BUG: Negative freq in date_range produces values out of start and end…

…points (#56832) * #56147 negative offset and year end interaction * #56147 tests * documentation * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fixing typing/pylint to mirror other branch * moved note to Datetimelike * documentation re-merge * whatsnew update * updated date_range docstring * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * reformatted docstring * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update doc/source/whatsnew/v3.0.0.rst Co-authored-by: Matthew Roeschke <[email protected]> --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Matthew Roeschke <[email protected]>
pandas-dev · Mar 20, 2024 · 1b84930 · 1b84930
1 parent 303d78b
commit 1b84930
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 8 deletions.
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -308,6 +308,7 @@ Categorical
 Datetimelike
 ^^^^^^^^^^^^
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
+- Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56382`)
 -
 
 Timedelta

diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
@@ -2777,7 +2777,12 @@ def _generate_range(
     if start and not offset.is_on_offset(start):
         # Incompatible types in assignment (expression has type "datetime",
         # variable has type "Optional[Timestamp]")
-        start = offset.rollforward(start)  # type: ignore[assignment]
+
+        # GH #56147 account for negative direction and range bounds
+        if offset.n >= 0:
+            start = offset.rollforward(start)  # type: ignore[assignment]
+        else:
+            start = offset.rollback(start)  # type: ignore[assignment]
 
     # Unsupported operand types for < ("Timestamp" and "None")
     if periods is None and end < start and offset.n >= 0:  # type: ignore[operator]

diff --git a/pandas/core/indexes/datetimes.py b/pandas/core/indexes/datetimes.py
@@ -841,13 +841,15 @@ def date_range(
     Return a fixed frequency DatetimeIndex.
 
     Returns the range of equally spaced time points (where the difference between any
-    two adjacent points is specified by the given frequency) such that they all
-    satisfy `start <[=] x <[=] end`, where the first one and the last one are, resp.,
-    the first and last time points in that range that fall on the boundary of ``freq``
-    (if given as a frequency string) or that are valid for ``freq`` (if given as a
-    :class:`pandas.tseries.offsets.DateOffset`). (If exactly one of ``start``,
-    ``end``, or ``freq`` is *not* specified, this missing parameter can be computed
-    given ``periods``, the number of timesteps in the range. See the note below.)
+    two adjacent points is specified by the given frequency) such that they fall in the
+    range `[start, end]` , where the first one and the last one are, resp., the first
+    and last time points in that range that fall on the boundary of ``freq`` (if given
+    as a frequency string) or that are valid for ``freq`` (if given as a
+    :class:`pandas.tseries.offsets.DateOffset`). If ``freq`` is positive, the points
+    satisfy `start <[=] x <[=] end`, and if ``freq`` is negative, the points satisfy
+    `end <[=] x <[=] start`. (If exactly one of ``start``, ``end``, or ``freq`` is *not*
+    specified, this missing parameter can be computed given ``periods``, the number of
+    timesteps in the range. See the note below.)
 
     Parameters
     ----------

diff --git a/pandas/tests/indexes/datetimes/test_date_range.py b/pandas/tests/indexes/datetimes/test_date_range.py
@@ -1735,3 +1735,18 @@ def test_date_range_partial_day_year_end(self, unit):
             freq="YE",
         )
         tm.assert_index_equal(rng, exp)
+
+    def test_date_range_negative_freq_year_end_inbounds(self, unit):
+        # GH#56147
+        rng = date_range(
+            start="2023-10-31 00:00:00",
+            end="2021-10-31 00:00:00",
+            freq="-1YE",
+            unit=unit,
+        )
+        exp = DatetimeIndex(
+            ["2022-12-31 00:00:00", "2021-12-31 00:00:00"],
+            dtype=f"M8[{unit}]",
+            freq="-1YE",
+        )
+        tm.assert_index_equal(rng, exp)