From c57415861833533db716172f6143b983169027a0 Mon Sep 17 00:00:00 2001
From: "renovate[bot]" <29139614+renovate[bot]@users.noreply.github.com>
Date: Tue, 18 Mar 2025 00:09:44 +0000
Subject: [PATCH 01/12] chore(actions): update dependency python to 3.13

---
 .github/workflows/pull-request.yml |  8 +--
 .github/workflows/release.yml      |  5 +-
 MANIFEST.in                        |  4 +-
 pyproject.toml                     | 81 ++++++++++++++++++------------
 setup.py                           |  5 --
 5 files changed, 57 insertions(+), 46 deletions(-)

diff --git a/.github/workflows/pull-request.yml b/.github/workflows/pull-request.yml
index d51d14932..c66e0317c 100644
--- a/.github/workflows/pull-request.yml
+++ b/.github/workflows/pull-request.yml
@@ -40,7 +40,7 @@ jobs:
     - name: Set up Python 3.11
       uses: actions/setup-python@v5
       with:
-        python-version: "3.13"
+        python-version: '3.11'
 
     - uses: actions/cache@v4
       name: Cache pip dependencies
@@ -52,7 +52,7 @@ jobs:
 
     - name: Install pip dependencies
       run: |
-        python -m pip install --upgrade pip setuptools
+        python -m pip install --upgrade pip
         python -m pip install ".[dev,test]"
 
     - name: Install pre-commit hooks
@@ -93,7 +93,7 @@ jobs:
     - name: Setup Python 3.11
       uses: actions/setup-python@v5
       with:
-        python-version: "3.13"
+        python-version: '3.11'
 
     - name: Cache pip dependencies
       id: cache
@@ -105,7 +105,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install ".[dev,test,docs]"
+        python -m pip install ".[docs]"
       
     - name: Install the package
       run: make install
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index b732a56cb..019d1cc14 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -80,7 +80,6 @@ jobs:
         name: built-artifacts
         path: dist/
 
-    - uses: pypa/gh-action-pypi-publish@v1.12.4
+    - uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+        packages-dir: dist/
diff --git a/MANIFEST.in b/MANIFEST.in
index 06909e0a6..36a019687 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -4,8 +4,6 @@ include requirements*.txt
 # Include license, Readme, etc.
 include LICENSE
 include *.md
-include mypy.ini
-include src/ydata_profiling/py.typed
 
 # Templates and static resources
 recursive-include src/ydata_profiling/report/presentation/flavours/html/templates *.html *.js *.css
@@ -20,7 +18,7 @@ recursive-include venv *.yml
 exclude .pre-commit-config.yaml
 exclude commitlint.config.js
 exclude .releaserc.json
-include Makefile make.bat
+exclude Makefile make.bat
 exclude docs examples tests docsrc .devcontainer
 recursive-exclude docs *
 recursive-exclude docsrc *
diff --git a/pyproject.toml b/pyproject.toml
index 72f019a1f..50e75eb96 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,18 +1,25 @@
 [build-system]
-requires = ["setuptools"]
 build-backend = "setuptools.build_meta"
+requires = [
+    "setuptools>=72.0.0,<80.0.0",
+    "setuptools-scm>=8.0.0,<9.0.0",
+    "wheel>=0.38.4,<1.0.0"
+]
+
+[packaging]
+package_name = "ydata-profiling"
 
 [project]
 name = "ydata-profiling"
+requires-python = ">=3.7,<3.13"
 authors = [
-    {name = "YData Labs Inc", email = "opensource@ydata.ai"},
+    {name = "YData Labs Inc", email = "opensource@ydata.ai"}
 ]
-description="Generate profile report for pandas DataFrame"
+description = "Generate profile report for pandas DataFrame"
+keywords = ["pandas", "data-science", "data-analysis", "python", "jupyter", "ipython"]
 readme = "README.md"
-requires-python=">=3.7, <3.13"
-keywords=["pandas", "data-science", "data-analysis", "python", "jupyter", "ipython"]
-license = {text = "MIT"}
-classifiers=[
+license = {file = "LICENSE.md"}
+classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Topic :: Software Development :: Build Tools",
     "License :: OSI Approved :: MIT License",
@@ -63,10 +70,11 @@ dependencies = [
     "numba>=0.56.0, <1",
 ]
 
-dynamic = ["version"]
+dynamic = [
+    "version",
+]
 
 [project.optional-dependencies]
-# dependencies for development and testing
 dev = [
     "black>=20.8b1",
     "isort>=5.0.7",
@@ -80,6 +88,22 @@ dev = [
     "sphinx-multiversion>=0.2.3",
     "autodoc_pydantic",
 ]
+
+docs = [
+    "mkdocs>=1.6.0,<1.7.0",
+    "mkdocs-material>=9.0.12,<10.0.0",
+    "mkdocs-material-extensions>=1.1.1,<2.0.0",
+    "mkdocs-table-reader-plugin<=2.2.0",
+    "mike>=2.1.1,<2.2.0",
+    "mkdocstrings[python]>=0.20.0,<1.0.0",
+    "mkdocs-badges",
+]
+
+notebook = [
+    "jupyter>=1.0.0",
+    "ipywidgets>=7.5.1",
+]
+
 # this provides the recommended pyspark and pyarrow versions for spark to work on pandas-profiling
 # note that if you are using pyspark 2.3 or 2.4 and pyarrow >= 0.15, you might need to
 # set ARROW_PRE_0_15_IPC_FORMAT=1 in your conf/spark-env.sh for toPandas functions to work properly
@@ -90,6 +114,7 @@ spark = [
     "numpy>=1.16.0,<1.24",
     "visions[type_image_path]>=0.7.5, <0.7.7",
 ]
+
 test = [
     "pytest",
     "coverage>=6.5, <8",
@@ -100,35 +125,29 @@ test = [
     "twine>=3.1.1",
     "kaggle",
 ]
-notebook = [
-    "jupyter>=1.0.0",
-    "ipywidgets>=7.5.1",
-]
-docs = [
-    "mkdocs>=1.6.0,<1.7.0",
-    "mkdocs-material>=9.0.12,<10.0.0",
-    "mkdocs-material-extensions>=1.1.1,<2.0.0",
-    "mkdocs-table-reader-plugin<=2.2.0",
-    "mike>=2.1.1,<2.2.0",
-    "mkdocstrings[python]>=0.20.0,<1.0.0",
-    "mkdocs-badges",
-]
+
 unicode= [
     "tangled-up-in-unicode==0.2.0",
 ]
 
-[tool.setuptools.packages.find]
-where = ["src"]
+[project.urls]
+Homepage = "https://ydata.ai"
+Repository = "https://github.com/ydataai/ydata-profiling"
 
-[tool.setuptools.package-data]
-ydata_profiling = ["py.typed"]
+[project.scripts]
+ydata_profiling = "ydata_profiling.controller.console:main"
+pandas_profiling = "ydata_profiling.controller.console:main"
+
+# setuptools relative
 
 [tool.setuptools]
 include-package-data = true
 
-[project.scripts]
-ydata_profiling = "ydata_profiling.controller.console:main"
-pandas_profiling = "ydata_profiling.controller.console:main"
+[tool.setuptools.package-data]
+ydata_profiling = ["py.typed"]
 
-[project.urls]
-homepage = "https://github.com/ydataai/ydata-profiling"
\ No newline at end of file
+[tool.distutils.bdist_wheel]
+universal = true
+
+[tool.setuptools.package-dir]
+"" = "src"
diff --git a/setup.py b/setup.py
index d64be44d8..4824966a1 100644
--- a/setup.py
+++ b/setup.py
@@ -4,8 +4,6 @@
 
 # Read the contents of README file
 source_root = Path(".")
-with (source_root / "README.md").open(encoding="utf-8") as f:
-    long_description = f.read()
 
 try:
     version = (source_root / "VERSION").read_text().rstrip("\n")
@@ -17,7 +15,4 @@
 
 setup(
     version=version,
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    options={"bdist_wheel": {"universal": True}},
 )

From 872bc270354d2632d8de9ce8421569dc6dd5e44a Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 08:32:28 -0700
Subject: [PATCH 02/12] chore: fix linting errors

---
 src/ydata_profiling/model/dataframe.py               | 5 ++---
 src/ydata_profiling/model/describe.py                | 2 +-
 src/ydata_profiling/model/handler.py                 | 2 +-
 src/ydata_profiling/model/pandas/dataframe_pandas.py | 1 -
 src/ydata_profiling/model/pandas/summary_pandas.py   | 4 ++--
 src/ydata_profiling/model/spark/summary_spark.py     | 1 -
 tests/issues/test_issue537.py                        | 1 -
 7 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/src/ydata_profiling/model/dataframe.py b/src/ydata_profiling/model/dataframe.py
index d182f9ff3..9b4311352 100644
--- a/src/ydata_profiling/model/dataframe.py
+++ b/src/ydata_profiling/model/dataframe.py
@@ -2,6 +2,8 @@
 from typing import Any
 
 import pandas as pd
+from ydata_profiling.config import Settings
+from ydata_profiling.model.pandas.dataframe_pandas import pandas_preprocess
 
 spec = importlib.util.find_spec("pyspark")
 if spec is None:
@@ -12,9 +14,6 @@
     from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore
     from ydata_profiling.model.spark.dataframe_spark import spark_preprocess
 
-from ydata_profiling.config import Settings
-from ydata_profiling.model.pandas.dataframe_pandas import pandas_preprocess
-
 
 def preprocess(config: Settings, df: Any) -> Any:
     """
diff --git a/src/ydata_profiling/model/describe.py b/src/ydata_profiling/model/describe.py
index 5b162f9fb..91386c51e 100644
--- a/src/ydata_profiling/model/describe.py
+++ b/src/ydata_profiling/model/describe.py
@@ -29,7 +29,7 @@
 
 def describe(
     config: Settings,
-    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # type: ignore
+    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # noqa: F821
     summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
     sample: Optional[dict] = None,
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index ebbb285cf..072e87708 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -1,7 +1,7 @@
 """
     Auxiliary handler methods for data summary extraction
 """
-from typing import Any, Callable, Dict, List, Sequence
+from typing import Callable, Dict, List, Sequence
 
 import networkx as nx
 from visions import VisionsTypeset
diff --git a/src/ydata_profiling/model/pandas/dataframe_pandas.py b/src/ydata_profiling/model/pandas/dataframe_pandas.py
index d4b07d1b2..3c6acbdfd 100644
--- a/src/ydata_profiling/model/pandas/dataframe_pandas.py
+++ b/src/ydata_profiling/model/pandas/dataframe_pandas.py
@@ -1,4 +1,3 @@
-import warnings
 
 import pandas as pd
 
diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index 3e48267b1..bfec2f4f6 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -20,7 +20,7 @@ def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
 def pandas_describe_1d(
     config: Settings,
     series: pd.Series,
-    summarizer: "BaseSummarizer",  # type:ignore
+    summarizer: "BaseSummarizer",  # noqa: F821
     typeset: VisionsTypeset,
 ) -> dict:
     """Describe a series (infer the variable type, then calculate type-specific values).
@@ -67,7 +67,7 @@ def pandas_describe_1d(
 def pandas_get_series_descriptions(
     config: Settings,
     df: pd.DataFrame,
-    summarizer: "BaseSummarizer",  # type:ignore
+    summarizer: "BaseSummarizer",  # noqa: F821
     typeset: VisionsTypeset,
     pbar: tqdm,
 ) -> dict:
diff --git a/src/ydata_profiling/model/spark/summary_spark.py b/src/ydata_profiling/model/spark/summary_spark.py
index 31a6c3f97..5a033b1d5 100644
--- a/src/ydata_profiling/model/spark/summary_spark.py
+++ b/src/ydata_profiling/model/spark/summary_spark.py
@@ -1,5 +1,4 @@
 """Compute statistical description of datasets."""
-import multiprocessing
 from typing import Tuple
 
 import numpy as np
diff --git a/tests/issues/test_issue537.py b/tests/issues/test_issue537.py
index 16bee3efe..7248a3ac8 100644
--- a/tests/issues/test_issue537.py
+++ b/tests/issues/test_issue537.py
@@ -86,7 +86,6 @@ def download_and_process_data():
             ("labels", "S16"),
         ]
 
-        dtype = np.dtype(dtype_mapping)
         split_text = np.array(split_text, dtype=object)
 
         # Convert each column to its appropriate type

From 5246f8c64ed6b3ee227ff09117739468ff8ff94c Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 09:06:03 -0700
Subject: [PATCH 03/12] fix: typing annotations

---
 src/ydata_profiling/model/correlations.py | 3 +--
 src/ydata_profiling/model/handler.py      | 2 +-
 src/ydata_profiling/model/summarizer.py   | 2 +-
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/ydata_profiling/model/correlations.py b/src/ydata_profiling/model/correlations.py
index 13f3f165a..78b8bc31f 100644
--- a/src/ydata_profiling/model/correlations.py
+++ b/src/ydata_profiling/model/correlations.py
@@ -12,7 +12,6 @@
 except ImportError:
     from pandas.errors import DataError
 
-
 class CorrelationBackend:
     """Helper class to select and cache the appropriate correlation backend (Pandas or Spark)."""
 
@@ -29,7 +28,7 @@ def __init__(self, df: Sized):
 
         self.backend = correlation_backend
 
-    def get_method(self, method_name: str):
+    def get_method(self, method_name: str): # noqa: ANN201
         """Retrieve the appropriate correlation method class from the backend."""
         if hasattr(self.backend, method_name):
             return getattr(self.backend, method_name)
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index 072e87708..c43a6eff0 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -15,7 +15,7 @@ def compose(functions: Sequence[Callable]) -> Callable:
     :return: combined function applying all functions in order.
     """
 
-    def composed_function(*args):
+    def composed_function(*args) -> List[Callable]:
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)
diff --git a/src/ydata_profiling/model/summarizer.py b/src/ydata_profiling/model/summarizer.py
index e54ad9a83..4ddb155c3 100644
--- a/src/ydata_profiling/model/summarizer.py
+++ b/src/ydata_profiling/model/summarizer.py
@@ -54,7 +54,7 @@ def summarize(
 class ProfilingSummarizer(BaseSummarizer):
     """A summarizer for Pandas DataFrames."""
 
-    def __init__(self, typeset: VisionsTypeset, use_spark=False):
+    def __init__(self, typeset: VisionsTypeset, use_spark: bool=False):
         self.use_spark = use_spark and is_pyspark_installed()
         self._summary_map = self._create_summary_map()
         super().__init__(self._summary_map, typeset)

From 286924303abba059f4d78e3ab83ada54d271f20c Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 09:14:12 -0700
Subject: [PATCH 04/12] fix: fix import linting error

---
 src/ydata_profiling/model/describe.py | 2 +-
 src/ydata_profiling/model/handler.py  | 4 ++--
 src/ydata_profiling/model/summary.py  | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/ydata_profiling/model/describe.py b/src/ydata_profiling/model/describe.py
index 91386c51e..3c81021e5 100644
--- a/src/ydata_profiling/model/describe.py
+++ b/src/ydata_profiling/model/describe.py
@@ -29,7 +29,7 @@
 
 def describe(
     config: Settings,
-    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # noqa: F821
+    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # type: ignore[name-defined]
     summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
     sample: Optional[dict] = None,
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index c43a6eff0..b34982100 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -1,7 +1,7 @@
 """
     Auxiliary handler methods for data summary extraction
 """
-from typing import Callable, Dict, List, Sequence
+from typing import Any, Callable, Dict, List, Sequence
 
 import networkx as nx
 from visions import VisionsTypeset
@@ -15,7 +15,7 @@ def compose(functions: Sequence[Callable]) -> Callable:
     :return: combined function applying all functions in order.
     """
 
-    def composed_function(*args) -> List[Callable]:
+    def composed_function(*args) -> List:
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)
diff --git a/src/ydata_profiling/model/summary.py b/src/ydata_profiling/model/summary.py
index a997a8933..0d90ce466 100644
--- a/src/ydata_profiling/model/summary.py
+++ b/src/ydata_profiling/model/summary.py
@@ -20,7 +20,7 @@
     sparkDataFrame = TypeVar("sparkDataFrame")  # type: ignore
     sparkSeries = TypeVar("sparkSeries")  # type: ignore
 else:
-    from pyspark.sql import DataFrame as sparkDataFrame  # noqa: E402
+    from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore[name-defined]
 
     from ydata_profiling.model.spark.summary_spark import ( # noqa: E402
         get_series_descriptions_spark,

From 572c7b922045bafffa7e15c396129a5b34d0a2d9 Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 09:21:43 -0700
Subject: [PATCH 05/12] fix: ignore linter

---
 src/ydata_profiling/model/correlations.py          | 8 ++++----
 src/ydata_profiling/model/handler.py               | 2 +-
 src/ydata_profiling/model/pandas/summary_pandas.py | 4 ++--
 src/ydata_profiling/model/summary.py               | 2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/ydata_profiling/model/correlations.py b/src/ydata_profiling/model/correlations.py
index 78b8bc31f..bb43e9e6d 100644
--- a/src/ydata_profiling/model/correlations.py
+++ b/src/ydata_profiling/model/correlations.py
@@ -18,12 +18,12 @@ class CorrelationBackend:
     def __init__(self, df: Sized):
         """Determine backend once and store it for all correlation computations."""
         if isinstance(df, pd.DataFrame):
-            from ydata_profiling.model.pandas import (
-                correlations_pandas as correlation_backend, #type: ignore
+            from ydata_profiling.model.pandas import ( # type: ignore
+                correlations_pandas as correlation_backend,
             )
         else:
-            from ydata_profiling.model.spark import (
-                correlations_spark as correlation_backend, # type: ignore
+            from ydata_profiling.model.spark import ( # type: ignore
+                correlations_spark as correlation_backend,
             )
 
         self.backend = correlation_backend
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index b34982100..7d946d669 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -15,7 +15,7 @@ def compose(functions: Sequence[Callable]) -> Callable:
     :return: combined function applying all functions in order.
     """
 
-    def composed_function(*args) -> List:
+    def composed_function(*args) -> List[Any]:
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)
diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index bfec2f4f6..b790db79c 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -20,7 +20,7 @@ def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
 def pandas_describe_1d(
     config: Settings,
     series: pd.Series,
-    summarizer: "BaseSummarizer",  # noqa: F821
+    summarizer: "BaseSummarizer",  # type: ignore # type: ignore
     typeset: VisionsTypeset,
 ) -> dict:
     """Describe a series (infer the variable type, then calculate type-specific values).
@@ -67,7 +67,7 @@ def pandas_describe_1d(
 def pandas_get_series_descriptions(
     config: Settings,
     df: pd.DataFrame,
-    summarizer: "BaseSummarizer",  # noqa: F821
+    summarizer: "BaseSummarizer",  # noqa: F821 # type: ignore
     typeset: VisionsTypeset,
     pbar: tqdm,
 ) -> dict:
diff --git a/src/ydata_profiling/model/summary.py b/src/ydata_profiling/model/summary.py
index 0d90ce466..87a2acc8a 100644
--- a/src/ydata_profiling/model/summary.py
+++ b/src/ydata_profiling/model/summary.py
@@ -20,7 +20,7 @@
     sparkDataFrame = TypeVar("sparkDataFrame")  # type: ignore
     sparkSeries = TypeVar("sparkSeries")  # type: ignore
 else:
-    from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore[name-defined]
+    from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore
 
     from ydata_profiling.model.spark.summary_spark import ( # noqa: E402
         get_series_descriptions_spark,

From 4e711642ac6098dc27e17b7a91b97192124d62ab Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 09:51:01 -0700
Subject: [PATCH 06/12] chore: ignore mypy linter for some cases

---
 src/ydata_profiling/model/correlations.py          | 3 +++
 src/ydata_profiling/model/handler.py               | 4 ++--
 src/ydata_profiling/model/pandas/summary_pandas.py | 2 ++
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/src/ydata_profiling/model/correlations.py b/src/ydata_profiling/model/correlations.py
index bb43e9e6d..82e37cee7 100644
--- a/src/ydata_profiling/model/correlations.py
+++ b/src/ydata_profiling/model/correlations.py
@@ -1,4 +1,7 @@
+# mypy: ignore-errors
+
 """Correlations between variables."""
+
 import warnings
 from typing import Dict, List, Optional, Sized
 
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index 7d946d669..ab0eaf8e5 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -19,9 +19,9 @@ def composed_function(*args) -> List[Any]:
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)
-        return result
+        return result # type: ignore
 
-    return composed_function
+    return composed_function # type: ignore
 
 
 class Handler:
diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index b790db79c..5878755f0 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -1,3 +1,5 @@
+# mypy: ignore-errors
+
 """Compute statistical description of datasets."""
 import multiprocessing
 from concurrent.futures import ThreadPoolExecutor

From 97899506a3d21c29de80f1de252ecfacbe64fc81 Mon Sep 17 00:00:00 2001
From: Azory YData Bot <azory@ydata.ai>
Date: Tue, 18 Mar 2025 16:54:18 +0000
Subject: [PATCH 07/12] fix(linting): code formatting

---
 src/ydata_profiling/model/correlations.py     | 11 +++----
 src/ydata_profiling/model/dataframe.py        |  2 ++
 src/ydata_profiling/model/handler.py          |  4 +--
 .../model/pandas/dataframe_pandas.py          |  1 -
 src/ydata_profiling/model/spark/__init__.py   |  2 +-
 .../model/spark/describe_counts_spark.py      | 29 +++++++++++--------
 .../model/spark/duplicates_spark.py           |  1 +
 .../model/spark/sample_spark.py               |  1 +
 .../model/spark/table_spark.py                |  1 +
 src/ydata_profiling/model/summarizer.py       |  2 +-
 src/ydata_profiling/model/summary.py          |  9 +++---
 .../model/summary_algorithms.py               |  1 +
 src/ydata_profiling/model/table.py            |  1 +
 src/ydata_profiling/profile_report.py         |  8 ++---
 .../spark_backend/test_correlations_spark.py  |  5 ++--
 .../spark_backend/test_descriptions_spark.py  |  2 +-
 tests/conftest.py                             |  9 ++++--
 17 files changed, 51 insertions(+), 38 deletions(-)

diff --git a/src/ydata_profiling/model/correlations.py b/src/ydata_profiling/model/correlations.py
index 82e37cee7..2138d88c8 100644
--- a/src/ydata_profiling/model/correlations.py
+++ b/src/ydata_profiling/model/correlations.py
@@ -15,23 +15,24 @@
 except ImportError:
     from pandas.errors import DataError
 
+
 class CorrelationBackend:
     """Helper class to select and cache the appropriate correlation backend (Pandas or Spark)."""
 
     def __init__(self, df: Sized):
         """Determine backend once and store it for all correlation computations."""
         if isinstance(df, pd.DataFrame):
-            from ydata_profiling.model.pandas import ( # type: ignore
-                correlations_pandas as correlation_backend,
+            from ydata_profiling.model.pandas import (
+                correlations_pandas as correlation_backend,  # type: ignore
             )
         else:
-            from ydata_profiling.model.spark import ( # type: ignore
-                correlations_spark as correlation_backend,
+            from ydata_profiling.model.spark import (
+                correlations_spark as correlation_backend,  # type: ignore
             )
 
         self.backend = correlation_backend
 
-    def get_method(self, method_name: str): # noqa: ANN201
+    def get_method(self, method_name: str):  # noqa: ANN201
         """Retrieve the appropriate correlation method class from the backend."""
         if hasattr(self.backend, method_name):
             return getattr(self.backend, method_name)
diff --git a/src/ydata_profiling/model/dataframe.py b/src/ydata_profiling/model/dataframe.py
index 9b4311352..dd01f8ffe 100644
--- a/src/ydata_profiling/model/dataframe.py
+++ b/src/ydata_profiling/model/dataframe.py
@@ -2,6 +2,7 @@
 from typing import Any
 
 import pandas as pd
+
 from ydata_profiling.config import Settings
 from ydata_profiling.model.pandas.dataframe_pandas import pandas_preprocess
 
@@ -12,6 +13,7 @@
     sparkDataFrame = TypeVar("sparkDataFrame")
 else:
     from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore
+
     from ydata_profiling.model.spark.dataframe_spark import spark_preprocess
 
 
diff --git a/src/ydata_profiling/model/handler.py b/src/ydata_profiling/model/handler.py
index ab0eaf8e5..992c1840c 100644
--- a/src/ydata_profiling/model/handler.py
+++ b/src/ydata_profiling/model/handler.py
@@ -19,9 +19,9 @@ def composed_function(*args) -> List[Any]:
         result = args  # Start with the input arguments
         for func in functions:
             result = func(*result) if isinstance(result, tuple) else func(result)
-        return result # type: ignore
+        return result  # type: ignore
 
-    return composed_function # type: ignore
+    return composed_function  # type: ignore
 
 
 class Handler:
diff --git a/src/ydata_profiling/model/pandas/dataframe_pandas.py b/src/ydata_profiling/model/pandas/dataframe_pandas.py
index 3c6acbdfd..e98dc7d24 100644
--- a/src/ydata_profiling/model/pandas/dataframe_pandas.py
+++ b/src/ydata_profiling/model/pandas/dataframe_pandas.py
@@ -1,4 +1,3 @@
-
 import pandas as pd
 
 from ydata_profiling.config import Settings
diff --git a/src/ydata_profiling/model/spark/__init__.py b/src/ydata_profiling/model/spark/__init__.py
index d77bd0a46..b71241218 100644
--- a/src/ydata_profiling/model/spark/__init__.py
+++ b/src/ydata_profiling/model/spark/__init__.py
@@ -29,7 +29,7 @@
             for name in dir(module)
             if not name.startswith("_")
         }
-    ) # type: ignore
+    )  # type: ignore
 
 # Explicitly list all available functions
 __all__ = [
diff --git a/src/ydata_profiling/model/spark/describe_counts_spark.py b/src/ydata_profiling/model/spark/describe_counts_spark.py
index 5c764c23d..d7a091e7f 100644
--- a/src/ydata_profiling/model/spark/describe_counts_spark.py
+++ b/src/ydata_profiling/model/spark/describe_counts_spark.py
@@ -2,13 +2,15 @@
     Pyspark counts
 """
 from typing import Tuple
+
 import pandas as pd
+from pyspark.sql import DataFrame
+from pyspark.sql import functions as F
 
 from ydata_profiling.config import Settings
-
-from pyspark.sql import DataFrame, functions as F
 from ydata_profiling.model.summary_algorithms import describe_counts
 
+
 @describe_counts.register
 def describe_counts_spark(
     config: Settings, series: DataFrame, summary: dict
@@ -34,7 +36,9 @@ def describe_counts_spark(
     value_counts_index_sorted = value_counts.orderBy(F.asc(series.columns[0]))
 
     # Count missing values
-    n_missing = value_counts.filter(F.col(series.columns[0]).isNull()).select("count").first()
+    n_missing = (
+        value_counts.filter(F.col(series.columns[0]).isNull()).select("count").first()
+    )
     n_missing = n_missing["count"] if n_missing else 0
 
     # Convert top 200 values to Pandas for frequency table display
@@ -51,11 +55,9 @@ def describe_counts_spark(
 
     column = series.columns[0]
 
-
-    if series.dtypes[0][1] in ('int', 'float', 'bigint', 'double'):
+    if series.dtypes[0][1] in ("int", "float", "bigint", "double"):
         value_counts_no_nan = (
-            value_counts
-            .filter(F.col(column).isNotNull())  # Exclude NaNs
+            value_counts.filter(F.col(column).isNotNull())  # Exclude NaNs
             .filter(~F.isnan(F.col(column)))  # Remove implicit NaNs (if numeric column)
             .groupBy(column)  # Group by unique values
             .count()  # Count occurrences
@@ -64,8 +66,7 @@ def describe_counts_spark(
         )
     else:
         value_counts_no_nan = (
-            value_counts
-            .filter(F.col(column).isNotNull())  # Exclude NULLs
+            value_counts.filter(F.col(column).isNotNull())  # Exclude NULLs
             .groupBy(column)  # Group by unique timestamp values
             .count()  # Count occurrences
             .orderBy(F.desc("count"))  # Sort by most frequent timestamps
@@ -75,8 +76,12 @@ def describe_counts_spark(
     # Convert to Pandas Series, forcing proper structure
     if value_counts_no_nan.count() > 0:
         pdf = value_counts_no_nan.toPandas().set_index(column)["count"]
-        summary["value_counts_without_nan"] = pd.Series(pdf)  # Ensures it's always a Series
+        summary["value_counts_without_nan"] = pd.Series(
+            pdf
+        )  # Ensures it's always a Series
     else:
-        summary["value_counts_without_nan"] = pd.Series(dtype=int)  # Ensures an empty Series
+        summary["value_counts_without_nan"] = pd.Series(
+            dtype=int
+        )  # Ensures an empty Series
 
-    return config, series, summary
\ No newline at end of file
+    return config, series, summary
diff --git a/src/ydata_profiling/model/spark/duplicates_spark.py b/src/ydata_profiling/model/spark/duplicates_spark.py
index 77f0379cf..95e32cc30 100644
--- a/src/ydata_profiling/model/spark/duplicates_spark.py
+++ b/src/ydata_profiling/model/spark/duplicates_spark.py
@@ -6,6 +6,7 @@
 from ydata_profiling.config import Settings
 from ydata_profiling.model.duplicates import get_duplicates
 
+
 @get_duplicates.register
 def get_duplicates_spark(
     config: Settings, df: DataFrame, supported_columns: Sequence
diff --git a/src/ydata_profiling/model/spark/sample_spark.py b/src/ydata_profiling/model/spark/sample_spark.py
index 0a608c6a7..05636b354 100644
--- a/src/ydata_profiling/model/spark/sample_spark.py
+++ b/src/ydata_profiling/model/spark/sample_spark.py
@@ -6,6 +6,7 @@
 from ydata_profiling.config import Settings
 from ydata_profiling.model.sample import Sample, get_sample
 
+
 @get_sample.register
 def get_sample_spark(config: Settings, df: DataFrame) -> List[Sample]:
     """Obtains a sample from head and tail of the DataFrame
diff --git a/src/ydata_profiling/model/spark/table_spark.py b/src/ydata_profiling/model/spark/table_spark.py
index 234c6531c..33e862e61 100644
--- a/src/ydata_profiling/model/spark/table_spark.py
+++ b/src/ydata_profiling/model/spark/table_spark.py
@@ -5,6 +5,7 @@
 from ydata_profiling.config import Settings
 from ydata_profiling.model.table import get_table_stats
 
+
 @get_table_stats.register
 def get_table_stats_spark(
     config: Settings, df: DataFrame, variable_stats: dict
diff --git a/src/ydata_profiling/model/summarizer.py b/src/ydata_profiling/model/summarizer.py
index 4ddb155c3..d733a7d36 100644
--- a/src/ydata_profiling/model/summarizer.py
+++ b/src/ydata_profiling/model/summarizer.py
@@ -54,7 +54,7 @@ def summarize(
 class ProfilingSummarizer(BaseSummarizer):
     """A summarizer for Pandas DataFrames."""
 
-    def __init__(self, typeset: VisionsTypeset, use_spark: bool=False):
+    def __init__(self, typeset: VisionsTypeset, use_spark: bool = False):
         self.use_spark = use_spark and is_pyspark_installed()
         self._summary_map = self._create_summary_map()
         super().__init__(self._summary_map, typeset)
diff --git a/src/ydata_profiling/model/summary.py b/src/ydata_profiling/model/summary.py
index 87a2acc8a..4fa9831a7 100644
--- a/src/ydata_profiling/model/summary.py
+++ b/src/ydata_profiling/model/summary.py
@@ -15,18 +15,19 @@
 
 spec = importlib.util.find_spec("pyspark")
 if spec is None:
-    from typing import TypeVar # noqa: E402
+    from typing import TypeVar  # noqa: E402
 
     sparkDataFrame = TypeVar("sparkDataFrame")  # type: ignore
     sparkSeries = TypeVar("sparkSeries")  # type: ignore
 else:
     from pyspark.sql import DataFrame as sparkDataFrame  # type: ignore
 
-    from ydata_profiling.model.spark.summary_spark import ( # noqa: E402
+    from ydata_profiling.model.spark.summary_spark import (  # noqa: E402
         get_series_descriptions_spark,
         spark_describe_1d,
     )
 
+
 def describe_1d(
     config: Settings,
     series: Any,
@@ -44,7 +45,7 @@ def describe_1d(
     """
     if isinstance(series, pd.Series):
         return pandas_describe_1d(config, series, summarizer, typeset)
-    elif isinstance(series, sparkDataFrame): # type: ignore
+    elif isinstance(series, sparkDataFrame):  # type: ignore
         return spark_describe_1d(config, series, summarizer, typeset)
     else:
         raise TypeError(f"Unsupported series type: {type(series)}")
@@ -59,7 +60,7 @@ def get_series_descriptions(
 ) -> dict:
     if isinstance(df, pd.DataFrame):
         return pandas_get_series_descriptions(config, df, summarizer, typeset, pbar)
-    elif isinstance(df, sparkDataFrame): # type: ignore
+    elif isinstance(df, sparkDataFrame):  # type: ignore
         return get_series_descriptions_spark(config, df, summarizer, typeset, pbar)
     else:
         raise TypeError(f"Unsupported dataframe type: {type(df)}")
diff --git a/src/ydata_profiling/model/summary_algorithms.py b/src/ydata_profiling/model/summary_algorithms.py
index cd98fc741..e70c467d2 100644
--- a/src/ydata_profiling/model/summary_algorithms.py
+++ b/src/ydata_profiling/model/summary_algorithms.py
@@ -101,6 +101,7 @@ def named_aggregate_summary(series: pd.Series, key: str) -> dict:
 
     return summary
 
+
 @multimethod
 def describe_counts(
     config: Settings, series: Any, summary: dict
diff --git a/src/ydata_profiling/model/table.py b/src/ydata_profiling/model/table.py
index c0ebadb4e..e5eb6fdc2 100644
--- a/src/ydata_profiling/model/table.py
+++ b/src/ydata_profiling/model/table.py
@@ -4,6 +4,7 @@
 
 from ydata_profiling.config import Settings
 
+
 @multimethod
 def get_table_stats(config: Settings, df: Any, variable_stats: dict) -> dict:
     raise NotImplementedError()
diff --git a/src/ydata_profiling/profile_report.py b/src/ydata_profiling/profile_report.py
index b99f0ade5..acf18c7e0 100644
--- a/src/ydata_profiling/profile_report.py
+++ b/src/ydata_profiling/profile_report.py
@@ -190,7 +190,7 @@ def __validate_inputs(
                 )
 
             if (
-                df is not None and df.rdd.isEmpty() # type: ignore
+                df is not None and df.rdd.isEmpty()  # type: ignore
             ):  # df.isEmpty is only support by 3.3.0 pyspark version
                 raise ValueError(
                     "DataFrame is empty. Please" "provide a non-empty DataFrame."
@@ -259,11 +259,9 @@ def summarizer(self) -> BaseSummarizer:
         if self._summarizer is None:
             use_spark = False
             if self._df_type is not pd.DataFrame:
-                use_spark=True
+                use_spark = True
 
-            self._summarizer = ProfilingSummarizer(
-                self.typeset, use_spark=use_spark
-            )
+            self._summarizer = ProfilingSummarizer(self.typeset, use_spark=use_spark)
         return self._summarizer
 
     @property
diff --git a/tests/backends/spark_backend/test_correlations_spark.py b/tests/backends/spark_backend/test_correlations_spark.py
index 6674ca2a3..ef16224a1 100644
--- a/tests/backends/spark_backend/test_correlations_spark.py
+++ b/tests/backends/spark_backend/test_correlations_spark.py
@@ -15,6 +15,7 @@
     spearman_compute as spark_spearman_compute,
 )
 
+
 @pytest.fixture
 def correlation_data_num(spark_session):
     correlation_testdata = pd.DataFrame(
@@ -79,6 +80,4 @@ def test_kendall_spark(correlation_data_cat):
     cfg = Settings()
 
     with pytest.raises(NotImplementedError):
-        kendall_compute(config=cfg,
-                        df=correlation_data_cat,
-                        summary={})
+        kendall_compute(config=cfg, df=correlation_data_cat, summary={})
diff --git a/tests/backends/spark_backend/test_descriptions_spark.py b/tests/backends/spark_backend/test_descriptions_spark.py
index c11330017..5c608f2f0 100644
--- a/tests/backends/spark_backend/test_descriptions_spark.py
+++ b/tests/backends/spark_backend/test_descriptions_spark.py
@@ -374,7 +374,7 @@ def test_describe_spark_df(
         describe_data[column] = [
             True if i else False for i in describe_data[column]  # noqa: SIM210
         ]
-    pdf= pd.DataFrame({column: describe_data[column]})# Convert to Pandas DataFrame
+    pdf = pd.DataFrame({column: describe_data[column]})  # Convert to Pandas DataFrame
     # Ensure NaNs are replaced with None (Spark does not support NaN in non-float columns)
     pdf = pdf.where(pd.notna(pdf), None)
     sdf = spark_session.createDataFrame(pdf)
diff --git a/tests/conftest.py b/tests/conftest.py
index 0bda369d0..4a5864d84 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,11 +1,13 @@
 import shutil
 import sys
 from pathlib import Path
+
 import pytest
 
 try:
+    from pyspark import SparkConf, SparkContext
     from pyspark.sql import SparkSession
-    from pyspark import SparkContext, SparkConf
+
     has_spark = True
 except ImportError:
     has_spark = False
@@ -45,6 +47,7 @@ def test_output_dir(tmpdir_factory):
 def summarizer(typeset):
     return ProfilingSummarizer(typeset)
 
+
 @pytest.fixture(scope="function")
 def summarizer_spark(typeset):
     return ProfilingSummarizer(typeset, use_spark=True)
@@ -70,7 +73,7 @@ def pytest_runtest_setup(item):
         pytest.skip(f"cannot run on platform {plat}")
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def spark_context():
     """Fixture for SparkContext initialization.
 
@@ -94,7 +97,7 @@ def spark_context():
     sc.stop()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def spark_session(spark_context):
     """Fixture for SparkSession initialization.
 

From 6edf2d6d11e4e66982010337c4974d854a6a4501 Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 09:59:57 -0700
Subject: [PATCH 08/12] chore: create basesummarizer as a variable

---
 src/ydata_profiling/model/pandas/summary_pandas.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index 5878755f0..e869a456b 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -1,5 +1,3 @@
-# mypy: ignore-errors
-
 """Compute statistical description of datasets."""
 import multiprocessing
 from concurrent.futures import ThreadPoolExecutor
@@ -14,6 +12,7 @@
 from ydata_profiling.model.typeset import ProfilingTypeSet
 from ydata_profiling.utils.dataframe import sort_column_names
 
+BaseSummarizer = "BaseSummarizer"
 
 def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
     return isinstance(typeset, ProfilingTypeSet) and series in typeset.type_schema
@@ -22,7 +21,7 @@ def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
 def pandas_describe_1d(
     config: Settings,
     series: pd.Series,
-    summarizer: "BaseSummarizer",  # type: ignore # type: ignore
+    summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
 ) -> dict:
     """Describe a series (infer the variable type, then calculate type-specific values).
@@ -69,7 +68,7 @@ def pandas_describe_1d(
 def pandas_get_series_descriptions(
     config: Settings,
     df: pd.DataFrame,
-    summarizer: "BaseSummarizer",  # noqa: F821 # type: ignore
+    summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
     pbar: tqdm,
 ) -> dict:

From a75f96f42df5dc62d9a3ee0ec7ab4ad6a3ec069b Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 10:15:22 -0700
Subject: [PATCH 09/12] chore: mypy type aliases

---
 src/ydata_profiling/model/pandas/summary_pandas.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index e869a456b..c06ff0b43 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -1,7 +1,7 @@
 """Compute statistical description of datasets."""
 import multiprocessing
 from concurrent.futures import ThreadPoolExecutor
-from typing import Tuple
+from typing import Tuple, TypeAlias
 
 import numpy as np
 import pandas as pd
@@ -12,7 +12,7 @@
 from ydata_profiling.model.typeset import ProfilingTypeSet
 from ydata_profiling.utils.dataframe import sort_column_names
 
-BaseSummarizer = "BaseSummarizer"
+BaseSummarizer: TypeAlias = "BaseSummarizer"
 
 def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
     return isinstance(typeset, ProfilingTypeSet) and series in typeset.type_schema

From 3a9c7a572d760c7a681ecc0f4932c82368fa374b Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 10:23:39 -0700
Subject: [PATCH 10/12] chore: fix typealias for older python versions

---
 src/ydata_profiling/model/pandas/summary_pandas.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index c06ff0b43..5ebd4f3a4 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -1,7 +1,7 @@
 """Compute statistical description of datasets."""
 import multiprocessing
 from concurrent.futures import ThreadPoolExecutor
-from typing import Tuple, TypeAlias
+from typing import Tuple, Any
 
 import numpy as np
 import pandas as pd
@@ -12,7 +12,7 @@
 from ydata_profiling.model.typeset import ProfilingTypeSet
 from ydata_profiling.utils.dataframe import sort_column_names
 
-BaseSummarizer: TypeAlias = "BaseSummarizer"
+BaseSummarizer: Any = "BaseSummarizer"  # type: ignore
 
 def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
     return isinstance(typeset, ProfilingTypeSet) and series in typeset.type_schema

From a0612fc1e7446784375061caace45b189a450427 Mon Sep 17 00:00:00 2001
From: Azory YData Bot <azory@ydata.ai>
Date: Tue, 18 Mar 2025 17:26:57 +0000
Subject: [PATCH 11/12] fix(linting): code formatting

---
 src/ydata_profiling/model/pandas/summary_pandas.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/ydata_profiling/model/pandas/summary_pandas.py b/src/ydata_profiling/model/pandas/summary_pandas.py
index 5ebd4f3a4..fb15bf98b 100644
--- a/src/ydata_profiling/model/pandas/summary_pandas.py
+++ b/src/ydata_profiling/model/pandas/summary_pandas.py
@@ -1,7 +1,7 @@
 """Compute statistical description of datasets."""
 import multiprocessing
 from concurrent.futures import ThreadPoolExecutor
-from typing import Tuple, Any
+from typing import Any, Tuple
 
 import numpy as np
 import pandas as pd
@@ -14,6 +14,7 @@
 
 BaseSummarizer: Any = "BaseSummarizer"  # type: ignore
 
+
 def _is_cast_type_defined(typeset: VisionsTypeset, series: str) -> bool:
     return isinstance(typeset, ProfilingTypeSet) and series in typeset.type_schema
 

From 430bcde238a0930114aec17a4281a4a0fefc4964 Mon Sep 17 00:00:00 2001
From: Fabiana <30911746+fabclmnt@users.noreply.github.com>
Date: Tue, 18 Mar 2025 10:32:15 -0700
Subject: [PATCH 12/12] chore: ignore F821

---
 src/ydata_profiling/model/describe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/ydata_profiling/model/describe.py b/src/ydata_profiling/model/describe.py
index 3c81021e5..74bdf924a 100644
--- a/src/ydata_profiling/model/describe.py
+++ b/src/ydata_profiling/model/describe.py
@@ -29,7 +29,7 @@
 
 def describe(
     config: Settings,
-    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # type: ignore[name-defined]
+    df: Union[pd.DataFrame, "pyspark.sql.DataFrame"],  # type: ignore[name-defined] # noqa: F821
     summarizer: BaseSummarizer,
     typeset: VisionsTypeset,
     sample: Optional[dict] = None,