CLN: VariableOffsetWindowIndexer (#54379)

* CLN: VariableOffsetWindowIndexer * Add gh number

Author: mroeschke

doc/source/whatsnew/v2.1.0.rst

@@ -209,6 +209,7 @@ Other enhancements
 - Improve error message when setting :class:`DataFrame` with wrong number of columns through :meth:`DataFrame.isetitem` (:issue:`51701`)
 - Improved error handling when using :meth:`DataFrame.to_json` with incompatible ``index`` and ``orient`` arguments (:issue:`52143`)
 - Improved error message when creating a DataFrame with empty data (0 rows), no index and an incorrect number of columns. (:issue:`52084`)
+- Improved error message when providing an invalid ``index`` or ``offset`` argument to :class:`pandas.api.indexers.VariableOffsetWindowIndexer` (:issue:`54379`)
 - Let :meth:`DataFrame.to_feather` accept a non-default :class:`Index` and non-string column names (:issue:`51787`)
 - Added a new parameter ``by_row`` to :meth:`Series.apply` and :meth:`DataFrame.apply`. When set to ``False`` the supplied callables will always operate on the whole Series or DataFrame (:issue:`53400`, :issue:`53601`).
 - :meth:`DataFrame.shift` and :meth:`Series.shift` now allow shifting by multiple periods by supplying a list of periods (:issue:`44424`)

pandas/core/indexers/objects.py

@@ -5,11 +5,14 @@
 
 import numpy as np
 
+from pandas._libs.tslibs import BaseOffset
 from pandas._libs.window.indexers import calculate_variable_window_bounds
 from pandas.util._decorators import Appender
 
 from pandas.core.dtypes.common import ensure_platform_int
 
+from pandas.core.indexes.datetimes import DatetimeIndex
+
 from pandas.tseries.offsets import Nano
 
 get_window_bounds_doc = """
@@ -183,12 +186,16 @@ def __init__(
  self,
  index_array: np.ndarray | None = None,
  window_size: int = 0,
- index=None,
- offset=None,
+ index: DatetimeIndex | None = None,
+ offset: BaseOffset | None = None,
  **kwargs,
  ) -> None:
  super().__init__(index_array, window_size, **kwargs)
+ if not isinstance(index, DatetimeIndex):
+ raise ValueError("index must be a DatetimeIndex.")
  self.index = index
+ if not isinstance(offset, BaseOffset):
+ raise ValueError("offset must be a DateOffset-like object.")
  self.offset = offset
 
  @Appender(get_window_bounds_doc)
@@ -216,6 +223,7 @@ def get_window_bounds(
  index_growth_sign = -1
  else:
  index_growth_sign = 1
+ offset_diff = index_growth_sign * self.offset
 
  start = np.empty(num_values, dtype="int64")
  start.fill(-1)
@@ -231,11 +239,12 @@ def get_window_bounds(
  else:
  end[0] = 0
 
+ zero = timedelta(0)
  # start is start of slice interval (including)
  # end is end of slice interval (not including)
  for i in range(1, num_values):
  end_bound = self.index[i]
- start_bound = self.index[i] - index_growth_sign * self.offset
+ start_bound = end_bound - offset_diff
 
  # left endpoint is closed
  if left_closed:
@@ -245,13 +254,15 @@ def get_window_bounds(
  # within the constraint
  start[i] = i
  for j in range(start[i - 1], i):
- if (self.index[j] - start_bound) * index_growth_sign > timedelta(0):
+ start_diff = (self.index[j] - start_bound) * index_growth_sign
+ if start_diff > zero:
  start[i] = j
  break
 
  # end bound is previous end
  # or current index
- if (self.index[end[i - 1]] - end_bound) * index_growth_sign <= timedelta(0):
+ end_diff = (self.index[end[i - 1]] - end_bound) * index_growth_sign
+ if end_diff <= zero:
  end[i] = i + 1
  else:
  end[i] = end[i - 1]

pandas/tests/window/test_base_indexer.py

@@ -268,6 +268,19 @@ def test_non_fixed_variable_window_indexer(closed, expected_data):
  tm.assert_frame_equal(result, expected)
 
 
+def test_variableoffsetwindowindexer_not_dti():
+ # GH 54379
+ with pytest.raises(ValueError, match="index must be a DatetimeIndex."):
+ VariableOffsetWindowIndexer(index="foo", offset=BusinessDay(1))
+
+
+def test_variableoffsetwindowindexer_not_offset():
+ # GH 54379
+ idx = date_range("2020", periods=10)
+ with pytest.raises(ValueError, match="offset must be a DateOffset-like object."):
+ VariableOffsetWindowIndexer(index=idx, offset="foo")
+
+
 def test_fixed_forward_indexer_count(step):
  # GH: 35579
  df = DataFrame({"b": [None, None, None, 7]})