PERF: Construction of a DatetimeIndex from a list of Timestamp with timezone (#51247)

* require tzdata on windows

* put minimum version?

* try installing with pip in conda envs

* fixup ci check

* whatsnew

* add tzdata to yaml files

* add tzdata>=2022.1 to test_wheels_windows.bat

* try using OR statement

* try another syntax

* try using the pypi install

* try marking windows in yaml

* fixup validation script

* clarify what tzdata is neeeded for, remove it as optional

* remove optional section on timezones

* require tzdata everywhere

* remove timezone extra in package-checks

* remove final timezone extra reference

---------

Co-authored-by: MarcoGorelli <>

Author: MarcoGorelli

.github/workflows/package-checks.yml

@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-22.04
     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"]
+        extra: ["test", "performance", "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:

ci/deps/actions-310-numpydev.yaml

@@ -18,9 +18,11 @@ dependencies:
   - python-dateutil
   - pytz
   - pip
+
   - pip:
     - "cython"
     - "--extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple"
     - "--pre"
     - "numpy"
     - "scipy"
+    - "tzdata>=2022.1"

ci/deps/actions-310.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-311.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-38-downstream_compat.yaml

@@ -68,3 +68,6 @@ dependencies:
   - pandas-gbq>=0.15.0
   - pyyaml
   - py
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-38-minimum_versions.yaml

@@ -52,11 +52,11 @@ dependencies:
   - scipy=1.7.1
   - sqlalchemy=1.4.16
   - tabulate=0.8.9
-  - tzdata=2022a
   - xarray=0.21.0
   - xlrd=2.0.1
   - xlsxwriter=1.4.3
   - zstandard=0.15.2
 
   - pip:
     - pyqt5==5.15.1
+    - tzdata==2022.1

ci/deps/actions-38.yaml

@@ -53,3 +53,6 @@ dependencies:
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-39.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-pypy-38.yaml

@@ -22,3 +22,6 @@ dependencies:
   - numpy
   - python-dateutil
   - pytz
+
+  - pip:
+    - tzdata>=2022.1

ci/test_wheels_windows.bat

@@ -3,7 +3,7 @@ pd.test(extra_args=['-m not clipboard and not single_cpu and not slow and not ne
 pd.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db'])
 
 python --version
-pip install pytz six numpy python-dateutil
+pip install pytz six numpy python-dateutil tzdata>=2022.1
 pip install hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17
 pip install --find-links=pandas/dist --no-index pandas
 python -c "%test_command%"

doc/source/getting_started/install.rst

@@ -308,25 +308,6 @@ Dependency                                            Minimum Version    pip ext
 `numba <https://github.com/numba/numba>`__            0.53.1             performance        Alternative execution engine for operations that accept ``engine="numba"`` using a JIT compiler that translates Python functions to optimized machine code using the LLVM compiler.
 ===================================================== ================== ================== ===================================================================================================================================================================================
 
-Timezones
-^^^^^^^^^
-
-Installable with ``pip install "pandas[timezone]"``
-
-========================= ========================= =============== =============================================================
-Dependency                Minimum Version           pip extra       Notes
-========================= ========================= =============== =============================================================
-tzdata                    2022.1(pypi)/             timezone        Allows the use of ``zoneinfo`` timezones with pandas.
-                          2022a(for system tzdata)                  **Note**: You only need to install the pypi package if your
-                                                                    system does not already provide the IANA tz database.
-                                                                    However, the minimum tzdata version still applies, even if it
-                                                                    is not enforced through an error.
-
-                                                                    If you would like to keep your system tzdata version updated,
-                                                                    it is recommended to use the ``tzdata`` package from
-                                                                    conda-forge.
-========================= ========================= =============== =============================================================
-
 Visualization
 ^^^^^^^^^^^^^
 

doc/source/whatsnew/v2.0.0.rst

@@ -25,7 +25,7 @@ When installing pandas using pip, sets of optional dependencies can also be inst
   pip install "pandas[performance, aws]>=2.0.0"
 
 The available extras, found in the :ref:`installation guide<install.dependencies>`, are
-``[all, performance, computation, timezone, fss, aws, gcp, excel, parquet, feather, hdf5, spss, postgresql, mysql,
+``[all, performance, computation, fss, aws, gcp, excel, parquet, feather, hdf5, spss, postgresql, mysql,
 sql-other, html, xml, plot, output_formatting, clipboard, compression, test]`` (:issue:`39164`).
 
 .. _whatsnew_200.enhancements.index_can_hold_numpy_numeric_dtypes:
@@ -650,6 +650,8 @@ If installed, we now require:
 +-------------------+-----------------+----------+---------+
 | python-dateutil   | 2.8.2           |    X     |    X    |
 +-------------------+-----------------+----------+---------+
+| tzdata            | 2022.1          |    X     |    X    |
++-------------------+-----------------+----------+---------+
 
 For `optional libraries <https://pandas.pydata.org/docs/getting_started/install.html>`_ the general recommendation is to use the latest version.
 The following table lists the lowest version per library that is currently being tested throughout the development of pandas.

environment.yml

@@ -52,7 +52,6 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
@@ -119,3 +118,4 @@ dependencies:
   - pip:
       - sphinx-toggleprompt
       - typing_extensions; python_version<"3.11"
+      - tzdata>=2022.1

pyproject.toml

@@ -27,7 +27,8 @@ dependencies = [
   "numpy>=1.21.0; python_version>='3.10'",
   "numpy>=1.23.2; python_version>='3.11'",
   "python-dateutil>=2.8.2",
-  "pytz>=2020.1"
+  "pytz>=2020.1",
+  "tzdata>=2022.1"
 ]
 classifiers = [
     'Development Status :: 5 - Production/Stable',
@@ -57,7 +58,6 @@ matplotlib = "pandas:plotting._matplotlib"
 [project.optional-dependencies]
 test = ['hypothesis>=6.34.2', 'pytest>=7.0.0', 'pytest-xdist>=2.2.0', 'pytest-asyncio>=0.17.0']
 performance = ['bottleneck>=1.3.2', 'numba>=0.53.1', 'numexpr>=2.7.1']
-timezone = ['tzdata>=2022.1']
 computation = ['scipy>=1.7.1', 'xarray>=0.21.0']
 fss = ['fsspec>=2021.07.0']
 aws = ['s3fs>=2021.08.0']
@@ -112,7 +112,6 @@ all = ['beautifulsoup4>=4.9.3',
        'SQLAlchemy>=1.4.16',
        'tables>=3.6.1',
        'tabulate>=0.8.9',
-       'tzdata>=2022.1',
        'xarray>=0.21.0',
        'xlrd>=2.0.1',
        'xlsxwriter>=1.4.3',

requirements-dev.txt

@@ -41,7 +41,6 @@ s3fs>=2021.08.0
 scipy>=1.7.1
 SQLAlchemy>=1.4.16
 tabulate>=0.8.9
-tzdata>=2022.1
 xarray>=0.21.0
 xlrd>=2.0.1
 xlsxwriter>=1.4.3
@@ -88,4 +87,5 @@ requests
 pygments
 sphinx-toggleprompt
 typing_extensions; python_version<"3.11"
+tzdata>=2022.1
 setuptools>=61.0.0

scripts/validate_min_versions_in_sync.py

@@ -39,7 +39,6 @@
 EXCLUDE_DEPS = {"tzdata", "blosc"}
 EXCLUSION_LIST = {
     "python=3.8[build=*_pypy]": None,
-    "tzdata": None,
     "pyarrow": None,
 }
 # pandas package is not available
@@ -228,10 +227,9 @@ def get_versions_from_ci(content: list[str]) -> tuple[dict[str, str], dict[str,
             continue
         elif seen_required and line.strip():
             if "==" in line:
-                package, version = line.strip().split("==")
-
+                package, version = line.strip().split("==", maxsplit=1)
             else:
-                package, version = line.strip().split("=")
+                package, version = line.strip().split("=", maxsplit=1)
             package = package[2:]
             if package in EXCLUDE_DEPS:
                 continue