Source code for quantdata.utils.testing

"""
Utility functions for testing Data Frames
=========================================
"""

import polars as pl
import pandas as pd
import numpy as np
import hashlib
from polars.testing import assert_frame_equal as pl_assert_frame_equal
from pandas.testing import assert_frame_equal as pd_assert_frame_equal

[docs] def assert_pl_frame_equal( actual: pl.DataFrame, expected: pl.DataFrame, *, sort_by: str | list[str] | None = None, check_dtypes: bool = True, check_column_order: bool = True, check_exact: bool = False, rel_tol: float = 1e-10, abs_tol: float = 1e-12, ) -> None: """ Assert that two Polars DataFrames are equal, with options for sorting and tolerance. """ if sort_by is not None: if isinstance(sort_by, str): sort_by = [sort_by] actual = actual.sort(sort_by) expected = expected.sort(sort_by) pl_assert_frame_equal( actual, expected, check_row_order=True, check_column_order=check_column_order, check_dtypes=check_dtypes, check_exact=check_exact, rel_tol=rel_tol, abs_tol=abs_tol, )
[docs] def assert_pd_frame_equal( actual: pd.DataFrame, expected: pd.DataFrame, *, sort_by: str | list[str] | None = None, reset_index: bool = True, check_dtype: bool = True, check_exact: bool = False, rtol: float = 1e-10, atol: float = 1e-12, ) -> None: """ Assert that two Pandas DataFrames are equal, with options for sorting and tolerance. """ if sort_by is not None: actual = actual.sort_values(sort_by) expected = expected.sort_values(sort_by) if reset_index: actual = actual.reset_index(drop=True) expected = expected.reset_index(drop=True) pd_assert_frame_equal( actual, expected, check_dtype=check_dtype, check_exact=check_exact, rtol=rtol, atol=atol, )
[docs] def hash_pandas_df( df: pd.DataFrame, *, include_index: bool = True, include_schema: bool = True, digest_size: int = 16, ) -> str: """ Compute a hash of a pandas DataFrame, including its data and optionally its schema and index. """ h = hashlib.blake2b(digest_size=digest_size) h.update(b"pandas-dataframe-v1") if include_schema: h.update(repr(tuple(df.columns)).encode("utf-8")) h.update(repr(tuple(map(str, df.dtypes))).encode("utf-8")) if include_index: h.update(str(df.index.dtype).encode("utf-8")) row_hashes = pd.util.hash_pandas_object( df, index=include_index, hash_key="0123456789123456", categorize=True, ).to_numpy(dtype=np.uint64, copy=False) h.update(row_hashes.tobytes()) return h.hexdigest()
[docs] def hash_polars_df( df: pl.DataFrame, *, include_schema: bool = True, digest_size: int = 16, ) -> str: """ Compute a hash of a Polars DataFrame, including its data and optionally its schema. """ h = hashlib.blake2b(digest_size=digest_size) h.update(b"polars-dataframe-v1") if include_schema: h.update(repr(tuple((name, str(dtype)) for name, dtype in df.schema.items())).encode("utf-8")) row_hashes = df.hash_rows( seed=0, seed_1=1, seed_2=2, seed_3=3, ).to_numpy() h.update(row_hashes.tobytes()) return h.hexdigest()