DEPR: dropna multiple axes, fillna int for td64, from_codes with floats, Series.nonzero (pandas-dev#29875)

Author: jbrockmendel

doc/source/whatsnew/v1.0.0.rst

@@ -459,6 +459,10 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - In :func:`concat` the default value for ``sort`` has been changed from ``None`` to ``False`` (:issue:`20613`)
 - Removed previously deprecated "raise_conflict" argument from :meth:`DataFrame.update`, use "errors" instead (:issue:`23585`)
 - Removed previously deprecated keyword "n" from :meth:`DatetimeIndex.shift`, :meth:`TimedeltaIndex.shift`, :meth:`PeriodIndex.shift`, use "periods" instead (:issue:`22458`)
+- Passing an integer to :meth:`Series.fillna` or :meth:`DataFrame.fillna` with ``timedelta64[ns]`` dtype now raises ``TypeError`` (:issue:`24694`)
+- Passing multiple axes to :meth:`DataFrame.dropna` is no longer supported (:issue:`20995`)
+- Removed previously deprecated :meth:`Series.nonzero`, use `to_numpy().nonzero()` instead (:issue:`24048`)
+- Passing floating dtype ``codes`` to :meth:`Categorical.from_codes` is no longer supported, pass ``codes.astype(np.int64)`` instead (:issue:`21775`)
 - Removed the previously deprecated :meth:`Series.to_dense`, :meth:`DataFrame.to_dense` (:issue:`26684`)
 - Removed the previously deprecated :meth:`Index.dtype_str`, use ``str(index.dtype)`` instead (:issue:`27106`)
 - :meth:`Categorical.ravel` returns a :class:`Categorical` instead of a ``ndarray`` (:issue:`27199`)

pandas/core/arrays/categorical.py

@@ -27,7 +27,6 @@
     is_dict_like,
     is_dtype_equal,
     is_extension_array_dtype,
-    is_float_dtype,
     is_integer_dtype,
     is_iterator,
     is_list_like,
@@ -646,22 +645,7 @@ def from_codes(cls, codes, categories=None, ordered=None, dtype=None):
 
         codes = np.asarray(codes)  # #21767
         if len(codes) and not is_integer_dtype(codes):
-            msg = "codes need to be array-like integers"
-            if is_float_dtype(codes):
-                icodes = codes.astype("i8")
-                if (icodes == codes).all():
-                    msg = None
-                    codes = icodes
-                    warn(
-                        (
-                            "float codes will be disallowed in the future and "
-                            "raise a ValueError"
-                        ),
-                        FutureWarning,
-                        stacklevel=2,
-                    )
-            if msg:
-                raise ValueError(msg)
+            raise ValueError("codes need to be array-like integers")
 
         if len(codes) and (codes.max() >= len(dtype.categories) or codes.min() < -1):
             raise ValueError("codes need to be between -1 and len(categories)-1")

pandas/core/frame.py

@@ -4475,7 +4475,7 @@ def dropna(self, axis=0, how="any", thresh=None, subset=None, inplace=False):
             * 0, or 'index' : Drop rows which contain missing values.
             * 1, or 'columns' : Drop columns which contain missing value.
 
-            .. deprecated:: 0.23.0
+            .. versionchanged:: 1.0.0
 
                Pass tuple or list to drop on multiple axes.
                Only a single axis is allowed.
@@ -4565,43 +4565,35 @@ def dropna(self, axis=0, how="any", thresh=None, subset=None, inplace=False):
         inplace = validate_bool_kwarg(inplace, "inplace")
         if isinstance(axis, (tuple, list)):
             # GH20987
-            msg = (
-                "supplying multiple axes to axis is deprecated and "
-                "will be removed in a future version."
-            )
-            warnings.warn(msg, FutureWarning, stacklevel=2)
+            raise TypeError("supplying multiple axes to axis is no longer supported.")
 
-            result = self
-            for ax in axis:
-                result = result.dropna(how=how, thresh=thresh, subset=subset, axis=ax)
+        axis = self._get_axis_number(axis)
+        agg_axis = 1 - axis
+
+        agg_obj = self
+        if subset is not None:
+            ax = self._get_axis(agg_axis)
+            indices = ax.get_indexer_for(subset)
+            check = indices == -1
+            if check.any():
+                raise KeyError(list(np.compress(check, subset)))
+            agg_obj = self.take(indices, axis=agg_axis)
+
+        count = agg_obj.count(axis=agg_axis)
+
+        if thresh is not None:
+            mask = count >= thresh
+        elif how == "any":
+            mask = count == len(agg_obj._get_axis(agg_axis))
+        elif how == "all":
+            mask = count > 0
         else:
-            axis = self._get_axis_number(axis)
-            agg_axis = 1 - axis
-
-            agg_obj = self
-            if subset is not None:
-                ax = self._get_axis(agg_axis)
-                indices = ax.get_indexer_for(subset)
-                check = indices == -1
-                if check.any():
-                    raise KeyError(list(np.compress(check, subset)))
-                agg_obj = self.take(indices, axis=agg_axis)
-
-            count = agg_obj.count(axis=agg_axis)
-
-            if thresh is not None:
-                mask = count >= thresh
-            elif how == "any":
-                mask = count == len(agg_obj._get_axis(agg_axis))
-            elif how == "all":
-                mask = count > 0
+            if how is not None:
+                raise ValueError("invalid how option: {h}".format(h=how))
             else:
-                if how is not None:
-                    raise ValueError("invalid how option: {h}".format(h=how))
-                else:
-                    raise TypeError("must specify how or thresh")
+                raise TypeError("must specify how or thresh")
 
-            result = self.loc(axis=axis)[mask]
+        result = self.loc(axis=axis)[mask]
 
         if inplace:
             self._update_inplace(result)

pandas/core/internals/blocks.py

@@ -2444,15 +2444,11 @@ def fillna(self, value, **kwargs):
         # interpreted as nanoseconds
         if is_integer(value):
             # Deprecation GH#24694, GH#19233
-            warnings.warn(
-                "Passing integers to fillna is deprecated, will "
-                "raise a TypeError in a future version.  To retain "
-                "the old behavior, pass pd.Timedelta(seconds=n) "
-                "instead.",
-                FutureWarning,
-                stacklevel=6,
+            raise TypeError(
+                "Passing integers to fillna for timedelta64[ns] dtype is no "
+                "longer supporetd.  To obtain the old behavior, pass "
+                "`pd.Timedelta(seconds=n)` instead."
             )
-            value = Timedelta(value, unit="s")
         return super().fillna(value, **kwargs)
 
     def should_store(self, value):

pandas/core/series.py

@@ -528,55 +528,6 @@ def compress(self, condition, *args, **kwargs):
         nv.validate_compress(args, kwargs)
         return self[condition]
 
-    def nonzero(self):
-        """
-        Return the *integer* indices of the elements that are non-zero.
-
-        .. deprecated:: 0.24.0
-           Please use .to_numpy().nonzero() as a replacement.
-
-        This method is equivalent to calling `numpy.nonzero` on the
-        series data. For compatibility with NumPy, the return value is
-        the same (a tuple with an array of indices for each dimension),
-        but it will always be a one-item tuple because series only have
-        one dimension.
-
-        Returns
-        -------
-        numpy.ndarray
-            Indices of elements that are non-zero.
-
-        See Also
-        --------
-        numpy.nonzero
-
-        Examples
-        --------
-        >>> s = pd.Series([0, 3, 0, 4])
-        >>> s.nonzero()
-        (array([1, 3]),)
-        >>> s.iloc[s.nonzero()[0]]
-        1    3
-        3    4
-        dtype: int64
-
-        # same return although index of s is different
-        >>> s = pd.Series([0, 3, 0, 4], index=['a', 'b', 'c', 'd'])
-        >>> s.nonzero()
-        (array([1, 3]),)
-        >>> s.iloc[s.nonzero()[0]]
-        b    3
-        d    4
-        dtype: int64
-        """
-        msg = (
-            "Series.nonzero() is deprecated "
-            "and will be removed in a future version."
-            "Use Series.to_numpy().nonzero() instead"
-        )
-        warnings.warn(msg, FutureWarning, stacklevel=2)
-        return self._values.nonzero()
-
     def put(self, *args, **kwargs):
         """
         Apply the `put` method to its `values` attribute if it has one.

pandas/tests/arrays/categorical/test_constructors.py

@@ -529,13 +529,11 @@ def test_from_codes_with_float(self):
         # empty codes should not raise for floats
         Categorical.from_codes([], dtype.categories)
 
-        with tm.assert_produces_warning(FutureWarning):
-            cat = Categorical.from_codes(codes, dtype.categories)
-        tm.assert_numpy_array_equal(cat.codes, np.array([1, 2, 0], dtype="i1"))
+        with pytest.raises(ValueError, match="codes need to be array-like integers"):
+            Categorical.from_codes(codes, dtype.categories)
 
-        with tm.assert_produces_warning(FutureWarning):
-            cat = Categorical.from_codes(codes, dtype=dtype)
-        tm.assert_numpy_array_equal(cat.codes, np.array([1, 2, 0], dtype="i1"))
+        with pytest.raises(ValueError, match="codes need to be array-like integers"):
+            Categorical.from_codes(codes, dtype=dtype)
 
         codes = [1.1, 2.0, 0]  # non-integer
         with pytest.raises(ValueError, match="codes need to be array-like integers"):

pandas/tests/frame/test_missing.py

@@ -165,23 +165,16 @@ def test_dropna_multiple_axes(self):
                 [7, np.nan, 8, 9],
             ]
         )
-        cp = df.copy()
 
         # GH20987
-        with tm.assert_produces_warning(FutureWarning):
-            result = df.dropna(how="all", axis=[0, 1])
-        with tm.assert_produces_warning(FutureWarning):
-            result2 = df.dropna(how="all", axis=(0, 1))
-        expected = df.dropna(how="all").dropna(how="all", axis=1)
-
-        tm.assert_frame_equal(result, expected)
-        tm.assert_frame_equal(result2, expected)
-        tm.assert_frame_equal(df, cp)
+        with pytest.raises(TypeError, match="supplying multiple axes"):
+            df.dropna(how="all", axis=[0, 1])
+        with pytest.raises(TypeError, match="supplying multiple axes"):
+            df.dropna(how="all", axis=(0, 1))
 
         inp = df.copy()
-        with tm.assert_produces_warning(FutureWarning):
+        with pytest.raises(TypeError, match="supplying multiple axes"):
             inp.dropna(how="all", axis=(0, 1), inplace=True)
-        tm.assert_frame_equal(inp, expected)
 
     def test_dropna_tz_aware_datetime(self):
         # GH13407

pandas/tests/series/test_missing.py

@@ -16,6 +16,7 @@
     MultiIndex,
     NaT,
     Series,
+    Timedelta,
     Timestamp,
     date_range,
     isna,
@@ -60,8 +61,7 @@ def test_timedelta_fillna(self):
         td = s.diff()
 
         # reg fillna
-        with tm.assert_produces_warning(FutureWarning):
-            result = td.fillna(0)
+        result = td.fillna(Timedelta(seconds=0))
         expected = Series(
             [
                 timedelta(0),
@@ -73,8 +73,10 @@ def test_timedelta_fillna(self):
         tm.assert_series_equal(result, expected)
 
         # interpreted as seconds, deprecated
-        with tm.assert_produces_warning(FutureWarning):
-            result = td.fillna(1)
+        with pytest.raises(TypeError, match="Passing integers to fillna"):
+            td.fillna(1)
+
+        result = td.fillna(Timedelta(seconds=1))
         expected = Series(
             [
                 timedelta(seconds=1),
@@ -122,16 +124,14 @@ def test_timedelta_fillna(self):
         # ffill
         td[2] = np.nan
         result = td.ffill()
-        with tm.assert_produces_warning(FutureWarning):
-            expected = td.fillna(0)
+        expected = td.fillna(Timedelta(seconds=0))
         expected[0] = np.nan
         tm.assert_series_equal(result, expected)
 
         # bfill
         td[2] = np.nan
         result = td.bfill()
-        with tm.assert_produces_warning(FutureWarning):
-            expected = td.fillna(0)
+        expected = td.fillna(Timedelta(seconds=0))
         expected[2] = timedelta(days=1, seconds=9 * 3600 + 60 + 1)
         tm.assert_series_equal(result, expected)
 
@@ -1597,12 +1597,6 @@ def test_series_interpolate_intraday(self):
 
         tm.assert_numpy_array_equal(result.values, exp.values)
 
-    def test_nonzero_warning(self):
-        # GH 24048
-        ser = pd.Series([1, 0, 3, 4])
-        with tm.assert_produces_warning(FutureWarning):
-            ser.nonzero()
-
     @pytest.mark.parametrize(
         "ind",
         [