API/BUG: freq retention in value_counts

doc/source/whatsnew/v3.0.0.rst

@@ -997,6 +997,7 @@ Datetimelike
 - Bug in comparison between objects with pyarrow date dtype and ``timestamp[pyarrow]`` or ``np.datetime64`` dtype failing to consider these as non-comparable (:issue:`62157`)
 - Bug in constructing arrays with :class:`ArrowDtype` with ``timestamp`` type incorrectly allowing ``Decimal("NaN")`` (:issue:`61773`)
 - Bug in constructing arrays with a timezone-aware :class:`ArrowDtype` from timezone-naive datetime objects incorrectly treating those as UTC times instead of wall times like :class:`DatetimeTZDtype` (:issue:`61775`)
+- Bug in retaining frequency in :meth:`value_counts` specifically for :meth:`DatetimeIndex` and :meth:`TimedeltaIndex` (:issue:`33830`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
 Timedelta

pandas/core/algorithms.py

@@ -868,8 +868,10 @@ def value_counts_internal(
  dropna: bool = True,
 ) -> Series:
  from pandas import (
+ DatetimeIndex,
  Index,
  Series,
+ TimedeltaIndex,
  )
 
  index_name = getattr(values, "name", None)
@@ -934,6 +936,17 @@ def value_counts_internal(
  # Starting in 3.0, we no longer perform dtype inference on the
  # Index object we construct here, xref GH#56161
  idx = Index(keys, dtype=keys.dtype, name=index_name)
+
+ if (
+ bins is None
+ and not sort
+ and isinstance(values, (DatetimeIndex, TimedeltaIndex))
+ and idx.equals(values)
+ and values.inferred_freq is not None
+ ):
+ # Preserve freq of original index
+ idx.freq = values.inferred_freq # type: ignore[attr-defined]
+
  result = Series(counts, index=idx, name=name, copy=False)
 
  if sort:

pandas/tests/base/test_value_counts.py

@@ -339,3 +339,59 @@ def test_value_counts_object_inference_deprecated():
  exp = dti.value_counts()
  exp.index = exp.index.astype(object)
  tm.assert_series_equal(res, exp)
+
+
+@pytest.mark.parametrize(
+ ("index", "expected_index"),
+ [
+ pytest.param(
+ pd.date_range("2016-01-01", periods=5, freq="D"),
+ pd.date_range("2016-01-01", periods=5, freq="D"),
+ ),
+ pytest.param(
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h"),
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h"),
+ ),
+ pytest.param(
+ pd.date_range("2016-01-01", periods=5, freq="D").insert(
+ 1, pd.date_range("2016-01-01", periods=5, freq="D")[1]
+ ),
+ DatetimeIndex(pd.date_range("2016-01-01", periods=5, freq="D")),
+ ),
+ pytest.param(
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h").insert(
+ 1, pd.timedelta_range(Timedelta(0), periods=5, freq="h")[1]
+ ),
+ TimedeltaIndex(pd.timedelta_range(Timedelta(0), periods=5, freq="h")),
+ ),
+ pytest.param(
+ pd.date_range("2016-01-01", periods=5, freq="D").delete(2),
+ DatetimeIndex(pd.date_range("2016-01-01", periods=5, freq="D").delete(2)),
+ ),
+ pytest.param(
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h").delete(2),
+ TimedeltaIndex(
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h").delete(2)
+ ),
+ ),
+ pytest.param(
+ pd.date_range("2016-01-01", periods=5, freq="D").insert(1, pd.NaT),
+ DatetimeIndex(
+ list(pd.date_range("2016-01-01", periods=5, freq="D")[:1])
+ + [pd.NaT]
+ + list(pd.date_range("2016-01-01", periods=5, freq="D")[1:])
+ ),
+ ),
+ pytest.param(
+ pd.timedelta_range(Timedelta(0), periods=5, freq="h").insert(1, pd.NaT),
+ TimedeltaIndex(
+ list(pd.timedelta_range(Timedelta(0), periods=5, freq="h")[:1])
+ + [pd.NaT]
+ + list(pd.timedelta_range(Timedelta(0), periods=5, freq="h")[1:])
+ ),
+ ),
+ ],
+)
+def test_value_counts_index_datetimelike(index, expected_index):
+ vc = index.value_counts(sort=False, dropna=False)
+ tm.assert_index_equal(vc.index, expected_index)