats, dtype=object)
-            result = libops.vec_binop(np.asarray(self), repeats, rep)
+            result = libops.vec_binop(
+                np.asarray(self),
+                np.asarray(repeats, dtype=object),
+                rep,
+            )
             if isinstance(self, BaseStringArray):
                 # Not going through map, so we have to do this here.
                 result = type(self)._from_sequence(result)
diff --git a/pandas/core/tools/datetimes.py b/pandas/core/tools/datetimes.py
index 3e1b6070ffc39..74210a1ce5ad8 100644
--- a/pandas/core/tools/datetimes.py
+++ b/pandas/core/tools/datetimes.py
@@ -56,7 +56,6 @@
     is_integer_dtype,
     is_list_like,
     is_numeric_dtype,
-    is_scalar,
 )
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
 from pandas.core.dtypes.generic import (
@@ -599,8 +598,7 @@ def _adjust_to_origin(arg, origin, unit):
     else:
         # arg must be numeric
         if not (
-            (is_scalar(arg) and (is_integer(arg) or is_float(arg)))
-            or is_numeric_dtype(np.asarray(arg))
+            (is_integer(arg) or is_float(arg)) or is_numeric_dtype(np.asarray(arg))
         ):
             raise ValueError(
                 f"'{arg}' is not compatible with origin='{origin}'; "
diff --git a/pandas/io/parsers/base_parser.py b/pandas/io/parsers/base_parser.py
index 0bac882756a91..93f9609fa64c1 100644
--- a/pandas/io/parsers/base_parser.py
+++ b/pandas/io/parsers/base_parser.py
@@ -250,8 +250,8 @@ def _has_complex_date_col(self) -> bool:
 
     @final
     def _should_parse_dates(self, i: int) -> bool:
-        if isinstance(self.parse_dates, bool):
-            return self.parse_dates
+        if lib.is_bool(self.parse_dates):
+            return bool(self.parse_dates)
         else:
             if self.index_names is not None:
                 name = self.index_names[i]
@@ -259,14 +259,9 @@ def _should_parse_dates(self, i: int) -> bool:
                 name = None
             j = i if self.index_col is None else self.index_col[i]
 
-            if is_scalar(self.parse_dates):
-                return (j == self.parse_dates) or (
-                    name is not None and name == self.parse_dates
-                )
-            else:
-                return (j in self.parse_dates) or (
-                    name is not None and name in self.parse_dates
-                )
+            return (j in self.parse_dates) or (
+                name is not None and name in self.parse_dates
+            )
 
     @final
     def _extract_multi_indexer_columns(
@@ -1370,13 +1365,12 @@ def _validate_parse_dates_arg(parse_dates):
         "for the 'parse_dates' parameter"
     )
 
-    if parse_dates is not None:
-        if is_scalar(parse_dates):
-            if not lib.is_bool(parse_dates):
-                raise TypeError(msg)
-
-        elif not isinstance(parse_dates, (list, dict)):
-            raise TypeError(msg)
+    if not (
+        parse_dates is None
+        or lib.is_bool(parse_dates)
+        or isinstance(parse_dates, (list, dict))
+    ):
+        raise TypeError(msg)
 
     return parse_dates
 

From 1e008b1226572eb9cb1f434e3c8d35e5ca8266a5 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 27 Apr 2023 12:20:02 -0700
Subject: [PATCH 2/4] comment

---
 pandas/core/ops/missing.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/pandas/core/ops/missing.py b/pandas/core/ops/missing.py
index 5a2ec11ac2c15..9707f5df927fb 100644
--- a/pandas/core/ops/missing.py
+++ b/pandas/core/ops/missing.py
@@ -53,6 +53,7 @@ def _fill_zeros(result, x, y):
     is_scalar_type = is_scalar(y)
 
     if not is_variable_type and not is_scalar_type:
+        # e.g. test_series_ops_name_retention with mod we get here with list/tuple
         return result
 
     if is_scalar_type:

From b6e76fd3a58940e6aac1fbf8dba064a5904cd96b Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 27 Apr 2023 15:33:33 -0700
Subject: [PATCH 3/4] infer_dtype->is_bool_array

---
 pandas/core/common.py | 3 +--
 pandas/core/series.py | 5 +----
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/pandas/core/common.py b/pandas/core/common.py
index da99b72d60302..0f0d40ccdc4f3 100644
--- a/pandas/core/common.py
+++ b/pandas/core/common.py
@@ -44,7 +44,6 @@
     ABCSeries,
 )
 from pandas.core.dtypes.inference import iterable_not_string
-from pandas.core.dtypes.missing import isna
 
 if TYPE_CHECKING:
     from pandas._typing import (
@@ -129,7 +128,7 @@ def is_bool_indexer(key: Any) -> bool:
 
             if not lib.is_bool_array(key_array):
                 na_msg = "Cannot mask with non-boolean array containing NA / NaN values"
-                if lib.infer_dtype(key_array) == "boolean" and isna(key_array).any():
+                if lib.is_bool_array(key_array, skipna=True):
                     # Don't raise on e.g. ["A", "B", np.nan], see
                     #  test_loc_getitem_list_of_labels_categoricalindex_with_na
                     raise ValueError(na_msg)
diff --git a/pandas/core/series.py b/pandas/core/series.py
index 53b56fc8686bf..2b71eb4a9480d 100644
--- a/pandas/core/series.py
+++ b/pandas/core/series.py
@@ -1019,10 +1019,7 @@ def _get_with(self, key):
         if not isinstance(key, (list, np.ndarray, ExtensionArray, Series, Index)):
             key = list(key)
 
-        if isinstance(key, Index):
-            key_type = key.inferred_type
-        else:
-            key_type = lib.infer_dtype(key, skipna=False)
+        key_type = lib.infer_dtype(key, skipna=False)
 
         # Note: The key_type == "boolean" case should be caught by the
         #  com.is_bool_indexer check in __getitem__

From 54719796e38c435dd0619648962cb1b6fea208b0 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 27 Apr 2023 18:53:17 -0700
Subject: [PATCH 4/4] fix invalid refs

---
 pandas/tests/frame/methods/test_reindex.py | 3 +--
 pandas/tests/frame/test_arithmetic.py      | 5 ++---
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/pandas/tests/frame/methods/test_reindex.py b/pandas/tests/frame/methods/test_reindex.py
index d481f25e9e0fe..a96dec5f34ce1 100644
--- a/pandas/tests/frame/methods/test_reindex.py
+++ b/pandas/tests/frame/methods/test_reindex.py
@@ -23,7 +23,6 @@
 )
 import pandas._testing as tm
 from pandas.api.types import CategoricalDtype as CDT
-import pandas.core.common as com
 
 
 class TestReindexSetIndex:
@@ -355,7 +354,7 @@ def test_reindex_frame_add_nat(self):
         result = df.reindex(range(15))
         assert np.issubdtype(result["B"].dtype, np.dtype("M8[ns]"))
 
-        mask = com.isna(result)["B"]
+        mask = isna(result)["B"]
         assert mask[-5:].all()
         assert not mask[:-5].any()
 
diff --git a/pandas/tests/frame/test_arithmetic.py b/pandas/tests/frame/test_arithmetic.py
index 090b3d64e7c41..c71ceae762e67 100644
--- a/pandas/tests/frame/test_arithmetic.py
+++ b/pandas/tests/frame/test_arithmetic.py
@@ -21,7 +21,6 @@
     Series,
 )
 import pandas._testing as tm
-import pandas.core.common as com
 from pandas.core.computation import expressions as expr
 from pandas.core.computation.expressions import (
     _MIN_ELEMENTS,
@@ -1246,12 +1245,12 @@ def test_operators_none_as_na(self, op):
         filled = df.fillna(np.nan)
         result = op(df, 3)
         expected = op(filled, 3).astype(object)
-        expected[com.isna(expected)] = None
+        expected[pd.isna(expected)] = None
         tm.assert_frame_equal(result, expected)
 
         result = op(df, df)
         expected = op(filled, filled).astype(object)
-        expected[com.isna(expected)] = None
+        expected[pd.isna(expected)] = None
         tm.assert_frame_equal(result, expected)
 
         result = op(df, df.fillna(7))