Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ENH: unique/factorize preserve non-nano #48670

Closed
wants to merge 5 commits into from
Closed

ENH: unique/factorize preserve non-nano #48670

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
678b3a7
ENH: unique/factorize preserve non-nano
jbrockmendel Sep 20, 2022
5afac86
Merge branch 'main' into nano-astype
jbrockmendel Oct 12, 2022
923a206
Merge branch 'main' into nano-astype
jbrockmendel Oct 13, 2022
9755256
Merge branch 'main' into nano-astype
jbrockmendel Oct 20, 2022
1b18b52
remove sanitize_to_nanoseconds
jbrockmendel Oct 20, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v1.6.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for mor

Other API changes
^^^^^^^^^^^^^^^^^
-
- :func:`factorize` and :func:`unique` preserve the original dtype when passed numpy timedelta64 or datetime64 with non-nanosecond resolution (:issue:`??`)
jbrockmendel marked this conversation as resolved.
Show resolved Hide resolved
-

.. ---------------------------------------------------------------------------
Expand Down
10 changes: 0 additions & 10 deletions pandas/core/algorithms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@
from pandas.core.dtypes.cast import (
construct_1d_object_array_from_listlike,
infer_dtype_from_array,
sanitize_to_nanoseconds,
)
from pandas.core.dtypes.common import (
ensure_float64,
Expand All @@ -51,7 +50,6 @@
is_bool_dtype,
is_categorical_dtype,
is_complex_dtype,
is_datetime64_dtype,
is_extension_array_dtype,
is_float_dtype,
is_integer,
Expand All @@ -61,7 +59,6 @@
is_object_dtype,
is_scalar,
is_signed_integer_dtype,
is_timedelta64_dtype,
needs_i8_conversion,
)
from pandas.core.dtypes.concat import concat_compat
Expand Down Expand Up @@ -184,8 +181,6 @@ def _ensure_data(values: ArrayLike) -> np.ndarray:

# datetimelike
elif needs_i8_conversion(values.dtype):
if isinstance(values, np.ndarray):
values = sanitize_to_nanoseconds(values)
npvalues = values.view("i8")
npvalues = cast(np.ndarray, npvalues)
return npvalues
Expand Down Expand Up @@ -223,11 +218,6 @@ def _reconstruct_data(
values = cls._from_sequence(values, dtype=dtype)

else:
if is_datetime64_dtype(dtype):
dtype = np.dtype("datetime64[ns]")
elif is_timedelta64_dtype(dtype):
dtype = np.dtype("timedelta64[ns]")

values = values.astype(dtype, copy=False)

return values
Expand Down
8 changes: 3 additions & 5 deletions pandas/tests/test_algos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,9 +342,7 @@ def test_datetime64_factorize(self, writable):
data = np.array([np.datetime64("2020-01-01T00:00:00.000")])
data.setflags(write=writable)
expected_codes = np.array([0], dtype=np.intp)
expected_uniques = np.array(
["2020-01-01T00:00:00.000000000"], dtype="datetime64[ns]"
)
expected_uniques = np.array(["2020-01-01T00:00:00.000"], dtype="datetime64[ms]")

codes, uniques = pd.factorize(data)
tm.assert_numpy_array_equal(codes, expected_codes)
Expand Down Expand Up @@ -609,13 +607,13 @@ def test_datetime64_dtype_array_returned(self):
def test_datetime_non_ns(self):
a = np.array(["2000", "2000", "2001"], dtype="datetime64[s]")
result = pd.unique(a)
expected = np.array(["2000", "2001"], dtype="datetime64[ns]")
expected = a[1:]
tm.assert_numpy_array_equal(result, expected)

def test_timedelta_non_ns(self):
a = np.array(["2000", "2000", "2001"], dtype="timedelta64[s]")
result = pd.unique(a)
expected = np.array([2000000000000, 2001000000000], dtype="timedelta64[ns]")
expected = a[1:]
tm.assert_numpy_array_equal(result, expected)

def test_timedelta64_dtype_array_returned(self):
Expand Down