feat(python): Drop python 3.8 support

.github/workflows/lint-python.yml

@@ -39,7 +39,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.8', '3.12']
+        python-version: ['3.9', '3.12']
 
     steps:
       - uses: actions/checkout@v4
@@ -63,4 +63,4 @@ jobs:
       # Allow untyped calls for older Python versions
       - name: Run mypy
         working-directory: py-polars
-        run: mypy ${{ (matrix.python-version == '3.8') && '--allow-untyped-calls' || '' }}
+        run: mypy ${{ (matrix.python-version == '3.9') && '--allow-untyped-calls' || '' }}

.github/workflows/release-python.yml

@@ -18,7 +18,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  PYTHON_VERSION: '3.8'
+  PYTHON_VERSION: '3.9'
   CARGO_INCREMENTAL: 0
   CARGO_NET_RETRY: 10
   RUSTUP_MAX_RETRIES: 10

.github/workflows/test-python.yml

@@ -39,7 +39,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.8', '3.11', '3.12']
+        python-version: ['3.9', '3.12']
         include:
           - os: windows-latest
             python-version: '3.12'

py-polars/Cargo.toml

@@ -12,7 +12,7 @@ libc = { workspace = true }
 # Explicit dependency is needed to add bigidx in CI during release
 polars = { workspace = true }
 polars-python = { workspace = true, features = ["pymethods", "iejoin"] }
-pyo3 = { workspace = true, features = ["abi3-py38", "chrono", "extension-module", "multiple-pymethods"] }
+pyo3 = { workspace = true, features = ["abi3-py39", "chrono", "extension-module", "multiple-pymethods"] }
 
 [build-dependencies]
 built = { version = "0.7", features = ["chrono", "git2", "cargo-lock"], optional = true }

py-polars/polars/_typing.py

@@ -1,17 +1,11 @@
 from __future__ import annotations
 
+from collections.abc import Collection, Iterable, Mapping, Sequence
 from typing import (
     TYPE_CHECKING,
     Any,
-    Collection,
-    Iterable,
-    List,
     Literal,
-    Mapping,
     Protocol,
-    Sequence,
-    Tuple,
-    Type,
     TypedDict,
     TypeVar,
     Union,
@@ -55,37 +49,37 @@ def __arrow_c_stream__(self, requested_schema: object | None = None) -> object:
 
 # Data types
 PolarsDataType: TypeAlias = Union["DataTypeClass", "DataType"]
-PolarsTemporalType: TypeAlias = Union[Type["TemporalType"], "TemporalType"]
-PolarsIntegerType: TypeAlias = Union[Type["IntegerType"], "IntegerType"]
+PolarsTemporalType: TypeAlias = Union[type["TemporalType"], "TemporalType"]
+PolarsIntegerType: TypeAlias = Union[type["IntegerType"], "IntegerType"]
 OneOrMoreDataTypes: TypeAlias = Union[PolarsDataType, Iterable[PolarsDataType]]
 PythonDataType: TypeAlias = Union[
-    Type[int],
-    Type[float],
-    Type[bool],
-    Type[str],
-    Type["date"],
-    Type["time"],
-    Type["datetime"],
-    Type["timedelta"],
-    Type[List[Any]],
-    Type[Tuple[Any, ...]],
-    Type[bytes],
-    Type[object],
-    Type["Decimal"],
-    Type[None],
+    type[int],
+    type[float],
+    type[bool],
+    type[str],
+    type["date"],
+    type["time"],
+    type["datetime"],
+    type["timedelta"],
+    type[list[Any]],
+    type[tuple[Any, ...]],
+    type[bytes],
+    type[object],
+    type["Decimal"],
+    type[None],
 ]
 
 SchemaDefinition: TypeAlias = Union[
     Mapping[str, Union[PolarsDataType, PythonDataType]],
-    Sequence[Union[str, Tuple[str, Union[PolarsDataType, PythonDataType, None]]]],
+    Sequence[Union[str, tuple[str, Union[PolarsDataType, PythonDataType, None]]]],
 ]
 SchemaDict: TypeAlias = Mapping[str, PolarsDataType]
 
 NumericLiteral: TypeAlias = Union[int, float, "Decimal"]
 TemporalLiteral: TypeAlias = Union["date", "time", "datetime", "timedelta"]
 NonNestedLiteral: TypeAlias = Union[NumericLiteral, TemporalLiteral, str, bool, bytes]
 # Python literal types (can convert into a `lit` expression)
-PythonLiteral: TypeAlias = Union[NonNestedLiteral, List[Any]]
+PythonLiteral: TypeAlias = Union[NonNestedLiteral, list[Any]]
 # Inputs that can convert into a `col` expression
 IntoExprColumn: TypeAlias = Union["Expr", "Series", str]
 # Inputs that can convert into an expression
@@ -204,7 +198,7 @@ def __arrow_c_stream__(self, requested_schema: object | None = None) -> object:
 # Excel IO
 ColumnFormatDict: TypeAlias = Mapping[
     # dict of colname(s) or selector(s) to format string or dict
-    Union[ColumnNameOrSelector, Tuple[ColumnNameOrSelector, ...]],
+    Union[ColumnNameOrSelector, tuple[ColumnNameOrSelector, ...]],
     Union[str, Mapping[str, str]],
 ]
 ConditionalFormatDict: TypeAlias = Mapping[
@@ -214,12 +208,12 @@ def __arrow_c_stream__(self, requested_schema: object | None = None) -> object:
 ]
 ColumnTotalsDefinition: TypeAlias = Union[
     # dict of colname(s) to str, a collection of str, or a boolean
-    Mapping[Union[ColumnNameOrSelector, Tuple[ColumnNameOrSelector]], str],
+    Mapping[Union[ColumnNameOrSelector, tuple[ColumnNameOrSelector]], str],
     Sequence[str],
     bool,
 ]
 ColumnWidthsDefinition: TypeAlias = Union[
-    Mapping[ColumnNameOrSelector, Union[Tuple[str, ...], int]], int
+    Mapping[ColumnNameOrSelector, Union[tuple[str, ...], int]], int
 ]
 RowTotalsDefinition: TypeAlias = Union[
     # dict of colname to str(s), a collection of str, or a boolean
@@ -234,7 +228,7 @@ def __arrow_c_stream__(self, requested_schema: object | None = None) -> object:
 # typevars for core polars types
 PolarsType = TypeVar("PolarsType", "DataFrame", "LazyFrame", "Series", "Expr")
 FrameType = TypeVar("FrameType", "DataFrame", "LazyFrame")
-BufferInfo: TypeAlias = Tuple[int, int, int]
+BufferInfo: TypeAlias = tuple[int, int, int]
 
 # type alias for supported spreadsheet engines
 ExcelSpreadsheetEngine: TypeAlias = Literal["xlsx2csv", "openpyxl", "calamine"]

py-polars/polars/_utils/async_.py

@@ -1,12 +1,14 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Awaitable, Generator, Generic, TypeVar
+from collections.abc import Awaitable
+from typing import TYPE_CHECKING, Any, Generic, TypeVar
 
 from polars._utils.wrap import wrap_df
 from polars.dependencies import _GEVENT_AVAILABLE
 
 if TYPE_CHECKING:
     from asyncio.futures import Future
+    from collections.abc import Generator
 
     from polars.polars import PyDataFrame
 

py-polars/polars/_utils/construction/dataframe.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import contextlib
+from collections.abc import Generator, Mapping
 from datetime import date, datetime, time, timedelta
 from functools import singledispatch
 from itertools import islice, zip_longest
@@ -9,11 +10,6 @@
     TYPE_CHECKING,
     Any,
     Callable,
-    Generator,
-    Iterable,
-    Mapping,
-    MutableMapping,
-    Sequence,
 )
 
 import polars._reexport as pl
@@ -63,6 +59,8 @@
     from polars.polars import PyDataFrame
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable, MutableMapping, Sequence
+
     from polars import DataFrame, Expr, Series
     from polars._typing import (
         Orientation,

py-polars/polars/_utils/construction/series.py

@@ -1,16 +1,13 @@
 from __future__ import annotations
 
 import contextlib
+from collections.abc import Generator, Iterator
 from datetime import date, datetime, time, timedelta
 from itertools import islice
 from typing import (
     TYPE_CHECKING,
     Any,
     Callable,
-    Generator,
-    Iterable,
-    Iterator,
-    Sequence,
 )
 
 import polars._reexport as pl
@@ -65,6 +62,8 @@
     from polars.polars import PySeries
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable, Sequence
+
     from polars import DataFrame, Series
     from polars._typing import PolarsDataType
     from polars.dependencies import pandas as pd

py-polars/polars/_utils/construction/utils.py

@@ -2,11 +2,13 @@
 
 import sys
 from functools import lru_cache
-from typing import TYPE_CHECKING, Any, Callable, Sequence, get_type_hints
+from typing import TYPE_CHECKING, Any, Callable, get_type_hints
 
 from polars.dependencies import _check_for_pydantic, pydantic
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
+
     import pandas as pd
 
 PANDAS_SIMPLE_NUMPY_DTYPES = {

py-polars/polars/_utils/convert.py

@@ -8,7 +8,6 @@
     Any,
     Callable,
     NoReturn,
-    Sequence,
     no_type_check,
     overload,
 )
@@ -26,6 +25,7 @@
 from polars.dependencies import _ZONEINFO_AVAILABLE, zoneinfo
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
     from datetime import date, tzinfo
     from decimal import Decimal
 

py-polars/polars/_utils/deprecation.py

@@ -1,14 +1,15 @@
 from __future__ import annotations
 
 import inspect
+from collections.abc import Sequence
 from functools import wraps
-from typing import TYPE_CHECKING, Callable, Sequence, TypeVar
+from typing import TYPE_CHECKING, Callable, TypeVar
 
 from polars._utils.various import issue_warning
 
 if TYPE_CHECKING:
     import sys
-    from typing import Mapping
+    from collections.abc import Mapping
 
     from polars._typing import Ambiguous
 

py-polars/polars/_utils/getitem.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Iterable, NoReturn, Sequence, overload
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, NoReturn, overload
 
 import polars._reexport as pl
 import polars.functions as F
@@ -22,6 +23,8 @@
 from polars.meta.index_type import get_index_type
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable
+
     from polars import DataFrame, Series
     from polars._typing import (
         MultiColSelector,

py-polars/polars/_utils/parse/expr.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
 import contextlib
-from typing import TYPE_CHECKING, Any, Iterable
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Any
 
 import polars._reexport as pl
 from polars import functions as F

py-polars/polars/_utils/udfs.py

@@ -16,11 +16,9 @@
 from pathlib import Path
 from typing import (
     TYPE_CHECKING,
-    AbstractSet,
     Any,
     Callable,
     ClassVar,
-    Iterator,
     Literal,
     NamedTuple,
     Union,
@@ -29,6 +27,8 @@
 from polars._utils.various import re_escape
 
 if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from collections.abc import Set as AbstractSet
     from dis import Instruction
 
     if sys.version_info >= (3, 10):

py-polars/polars/_utils/various.py

@@ -5,18 +5,21 @@
 import re
 import sys
 import warnings
-from collections.abc import MappingView, Sized
+from collections.abc import (
+    Collection,
+    Generator,
+    Iterable,
+    MappingView,
+    Sequence,
+    Sized,
+)
 from enum import Enum
 from pathlib import Path
 from typing import (
     TYPE_CHECKING,
     Any,
     Callable,
-    Collection,
-    Generator,
-    Iterable,
     Literal,
-    Sequence,
     TypeVar,
     overload,
 )

py-polars/polars/convert/general.py

@@ -3,7 +3,8 @@
 import io
 import itertools
 import re
-from typing import TYPE_CHECKING, Any, Iterable, Mapping, Sequence, overload
+from collections.abc import Iterable, Sequence
+from typing import TYPE_CHECKING, Any, overload
 
 import polars._reexport as pl
 from polars import functions as F
@@ -24,6 +25,8 @@
 from polars.exceptions import NoDataError
 
 if TYPE_CHECKING:
+    from collections.abc import Mapping
+
     from polars import DataFrame, Series
     from polars._typing import Orientation, SchemaDefinition, SchemaDict
     from polars.dependencies import numpy as np

py-polars/polars/convert/normalize.py

@@ -4,27 +4,20 @@
 
 import json
 from collections import abc
-from typing import TYPE_CHECKING, Any, Sequence
+from typing import TYPE_CHECKING, Any
 
 from polars._utils.unstable import unstable
 from polars.dataframe import DataFrame
 from polars.datatypes.constants import N_INFER_DEFAULT
 
 if TYPE_CHECKING:
-    from polars.schema import Schema
-
-import sys
+    from collections.abc import Sequence
 
-if sys.version_info >= (3, 9):
+    from polars.schema import Schema
 
-    def _remove_prefix(text: str, prefix: str) -> str:
-        return text.removeprefix(prefix)
-else:
 
-    def _remove_prefix(text: str, prefix: str) -> str:
-        if text.startswith(prefix):
-            return text[len(prefix) :]
-        return text
+def _remove_prefix(text: str, prefix: str) -> str:
+    return text.removeprefix(prefix)
 
 
 def _simple_json_normalize(