fix: merge in upstream/main

Author: Dr-Irv

.github/workflows/package-checks.yml

@@ -0,0 +1,56 @@
+name: Package Checks
+
+on:
+  push:
+    branches:
+      - main
+      - 1.5.x
+  pull_request:
+    branches:
+      - main
+      - 1.5.x
+
+permissions:
+  contents: read
+
+jobs:
+  pip:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        extra: ["test", "performance", "timezone", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output_formatting", "clipboard", "compression", "all"]
+      fail-fast: false
+    name: Install Extras - ${{ matrix.extra }}
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-pip-extras-${{ matrix.extra }}
+      cancel-in-progress: true
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python
+        id: setup_python
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.8'
+
+      # Hacky patch to disable building cython extensions.
+      # This job should only check that the extras successfully install.
+      - name: Disable building ext_modules
+        run: |
+          sed -i '/ext_modules=/d' setup.py
+        shell: bash -el {0}
+
+      - name: Install required dependencies
+        run: |
+          python -m pip install --upgrade pip setuptools wheel python-dateutil pytz numpy cython
+        shell: bash -el {0}
+
+      - name: Pip install with extra
+        run: |
+          python -m pip install -e .[${{ matrix.extra }}] --no-build-isolation
+        shell: bash -el {0}

asv_bench/benchmarks/hash_functions.py

@@ -57,14 +57,14 @@ def time_unique(self, exponent):
 class NumericSeriesIndexing:
 
     params = [
-        (pd.Int64Index, pd.UInt64Index, pd.Float64Index),
+        (np.int64, np.uint64, np.float64),
         (10**4, 10**5, 5 * 10**5, 10**6, 5 * 10**6),
     ]
-    param_names = ["index_dtype", "N"]
+    param_names = ["dtype", "N"]
 
-    def setup(self, index, N):
-        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)))
-        indices = index(vals)
+    def setup(self, dtype, N):
+        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
+        indices = pd.Index(vals)
         self.data = pd.Series(np.arange(N), index=indices)
 
     def time_loc_slice(self, index, N):
@@ -75,15 +75,15 @@ def time_loc_slice(self, index, N):
 class NumericSeriesIndexingShuffled:
 
     params = [
-        (pd.Int64Index, pd.UInt64Index, pd.Float64Index),
+        (np.int64, np.uint64, np.float64),
         (10**4, 10**5, 5 * 10**5, 10**6, 5 * 10**6),
     ]
-    param_names = ["index_dtype", "N"]
+    param_names = ["dtype", "N"]
 
-    def setup(self, index, N):
-        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)))
+    def setup(self, dtype, N):
+        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
         np.random.shuffle(vals)
-        indices = index(vals)
+        indices = pd.Index(vals)
         self.data = pd.Series(np.arange(N), index=indices)
 
     def time_loc_slice(self, index, N):

asv_bench/benchmarks/index_cached_properties.py

@@ -30,7 +30,7 @@ def setup(self, index_type):
         elif index_type == "DatetimeIndex":
             self.idx = pd.date_range("1/1/2000", freq="T", periods=N)
         elif index_type == "Int64Index":
-            self.idx = pd.Index(range(N))
+            self.idx = pd.Index(range(N), dtype="int64")
         elif index_type == "PeriodIndex":
             self.idx = pd.period_range("1/1/2000", freq="T", periods=N)
         elif index_type == "RangeIndex":
@@ -40,9 +40,9 @@ def setup(self, index_type):
         elif index_type == "TimedeltaIndex":
             self.idx = pd.TimedeltaIndex(range(N))
         elif index_type == "Float64Index":
-            self.idx = pd.Float64Index(range(N))
+            self.idx = pd.Index(range(N), dtype="float64")
         elif index_type == "UInt64Index":
-            self.idx = pd.UInt64Index(range(N))
+            self.idx = pd.Index(range(N), dtype="uint64")
         elif index_type == "CategoricalIndex":
             self.idx = pd.CategoricalIndex(range(N), range(N))
         else:

asv_bench/benchmarks/index_object.py

@@ -4,7 +4,6 @@
 
 from pandas import (
     DatetimeIndex,
-    Float64Index,
     Index,
     IntervalIndex,
     MultiIndex,
@@ -202,8 +201,8 @@ class Float64IndexMethod:
     # GH 13166
     def setup(self):
         N = 100_000
-        a = np.arange(N)
-        self.ind = Float64Index(a * 4.8000000418824129e-08)
+        a = np.arange(N, dtype=np.float64)
+        self.ind = Index(a * 4.8000000418824129e-08)
 
     def time_get_loc(self):
         self.ind.get_loc(0)

asv_bench/benchmarks/indexing.py

@@ -12,12 +12,10 @@
 from pandas import (
     CategoricalIndex,
     DataFrame,
-    Float64Index,
-    Int64Index,
+    Index,
     IntervalIndex,
     MultiIndex,
     Series,
-    UInt64Index,
     concat,
     date_range,
     option_context,
@@ -30,17 +28,17 @@
 class NumericSeriesIndexing:
 
     params = [
-        (Int64Index, UInt64Index, Float64Index),
+        (np.int64, np.uint64, np.float64),
         ("unique_monotonic_inc", "nonunique_monotonic_inc"),
     ]
-    param_names = ["index_dtype", "index_structure"]
+    param_names = ["dtype", "index_structure"]
 
-    def setup(self, index, index_structure):
+    def setup(self, dtype, index_structure):
         N = 10**6
         indices = {
-            "unique_monotonic_inc": index(range(N)),
-            "nonunique_monotonic_inc": index(
-                list(range(55)) + [54] + list(range(55, N - 1))
+            "unique_monotonic_inc": Index(range(N), dtype=dtype),
+            "nonunique_monotonic_inc": Index(
+                list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
             ),
         }
         self.data = Series(np.random.rand(N), index=indices[index_structure])
@@ -159,17 +157,17 @@ def time_boolean_rows_boolean(self):
 class DataFrameNumericIndexing:
 
     params = [
-        (Int64Index, UInt64Index, Float64Index),
+        (np.int64, np.uint64, np.float64),
         ("unique_monotonic_inc", "nonunique_monotonic_inc"),
     ]
-    param_names = ["index_dtype", "index_structure"]
+    param_names = ["dtype", "index_structure"]
 
-    def setup(self, index, index_structure):
+    def setup(self, dtype, index_structure):
         N = 10**5
         indices = {
-            "unique_monotonic_inc": index(range(N)),
-            "nonunique_monotonic_inc": index(
-                list(range(55)) + [54] + list(range(55, N - 1))
+            "unique_monotonic_inc": Index(range(N), dtype=dtype),
+            "nonunique_monotonic_inc": Index(
+                list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
             ),
         }
         self.idx_dupe = np.array(range(30)) * 99
@@ -201,7 +199,7 @@ class Take:
     def setup(self, index):
         N = 100000
         indexes = {
-            "int": Int64Index(np.arange(N)),
+            "int": Index(np.arange(N), dtype=np.int64),
             "datetime": date_range("2011-01-01", freq="S", periods=N),
         }
         index = indexes[index]

asv_bench/benchmarks/package.py

@@ -11,7 +11,7 @@ def time_import(self):
         #  measurement of the import time we actually care about,
         #  without the subprocess or interpreter overhead
         cmd = [sys.executable, "-X", "importtime", "-c", "import pandas as pd"]
-        p = subprocess.run(cmd, stderr=subprocess.PIPE)
+        p = subprocess.run(cmd, stderr=subprocess.PIPE, check=True)
 
         line = p.stderr.splitlines()[-1]
         field = line.split(b"|")[-2].strip()

doc/source/conf.py

@@ -583,7 +583,14 @@ class AccessorCallableDocumenter(AccessorLevelDocumenter, MethodDocumenter):
     priority = 0.5
 
     def format_name(self):
-        return MethodDocumenter.format_name(self).rstrip(".__call__")
+        if sys.version_info < (3, 9):
+            # NOTE pyupgrade will remove this when we run it with --py39-plus
+            # so don't remove the unnecessary `else` statement below
+            from pandas.util._str_methods import removesuffix
+
+            return removesuffix(MethodDocumenter.format_name(self), ".__call__")
+        else:
+            return MethodDocumenter.format_name(self).removesuffix(".__call__")
 
 
 class PandasAutosummary(Autosummary):

doc/source/getting_started/install.rst

@@ -415,7 +415,7 @@ depending on required compatibility.
 Dependency                Minimum Version    optional_extra   Notes
 ========================= ================== ================ =============================================================
 PyTables                  3.6.1              hdf5             HDF5-based reading / writing
-blosc                     1.21.0             hdf5             Compression for HDF5
+blosc                     1.21.0             hdf5             Compression for HDF5; only available on ``conda``
 zlib                                         hdf5             Compression for HDF5
 fastparquet               0.6.3              -                Parquet reading / writing (pyarrow is default)
 pyarrow                   6.0.0              parquet, feather Parquet, ORC, and feather reading / writing

doc/source/reference/indexing.rst

@@ -166,9 +166,6 @@ Numeric Index
    :template: autosummary/class_without_autosummary.rst
 
    RangeIndex
-   Int64Index
-   UInt64Index
-   Float64Index
 
 .. We need this autosummary so that the methods are generated.
 .. Separate block, since they aren't classes.

doc/source/user_guide/merging.rst

@@ -151,8 +151,7 @@ It's not a stretch to see how this can be very useful. More detail on this
 functionality below.
 
 .. note::
-   It is worth noting that :func:`~pandas.concat` (and therefore
-   :func:`~pandas.append`) makes a full copy of the data, and that constantly
+   It is worth noting that :func:`~pandas.concat` makes a full copy of the data, and that constantly
    reusing this function can create a significant performance hit. If you need
    to use the operation over several datasets, use a list comprehension.
 

doc/source/whatsnew/v1.5.0.rst

@@ -1155,7 +1155,6 @@ Plotting
 - Bug in :meth:`DataFrame.boxplot` that prevented passing in ``xlabel`` and ``ylabel`` (:issue:`45463`)
 - Bug in :meth:`DataFrame.boxplot` that prevented specifying ``vert=False`` (:issue:`36918`)
 - Bug in :meth:`DataFrame.plot.scatter` that prevented specifying ``norm`` (:issue:`45809`)
-- The function :meth:`DataFrame.plot.scatter` now accepts ``color`` as an alias for ``c`` and ``size`` as an alias for ``s`` for consistency to other plotting functions (:issue:`44670`)
 - Fix showing "None" as ylabel in :meth:`Series.plot` when not setting ylabel (:issue:`46129`)
 - Bug in :meth:`DataFrame.plot` that led to xticks and vertical grids being improperly placed when plotting a quarterly series (:issue:`47602`)
 - Bug in :meth:`DataFrame.plot` that prevented setting y-axis label, limits and ticks for a secondary y-axis (:issue:`47753`)

doc/source/whatsnew/v1.5.2.rst

@@ -15,18 +15,20 @@ Fixed regressions
 ~~~~~~~~~~~~~~~~~
 - Fixed regression in :meth:`MultiIndex.join` for extension array dtypes (:issue:`49277`)
 - Fixed regression in :meth:`Series.replace` raising ``RecursionError`` with numeric dtype and when specifying ``value=None`` (:issue:`45725`)
+- Fixed regression in arithmetic operations for :class:`DataFrame` with :class:`MultiIndex` columns with different dtypes (:issue:`49769`)
 - Fixed regression in :meth:`DataFrame.plot` preventing :class:`~matplotlib.colors.Colormap` instance
   from being passed using the ``colormap`` argument if Matplotlib 3.6+ is used (:issue:`49374`)
 - Fixed regression in :func:`date_range` returning an invalid set of periods for ``CustomBusinessDay`` frequency and ``start`` date with timezone (:issue:`49441`)
 - Fixed performance regression in groupby operations (:issue:`49676`)
--
+- Fixed regression in :class:`Timedelta` constructor returning object of wrong type when subclassing ``Timedelta`` (:issue:`49579`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_152.bug_fixes:
 
 Bug fixes
 ~~~~~~~~~
 - Bug in the Copy-on-Write implementation losing track of views in certain chained indexing cases (:issue:`48996`)
+- Fixed memory leak in :meth:`.Styler.to_excel` (:issue:`49751`)
 - Fixed bug when instantiating a :class:`DataFrame` subclass inheriting from ``typing.Generic`` that triggered a ``UserWarning`` on python 3.11 (:issue:`49649`)
 -
 
@@ -35,7 +37,7 @@ Bug fixes
 
 Other
 ~~~~~
--
+- Reverted ``color`` as an alias for ``c`` and ``size`` as an alias for ``s`` in function :meth:`DataFrame.plot.scatter` (:issue:`49732`)
 -
 
 .. ---------------------------------------------------------------------------