Merge remote-tracking branch 'upstream/main' into td-construction

Author: patrickmckenna

.github/workflows/32-bit-linux.yml

@@ -0,0 +1,43 @@
+name: 32 Bit Linux
+
+on:
+  push:
+    branches:
+      - main
+      - 1.4.x
+  pull_request:
+    branches:
+      - main
+      - 1.4.x
+    paths-ignore:
+      - "doc/**"
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Run 32-bit manylinux2014 Docker Build / Tests
+        run: |
+          docker pull quay.io/pypa/manylinux2014_i686
+          docker run --platform linux/386 -v $(pwd):/pandas quay.io/pypa/manylinux2014_i686 \
+          /bin/bash -xc "cd pandas && \
+          /opt/python/cp38-cp38/bin/python -m venv ~/virtualenvs/pandas-dev && \
+          . ~/virtualenvs/pandas-dev/bin/activate && \
+          python -m pip install --no-deps -U pip wheel 'setuptools<60.0.0' && \
+          pip install cython numpy python-dateutil pytz pytest pytest-xdist pytest-asyncio>=0.17 hypothesis && \
+          python setup.py build_ext -q -j2 && \
+          python -m pip install --no-build-isolation --no-use-pep517 -e . && \
+          export PANDAS_CI=1 && \
+          pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml"
+
+      - name: Publish test results for Python 3.8-32 bit full Linux
+        uses: actions/upload-artifact@v3
+        with:
+          name: Test results
+          path: test-data.xml
+        if: failure()

.github/workflows/code-checks.yml

@@ -74,7 +74,7 @@ jobs:
 
     - name: Install pyright
       # note: keep version in sync with .pre-commit-config.yaml
-      run: npm install -g pyright@1.1.245
+      run: npm install -g pyright@1.1.247
 
     - name: Build Pandas
       id: build

.github/workflows/python-dev.yml

@@ -2,7 +2,7 @@
 # Unfreeze(by commentingthe if: false() condition) once the
 # next Python Dev version has released beta 1 and both Cython and numpy support it
 # After that Python has released, migrate the workflows to the
-# posix GHA workflows/Azure pipelines and "freeze" this file by
+# posix GHA workflows and "freeze" this file by
 # uncommenting the if: false() condition
 # Feel free to modify this comment as necessary.
 

.pre-commit-config.yaml

@@ -89,7 +89,7 @@ repos:
         types: [python]
         stages: [manual]
         # note: keep version in sync with .github/workflows/code-checks.yml
-        additional_dependencies: ['pyright@1.1.245']
+        additional_dependencies: ['pyright@1.1.247']
 -   repo: local
     hooks:
     -   id: flake8-rst

LICENSES/ULTRAJSON_LICENSE

@@ -28,7 +28,7 @@ Portions of code from MODP_ASCII - Ascii transformations (upper/lower, etc)
 https://github.com/client9/stringencoders
 Copyright (c) 2007  Nick Galbreath -- nickg [at] modp [dot] com. All rights reserved.
 
-Numeric decoder derived from from TCL library
+Numeric decoder derived from TCL library
 http://www.opensource.apple.com/source/tcl/tcl-14/tcl/license.terms
  * Copyright (c) 1988-1993 The Regents of the University of California.
  * Copyright (c) 1994 Sun Microsystems, Inc.

README.md

@@ -10,7 +10,6 @@
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3509134.svg)](https://doi.org/10.5281/zenodo.3509134)
 [![Package Status](https://img.shields.io/pypi/status/pandas.svg)](https://pypi.org/project/pandas/)
 [![License](https://img.shields.io/pypi/l/pandas.svg)](https://github.com/pandas-dev/pandas/blob/main/LICENSE)
-[![Azure Build Status](https://dev.azure.com/pandas-dev/pandas/_apis/build/status/pandas-dev.pandas?branch=main)](https://dev.azure.com/pandas-dev/pandas/_build/latest?definitionId=1&branch=main)
 [![Coverage](https://codecov.io/github/pandas-dev/pandas/coverage.svg?branch=main)](https://codecov.io/gh/pandas-dev/pandas)
 [![Downloads](https://static.pepy.tech/personalized-badge/pandas?period=month&units=international_system&left_color=black&right_color=orange&left_text=PyPI%20downloads%20per%20month)](https://pepy.tech/project/pandas)
 [![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/pydata/pandas)

asv_bench/benchmarks/sparse.py

@@ -146,10 +146,10 @@ def setup(self, fill_value):
 
     def make_block_array(self, length, num_blocks, block_size, fill_value):
         arr = np.full(length, fill_value)
-        indicies = np.random.choice(
+        indices = np.random.choice(
             np.arange(0, length, block_size), num_blocks, replace=False
         )
-        for ind in indicies:
+        for ind in indices:
             arr[ind : ind + block_size] = np.random.randint(0, 100, block_size)
         return SparseArray(arr, fill_value=fill_value)
 

azure-pipelines.yml

@@ -104,6 +104,6 @@ echo "Build extensions"
 python setup.py build_ext -q -j3
 
 echo "Install pandas"
-python -m pip install --no-build-isolation -e .
+python -m pip install --no-build-isolation --no-use-pep517 -e .
 
 echo "done"

ci/setup_env.sh

@@ -289,13 +289,11 @@ library. This makes type checkers aware of the type annotations shipped with pan
 Testing with continuous integration
 -----------------------------------
 
-The pandas test suite will run automatically on `GitHub Actions <https://github.com/features/actions/>`__ and
-`Azure Pipelines <https://azure.microsoft.com/en-us/services/devops/pipelines/>`__
+The pandas test suite will run automatically on `GitHub Actions <https://github.com/features/actions/>`__
 continuous integration services, once your pull request is submitted.
 However, if you wish to run the test suite on a branch prior to submitting the pull request,
 then the continuous integration services need to be hooked to your GitHub repository. Instructions are here
-for `GitHub Actions <https://docs.github.com/en/actions/>`__ and
-`Azure Pipelines <https://docs.microsoft.com/en-us/azure/devops/pipelines/?view=azure-devops>`__.
+for `GitHub Actions <https://docs.github.com/en/actions/>`__.
 
 A pull-request will be considered for merging when you have an all 'green' build. If any tests are failing,
 then you will get a red 'X', where you can click through to see the individual failed tests.

doc/source/development/contributing_codebase.rst

@@ -3529,7 +3529,7 @@ See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
    **Please do not report issues when using ``xlrd`` to read ``.xlsx`` files.**
    This is no longer supported, switch to using ``openpyxl`` instead.
 
-   Attempting to use the the ``xlwt`` engine will raise a ``FutureWarning``
+   Attempting to use the ``xlwt`` engine will raise a ``FutureWarning``
    unless the option :attr:`io.excel.xls.writer` is set to ``"xlwt"``.
    While this option is now deprecated and will also raise a ``FutureWarning``,
    it can be globally set and the warning suppressed. Users are recommended to
@@ -5470,7 +5470,7 @@ See the documentation for `pyarrow <https://arrow.apache.org/docs/python/>`__ an
 .. note::
 
    These engines are very similar and should read/write nearly identical parquet format files.
-   Currently ``pyarrow`` does not support timedelta data, ``fastparquet>=0.1.4`` supports timezone aware datetimes.
+   ``pyarrow>=8.0.0`` supports timedelta data, ``fastparquet>=0.1.4`` supports timezone aware datetimes.
    These libraries differ by having different underlying dependencies (``fastparquet`` by using ``numba``, while ``pyarrow`` uses a c-library).
 
 .. ipython:: python

doc/source/user_guide/io.rst

@@ -612,7 +612,7 @@
    "source": [
     "### Acting on the Index and Column Headers\n",
     "\n",
-    "Similar application is acheived for headers by using:\n",
+    "Similar application is achieved for headers by using:\n",
     "    \n",
     "- [.applymap_index()][applymapindex] (elementwise): accepts a function that takes a single value and returns a string with the CSS attribute-value pair.\n",
     "- [.apply_index()][applyindex] (level-wise): accepts a function that takes a Series and returns a Series, or numpy array with an identical shape where each element is a string with a CSS attribute-value pair. This method passes each level of your Index one-at-a-time. To style the index use `axis=0` and to style the column headers use `axis=1`.\n",

doc/source/user_guide/style.ipynb

@@ -360,7 +360,7 @@ If installed, we now require:
 +-----------------+-----------------+----------+---------+
 | Package         | Minimum Version | Required | Changed |
 +=================+=================+==========+=========+
-| mypy (dev)      | 0.941           |          |    X    |
+| mypy (dev)      | 0.950           |          |    X    |
 +-----------------+-----------------+----------+---------+
 
 

doc/source/whatsnew/v1.5.0.rst

@@ -24,7 +24,7 @@ dependencies:
   - flake8-bugbear=21.3.2  # used by flake8, find likely bugs
   - flake8-comprehensions=3.7.0  # used by flake8, linting of unnecessary comprehensions
   - isort>=5.2.1  # check that imports are in the right order
-  - mypy=0.941
+  - mypy=0.950
   - pre-commit>=2.9.2
   - pycodestyle  # used by flake8
   - pyupgrade

environment.yml

@@ -45,7 +45,9 @@ def set_locale(
         locale.setlocale(lc_var, new_locale)
         normalized_locale = locale.getlocale()
         if all(x is not None for x in normalized_locale):
-            yield ".".join(normalized_locale)
+            # error: Argument 1 to "join" of "str" has incompatible type
+            # "Tuple[Optional[str], Optional[str]]"; expected "Iterable[str]"
+            yield ".".join(normalized_locale)  # type: ignore[arg-type]
         else:
             yield new_locale
     finally:

pandas/_config/localization.py

@@ -58,9 +58,7 @@
 )
 from pandas._libs.tslibs.timestamps import Timestamp
 from pandas._libs.tslibs.timezones import tz_compare
-from pandas._libs.tslibs.tzconversion import (
-    py_tz_convert_from_utc_single as tz_convert_from_utc_single,
-)
+from pandas._libs.tslibs.tzconversion import tz_convert_from_utc_single
 from pandas._libs.tslibs.vectorized import (
     dt64arr_to_periodarr,
     get_resolution,

pandas/_libs/tslibs/__init__.py

@@ -54,10 +54,7 @@ from pandas._libs.tslibs.ccalendar cimport (
     get_firstbday,
     get_lastbday,
 )
-from pandas._libs.tslibs.conversion cimport (
-    convert_datetime_to_tsobject,
-    localize_pydatetime,
-)
+from pandas._libs.tslibs.conversion cimport localize_pydatetime
 from pandas._libs.tslibs.nattype cimport (
     NPY_NAT,
     c_NaT as NaT,
@@ -68,7 +65,6 @@ from pandas._libs.tslibs.np_datetime cimport (
     npy_datetimestruct,
     pydate_to_dtstruct,
 )
-from pandas._libs.tslibs.tzconversion cimport tz_convert_from_utc_single
 
 from .dtypes cimport PeriodDtypeCode
 from .timedeltas cimport (
@@ -270,10 +266,8 @@ cdef _to_dt64D(dt):
     if getattr(dt, 'tzinfo', None) is not None:
         # Get the nanosecond timestamp,
         #  equiv `Timestamp(dt).value` or `dt.timestamp() * 10**9`
-        nanos = getattr(dt, "nanosecond", 0)
-        i8 = convert_datetime_to_tsobject(dt, tz=None, nanos=nanos).value
-        dt = tz_convert_from_utc_single(i8, dt.tzinfo)
-        dt = np.int64(dt).astype('datetime64[ns]')
+        naive = dt.astimezone(None)
+        dt = np.datetime64(naive, "D")
     else:
         dt = np.datetime64(dt)
     if dt.dtype.name != "datetime64[D]":

pandas/_libs/tslibs/offsets.pyx

@@ -113,7 +113,7 @@ class Timestamp(datetime):
     def time(self) -> _time: ...
     def timetz(self) -> _time: ...
     def replace(
-        self,
+        self: _DatetimeT,
         year: int = ...,
         month: int = ...,
         day: int = ...,
@@ -123,7 +123,7 @@ class Timestamp(datetime):
         microsecond: int = ...,
         tzinfo: _tzinfo | None = ...,
         fold: int = ...,
-    ) -> datetime: ...
+    ) -> _DatetimeT: ...
     def astimezone(self: _DatetimeT, tz: _tzinfo | None = ...) -> _DatetimeT: ...
     def ctime(self) -> str: ...
     def isoformat(self, sep: str = ..., timespec: str = ...) -> str: ...

pandas/_libs/tslibs/timestamps.pyi

@@ -1981,22 +1981,19 @@ default 'raise'
             value = tz_localize_to_utc_single(self.value, tz,
                                               ambiguous=ambiguous,
                                               nonexistent=nonexistent)
-            out = Timestamp(value, tz=tz)
-            if out is not NaT:
-                out._set_freq(self._freq)  # avoid warning in constructor
-            return out
+        elif tz is None:
+            # reset tz
+            value = tz_convert_from_utc_single(self.value, self.tz)
+
         else:
-            if tz is None:
-                # reset tz
-                value = tz_convert_from_utc_single(self.value, self.tz)
-                out = Timestamp(value, tz=tz)
-                if out is not NaT:
-                    out._set_freq(self._freq)  # avoid warning in constructor
-                return out
-            else:
-                raise TypeError(
-                    "Cannot localize tz-aware Timestamp, use tz_convert for conversions"
-                )
+            raise TypeError(
+                "Cannot localize tz-aware Timestamp, use tz_convert for conversions"
+            )
+
+        out = Timestamp(value, tz=tz)
+        if out is not NaT:
+            out._set_freq(self._freq)  # avoid warning in constructor
+        return out
 
     def tz_convert(self, tz):
         """

pandas/_libs/tslibs/timestamps.pyx

@@ -6,8 +6,8 @@ from numpy cimport (
 )
 
 
-cdef int64_t tz_convert_from_utc_single(
-    int64_t utc_val, tzinfo tz, bint* fold=?, Py_ssize_t* outpos=?
+cpdef int64_t tz_convert_from_utc_single(
+    int64_t utc_val, tzinfo tz
 ) except? -1
 cdef int64_t tz_localize_to_utc_single(
     int64_t val, tzinfo tz, object ambiguous=*, object nonexistent=*

pandas/_libs/tslibs/tzconversion.pxd

@@ -8,8 +8,8 @@ import numpy as np
 
 from pandas._typing import npt
 
-# py_tz_convert_from_utc_single exposed for testing
-def py_tz_convert_from_utc_single(val: np.int64, tz: tzinfo) -> np.int64: ...
+# tz_convert_from_utc_single exposed for testing
+def tz_convert_from_utc_single(val: np.int64, tz: tzinfo) -> np.int64: ...
 def tz_localize_to_utc(
     vals: npt.NDArray[np.int64],
     tz: tzinfo | None,