Merge branch 'main' of https://github.com/pandas-dev/pandas into bug_groupby_all_na_min_max

Author: rhshadrach

.github/CODEOWNERS

@@ -10,10 +10,8 @@ doc/source/development            @noatamir
 
 # pandas
 pandas/_libs/                     @WillAyd
-pandas/_libs/tslibs/*             @MarcoGorelli
 pandas/_typing.py                 @Dr-Irv
 pandas/core/groupby/*             @rhshadrach
-pandas/core/tools/datetimes.py    @MarcoGorelli
 pandas/io/excel/*                 @rhshadrach
 pandas/io/formats/style.py        @attack68
 pandas/io/formats/style_render.py @attack68

ci/meta.yaml

@@ -89,4 +89,3 @@ extra:
     - datapythonista
     - phofl
     - lithomas1
-    - marcogorelli

doc/source/user_guide/basics.rst

@@ -36,7 +36,7 @@ of elements to display is five, but you may pass a custom number.
 Attributes and underlying data
 ------------------------------
 
-pandas objects have a number of attributes enabling you to access the metadata
+pandas objects have a number of attributes enabling you to access the metadata.
 
 * **shape**: gives the axis dimensions of the object, consistent with ndarray
 * Axis labels
@@ -59,7 +59,7 @@ NumPy's type system to add support for custom arrays
 (see :ref:`basics.dtypes`).
 
 To get the actual data inside a :class:`Index` or :class:`Series`, use
-the ``.array`` property
+the ``.array`` property.
 
 .. ipython:: python
 
@@ -88,18 +88,18 @@ NumPy doesn't have a dtype to represent timezone-aware datetimes, so there
 are two possibly useful representations:
 
 1. An object-dtype :class:`numpy.ndarray` with :class:`Timestamp` objects, each
-   with the correct ``tz``
+   with the correct ``tz``.
 2. A ``datetime64[ns]`` -dtype :class:`numpy.ndarray`, where the values have
-   been converted to UTC and the timezone discarded
+   been converted to UTC and the timezone discarded.
 
-Timezones may be preserved with ``dtype=object``
+Timezones may be preserved with ``dtype=object``:
 
 .. ipython:: python
 
    ser = pd.Series(pd.date_range("2000", periods=2, tz="CET"))
    ser.to_numpy(dtype=object)
 
-Or thrown away with ``dtype='datetime64[ns]'``
+Or thrown away with ``dtype='datetime64[ns]'``:
 
 .. ipython:: python
 

doc/source/whatsnew/v3.0.0.rst

@@ -673,6 +673,7 @@ Timezones
 
 Numeric
 ^^^^^^^
+- Bug in :meth:`DataFrame.corr` where numerical precision errors resulted in correlations above ``1.0`` (:issue:`61120`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)
 - Bug in ``np.matmul`` with :class:`Index` inputs raising a ``TypeError`` (:issue:`57079`)
 
@@ -772,6 +773,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)
+- Bug in :meth:`DataFrame.resample` changing index type to :class:`MultiIndex` when the dataframe is empty and using an upsample method (:issue:`55572`)
 - Bug in :meth:`DataFrameGroupBy.agg` that raises ``AttributeError`` when there is dictionary input and duplicated columns, instead of returning a DataFrame with the aggregation of all duplicate columns. (:issue:`55041`)
 - Bug in :meth:`DataFrameGroupBy.apply` and :meth:`SeriesGroupBy.apply` for empty data frame with ``group_keys=False`` still creating output index using group keys. (:issue:`60471`)
 - Bug in :meth:`DataFrameGroupBy.apply` that was returning a completely empty DataFrame when all return values of ``func`` were ``None`` instead of returning an empty DataFrame with the original columns and dtypes. (:issue:`57775`)

pandas/_libs/algos.pyx

@@ -353,10 +353,9 @@ def nancorr(const float64_t[:, :] mat, bint cov=False, minp=None):
         float64_t[:, ::1] result
         uint8_t[:, :] mask
         int64_t nobs = 0
-        float64_t vx, vy, dx, dy, meanx, meany, divisor, ssqdmx, ssqdmy, covxy
+        float64_t vx, vy, dx, dy, meanx, meany, divisor, ssqdmx, ssqdmy, covxy, val
 
     N, K = (<object>mat).shape
-
     if minp is None:
         minpv = 1
     else:
@@ -389,8 +388,14 @@ def nancorr(const float64_t[:, :] mat, bint cov=False, minp=None):
                 else:
                     divisor = (nobs - 1.0) if cov else sqrt(ssqdmx * ssqdmy)
 
+                    # clip `covxy / divisor` to ensure coeff is within bounds
                     if divisor != 0:
-                        result[xi, yi] = result[yi, xi] = covxy / divisor
+                        val = covxy / divisor
+                        if val > 1.0:
+                            val = 1.0
+                        elif val < -1.0:
+                            val = -1.0
+                        result[xi, yi] = result[yi, xi] = val
                     else:
                         result[xi, yi] = result[yi, xi] = NaN
 

pandas/_libs/tslibs/period.pyx

@@ -1752,9 +1752,6 @@ cdef class _Period(PeriodMixin):
     def __cinit__(self, int64_t ordinal, BaseOffset freq):
         self.ordinal = ordinal
         self.freq = freq
-        # Note: this is more performant than PeriodDtype.from_date_offset(freq)
-        #  because from_date_offset cannot be made a cdef method (until cython
-        #  supported cdef classmethods)
         self._dtype = PeriodDtypeBase(freq._period_dtype_code, freq.n)
 
     @classmethod
@@ -1913,7 +1910,7 @@ cdef class _Period(PeriodMixin):
 
         Parameters
         ----------
-        freq : str, BaseOffset
+        freq : str, DateOffset
             The target frequency to convert the Period object to.
             If a string is provided,
             it must be a valid :ref:`period alias <timeseries.period_aliases>`.
@@ -2599,7 +2596,7 @@ cdef class _Period(PeriodMixin):
 
         Parameters
         ----------
-        freq : str, BaseOffset
+        freq : str, DateOffset
             Frequency to use for the returned period.
 
         See Also

pandas/core/resample.py

@@ -507,22 +507,12 @@ def _wrap_result(self, result):
         """
         Potentially wrap any results.
         """
-        # GH 47705
-        obj = self.obj
-        if (
-            isinstance(result, ABCDataFrame)
-            and len(result) == 0
-            and not isinstance(result.index, PeriodIndex)
-        ):
-            result = result.set_index(
-                _asfreq_compat(obj.index[:0], freq=self.freq), append=True
-            )
-
         if isinstance(result, ABCSeries) and self._selection is not None:
             result.name = self._selection
 
         if isinstance(result, ABCSeries) and result.empty:
             # When index is all NaT, result is empty but index is not
+            obj = self.obj
             result.index = _asfreq_compat(obj.index[:0], freq=self.freq)
             result.name = getattr(obj, "name", None)
 
@@ -1756,6 +1746,17 @@ def func(x):
             return x.apply(f, *args, **kwargs)
 
         result = self._groupby.apply(func)
+
+        # GH 47705
+        if (
+            isinstance(result, ABCDataFrame)
+            and len(result) == 0
+            and not isinstance(result.index, PeriodIndex)
+        ):
+            result = result.set_index(
+                _asfreq_compat(self.obj.index[:0], freq=self.freq), append=True
+            )
+
         return self._wrap_result(result)
 
     _upsample = _apply

pandas/tests/frame/methods/test_cov_corr.py

@@ -485,3 +485,15 @@ def test_corrwith_min_periods_boolean(self):
         result = df_bool.corrwith(ser_bool, min_periods=3)
         expected = Series([0.57735, 0.57735], index=["A", "B"])
         tm.assert_series_equal(result, expected)
+
+    def test_corr_within_bounds(self):
+        df1 = DataFrame({"x": [0, 1], "y": [1.35951, 1.3595100000000007]})
+        result1 = df1.corr().max().max()
+        expected1 = 1.0
+        tm.assert_equal(result1, expected1)
+
+        rng = np.random.default_rng(seed=42)
+        df2 = DataFrame(rng.random((100, 4)))
+        corr_matrix = df2.corr()
+        assert corr_matrix.min().min() >= -1.0
+        assert corr_matrix.max().max() <= 1.0

pandas/tests/resample/test_base.py

@@ -438,6 +438,24 @@ def test_resample_size_empty_dataframe(freq, index):
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.parametrize("index", [DatetimeIndex([]), TimedeltaIndex([])])
+@pytest.mark.parametrize("freq", ["D", "h"])
+@pytest.mark.parametrize(
+    "method", ["ffill", "bfill", "nearest", "asfreq", "interpolate", "mean"]
+)
+def test_resample_apply_empty_dataframe(index, freq, method):
+    # GH#55572
+    empty_frame_dti = DataFrame(index=index)
+
+    rs = empty_frame_dti.resample(freq)
+    result = rs.apply(getattr(rs, method))
+
+    expected_index = _asfreq_compat(empty_frame_dti.index, freq)
+    expected = DataFrame([], index=expected_index)
+
+    tm.assert_frame_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "index",
     [

web/pandas/config.yml

@@ -84,7 +84,6 @@ maintainers:
   - alimcmaster1
   - bashtage
   - Dr-Irv
-  - MarcoGorelli
   - rhshadrach
   - phofl
   - attack68
@@ -108,6 +107,7 @@ maintainers:
   - gfyoung
   - mzeitlin11
   - twoertwein
+  - MarcoGorelli
 workgroups:
   coc:
     name: Code of Conduct
@@ -139,53 +139,28 @@ workgroups:
     contact: [email protected]
     responsibilities: "Share relevant information with the broader community, mainly via our social networks, as well as being the main point of contact between NumFOCUS and the core team."
     members:
-    - Marco Gorelli
+    - datapythonista
 sponsors:
   active:
   - name: "NumFOCUS"
     url: https://numfocus.org/
     logo: static/img/partners/numfocus.svg
     kind: numfocus
-  - name: "Two Sigma"
-    url: https://www.twosigma.com/
-    logo: static/img/partners/two_sigma.svg
-    kind: partner
-    description: "Jeff Reback"
-  - name: "Voltron Data"
-    url: https://voltrondata.com/
-    logo: static/img/partners/voltron_data.svg
-    kind: partner
-    description: "Joris Van den Bossche"
   - name: "Coiled"
     url: https://www.coiled.io
     logo: static/img/partners/coiled.svg
     kind: partner
     description: "Patrick Hoefler"
-  - name: "Quansight"
-    url: https://quansight.com/
-    logo: static/img/partners/quansight_labs.svg
-    kind: partner
-    description: "Marco Gorelli"
   - name: "Nvidia"
     url: https://www.nvidia.com
     logo: static/img/partners/nvidia.svg
     kind: partner
     description: "Matthew Roeschke"
-  - name: "Intel"
-    url: https://www.intel.com/
-    logo: /static/img/partners/intel.svg
-    kind: partner
-    description: "Brock Mendel"
   - name: "Tidelift"
     url: https://tidelift.com
     logo: static/img/partners/tidelift.svg
     kind: regular
     description: "<i>pandas</i> is part of the <a href=\"https://tidelift.com/subscription/pkg/pypi-pandas?utm_source=pypi-pandas&utm_medium=referral&utm_campaign=readme\">Tidelift subscription</a>. You can support pandas by becoming a Tidelift subscriber."
-  - name: "Chan Zuckerberg Initiative"
-    url: https://chanzuckerberg.com/
-    logo: static/img/partners/czi.svg
-    kind: regular
-    description: "<i>pandas</i> is funded by the Essential Open Source Software for Science program of the Chan Zuckerberg Initiative. The funding is used for general maintenance, improve extension types, and a efficient string type."
   - name: "Bodo"
     url: https://www.bodo.ai/
     logo: static/img/partners/bodo.svg