How to use infer_dataframe_schema method in pandera

Best Python code snippet using pandera_python

test_schema_inference.py

Source:test_schema_inference.py

...57@pytest.mark.parametrize(58    "multi_index",59    [False, True],60)61def test_infer_dataframe_schema(multi_index: bool) -> None:62    """Test dataframe schema is correctly inferred."""63    dataframe = _create_dataframe(multi_index=multi_index)64    schema = schema_inference.infer_dataframe_schema(dataframe)65    assert isinstance(schema, pa.DataFrameSchema)66    if multi_index:67        assert isinstance(schema.index, pa.MultiIndex)68    else:69        assert isinstance(schema.index, pa.Index)70    with pytest.warns(71        UserWarning,72        match="^This .+ is an inferred schema that hasn't been modified",73    ):74        schema.validate(dataframe)75    # modifying an inferred schema should set _is_inferred to False76    schema_with_added_cols = schema.add_columns({"foo": pa.Column(pa.String)})77    assert schema._is_inferred78    assert not schema_with_added_cols._is_inferred...

schema_inference.py

Source:schema_inference.py

...16    :returns: DataFrameSchema or SeriesSchema17    :raises: TypeError if pandas_obj is not expected type.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        },...

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.