How to use infer_series_schema method in pandera

Best Python code snippet using pandera_python

test_schema_inference.py

Source:test_schema_inference.py

...97        pd.Series(list("abcdefg"), dtype="category"),98        pd.Series(pd.to_datetime(["20180101", "20180102", "20180103"])),99    ],100)101def test_infer_series_schema(series: pd.Series) -> None:102    """Test series schema is correctly inferred."""103    schema = schema_inference.infer_series_schema(series)104    assert isinstance(schema, pa.SeriesSchema)105    with pytest.warns(106        UserWarning,107        match="^This .+ is an inferred schema that hasn't been modified",108    ):109        schema.validate(series)110    # modifying an inferred schema should set _is_inferred to False111    schema_with_new_checks = schema.set_checks(112        [pa.Check(lambda x: x is not None)]113    )114    assert schema._is_inferred115    assert not schema_with_new_checks._is_inferred...

schema_inference.py

Source:schema_inference.py

...18    """19    if isinstance(pandas_obj, pd.DataFrame):20        return infer_dataframe_schema(pandas_obj)21    elif isinstance(pandas_obj, pd.Series):22        return infer_series_schema(pandas_obj)23    else:24        raise TypeError(25            "pandas_obj type not recognized. Expected a pandas DataFrame or "26            f"Series, found {type(pandas_obj)}"27        )28def _create_index(index_statistics):29    index = [30        Index(31            properties["dtype"],32            checks=parse_check_statistics(properties["checks"]),33            nullable=properties["nullable"],34            name=properties["name"],35        )36        for properties in index_statistics37    ]38    if len(index) == 1:39        index = index[0]  # type: ignore40    else:41        index = MultiIndex(index)  # type: ignore42    return index43def infer_dataframe_schema(df: pd.DataFrame) -> DataFrameSchema:44    """Infer a DataFrameSchema from a pandas DataFrame.45    :param df: DataFrame object to infer.46    :returns: DataFrameSchema47    """48    df_statistics = infer_dataframe_statistics(df)49    schema = DataFrameSchema(50        columns={51            colname: Column(52                properties["dtype"],53                checks=parse_check_statistics(properties["checks"]),54                nullable=properties["nullable"],55            )56            for colname, properties in df_statistics["columns"].items()57        },58        index=_create_index(df_statistics["index"]),59        coerce=True,60    )61    schema._is_inferred = True62    return schema63def infer_series_schema(series) -> SeriesSchema:64    """Infer a SeriesSchema from a pandas DataFrame.65    :param series: Series object to infer.66    :returns: SeriesSchema67    """68    series_statistics = infer_series_statistics(series)69    schema = SeriesSchema(70        dtype=series_statistics["dtype"],71        checks=parse_check_statistics(series_statistics["checks"]),72        nullable=series_statistics["nullable"],73        name=series_statistics["name"],74        coerce=True,75    )76    schema._is_inferred = True77    return schema

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.