DEP: remove deprecated loffset and base args for resample and Grouper (pandas-dev#49101)

* pylint: disable access-member-before-definition for loffset

* remove deprecated loffset and base args

* fix docstring for resample

* change date_range import to avoid flake8 warning

* fix resample test_depecerated imports

* move change note to deprecation section

* remove all deprecated tests for resample

Author: vamsi-verma-s

doc/source/whatsnew/v2.0.0.rst

@@ -273,6 +273,7 @@ Removal of prior version deprecations/changes
 - Changed behavior of :class:`DataFrame` constructor when passed a ``dtype`` (other than int) that the data cannot be cast to; it now raises instead of silently ignoring the dtype (:issue:`41733`)
 - Changed the behavior of :class:`Series` constructor, it will no longer infer a datetime64 or timedelta64 dtype from string entries (:issue:`41731`)
 - Changed behavior of :class:`Index` constructor when passed a ``SparseArray`` or ``SparseDtype`` to retain that dtype instead of casting to ``numpy.ndarray`` (:issue:`43930`)
+- Removed the deprecated ``base`` and ``loffset`` arguments from :meth:`pandas.DataFrame.resample`, :meth:`pandas.Series.resample` and :class:`pandas.Grouper`. Use ``offset`` or ``origin`` instead (:issue:`31809`)
 - Changed behavior of :meth:`DataFrame.any` and :meth:`DataFrame.all` with ``bool_only=True``; object-dtype columns with all-bool values will no longer be included, manually cast to ``bool`` dtype first (:issue:`46188`)
 -
 

pandas/core/frame.py

@@ -11336,8 +11336,6 @@ def resample(
         label: str | None = None,
         convention: str = "start",
         kind: str | None = None,
-        loffset=None,
-        base: int | None = None,
         on: Level = None,
         level: Level = None,
         origin: str | TimestampConvertibleTypes = "start_day",
@@ -11351,8 +11349,6 @@ def resample(
             label=label,
             convention=convention,
             kind=kind,
-            loffset=loffset,
-            base=base,
             on=on,
             level=level,
             origin=origin,

pandas/core/generic.py

@@ -8454,8 +8454,6 @@ def resample(
         label: str | None = None,
         convention: str = "start",
         kind: str | None = None,
-        loffset=None,
-        base: int | None = None,
         on: Level = None,
         level: Level = None,
         origin: str | TimestampConvertibleTypes = "start_day",
@@ -8493,20 +8491,6 @@ def resample(
             Pass 'timestamp' to convert the resulting index to a
             `DateTimeIndex` or 'period' to convert it to a `PeriodIndex`.
             By default the input representation is retained.
-        loffset : timedelta, default None
-            Adjust the resampled time labels.
-
-            .. deprecated:: 1.1.0
-                You should add the loffset to the `df.index` after the resample.
-                See below.
-
-        base : int, default 0
-            For frequencies that evenly subdivide 1 day, the "origin" of the
-            aggregated intervals. For example, for '5min' frequency, base could
-            range from 0 through 4. Defaults to 0.
-
-            .. deprecated:: 1.1.0
-                The new arguments that you should use are 'offset' or 'origin'.
 
         on : str, optional
             For a DataFrame, column to use instead of index for resampling.
@@ -8842,31 +8826,6 @@ def resample(
         2000-10-02 00:12:00    45
         2000-10-02 00:29:00    45
         Freq: 17T, dtype: int64
-
-        To replace the use of the deprecated `base` argument, you can now use `offset`,
-        in this example it is equivalent to have `base=2`:
-
-        >>> ts.resample('17min', offset='2min').sum()
-        2000-10-01 23:16:00     0
-        2000-10-01 23:33:00     9
-        2000-10-01 23:50:00    36
-        2000-10-02 00:07:00    39
-        2000-10-02 00:24:00    24
-        Freq: 17T, dtype: int64
-
-        To replace the use of the deprecated `loffset` argument:
-
-        >>> from pandas.tseries.frequencies import to_offset
-        >>> loffset = '19min'
-        >>> ts_out = ts.resample('17min').sum()
-        >>> ts_out.index = ts_out.index + to_offset(loffset)
-        >>> ts_out
-        2000-10-01 23:33:00     0
-        2000-10-01 23:50:00     9
-        2000-10-02 00:07:00    21
-        2000-10-02 00:24:00    54
-        2000-10-02 00:41:00    24
-        Freq: 17T, dtype: int64
         """
         from pandas.core.resample import get_resampler
 
@@ -8878,9 +8837,7 @@ def resample(
             closed=closed,
             axis=axis,
             kind=kind,
-            loffset=loffset,
             convention=convention,
-            base=base,
             key=on,
             level=level,
             origin=origin,

pandas/core/groupby/grouper.py

@@ -11,7 +11,6 @@
     Iterator,
     final,
 )
-import warnings
 
 import numpy as np
 
@@ -23,7 +22,6 @@
 )
 from pandas.errors import InvalidIndexError
 from pandas.util._decorators import cache_readonly
-from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
     is_categorical_dtype,
@@ -86,23 +84,6 @@ class Grouper:
         Only when `freq` parameter is passed.
     convention : {'start', 'end', 'e', 's'}
         If grouper is PeriodIndex and `freq` parameter is passed.
-    base : int, default 0
-        Only when `freq` parameter is passed.
-        For frequencies that evenly subdivide 1 day, the "origin" of the
-        aggregated intervals. For example, for '5min' frequency, base could
-        range from 0 through 4. Defaults to 0.
-
-        .. deprecated:: 1.1.0
-            The new arguments that you should use are 'offset' or 'origin'.
-
-    loffset : str, DateOffset, timedelta object
-        Only when `freq` parameter is passed.
-
-        .. deprecated:: 1.1.0
-            loffset is only working for ``.resample(...)`` and not for
-            Grouper (:issue:`28302`).
-            However, loffset is also deprecated for ``.resample(...)``
-            See: :class:`DataFrame.resample`
 
     origin : Timestamp or str, default 'start_day'
         The timestamp on which to adjust the grouping. The timezone of origin must
@@ -266,7 +247,6 @@ def __new__(cls, *args, **kwargs):
         if kwargs.get("freq") is not None:
             from pandas.core.resample import TimeGrouper
 
-            _check_deprecated_resample_kwargs(kwargs, origin=cls)
             cls = TimeGrouper
         return super().__new__(cls)
 
@@ -954,51 +934,3 @@ def _convert_grouper(axis: Index, grouper):
         return grouper
     else:
         return grouper
-
-
-def _check_deprecated_resample_kwargs(kwargs, origin) -> None:
-    """
-    Check for use of deprecated parameters in ``resample`` and related functions.
-
-    Raises the appropriate warnings if these parameters are detected.
-    Only sets an approximate ``stacklevel`` for the warnings (see #37603, #36629).
-
-    Parameters
-    ----------
-    kwargs : dict
-        Dictionary of keyword arguments to check for deprecated parameters.
-    origin : object
-        From where this function is being called; either Grouper or TimeGrouper. Used
-        to determine an approximate stacklevel.
-    """
-    # Deprecation warning of `base` and `loffset` since v1.1.0:
-    # we are raising the warning here to be able to set the `stacklevel`
-    # properly since we need to raise the `base` and `loffset` deprecation
-    # warning from three different cases:
-    #   core/generic.py::NDFrame.resample
-    #   core/groupby/groupby.py::GroupBy.resample
-    #   core/groupby/grouper.py::Grouper
-    # raising these warnings from TimeGrouper directly would fail the test:
-    #   tests/resample/test_deprecated.py::test_deprecating_on_loffset_and_base
-
-    if kwargs.get("base", None) is not None:
-        warnings.warn(
-            "'base' in .resample() and in Grouper() is deprecated.\n"
-            "The new arguments that you should use are 'offset' or 'origin'.\n"
-            '\n>>> df.resample(freq="3s", base=2)\n'
-            "\nbecomes:\n"
-            '\n>>> df.resample(freq="3s", offset="2s")\n',
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )
-    if kwargs.get("loffset", None) is not None:
-        warnings.warn(
-            "'loffset' in .resample() and in Grouper() is deprecated.\n"
-            '\n>>> df.resample(freq="3s", loffset="8H")\n'
-            "\nbecomes:\n"
-            "\n>>> from pandas.tseries.frequencies import to_offset"
-            '\n>>> df = df.resample(freq="3s").mean()'
-            '\n>>> df.index = df.index.to_timestamp() + to_offset("8H")\n',
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )

pandas/core/resample.py

@@ -89,7 +89,6 @@
     is_superperiod,
 )
 from pandas.tseries.offsets import (
-    DateOffset,
     Day,
     Nano,
     Tick,
@@ -139,7 +138,6 @@ class Resampler(BaseGroupBy, PandasObject):
         "closed",
         "label",
         "convention",
-        "loffset",
         "kind",
         "origin",
         "offset",
@@ -358,7 +356,6 @@ def aggregate(self, func=None, *args, **kwargs):
             how = func
             result = self._groupby_and_aggregate(how, *args, **kwargs)
 
-        result = self._apply_loffset(result)
         return result
 
     agg = aggregate
@@ -475,38 +472,8 @@ def _groupby_and_aggregate(self, how, *args, **kwargs):
             # try to evaluate
             result = grouped.apply(how, *args, **kwargs)
 
-        result = self._apply_loffset(result)
         return self._wrap_result(result)
 
-    def _apply_loffset(self, result):
-        """
-        If loffset is set, offset the result index.
-
-        This is NOT an idempotent routine, it will be applied
-        exactly once to the result.
-
-        Parameters
-        ----------
-        result : Series or DataFrame
-            the result of resample
-        """
-        # error: Cannot determine type of 'loffset'
-        needs_offset = (
-            isinstance(
-                self.loffset,  # type: ignore[has-type]
-                (DateOffset, timedelta, np.timedelta64),
-            )
-            and isinstance(result.index, DatetimeIndex)
-            and len(result.index) > 0
-        )
-
-        if needs_offset:
-            # error: Cannot determine type of 'loffset'
-            result.index = result.index + self.loffset  # type: ignore[has-type]
-
-        self.loffset = None
-        return result
-
     def _get_resampler_for_grouping(self, groupby, key=None):
         """
         Return the correct class for resampling with groupby.
@@ -1295,7 +1262,6 @@ def _downsample(self, how, **kwargs):
         # we want to call the actual grouper method here
         result = obj.groupby(self.grouper, axis=self.axis).aggregate(how, **kwargs)
 
-        result = self._apply_loffset(result)
         return self._wrap_result(result)
 
     def _adjust_binner_for_upsample(self, binner):
@@ -1353,7 +1319,6 @@ def _upsample(self, method, limit=None, fill_value=None):
                 res_index, method=method, limit=limit, fill_value=fill_value
             )
 
-        result = self._apply_loffset(result)
         return self._wrap_result(result)
 
     def _wrap_result(self, result):
@@ -1398,11 +1363,6 @@ def _convert_obj(self, obj: NDFrameT) -> NDFrameT:
             )
             raise NotImplementedError(msg)
 
-        if self.loffset is not None:
-            # Cannot apply loffset/timedelta to PeriodIndex -> convert to
-            # timestamps
-            self.kind = "timestamp"
-
         # convert to timestamp
         if self.kind == "timestamp":
             obj = obj.to_timestamp(how=self.convention)
@@ -1563,7 +1523,6 @@ class TimeGrouper(Grouper):
         "closed",
         "label",
         "how",
-        "loffset",
         "kind",
         "convention",
         "origin",
@@ -1581,10 +1540,8 @@ def __init__(
         axis: Axis = 0,
         fill_method=None,
         limit=None,
-        loffset=None,
         kind: str | None = None,
         convention: Literal["start", "end", "e", "s"] | None = None,
-        base: int | None = None,
         origin: Literal["epoch", "start", "start_day", "end", "end_day"]
         | TimestampConvertibleTypes = "start_day",
         offset: TimedeltaConvertibleTypes | None = None,
@@ -1664,22 +1621,6 @@ def __init__(
         # always sort time groupers
         kwargs["sort"] = True
 
-        # Handle deprecated arguments since v1.1.0 of `base` and `loffset` (GH #31809)
-        if base is not None and offset is not None:
-            raise ValueError("'offset' and 'base' cannot be present at the same time")
-
-        if base and isinstance(freq, Tick):
-            # this conversion handle the default behavior of base and the
-            # special case of GH #10530. Indeed in case when dealing with
-            # a TimedeltaIndex base was treated as a 'pure' offset even though
-            # the default behavior of base was equivalent of a modulo on
-            # freq_nanos.
-            self.offset = Timedelta(base * freq.nanos // freq.n)
-
-        if isinstance(loffset, str):
-            loffset = to_offset(loffset)
-        self.loffset = loffset
-
         super().__init__(freq=freq, axis=axis, **kwargs)
 
     def _get_resampler(self, obj, kind=None):
@@ -1840,9 +1781,6 @@ def _get_time_delta_bins(self, ax: TimedeltaIndex):
         if self.offset:
             # GH 10530 & 31809
             labels += self.offset
-        if self.loffset:
-            # GH 33498
-            labels += self.loffset
 
         return binner, bins, labels
 

pandas/core/series.py

@@ -5809,8 +5809,6 @@ def resample(
         label: str | None = None,
         convention: str = "start",
         kind: str | None = None,
-        loffset=None,
-        base: int | None = None,
         on: Level = None,
         level: Level = None,
         origin: str | TimestampConvertibleTypes = "start_day",
@@ -5824,8 +5822,6 @@ def resample(
             label=label,
             convention=convention,
             kind=kind,
-            loffset=loffset,
-            base=base,
             on=on,
             level=level,
             origin=origin,