Re-enable isort and run on codebase

.pre-commit-config.yaml

@@ -25,7 +25,6 @@ repos:
     rev: v5.10.1
     hooks:
       - id: isort
-        args: ["--line-length=79", "--skip=docs/source/conf.py", "--diff"]
 
   - repo: https://github.com/ikamensh/flynt
     rev: "0.76"

pandera/__init__.py

@@ -2,14 +2,17 @@
 import platform
 
 import pandera.backends
+import pandera.backends.base.builtin_checks
+import pandera.backends.base.builtin_hypotheses
+import pandera.backends.pandas
 from pandera import errors, external_config, typing
 from pandera.accessors import pandas_accessor
 from pandera.api import extensions
 from pandera.api.checks import Check
 from pandera.api.hypotheses import Hypothesis
 from pandera.api.pandas.array import SeriesSchema
-from pandera.api.pandas.container import DataFrameSchema
 from pandera.api.pandas.components import Column, Index, MultiIndex
+from pandera.api.pandas.container import DataFrameSchema
 from pandera.api.pandas.model import DataFrameModel, SchemaModel
 from pandera.api.pandas.model_components import Field, check, dataframe_check
 from pandera.decorators import check_input, check_io, check_output, check_types
@@ -57,15 +60,9 @@
     UINT64,
     pandas_version,
 )
-
-import pandera.backends.base.builtin_checks
-import pandera.backends.base.builtin_hypotheses
-import pandera.backends.pandas
-
 from pandera.schema_inference.pandas import infer_schema
 from pandera.version import __version__
 
-
 if platform.system() != "Windows":
     # pylint: disable=ungrouped-imports
     from pandera.dtypes import Complex256, Float128

pandera/api/base/schema.py

@@ -8,11 +8,11 @@
 import inspect
 from abc import ABC
 from functools import wraps
-from typing import Any, Dict, Tuple, Type, Optional, Union
+from typing import Any, Dict, Optional, Tuple, Type, Union
 
 from pandera.backends.base import BaseSchemaBackend
-from pandera.errors import BackendNotFoundError
 from pandera.dtypes import DataType
+from pandera.errors import BackendNotFoundError
 
 DtypeInputTypes = Union[str, type, DataType, Type]
 

pandera/api/pandas/array.py

@@ -3,6 +3,7 @@
 import copy
 import warnings
 from typing import Any, List, Optional, TypeVar, Union, cast
+
 import pandas as pd
 
 from pandera import errors
@@ -13,11 +14,11 @@
 from pandera.api.pandas.types import CheckList, PandasDtypeInputTypes, is_field
 from pandera.config import CONFIG
 from pandera.dtypes import DataType, UniqueSettings
-from pandera.engines import pandas_engine, PYDANTIC_V2
+from pandera.engines import PYDANTIC_V2, pandas_engine
 
 if PYDANTIC_V2:
-    from pydantic_core import core_schema
     from pydantic import GetCoreSchemaHandler
+    from pydantic_core import core_schema
 
 
 TArraySchemaBase = TypeVar("TArraySchemaBase", bound="ArraySchema")

pandera/api/pandas/container.py

@@ -11,7 +11,6 @@
 import pandas as pd
 
 from pandera import errors
-from pandera.config import CONFIG
 from pandera import strategies as st
 from pandera.api.base.schema import BaseSchema, inferred_schema_guard
 from pandera.api.checks import Check
@@ -21,12 +20,13 @@
     PandasDtypeInputTypes,
     StrictType,
 )
+from pandera.config import CONFIG
 from pandera.dtypes import DataType, UniqueSettings
-from pandera.engines import pandas_engine, PYDANTIC_V2
+from pandera.engines import PYDANTIC_V2, pandas_engine
 
 if PYDANTIC_V2:
-    from pydantic_core import core_schema
     from pydantic import GetCoreSchemaHandler
+    from pydantic_core import core_schema
 
 N_INDENT_SPACES = 4
 

pandera/api/pandas/model.py

@@ -44,8 +44,8 @@
 from pandera.typing.common import DataFrameBase
 
 if PYDANTIC_V2:
+    from pydantic import GetCoreSchemaHandler, GetJsonSchemaHandler
     from pydantic_core import core_schema
-    from pydantic import GetJsonSchemaHandler, GetCoreSchemaHandler
 
 try:
     from typing_extensions import get_type_hints

pandera/api/pyspark/container.py

@@ -11,7 +11,6 @@
 from pyspark.sql import DataFrame
 
 from pandera import errors
-from pandera.config import CONFIG
 from pandera.api.base.schema import BaseSchema
 from pandera.api.checks import Check
 from pandera.api.pyspark.error_handler import ErrorHandler
@@ -20,6 +19,7 @@
     PySparkDtypeInputTypes,
     StrictType,
 )
+from pandera.config import CONFIG
 from pandera.dtypes import DataType, UniqueSettings
 from pandera.engines import pyspark_engine
 

pandera/backends/pandas/__init__.py

@@ -6,20 +6,18 @@
 from pandera.api.checks import Check
 from pandera.api.hypotheses import Hypothesis
 from pandera.api.pandas.array import SeriesSchema
-from pandera.api.pandas.container import DataFrameSchema
 from pandera.api.pandas.components import Column, Index, MultiIndex
-
+from pandera.api.pandas.container import DataFrameSchema
 from pandera.backends.pandas import builtin_checks, builtin_hypotheses
-from pandera.backends.pandas.checks import PandasCheckBackend
-from pandera.backends.pandas.hypotheses import PandasHypothesisBackend
 from pandera.backends.pandas.array import SeriesSchemaBackend
-from pandera.backends.pandas.container import DataFrameSchemaBackend
+from pandera.backends.pandas.checks import PandasCheckBackend
 from pandera.backends.pandas.components import (
     ColumnBackend,
     IndexBackend,
     MultiIndexBackend,
 )
-
+from pandera.backends.pandas.container import DataFrameSchemaBackend
+from pandera.backends.pandas.hypotheses import PandasHypothesisBackend
 
 dataframe_datatypes = [pd.DataFrame]
 series_datatypes = [pd.Series]

pandera/backends/pandas/array.py

@@ -1,12 +1,12 @@
 """Pandera array backends."""
 
-from typing import cast, List, Optional
+from typing import List, Optional, cast
 
 import pandas as pd
 from multimethod import DispatchError
 
-from pandera.backends.base import CoreCheckResult
 from pandera.api.pandas.types import is_field
+from pandera.backends.base import CoreCheckResult
 from pandera.backends.pandas.base import PandasSchemaBackend
 from pandera.backends.pandas.error_formatters import (
     reshape_failure_cases,
@@ -17,10 +17,10 @@
 from pandera.error_handlers import SchemaErrorHandler
 from pandera.errors import (
     ParserError,
+    SchemaDefinitionError,
     SchemaError,
     SchemaErrorReason,
     SchemaErrors,
-    SchemaDefinitionError,
 )
 
 

pandera/backends/pandas/components.py

@@ -8,22 +8,22 @@
 import numpy as np
 import pandas as pd
 
-from pandera.backends.base import CoreCheckResult
-from pandera.backends.pandas.array import ArraySchemaBackend
-from pandera.backends.pandas.container import DataFrameSchemaBackend
 from pandera.api.pandas.types import (
     is_field,
     is_index,
     is_multiindex,
     is_table,
 )
+from pandera.backends.base import CoreCheckResult
+from pandera.backends.pandas.array import ArraySchemaBackend
+from pandera.backends.pandas.container import DataFrameSchemaBackend
 from pandera.backends.pandas.error_formatters import scalar_failure_case
 from pandera.error_handlers import SchemaErrorHandler
 from pandera.errors import (
+    SchemaDefinitionError,
     SchemaError,
-    SchemaErrors,
     SchemaErrorReason,
-    SchemaDefinitionError,
+    SchemaErrors,
 )
 
 

pandera/backends/pyspark/__init__.py

@@ -12,7 +12,6 @@
 from pandera.backends.pyspark.components import ColumnBackend
 from pandera.backends.pyspark.container import DataFrameSchemaBackend
 
-
 for t in [pst.DataFrame]:
     Check.register_backend(t, PySparkCheckBackend)
     ColumnSchema.register_backend(t, ColumnSchemaBackend)

pandera/backends/pyspark/column.py

@@ -9,8 +9,8 @@
 
 from pandera.api.pyspark.error_handler import ErrorCategory, ErrorHandler
 from pandera.backends.pyspark.base import PysparkSchemaBackend
-from pandera.backends.pyspark.decorators import validate_scope, ValidationScope
+from pandera.backends.pyspark.decorators import ValidationScope, validate_scope
 from pandera.backends.pyspark.error_formatters import scalar_failure_case
 from pandera.engines.pyspark_engine import Engine
 from pandera.errors import ParserError, SchemaError, SchemaErrorReason
 

pandera/backends/pyspark/components.py

@@ -10,7 +10,7 @@
 
 from pandera.api.pyspark.error_handler import ErrorCategory, ErrorHandler
 from pandera.backends.pyspark.column import ColumnSchemaBackend
-from pandera.backends.pyspark.decorators import validate_scope, ValidationScope
+from pandera.backends.pyspark.decorators import ValidationScope, validate_scope
 from pandera.backends.pyspark.error_formatters import scalar_failure_case
 from pandera.errors import SchemaError, SchemaErrorReason
 

pandera/backends/pyspark/container.py

@@ -13,8 +13,8 @@
 from pandera.backends.pyspark.base import ColumnInfo, PysparkSchemaBackend
 from pandera.backends.pyspark.decorators import (
     ValidationScope,
-    validate_scope,
     cache_check_obj,
+    validate_scope,
 )
 from pandera.backends.pyspark.error_formatters import scalar_failure_case
 from pandera.config import CONFIG

pandera/backends/pyspark/decorators.py

@@ -8,6 +8,7 @@
 from typing import List, Type
 
 from pyspark.sql import DataFrame
+
 from pandera.api.pyspark.types import PysparkDefaultTypes
 from pandera.config import CONFIG, ValidationDepth
 from pandera.errors import SchemaError

pandera/engines/__init__.py

@@ -2,5 +2,4 @@
 
 from pandera.engines.utils import pydantic_version
 
-
 PYDANTIC_V2 = pydantic_version().release >= (2, 0, 0)

pandera/engines/engine.py

@@ -25,7 +25,6 @@
 
 from pandera.dtypes import DataType
 
-
 # register different TypedDict type depending on python version
 if sys.version_info >= (3, 12):
     from typing import TypedDict

pandera/engines/pandas_engine.py

@@ -34,14 +34,13 @@
 
 from pandera import dtypes, errors
 from pandera.dtypes import immutable
-from pandera.engines import engine, numpy_engine, utils
+from pandera.engines import PYDANTIC_V2, engine, numpy_engine, utils
 from pandera.engines.type_aliases import (
     PandasDataType,
     PandasExtensionType,
     PandasObject,
 )
 from pandera.engines.utils import pandas_version
-from pandera.engines import PYDANTIC_V2
 from pandera.system import FLOAT_128_AVAILABLE
 
 if PYDANTIC_V2:
@@ -1068,10 +1067,10 @@ def from_parametrized_dtype(cls, pd_dtype: pd.IntervalDtype):
 
 if GEOPANDAS_INSTALLED:
 
-    from geopandas.array import GeometryArray, GeometryDtype, from_shapely
+    import pyproj
     import shapely
     import shapely.geometry
-    import pyproj
+    from geopandas.array import GeometryArray, GeometryDtype, from_shapely
 
     GeoPandasObject = Union[
         pd.Series, pd.DataFrame, gpd.GeoSeries, gpd.GeoDataFrame

pandera/engines/pyspark_engine.py

@@ -10,13 +10,13 @@
 import dataclasses
 import inspect
 import re
-import warnings
-from typing import Any, Iterable, Union, Optional
 import sys
-from packaging import version
+import warnings
+from typing import Any, Iterable, Optional, Union
 
 import pyspark
 import pyspark.sql.types as pst
+from packaging import version
 
 from pandera import dtypes, errors
 from pandera.dtypes import immutable

pandera/error_handlers.py

@@ -2,7 +2,7 @@
 
 from typing import List, Optional
 
-from pandera.errors import SchemaError, SchemaErrors, SchemaErrorReason
+from pandera.errors import SchemaError, SchemaErrorReason, SchemaErrors
 
 
 class SchemaErrorHandler:

pandera/pyspark.py

@@ -1,21 +1,11 @@
 """A flexible and expressive pyspark validation library."""
 # pylint: disable=unused-import
-from pandera.accessors import pyspark_sql_accessor
+import pandera.backends.pyspark
 from pandera.api.checks import Check
 from pandera.api.pyspark import Column, DataFrameSchema
 from pandera.api.pyspark.model import DataFrameModel, SchemaModel
-from pandera.api.pyspark.model_components import (
-    Field,
-    check,
-    dataframe_check,
-)
-import pandera.backends.pyspark
-from pandera.decorators import (
-    check_input,
-    check_io,
-    check_output,
-    check_types,
-)
+from pandera.api.pyspark.model_components import Field, check, dataframe_check
+from pandera.decorators import check_input, check_io, check_output, check_types
 from pandera.dtypes import (
     Bool,
     Category,
@@ -51,7 +41,6 @@
 from pandera.typing import pyspark_sql
 from pandera.version import __version__
 
-
 __all__ = [
     # dtypes
     "Bool",

pandera/typing/__init__.py

@@ -50,7 +50,6 @@
 )
 from pandera.typing.pandas import DataFrame, Index, Series
 
-
 DATAFRAME_TYPES: Set[Type] = {DataFrame}
 SERIES_TYPES: Set[Type] = {Series}
 INDEX_TYPES: Set[Type] = {Index}

pandera/typing/fastapi.py

@@ -21,8 +21,8 @@
 
 
 if PYDANTIC_V2:
-    from pydantic_core import core_schema
     from pydantic import GetCoreSchemaHandler
+    from pydantic_core import core_schema
 
 
 if FASTAPI_INSTALLED: