polars-runtime-compat 1.34.0b2__cp39-abi3-macosx_11_0_arm64.whl → 1.34.0b4__cp39-abi3-macosx_11_0_arm64.whl

polars/sql/functions.py

@@ -1,139 +0,0 @@
-from __future__ import annotations
-
-from typing import TYPE_CHECKING, Literal, overload
-
-if TYPE_CHECKING:
-    from polars.dataframe import DataFrame
-    from polars.lazyframe import LazyFrame
-
-
-__all__ = ["sql"]
-
-
-@overload
-def sql(query: str, *, eager: Literal[False] = False) -> LazyFrame: ...
-
-
-@overload
-def sql(query: str, *, eager: Literal[True]) -> DataFrame: ...
-
-
-def sql(query: str, *, eager: bool = False) -> DataFrame | LazyFrame:
-    """
-    Execute a SQL query against frames in the global namespace.
-
-    .. versionadded:: 0.20.31
-
-    Parameters
-    ----------
-    query
-        SQL query to execute.
-    eager
-        Automatically collect the result and return a DataFrame instead of a LazyFrame.
-
-    Notes
-    -----
-    * The Polars SQL engine can operate against Polars DataFrame, LazyFrame, and Series
-      objects, as well as Pandas DataFrame and Series, PyArrow Table and RecordBatch.
-    * Additional control over registration and execution behaviour is available
-      with the :class:`SQLContext` object.
-
-    See Also
-    --------
-    SQLContext
-
-    Examples
-    --------
-    >>> lf1 = pl.LazyFrame({"a": [1, 2, 3], "b": [6, 7, 8], "c": ["z", "y", "x"]})
-    >>> lf2 = pl.LazyFrame({"a": [3, 2, 1], "d": [125, -654, 888]})
-
-    Query the LazyFrame using SQL:
-
-    >>> lf1.sql("SELECT c, b FROM self WHERE a > 1").collect()
-    shape: (2, 2)
-    ┌─────┬─────┐
-    │ c   ┆ b   │
-    │ --- ┆ --- │
-    │ str ┆ i64 │
-    ╞═════╪═════╡
-    │ y   ┆ 7   │
-    │ x   ┆ 8   │
-    └─────┴─────┘
-
-    Join two LazyFrames:
-
-    >>> pl.sql(
-    ...     '''
-    ...     SELECT lf1.*, d
-    ...     FROM lf1
-    ...     INNER JOIN lf2 USING (a)
-    ...     WHERE a > 1 AND b < 8
-    ...     '''
-    ... ).collect()
-    shape: (1, 4)
-    ┌─────┬─────┬─────┬──────┐
-    │ a   ┆ b   ┆ c   ┆ d    │
-    │ --- ┆ --- ┆ --- ┆ ---  │
-    │ i64 ┆ i64 ┆ str ┆ i64  │
-    ╞═════╪═════╪═════╪══════╡
-    │ 2   ┆ 7   ┆ y   ┆ -654 │
-    └─────┴─────┴─────┴──────┘
-
-    Apply SQL transforms and subsequently filter natively (you can freely mix SQL and
-    native operations):
-
-    >>> pl.sql(
-    ...     query='''
-    ...         SELECT
-    ...             a,
-    ...             (a % 2 == 0) AS a_is_even,
-    ...             (b::float4 / 2) AS "b/2",
-    ...             CONCAT_WS(':', c, c, c) AS c_c_c
-    ...         FROM lf1
-    ...         ORDER BY a
-    ...     ''',
-    ... ).filter(~pl.col("c_c_c").str.starts_with("x")).collect()
-    shape: (2, 4)
-    ┌─────┬───────────┬─────┬───────┐
-    │ a   ┆ a_is_even ┆ b/2 ┆ c_c_c │
-    │ --- ┆ ---       ┆ --- ┆ ---   │
-    │ i64 ┆ bool      ┆ f32 ┆ str   │
-    ╞═════╪═══════════╪═════╪═══════╡
-    │ 1   ┆ false     ┆ 3.0 ┆ z:z:z │
-    │ 2   ┆ true      ┆ 3.5 ┆ y:y:y │
-    └─────┴───────────┴─────┴───────┘
-
-    Join polars LazyFrame with a pandas DataFrame and a pyarrow Table:
-
-    >>> import pandas as pd
-    >>> import pyarrow as pa
-    >>> pl_frame = lf1
-    >>> pd_frame = pd.DataFrame({"a": [2, 3, 4], "d": [-0.5, 0.0, 0.5]})
-    >>> pa_table = pa.Table.from_arrays(
-    ...     [pa.array([1, 2, 3]), pa.array(["x", "y", "z"])],
-    ...     names=["a", "e"],
-    ... )
-    >>> pl.sql(
-    ...     query='''
-    ...         SELECT pl_frame.*, d, e
-    ...         FROM pl_frame
-    ...         JOIN pd_frame USING(a)
-    ...         JOIN pa_table USING(a)
-    ...     ''',
-    ... ).collect()
-    shape: (2, 5)
-    ┌─────┬─────┬─────┬──────┬─────┐
-    │ a   ┆ b   ┆ c   ┆ d    ┆ e   │
-    │ --- ┆ --- ┆ --- ┆ ---  ┆ --- │
-    │ i64 ┆ i64 ┆ str ┆ f64  ┆ str │
-    ╞═════╪═════╪═════╪══════╪═════╡
-    │ 2   ┆ 7   ┆ y   ┆ -0.5 ┆ y   │
-    │ 3   ┆ 8   ┆ x   ┆ 0.0  ┆ z   │
-    └─────┴─────┴─────┴──────┴─────┘
-    """
-    from polars.sql import SQLContext
-
-    return SQLContext.execute_global(
-        query=query,
-        eager=eager,
-    )

polars/string_cache.py

@@ -1,185 +0,0 @@
-from __future__ import annotations
-
-import contextlib
-from typing import TYPE_CHECKING
-
-with contextlib.suppress(ImportError):  # Module not available when building docs
-    import polars._plr as plr
-    from polars._plr import PyStringCacheHolder
-
-if TYPE_CHECKING:
-    import sys
-    from types import TracebackType
-
-    if sys.version_info >= (3, 11):
-        from typing import Self
-    else:
-        from typing_extensions import Self
-
-
-__all__ = [
-    "StringCache",
-    "disable_string_cache",
-    "enable_string_cache",
-    "using_string_cache",
-]
-
-
-class StringCache(contextlib.ContextDecorator):
-    """
-    Context manager for enabling and disabling the global string cache.
-
-    :class:`Categorical` columns created under the same global string cache have
-    the same underlying physical value when string values are equal. This allows the
-    columns to be concatenated or used in a join operation, for example.
-
-    Notes
-    -----
-    Enabling the global string cache introduces some overhead.
-    The amount of overhead depends on the number of categories in your data.
-    It is advised to enable the global string cache only when strictly necessary.
-
-    If `StringCache` calls are nested, the global string cache will only be disabled
-    and cleared when the outermost context exits.
-
-    Examples
-    --------
-    Construct two Series using the same global string cache.
-
-    >>> with pl.StringCache():
-    ...     s1 = pl.Series("color", ["red", "green", "red"], dtype=pl.Categorical)
-    ...     s2 = pl.Series("color", ["blue", "red", "green"], dtype=pl.Categorical)
-
-    As both Series are constructed under the same global string cache,
-    they can be concatenated.
-
-    >>> pl.concat([s1, s2])
-    shape: (6,)
-    Series: 'color' [cat]
-    [
-            "red"
-            "green"
-            "red"
-            "blue"
-            "red"
-            "green"
-    ]
-
-    The class can also be used as a function decorator, in which case the string cache
-    is enabled during function execution, and disabled afterwards.
-
-    >>> @pl.StringCache()
-    ... def construct_categoricals() -> pl.Series:
-    ...     s1 = pl.Series("color", ["red", "green", "red"], dtype=pl.Categorical)
-    ...     s2 = pl.Series("color", ["blue", "red", "green"], dtype=pl.Categorical)
-    ...     return pl.concat([s1, s2])
-    """
-
-    def __enter__(self) -> Self:
-        self._string_cache = PyStringCacheHolder()
-        return self
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_val: BaseException | None,
-        exc_tb: TracebackType | None,
-    ) -> None:
-        del self._string_cache
-
-
-def enable_string_cache() -> None:
-    """
-    Enable the global string cache.
-
-    :class:`Categorical` columns created under the same global string cache have
-    the same underlying physical value when string values are equal. This allows the
-    columns to be concatenated or used in a join operation, for example.
-
-    See Also
-    --------
-    StringCache : Context manager for enabling and disabling the string cache.
-    disable_string_cache : Function to disable the string cache.
-
-    Notes
-    -----
-    Enabling the global string cache introduces some overhead.
-    The amount of overhead depends on the number of categories in your data.
-    It is advised to enable the global string cache only when strictly necessary.
-
-    Consider using the :class:`StringCache` context manager for a more reliable way of
-    enabling and disabling the string cache.
-
-    Examples
-    --------
-    Construct two Series using the same global string cache.
-
-    >>> pl.enable_string_cache()
-    >>> s1 = pl.Series("color", ["red", "green", "red"], dtype=pl.Categorical)
-    >>> s2 = pl.Series("color", ["blue", "red", "green"], dtype=pl.Categorical)
-    >>> pl.disable_string_cache()
-
-    As both Series are constructed under the same global string cache,
-    they can be concatenated.
-
-    >>> pl.concat([s1, s2])
-    shape: (6,)
-    Series: 'color' [cat]
-    [
-            "red"
-            "green"
-            "red"
-            "blue"
-            "red"
-            "green"
-    ]
-    """
-    plr.enable_string_cache()
-
-
-def disable_string_cache() -> None:
-    """
-    Disable and clear the global string cache.
-
-    See Also
-    --------
-    enable_string_cache : Function to enable the string cache.
-    StringCache : Context manager for enabling and disabling the string cache.
-
-    Notes
-    -----
-    Consider using the :class:`StringCache` context manager for a more reliable way of
-    enabling and disabling the string cache.
-
-    When used in conjunction with the :class:`StringCache` context manager, the string
-    cache will not be disabled until the context manager exits.
-
-    Examples
-    --------
-    Construct two Series using the same global string cache.
-
-    >>> pl.enable_string_cache()
-    >>> s1 = pl.Series("color", ["red", "green", "red"], dtype=pl.Categorical)
-    >>> s2 = pl.Series("color", ["blue", "red", "green"], dtype=pl.Categorical)
-    >>> pl.disable_string_cache()
-
-    As both Series are constructed under the same global string cache,
-    they can be concatenated.
-
-    >>> pl.concat([s1, s2])
-    shape: (6,)
-    Series: 'color' [cat]
-    [
-            "red"
-            "green"
-            "red"
-            "blue"
-            "red"
-            "green"
-    ]
-    """
-
-
-def using_string_cache() -> bool:
-    """Check whether the global string cache is enabled."""
-    return plr.using_string_cache()

polars/testing/__init__.py

@@ -1,13 +0,0 @@
-from polars.testing.asserts import (
-    assert_frame_equal,
-    assert_frame_not_equal,
-    assert_series_equal,
-    assert_series_not_equal,
-)
-
-__all__ = [
-    "assert_frame_equal",
-    "assert_frame_not_equal",
-    "assert_series_equal",
-    "assert_series_not_equal",
-]

polars/testing/asserts/__init__.py

@@ -1,9 +0,0 @@
-from polars.testing.asserts.frame import assert_frame_equal, assert_frame_not_equal
-from polars.testing.asserts.series import assert_series_equal, assert_series_not_equal
-
-__all__ = [
-    "assert_frame_equal",
-    "assert_frame_not_equal",
-    "assert_series_equal",
-    "assert_series_not_equal",
-]

polars/testing/asserts/frame.py

@@ -1,231 +0,0 @@
-from __future__ import annotations
-
-import contextlib
-from typing import cast
-
-from polars._utils.deprecation import deprecate_renamed_parameter
-from polars.dataframe import DataFrame
-from polars.lazyframe import LazyFrame
-from polars.testing.asserts.utils import raise_assertion_error
-
-with contextlib.suppress(ImportError):  # Module not available when building docs
-    from polars._plr import assert_dataframe_equal_py
-
-
-def _assert_correct_input_type(
-    left: DataFrame | LazyFrame, right: DataFrame | LazyFrame
-) -> bool:
-    __tracebackhide__ = True
-
-    if isinstance(left, DataFrame) and isinstance(right, DataFrame):
-        return False
-    elif isinstance(left, LazyFrame) and isinstance(right, LazyFrame):
-        return True
-    else:
-        raise_assertion_error(
-            "inputs",
-            "unexpected input types",
-            type(left).__name__,
-            type(right).__name__,
-        )
-
-
-@deprecate_renamed_parameter("check_dtype", "check_dtypes", version="0.20.31")
-@deprecate_renamed_parameter("rtol", "rel_tol", version="1.32.3")
-@deprecate_renamed_parameter("atol", "abs_tol", version="1.32.3")
-def assert_frame_equal(
-    left: DataFrame | LazyFrame,
-    right: DataFrame | LazyFrame,
-    *,
-    check_row_order: bool = True,
-    check_column_order: bool = True,
-    check_dtypes: bool = True,
-    check_exact: bool = False,
-    rel_tol: float = 1e-5,
-    abs_tol: float = 1e-8,
-    categorical_as_str: bool = False,
-) -> None:
-    """
-    Assert that the left and right frame are equal.
-
-    Raises a detailed `AssertionError` if the frames differ.
-    This function is intended for use in unit tests.
-
-    .. versionchanged:: 0.20.31
-        The `check_dtype` parameter was renamed `check_dtypes`.
-
-    .. versionchanged:: 1.32.3
-        The `rtol` and `atol` parameters were renamed to `rel_tol` and `abs_tol`,
-        respectively.
-
-    Parameters
-    ----------
-    left
-        The first DataFrame or LazyFrame to compare.
-    right
-        The second DataFrame or LazyFrame to compare.
-    check_row_order
-        Requires row order to match.
-    check_column_order
-        Requires column order to match.
-    check_dtypes
-        Requires data types to match.
-    check_exact
-        Requires float values to match exactly. If set to `False`, values are considered
-        equal when within tolerance of each other (see `rel_tol` and `abs_tol`).
-        Only affects columns with a Float data type.
-    rel_tol
-        Relative tolerance for inexact checking. Fraction of values in `right`.
-    abs_tol
-        Absolute tolerance for inexact checking.
-    categorical_as_str
-        Cast categorical columns to string before comparing. Enabling this helps
-        compare columns that do not share the same string cache.
-
-    See Also
-    --------
-    assert_series_equal
-    assert_frame_not_equal
-
-    Notes
-    -----
-    When using pytest, it may be worthwhile to shorten Python traceback printing
-    by passing `--tb=short`. The default mode tends to be unhelpfully verbose.
-    More information in the
-    `pytest docs <https://docs.pytest.org/en/latest/how-to/output.html#modifying-python-traceback-printing>`_.
-
-    Examples
-    --------
-    >>> from polars.testing import assert_frame_equal
-    >>> df1 = pl.DataFrame({"a": [1, 2, 3]})
-    >>> df2 = pl.DataFrame({"a": [1, 5, 3]})
-    >>> assert_frame_equal(df1, df2)
-    Traceback (most recent call last):
-    ...
-    AssertionError: DataFrames are different (value mismatch for column "a")
-    [left]: shape: (3,)
-    Series: 'a' [i64]
-    [
-        1
-        2
-        3
-    ]
-    [right]: shape: (3,)
-    Series: 'a' [i64]
-    [
-        1
-        5
-        3
-    ]
-    """
-    __tracebackhide__ = True
-
-    lazy = _assert_correct_input_type(left, right)
-
-    # Rust back-end function expects DataFrames so LazyFrames must be collected
-    if lazy:
-        left, right = left.collect(), right.collect()  # type: ignore[union-attr]
-
-    # Tell type checker these are now DataFrames to prevent type errors
-    left, right = cast("DataFrame", left), cast("DataFrame", right)
-
-    assert_dataframe_equal_py(
-        left._df,
-        right._df,
-        check_row_order=check_row_order,
-        check_column_order=check_column_order,
-        check_dtypes=check_dtypes,
-        check_exact=check_exact,
-        rel_tol=rel_tol,
-        abs_tol=abs_tol,
-        categorical_as_str=categorical_as_str,
-    )
-
-
-@deprecate_renamed_parameter("check_dtype", "check_dtypes", version="0.20.31")
-@deprecate_renamed_parameter("rtol", "rel_tol", version="1.32.3")
-@deprecate_renamed_parameter("atol", "abs_tol", version="1.32.3")
-def assert_frame_not_equal(
-    left: DataFrame | LazyFrame,
-    right: DataFrame | LazyFrame,
-    *,
-    check_row_order: bool = True,
-    check_column_order: bool = True,
-    check_dtypes: bool = True,
-    check_exact: bool = False,
-    rel_tol: float = 1e-5,
-    abs_tol: float = 1e-8,
-    categorical_as_str: bool = False,
-) -> None:
-    """
-    Assert that the left and right frame are **not** equal.
-
-    This function is intended for use in unit tests.
-
-    .. versionchanged:: 0.20.31
-        The `check_dtype` parameter was renamed `check_dtypes`.
-
-    .. versionchanged:: 1.32.3
-        The `rtol` and `atol` parameters were renamed to `rel_tol` and `abs_tol`,
-        respectively.
-
-    Parameters
-    ----------
-    left
-        The first DataFrame or LazyFrame to compare.
-    right
-        The second DataFrame or LazyFrame to compare.
-    check_row_order
-        Requires row order to match.
-    check_column_order
-        Requires column order to match.
-    check_dtypes
-        Requires data types to match.
-    check_exact
-        Requires float values to match exactly. If set to `False`, values are considered
-        equal when within tolerance of each other (see `rel_tol` and `abs_tol`).
-        Only affects columns with a Float data type.
-    rel_tol
-        Relative tolerance for inexact checking. Fraction of values in `right`.
-    abs_tol
-        Absolute tolerance for inexact checking.
-    categorical_as_str
-        Cast categorical columns to string before comparing. Enabling this helps
-        compare columns that do not share the same string cache.
-
-    See Also
-    --------
-    assert_frame_equal
-    assert_series_not_equal
-
-    Examples
-    --------
-    >>> from polars.testing import assert_frame_not_equal
-    >>> df1 = pl.DataFrame({"a": [1, 2, 3]})
-    >>> df2 = pl.DataFrame({"a": [1, 2, 3]})
-    >>> assert_frame_not_equal(df1, df2)
-    Traceback (most recent call last):
-    ...
-    AssertionError: DataFrames are equal (but are expected not to be)
-    """
-    __tracebackhide__ = True
-
-    lazy = _assert_correct_input_type(left, right)
-    try:
-        assert_frame_equal(
-            left=left,
-            right=right,
-            check_column_order=check_column_order,
-            check_row_order=check_row_order,
-            check_dtypes=check_dtypes,
-            check_exact=check_exact,
-            rel_tol=rel_tol,
-            abs_tol=abs_tol,
-            categorical_as_str=categorical_as_str,
-        )
-    except AssertionError:
-        return
-    else:
-        objects = "LazyFrames" if lazy else "DataFrames"
-        msg = f"{objects} are equal (but are expected not to be)"
-        raise AssertionError(msg)