How to use field_element_strategy method in pandera

Best Python code snippet using pandera_python

strategies.py

Source:strategies.py

...617    nanoseconds if given a pandas.Timestamp. We need to pass the unix epoch via618    the pandas.Timestamp.value attribute.619    """620    return st.builds(lambda x: np.datetime64(x.value, "ns"), strategy)621def field_element_strategy(622    pandera_dtype: Union[numpy_engine.DataType, pandas_engine.DataType],623    strategy: Optional[SearchStrategy] = None,624    *,625    checks: Optional[Sequence] = None,626) -> SearchStrategy:627    """Strategy to generate elements of a column or index.628    :param pandera_dtype: :class:`pandera.dtypes.DataType` instance.629    :param strategy: an optional hypothesis strategy. If specified, the630        pandas dtype strategy will be chained onto this strategy.631    :param checks: sequence of :class:`~pandera.checks.Check` s to constrain632        the values of the data in the column/index.633    :returns: ``hypothesis`` strategy634    """635    if strategy:636        raise BaseStrategyOnlyError(637            "The series strategy is a base strategy. You cannot specify the "638            "strategy argument to chain it to a parent strategy."639        )640    checks = [] if checks is None else checks641    elements = None642    def undefined_check_strategy(elements, check):643        """Strategy for checks with undefined strategies."""644        warnings.warn(645            "Element-wise check doesn't have a defined strategy."646            "Falling back to filtering drawn values based on the check "647            "definition. This can considerably slow down data-generation."648        )649        return (650            pandas_dtype_strategy(pandera_dtype)651            if elements is None652            else elements653        ).filter(check._check_fn)654    for check in checks:655        if hasattr(check, "strategy"):656            elements = check.strategy(pandera_dtype, elements)657        elif check.element_wise:658            elements = undefined_check_strategy(elements, check)659        # NOTE: vectorized checks with undefined strategies should be handled660        # by the series/dataframe strategy.661    if elements is None:662        elements = pandas_dtype_strategy(pandera_dtype)663    # Hypothesis only supports pure numpy datetime64 (i.e. timezone naive).664    # We cast to datetime64 after applying the check strategy so that checks665    # can see timezone-aware values.666    if _is_datetime_tz(pandera_dtype):667        elements = _timestamp_to_datetime64_strategy(elements)668    return elements669def series_strategy(670    pandera_dtype: Union[numpy_engine.DataType, pandas_engine.DataType],671    strategy: Optional[SearchStrategy] = None,672    *,673    checks: Optional[Sequence] = None,674    nullable: bool = False,675    unique: bool = False,676    name: Optional[str] = None,677    size: Optional[int] = None,678):679    """Strategy to generate a pandas Series.680    :param pandera_dtype: :class:`pandera.dtypes.DataType` instance.681    :param strategy: an optional hypothesis strategy. If specified, the682        pandas dtype strategy will be chained onto this strategy.683    :param checks: sequence of :class:`~pandera.checks.Check` s to constrain684        the values of the data in the column/index.685    :param nullable: whether or not generated Series contains null values.686    :param unique: whether or not generated Series contains unique values.687    :param name: name of the Series.688    :param size: number of elements in the Series.689    :returns: ``hypothesis`` strategy.690    """691    elements = field_element_strategy(pandera_dtype, strategy, checks=checks)692    strategy = (693        pdst.series(694            elements=elements,695            dtype=to_numpy_dtype(pandera_dtype),696            index=pdst.range_indexes(697                min_size=0 if size is None else size, max_size=size698            ),699            unique=unique,700        )701        .filter(lambda x: x.shape[0] > 0)702        .map(lambda x: x.rename(name))703        .map(lambda x: x.astype(pandera_dtype.type))704    )705    if nullable:706        strategy = null_field_masks(strategy)707    def undefined_check_strategy(strategy, check):708        """Strategy for checks with undefined strategies."""709        warnings.warn(710            "Vectorized check doesn't have a defined strategy."711            "Falling back to filtering drawn values based on the check "712            "definition. This can considerably slow down data-generation."713        )714        def _check_fn(series):715            return check(series).check_passed716        return strategy.filter(_check_fn)717    for check in checks if checks is not None else []:718        if not hasattr(check, "strategy") and not check.element_wise:719            strategy = undefined_check_strategy(strategy, check)720    return strategy721def column_strategy(722    pandera_dtype: Union[numpy_engine.DataType, pandas_engine.DataType],723    strategy: Optional[SearchStrategy] = None,724    *,725    checks: Optional[Sequence] = None,726    unique: bool = False,727    name: Optional[str] = None,728):729    # pylint: disable=line-too-long730    """Create a data object describing a column in a DataFrame.731    :param pandera_dtype: :class:`pandera.dtypes.DataType` instance.732    :param strategy: an optional hypothesis strategy. If specified, the733        pandas dtype strategy will be chained onto this strategy.734    :param checks: sequence of :class:`~pandera.checks.Check` s to constrain735        the values of the data in the column/index.736    :param unique: whether or not generated Series contains unique values.737    :param name: name of the Series.738    :returns: a `column <https://hypothesis.readthedocs.io/en/latest/numpy.html#hypothesis.extra.pandas.column>`_ object.739    """740    verify_dtype(pandera_dtype, schema_type="column", name=name)741    elements = field_element_strategy(pandera_dtype, strategy, checks=checks)742    return pdst.column(743        name=name,744        elements=elements,745        dtype=to_numpy_dtype(pandera_dtype),746        unique=unique,747    )748def index_strategy(749    pandera_dtype: Union[numpy_engine.DataType, pandas_engine.DataType],750    strategy: Optional[SearchStrategy] = None,751    *,752    checks: Optional[Sequence] = None,753    nullable: bool = False,754    unique: bool = False,755    name: Optional[str] = None,756    size: Optional[int] = None,757):758    """Strategy to generate a pandas Index.759    :param pandera_dtype: :class:`pandera.dtypes.DataType` instance.760    :param strategy: an optional hypothesis strategy. If specified, the761        pandas dtype strategy will be chained onto this strategy.762    :param checks: sequence of :class:`~pandera.checks.Check` s to constrain763        the values of the data in the column/index.764    :param nullable: whether or not generated Series contains null values.765    :param unique: whether or not generated Series contains unique values.766    :param name: name of the Series.767    :param size: number of elements in the Series.768    :returns: ``hypothesis`` strategy.769    """770    verify_dtype(pandera_dtype, schema_type="index", name=name)771    elements = field_element_strategy(pandera_dtype, strategy, checks=checks)772    strategy = pdst.indexes(773        elements=elements,774        dtype=to_numpy_dtype(pandera_dtype),775        min_size=0 if size is None else size,776        max_size=size,777        unique=unique,778    ).map(lambda x: x.astype(pandera_dtype.type))779    # this is a hack to convert np.str_ data values into native python str.780    col_dtype = str(pandera_dtype)781    if col_dtype in {"object", "str"} or col_dtype.startswith("string"):782        # pylint: disable=cell-var-from-loop,undefined-loop-variable783        strategy = strategy.map(lambda index: index.map(str))784    if name is not None:785        strategy = strategy.map(lambda index: index.rename(name))...

test_strategies.py

Source:test_strategies.py

...584        example = multiindex.example()585        multiindex(pd.DataFrame(index=example))586@pytest.mark.parametrize("data_type", NULLABLE_DTYPES)587@hypothesis.given(st.data())588def test_field_element_strategy(data_type, data):589    """Test strategy for generating elements in columns/indexes."""590    strategy = strategies.field_element_strategy(data_type)591    element = data.draw(strategy)592    expected_type = strategies.to_numpy_dtype(data_type).type593    assert element.dtype.type == expected_type594    with pytest.raises(pa.errors.BaseStrategyOnlyError):595        strategies.field_element_strategy(596            data_type, strategies.pandas_dtype_strategy(data_type)597        )598@pytest.mark.parametrize("data_type", NULLABLE_DTYPES)599@pytest.mark.parametrize(600    "field_strategy",601    [strategies.index_strategy, strategies.series_strategy],602)603@pytest.mark.parametrize("nullable", [True, False])604@hypothesis.given(st.data())605@hypothesis.settings(606    suppress_health_check=[hypothesis.HealthCheck.too_slow],607)608def test_check_nullable_field_strategy(609    data_type, field_strategy, nullable, data...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.