Use Ruff instead of Black, pyupgrade and isort (#2171)

* Replace black with ruff format for code formatting

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Replace pyupgrade with Ruff check, and select "UP"

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Bump the target version for Ruff up to Python 3.10

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Ignore `UP045` in cases when used programmatically

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Remedy a violation of Liskov uncertainty principle

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Reformat the affected files using Ruff Black rules

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Replace isort with Ruff for organizing the imports

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

* Replace black with ruff format for code formatting

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

---------

Signed-off-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

Author: deepyaman

.github/workflows/ci-tests.yml

@@ -68,12 +68,13 @@ jobs:
       - name: Check requirements
         run: nox -db uv -r --non-interactive --python ${{ matrix.python-version }} --session requirements-${{ matrix.python-version }}
 
-      - name: Sort Imports
-        run: pre-commit run isort --all-files
+      - if: always()
+        uses: astral-sh/ruff-action@v3
 
-      - name: Black
-        if: always()
-        run: pre-commit run black --all-files
+      - if: always()
+        uses: astral-sh/ruff-action@v3
+        with:
+          args: "format --check --diff"
 
       - name: Mypy Type Checking
         if: always()

.pre-commit-config.yaml

@@ -32,10 +32,12 @@ repos:
     hooks:
       - id: flynt
 
-  - repo: https://github.com/psf/black
-    rev: 24.4.2
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.14.5
     hooks:
-      - id: black
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format
 
   - repo: https://github.com/asottile/pyupgrade
     rev: v3.20.0

docs/source/notebooks/try_pandera.ipynb

@@ -71,6 +71,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
+    "\n",
     "import pandera.pandas as pa\n",
     "from pandera.typing import DataFrame, Series\n",
     "\n",
@@ -127,7 +128,7 @@
     "@pa.check_types(lazy=True)\n",
     "def add_sales_tax(data: DataFrame[Schema]):\n",
     "    # creates a new column in the data frame that calculates prices after sales tax\n",
-    "    data['after_tax'] = data['price'] + (data['price'] * .06)\n",
+    "    data[\"after_tax\"] = data[\"price\"] + (data[\"price\"] * 0.06)\n",
     "    return data"
    ]
   },
@@ -153,10 +154,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "valid_data = pd.DataFrame.from_records([\n",
-    "    {\"item\": \"apple\", \"price\": 0.5},\n",
-    "    {\"item\": \"orange\", \"price\": 0.75}\n",
-    "])\n",
+    "valid_data = pd.DataFrame.from_records(\n",
+    "    [{\"item\": \"apple\", \"price\": 0.5}, {\"item\": \"orange\", \"price\": 0.75}]\n",
+    ")\n",
     "\n",
     "add_sales_tax(valid_data)"
    ]
@@ -177,10 +177,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "invalid_data = pd.DataFrame.from_records([\n",
-    "    {\"item\": \"applee\", \"price\": 0.5},\n",
-    "    {\"item\": \"orange\", \"price\": -1000}\n",
-    "])\n",
+    "invalid_data = pd.DataFrame.from_records(\n",
+    "    [{\"item\": \"applee\", \"price\": 0.5}, {\"item\": \"orange\", \"price\": -1000}]\n",
+    ")\n",
     "\n",
     "try:\n",
     "    add_sales_tax(invalid_data)\n",
@@ -262,6 +261,7 @@
     "    item: Series[str] = pa.Field(isin=[\"apple\", \"orange\"], coerce=True)\n",
     "    price: Series[float] = pa.Field(gt=0, coerce=True)\n",
     "\n",
+    "\n",
     "class TransformedSchema(Schema):\n",
     "    expiry: Series[pd.Timestamp] = pa.Field(coerce=True)"
    ]
@@ -289,13 +289,12 @@
    "outputs": [],
    "source": [
     "from datetime import datetime\n",
-    "from typing import List\n",
     "\n",
     "\n",
     "@pa.check_types(lazy=True)\n",
     "def transform_data(\n",
     "    data: DataFrame[Schema],\n",
-    "    expiry: List[datetime],\n",
+    "    expiry: list[datetime],\n",
     ") -> DataFrame[TransformedSchema]:\n",
     "    return data.assign(expiry=expiry)\n",
     "\n",
@@ -381,11 +380,16 @@
     "    item: Series[str] = pa.Field(isin=[\"apple\", \"orange\"], coerce=True)\n",
     "    price: Series[float] = pa.Field(gt=0, coerce=True)\n",
     "\n",
+    "\n",
     "# object-based API\n",
-    "schema = pa.DataFrameSchema({\n",
-    "    \"item\": pa.Column(str, pa.Check.isin([\"apple\", \"orange\"]), coerce=True),\n",
-    "    \"price\": pa.Column(float, pa.Check.gt(0), coerce=True),\n",
-    "})"
+    "schema = pa.DataFrameSchema(\n",
+    "    {\n",
+    "        \"item\": pa.Column(\n",
+    "            str, pa.Check.isin([\"apple\", \"orange\"]), coerce=True\n",
+    "        ),\n",
+    "        \"price\": pa.Column(float, pa.Check.gt(0), coerce=True),\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -407,7 +411,9 @@
    "source": [
     "transformed_schema = schema.add_columns({\"expiry\": pa.Column(pd.Timestamp)})\n",
     "schema.remove_columns([\"item\"])  # remove the \"item\" column\n",
-    "schema.update_column(\"price\", dtype=int)  # update the datatype of the \"price\" column to integer"
+    "schema.update_column(\n",
+    "    \"price\", dtype=int\n",
+    ")  # update the datatype of the \"price\" column to integer"
    ]
   },
   {

noxfile.py

@@ -8,7 +8,7 @@
 import os
 import shutil
 import sys
-from typing import Optional, Tuple, List
+from typing import Optional
 
 import nox
 from nox import Session
@@ -115,12 +115,11 @@ def requirements(session: Session) -> None:
 
 def _testing_requirements(
     session: Session,
-    extra: Optional[str] = None,
-    pandas: Optional[str] = None,
-    pydantic: Optional[str] = None,
-    polars: Optional[str] = None,
+    extra: str | None = None,
+    pandas: str | None = None,
+    pydantic: str | None = None,
+    polars: str | None = None,
 ) -> list[str]:
-
     pandas = pandas or PANDAS_VERSIONS[-1]
     pydantic = pydantic or PYDANTIC_VERSIONS[-1]
     polars = polars or POLARS_VERSIONS[-1]
@@ -137,7 +136,7 @@ def _testing_requirements(
 
     _requirements = list(set(_requirements))
 
-    _numpy: Optional[str] = None
+    _numpy: str | None = None
     if pandas != "2.3.3" or (
         extra == "pyspark" and session.python in ("3.10",)
     ):
@@ -178,7 +177,7 @@ def _testing_requirements(
 
 
 # the base module with no extras
-EXTRA_PYTHON_PYDANTIC: list[tuple[Optional[str], ...]] = [
+EXTRA_PYTHON_PYDANTIC: list[tuple[str | None, ...]] = [
     (None, None, None, None)
 ]
 DATAFRAME_EXTRAS = {
@@ -222,10 +221,10 @@ def _testing_requirements(
 @nox.parametrize("extra, pandas, pydantic, polars", EXTRA_PYTHON_PYDANTIC)
 def tests(
     session: Session,
-    extra: Optional[str] = None,
-    pandas: Optional[str] = None,
-    pydantic: Optional[str] = None,
-    polars: Optional[str] = None,
+    extra: str | None = None,
+    pandas: str | None = None,
+    pydantic: str | None = None,
+    polars: str | None = None,
 ) -> None:
     """Run the test suite."""
 

pandera/__init__.py

@@ -2,17 +2,15 @@
 
 from pandera._version import __version__
 
-
 try:
     # Only add pandas to the top-level pandera namespace
     # if pandas and numpy are installed
-    import pandas as pd
     import numpy as np
+    import pandas as pd
 
+    from pandera import dtypes, typing
     from pandera._pandas_deprecated import *
     from pandera._pandas_deprecated import __all__ as _pandas_deprecated_all
-    from pandera import dtypes
-    from pandera import typing
 
     __all__ = [
         "__version__",
@@ -33,8 +31,7 @@
     else:
         raise  # Re-raise any other `ImportError` exceptions
 
-    from pandera import dtypes
-    from pandera import typing
+    from pandera import dtypes, typing
     from pandera.api.checks import Check
     from pandera.api.dataframe.model_components import (
         Field,

pandera/_pandas_deprecated.py

@@ -8,11 +8,9 @@
 import platform
 import warnings
 
-from packaging.version import parse
-
-import pandas as pd
 import numpy as np
-
+import pandas as pd
+from packaging.version import parse
 
 _min_pandas_version = parse("2.1.1")
 _min_numpy_version = parse("1.24.4")
@@ -105,7 +103,6 @@
 )
 from pandera.schema_inference.pandas import infer_schema
 
-
 _future_warning = """Importing pandas-specific classes and functions from the
 top-level pandera module will be **removed in a future version of pandera**.
 If you're using pandera to validate pandas objects, we highly recommend updating
@@ -248,7 +245,6 @@ def __init_subclass__(cls, **kwargs):
 
 
 if platform.system() != "Windows":
-
     from pandera.dtypes import Complex256, Float128
 
     __all__.extend(["Complex256", "Float128"])

pandera/accessors/pandas_accessor.py

@@ -16,7 +16,7 @@ class PanderaAccessor:
     def __init__(self, pandas_obj):
         """Initialize the pandera accessor."""
         self._pandas_obj = pandas_obj
-        self._schema: Optional[Schemas] = None
+        self._schema: Schemas | None = None
 
     @staticmethod
     def check_schema_type(schema: Schemas):
@@ -30,7 +30,7 @@ def add_schema(self, schema):
         return self._pandas_obj
 
     @property
-    def schema(self) -> Optional[Schemas]:
+    def schema(self) -> Schemas | None:
         """Access schema metadata."""
         return self._schema
 

pandera/accessors/pyspark_sql_accessor.py

@@ -2,9 +2,10 @@
 
 import warnings
 from typing import Optional
-from packaging import version
 
 import pyspark
+from packaging import version
+
 from pandera.api.base.error_handler import ErrorHandler
 from pandera.api.pyspark.container import DataFrameSchema
 
@@ -18,8 +19,8 @@ class PanderaAccessor:
     def __init__(self, pyspark_obj):
         """Initialize the pandera accessor."""
         self._pyspark_obj = pyspark_obj
-        self._schema: Optional[Schemas] = None
-        self._errors: Optional[Errors] = None
+        self._schema: Schemas | None = None
+        self._errors: Errors | None = None
 
     @staticmethod
     def check_schema_type(schema: Schemas):  # type: ignore
@@ -33,17 +34,17 @@ def add_schema(self, schema):
         return self._pyspark_obj
 
     @property
-    def schema(self) -> Optional[Schemas]:  # type: ignore
+    def schema(self) -> Schemas | None:  # type: ignore
         """Access schema metadata."""
         return self._schema
 
     @property
-    def errors(self) -> Optional[Errors]:  # type: ignore
+    def errors(self) -> Errors | None:  # type: ignore
         """Access errors details."""
         return self._errors
 
     @errors.setter
-    def errors(self, value: Optional[Errors]):  # type: ignore
+    def errors(self, value: Errors | None):  # type: ignore
         """Set errors details."""
         self._errors = value
 

pandera/api/base/checks.py

@@ -1,20 +1,18 @@
 """Data validation base check."""
 
 import inspect
+from collections.abc import Callable, Iterable
 from itertools import chain
 from typing import (
     Any,
-    Callable,
     NamedTuple,
     Optional,
     TypeVar,
     Union,
     no_type_check,
 )
-from collections.abc import Iterable
 
 from pandera.api.function_dispatch import Dispatcher
-
 from pandera.backends.base import BaseCheckBackend
 
 
@@ -33,9 +31,7 @@ class CheckResult(NamedTuple):
 class MetaCheck(type):  # pragma: no cover
     """Check metaclass."""
 
-    BACKEND_REGISTRY: dict[tuple[type, type], type[BaseCheckBackend]] = (
-        {}
-    )  # noqa
+    BACKEND_REGISTRY: dict[tuple[type, type], type[BaseCheckBackend]] = {}  # noqa
     """Registry of check backends implemented for specific data objects."""
 
     CHECK_FUNCTION_REGISTRY: dict[str, Dispatcher] = {}  # noqa
@@ -86,9 +82,9 @@ class BaseCheck(metaclass=MetaCheck):
 
     def __init__(
         self,
-        name: Optional[str] = None,
-        error: Optional[str] = None,
-        statistics: Optional[dict[str, Any]] = None,
+        name: str | None = None,
+        error: str | None = None,
+        statistics: dict[str, Any] | None = None,
     ):
         self.name = name
         self.error = error
@@ -122,8 +118,8 @@ def from_builtin_check_name(
         name: str,
         init_kwargs,
         error: Union[str, Callable],
-        statistics: Optional[dict[str, Any]] = None,
-        defaults: Optional[dict[str, Any]] = None,
+        statistics: dict[str, Any] | None = None,
+        defaults: dict[str, Any] | None = None,
         **check_kwargs,
     ):
         """Create a Check object from a built-in check's name."""

pandera/api/base/error_handler.py

@@ -52,7 +52,7 @@ def _count_failure_cases(failure_cases: Any) -> int:
     def collect_error(
         self,
         error_type: ErrorCategory,
-        reason_code: Optional[SchemaErrorReason],
+        reason_code: SchemaErrorReason | None,
         schema_error: SchemaError,
         original_exc: Union[BaseException, None] = None,
     ):