Merge branch 'main' into docs_pandas.api.indexers.VariableOffsetWindowIndexer

Author: mroeschke

.circleci/config.yml

@@ -15,15 +15,16 @@ jobs:
       - checkout
       - run:
           name: Install Environment and Run Tests
-          shell: /bin/bash -exuo pipefail
+          shell: /bin/bash -exo pipefail
+          # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
           command: |
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-            export PATH=$MAMBA_DIR/bin:$PATH
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
             conda info -a
             conda env create -q -n pandas-dev -f $ENV_FILE
             conda list -n pandas-dev
@@ -33,6 +34,7 @@ jobs:
             fi
             python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
             PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+            sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
             ci/run_tests.sh
   test-linux-musl:
     docker:
@@ -97,21 +99,16 @@ jobs:
 
       - run:
           name: Install Anaconda Client & Upload Wheels
+          shell: /bin/bash -exo pipefail
           command: |
-            echo "Install Mambaforge"
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            echo "Downloading $MAMBA_URL"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-
-            export PATH=$MAMBA_DIR/bin:$PATH
-
-            mamba install -y -c conda-forge anaconda-client
-
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
+            conda install -y -c conda-forge anaconda-client
             source ci/upload_wheels.sh
             set_upload_vars
             upload_wheels

.github/workflows/code-checks.yml

@@ -51,6 +51,11 @@ jobs:
     # TODO: The doctests have to be run first right now, since the Cython doctests only work
     # with pandas installed in non-editable mode
     # This can be removed once pytest-cython doesn't require C extensions to be installed inplace
+
+    - name: Extra installs
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
+
     - name: Run doctests
       run: cd ci && ./code_checks.sh doctests
       if: ${{ steps.build.outcome == 'success' && always() }}

.github/workflows/docbuild-and-upload.yml

@@ -46,6 +46,10 @@ jobs:
     - name: Build Pandas
       uses: ./.github/actions/build_pandas
 
+    - name: Extra installs
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
+
     - name: Test website
       run: python -m pytest web/
 

.github/workflows/unit-tests.yml

@@ -134,8 +134,8 @@ jobs:
         fetch-depth: 0
 
     - name: Extra installs
-      run: sudo apt-get update && sudo apt-get install -y ${{ matrix.extra_apt }}
-      if: ${{ matrix.extra_apt }}
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0 ${{ matrix.extra_apt || ''}}
 
     - name: Generate extra locales
       # These extra locales will be available for locale.setlocale() calls in tests

ci/code_checks.sh

@@ -70,7 +70,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.MultiIndex.get_level_values SA01" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
         -i "pandas.MultiIndex.names SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
@@ -165,9 +164,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.center RT03,SA01" \
         -i "pandas.Series.str.decode PR07,RT03,SA01" \
         -i "pandas.Series.str.encode PR07,RT03,SA01" \
-        -i "pandas.Series.str.find RT03" \
         -i "pandas.Series.str.fullmatch RT03" \
-        -i "pandas.Series.str.get RT03,SA01" \
         -i "pandas.Series.str.index RT03" \
         -i "pandas.Series.str.ljust RT03,SA01" \
         -i "pandas.Series.str.lower RT03" \
@@ -177,7 +174,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.partition RT03" \
         -i "pandas.Series.str.repeat SA01" \
         -i "pandas.Series.str.replace SA01" \
-        -i "pandas.Series.str.rfind RT03" \
         -i "pandas.Series.str.rindex RT03" \
         -i "pandas.Series.str.rjust RT03,SA01" \
         -i "pandas.Series.str.rpartition RT03" \
@@ -268,7 +264,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.extensions.ExtensionArray.unique RT03,SA01" \
         -i "pandas.api.extensions.ExtensionArray.view SA01" \
         -i "pandas.api.interchange.from_dataframe RT03,SA01" \
-        -i "pandas.api.types.is_any_real_numeric_dtype SA01" \
         -i "pandas.api.types.is_bool PR01,SA01" \
         -i "pandas.api.types.is_bool_dtype SA01" \
         -i "pandas.api.types.is_categorical_dtype SA01" \
@@ -295,7 +290,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_period_dtype SA01" \
         -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
-        -i "pandas.api.types.is_sparse SA01" \
         -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \

doc/source/user_guide/basics.rst

@@ -155,16 +155,6 @@ speedups. ``numexpr`` uses smart chunking, caching, and multiple cores. ``bottle
 a set of specialized cython routines that are especially fast when dealing with arrays that have
 ``nans``.
 
-Here is a sample (using 100 column x 100,000 row ``DataFrames``):
-
-.. csv-table::
-    :header: "Operation", "0.11.0 (ms)", "Prior Version (ms)", "Ratio to Prior"
-    :widths: 25, 25, 25, 25
-
-    ``df1 > df2``, 13.32, 125.35,  0.1063
-    ``df1 * df2``, 21.71,  36.63,  0.5928
-    ``df1 + df2``, 22.04,  36.50,  0.6039
-
 You are highly encouraged to install both libraries. See the section
 :ref:`Recommended Dependencies <install.recommended_dependencies>` for more installation info.
 

doc/source/whatsnew/v3.0.0.rst

@@ -589,7 +589,7 @@ I/O
 
 Period
 ^^^^^^
--
+- Fixed error message when passing invalid period alias to :meth:`PeriodIndex.to_timestamp` (:issue:`58974`)
 -
 
 Plotting

pandas/_libs/tslibs/offsets.pyx

@@ -4752,20 +4752,16 @@ def _validate_to_offset_alias(alias: str, is_period: bool) -> None:
                 alias.lower() not in {"s", "ms", "us", "ns"} and
                 alias.upper().split("-")[0].endswith(("S", "E"))):
             raise ValueError(INVALID_FREQ_ERR_MSG.format(alias))
-    if (is_period and
-            alias.upper() in c_OFFSET_TO_PERIOD_FREQSTR and
-            alias != "ms" and
-            alias.upper().split("-")[0].endswith(("S", "E"))):
-        if (alias.upper().startswith("B") or
-                alias.upper().startswith("S") or
-                alias.upper().startswith("C")):
-            raise ValueError(INVALID_FREQ_ERR_MSG.format(alias))
-        else:
-            alias_msg = "".join(alias.upper().split("E", 1))
-            raise ValueError(
-                f"for Period, please use \'{alias_msg}\' "
-                f"instead of \'{alias}\'"
-            )
+    if (
+        is_period and
+        alias in c_OFFSET_TO_PERIOD_FREQSTR and
+        alias != c_OFFSET_TO_PERIOD_FREQSTR[alias]
+    ):
+        alias_msg = c_OFFSET_TO_PERIOD_FREQSTR.get(alias)
+        raise ValueError(
+            f"for Period, please use \'{alias_msg}\' "
+            f"instead of \'{alias}\'"
+        )
 
 
 # TODO: better name?

pandas/conftest.py

@@ -1296,7 +1296,6 @@ def nullable_string_dtype(request):
     params=[
         "python",
         pytest.param("pyarrow", marks=td.skip_if_no("pyarrow")),
-        pytest.param("pyarrow_numpy", marks=td.skip_if_no("pyarrow")),
     ]
 )
 def string_storage(request):
@@ -1305,7 +1304,24 @@ def string_storage(request):
 
     * 'python'
     * 'pyarrow'
-    * 'pyarrow_numpy'
+    """
+    return request.param
+
+
+@pytest.fixture(
+    params=[
+        ("python", pd.NA),
+        pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
+        pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
+    ]
+)
+def string_dtype_arguments(request):
+    """
+    Parametrized fixture for StringDtype storage and na_value.
+
+    * 'python' + pd.NA
+    * 'pyarrow' + pd.NA
+    * 'pyarrow' + np.nan
     """
     return request.param
 

pandas/core/config_init.py

@@ -14,6 +14,7 @@
 
 from collections.abc import Callable
 import os
+from typing import Any
 
 import pandas._config.config as cf
 from pandas._config.config import (
@@ -455,12 +456,27 @@ def is_terminal() -> bool:
     ``future.infer_string`` is set to True.
 """
 
+
+def is_valid_string_storage(value: Any) -> None:
+    legal_values = ["python", "pyarrow"]
+    if value not in legal_values:
+        msg = "Value must be one of python|pyarrow"
+        if value == "pyarrow_numpy":
+            # TODO: we can remove extra message after 3.0
+            msg += (
+                ". 'pyarrow_numpy' was specified, but this option should be "
+                "enabled using pandas.options.future.infer_string instead"
+            )
+        raise ValueError(msg)
+
+
 with cf.config_prefix("mode"):
     cf.register_option(
         "string_storage",
         "python",
         string_storage_doc,
-        validator=is_one_of_factory(["python", "pyarrow", "pyarrow_numpy"]),
+        # validator=is_one_of_factory(["python", "pyarrow"]),
+        validator=is_valid_string_storage,
     )