CLN: rename reduce-->do_reduce (#27706)

Author: jbrockmendel

pandas/_libs/reduction.pyx

@@ -628,7 +628,7 @@ cdef class BlockSlider:
             arr.shape[1] = 0
 
 
-def reduce(arr, f, axis=0, dummy=None, labels=None):
+def compute_reduction(arr, f, axis=0, dummy=None, labels=None):
     """
 
     Parameters

pandas/_libs/tslibs/timedeltas.pyx

@@ -1280,7 +1280,8 @@ class Timedelta(_Timedelta):
         else:
             raise ValueError(
                 "Value must be Timedelta, string, integer, "
-                "float, timedelta or convertible")
+                "float, timedelta or convertible, not {typ}"
+                .format(typ=type(value).__name__))
 
         if is_timedelta64_object(value):
             value = value.view('i8')

pandas/core/apply.py

@@ -221,7 +221,7 @@ def apply_raw(self):
         """ apply to the values as a numpy array """
 
         try:
-            result = reduction.reduce(self.values, self.f, axis=self.axis)
+            result = reduction.compute_reduction(self.values, self.f, axis=self.axis)
         except Exception:
             result = np.apply_along_axis(self.f, self.axis, self.values)
 
@@ -281,7 +281,7 @@ def apply_standard(self):
             dummy = Series(empty_arr, index=index, dtype=values.dtype)
 
             try:
-                result = reduction.reduce(
+                result = reduction.compute_reduction(
                     values, self.f, axis=self.axis, dummy=dummy, labels=labels
                 )
                 return self.obj._constructor_sliced(result, index=labels)

pandas/core/arrays/categorical.py

@@ -2703,7 +2703,7 @@ def _convert_to_list_like(list_like):
     elif is_scalar(list_like):
         return [list_like]
     else:
-        # is this reached?
+        # TODO: is this reached?
         return [list_like]
 
 

pandas/core/arrays/datetimelike.py

@@ -57,21 +57,10 @@
 class AttributesMixin:
     _data = None  # type: np.ndarray
 
-    @property
-    def _attributes(self):
-        # Inheriting subclass should implement _attributes as a list of strings
-        raise AbstractMethodError(self)
-
     @classmethod
     def _simple_new(cls, values, **kwargs):
         raise AbstractMethodError(cls)
 
-    def _get_attributes_dict(self):
-        """
-        return an attributes dict for my class
-        """
-        return {k: getattr(self, k, None) for k in self._attributes}
-
     @property
     def _scalar_type(self) -> Type[DatetimeLikeScalar]:
         """The scalar associated with this datelike

pandas/core/arrays/datetimes.py

@@ -328,7 +328,6 @@ class DatetimeArray(dtl.DatetimeLikeArrayMixin, dtl.TimelikeOps, dtl.DatelikeOps
     # -----------------------------------------------------------------
     # Constructors
 
-    _attributes = ["freq", "tz"]
     _dtype = None  # type: Union[np.dtype, DatetimeTZDtype]
     _freq = None
 

pandas/core/arrays/period.py

@@ -161,7 +161,6 @@ class PeriodArray(dtl.DatetimeLikeArrayMixin, dtl.DatelikeOps):
 
     # array priority higher than numpy scalars
     __array_priority__ = 1000
-    _attributes = ["freq"]
     _typ = "periodarray"  # ABCPeriodArray
     _scalar_type = Period
 

pandas/core/arrays/timedeltas.py

@@ -199,7 +199,6 @@ def dtype(self):
 
     # ----------------------------------------------------------------
     # Constructors
-    _attributes = ["freq"]
 
     def __init__(self, values, dtype=_TD_DTYPE, freq=None, copy=False):
         if isinstance(values, (ABCSeries, ABCIndexClass)):

pandas/core/generic.py

@@ -3556,7 +3556,7 @@ def _iget_item_cache(self, item):
     def _box_item_values(self, key, values):
         raise AbstractMethodError(self)
 
-    def _slice(self, slobj, axis=0, kind=None):
+    def _slice(self, slobj: slice, axis=0, kind=None):
         """
         Construct a slice of this container.
 
@@ -6183,8 +6183,6 @@ def fillna(
             axis = 0
         axis = self._get_axis_number(axis)
 
-        from pandas import DataFrame
-
         if value is None:
 
             if self._is_mixed_type and axis == 1:
@@ -6247,7 +6245,7 @@ def fillna(
                 new_data = self._data.fillna(
                     value=value, limit=limit, inplace=inplace, downcast=downcast
                 )
-            elif isinstance(value, DataFrame) and self.ndim == 2:
+            elif isinstance(value, ABCDataFrame) and self.ndim == 2:
                 new_data = self.where(self.notna(), value)
             else:
                 raise ValueError("invalid fill value with a %s" % type(value))

pandas/core/groupby/groupby.py

@@ -29,14 +29,16 @@ class providing the base-class of operations.
 from pandas.core.dtypes.cast import maybe_downcast_to_dtype
 from pandas.core.dtypes.common import (
     ensure_float,
+    is_datetime64_dtype,
     is_datetime64tz_dtype,
     is_extension_array_dtype,
+    is_integer_dtype,
     is_numeric_dtype,
+    is_object_dtype,
     is_scalar,
 )
 from pandas.core.dtypes.missing import isna, notna
 
-from pandas.api.types import is_datetime64_dtype, is_integer_dtype, is_object_dtype
 import pandas.core.algorithms as algorithms
 from pandas.core.arrays import Categorical
 from pandas.core.base import (
@@ -343,7 +345,7 @@ class _GroupBy(PandasObject, SelectionMixin):
 
     def __init__(
         self,
-        obj,
+        obj: NDFrame,
         keys=None,
         axis=0,
         level=None,
@@ -360,8 +362,8 @@ def __init__(
 
         self._selection = selection
 
-        if isinstance(obj, NDFrame):
-            obj._consolidate_inplace()
+        assert isinstance(obj, NDFrame), type(obj)
+        obj._consolidate_inplace()
 
         self.level = level
 

pandas/core/groupby/grouper.py

@@ -25,6 +25,7 @@
 from pandas.core.arrays import Categorical, ExtensionArray
 import pandas.core.common as com
 from pandas.core.frame import DataFrame
+from pandas.core.generic import NDFrame
 from pandas.core.groupby.categorical import recode_for_groupby, recode_from_groupby
 from pandas.core.groupby.ops import BaseGrouper
 from pandas.core.index import CategoricalIndex, Index, MultiIndex
@@ -423,7 +424,7 @@ def groups(self):
 
 
 def _get_grouper(
-    obj,
+    obj: NDFrame,
     key=None,
     axis=0,
     level=None,

pandas/core/groupby/ops.py

@@ -906,7 +906,7 @@ def _get_sorted_data(self):
         return self.data.take(self.sort_idx, axis=self.axis)
 
     def _chop(self, sdata, slice_obj):
-        return sdata.iloc[slice_obj]
+        raise AbstractMethodError(self)
 
     def apply(self, f):
         raise AbstractMethodError(self)
@@ -933,7 +933,7 @@ def _chop(self, sdata, slice_obj):
         if self.axis == 0:
             return sdata.iloc[slice_obj]
         else:
-            return sdata._slice(slice_obj, axis=1)  # .loc[:, slice_obj]
+            return sdata._slice(slice_obj, axis=1)
 
 
 def get_splitter(data, *args, **kwargs):

pandas/core/ops/__init__.py

@@ -37,6 +37,7 @@
 from pandas.core.dtypes.generic import (
     ABCDataFrame,
     ABCDatetimeArray,
+    ABCDatetimeIndex,
     ABCIndex,
     ABCIndexClass,
     ABCSeries,
@@ -47,7 +48,7 @@
 
 import pandas as pd
 from pandas._typing import ArrayLike
-import pandas.core.common as com
+from pandas.core.construction import extract_array
 
 from . import missing
 from .docstrings import (
@@ -1022,7 +1023,7 @@ def wrapper(left, right):
             #  does inference in the case where `result` has object-dtype.
             return construct_result(left, result, index=left.index, name=res_name)
 
-        elif isinstance(right, (ABCDatetimeArray, pd.DatetimeIndex)):
+        elif isinstance(right, (ABCDatetimeArray, ABCDatetimeIndex)):
             result = op(left._values, right)
             return construct_result(left, result, index=left.index, name=res_name)
 
@@ -1194,7 +1195,7 @@ def wrapper(self, other, axis=None):
                 )
 
             # always return a full value series here
-            res_values = com.values_from_object(res)
+            res_values = extract_array(res, extract_numpy=True)
             return self._constructor(
                 res_values, index=self.index, name=res_name, dtype="bool"
             )

pandas/tests/groupby/test_bin_groupby.py

@@ -6,15 +6,13 @@
 
 from pandas.core.dtypes.common import ensure_int64
 
-from pandas import Index, isna
+from pandas import Index, Series, isna
 from pandas.core.groupby.ops import generate_bins_generic
 import pandas.util.testing as tm
 from pandas.util.testing import assert_almost_equal
 
 
 def test_series_grouper():
-    from pandas import Series
-
     obj = Series(np.random.randn(10))
     dummy = obj[:0]
 
@@ -31,8 +29,6 @@ def test_series_grouper():
 
 
 def test_series_bin_grouper():
-    from pandas import Series
-
     obj = Series(np.random.randn(10))
     dummy = obj[:0]
 
@@ -123,30 +119,32 @@ class TestMoments:
 
 class TestReducer:
     def test_int_index(self):
-        from pandas.core.series import Series
-
         arr = np.random.randn(100, 4)
-        result = reduction.reduce(arr, np.sum, labels=Index(np.arange(4)))
+        result = reduction.compute_reduction(arr, np.sum, labels=Index(np.arange(4)))
         expected = arr.sum(0)
         assert_almost_equal(result, expected)
 
-        result = reduction.reduce(arr, np.sum, axis=1, labels=Index(np.arange(100)))
+        result = reduction.compute_reduction(
+            arr, np.sum, axis=1, labels=Index(np.arange(100))
+        )
         expected = arr.sum(1)
         assert_almost_equal(result, expected)
 
         dummy = Series(0.0, index=np.arange(100))
-        result = reduction.reduce(arr, np.sum, dummy=dummy, labels=Index(np.arange(4)))
+        result = reduction.compute_reduction(
+            arr, np.sum, dummy=dummy, labels=Index(np.arange(4))
+        )
         expected = arr.sum(0)
         assert_almost_equal(result, expected)
 
         dummy = Series(0.0, index=np.arange(4))
-        result = reduction.reduce(
+        result = reduction.compute_reduction(
             arr, np.sum, axis=1, dummy=dummy, labels=Index(np.arange(100))
         )
         expected = arr.sum(1)
         assert_almost_equal(result, expected)
 
-        result = reduction.reduce(
+        result = reduction.compute_reduction(
             arr, np.sum, axis=1, dummy=dummy, labels=Index(np.arange(100))
         )
         assert_almost_equal(result, expected)