How to use _dataframe_strategy method in pandera

Best Python code snippet using pandera_python

strategies.py

Source:strategies.py

...864        if strategy is None:865            strategy = pandas_dtype_strategy(col.dtype)866        return strategy867    @composite868    def _dataframe_strategy(draw):869        row_strategy_checks = []870        undefined_strat_df_checks = []871        for check in checks:872            if hasattr(check, "strategy") or check.element_wise:873                # we can apply element-wise checks defined at the dataframe874                # level to the row strategy875                row_strategy_checks.append(check)876            else:877                undefined_strat_df_checks.append(check)878        # expand column set to generate column names for columns where879        # regex=True.880        expanded_columns = {}881        for col_name, column in columns.items():882            if unique and col_name in unique:883                # if the column is in the set of columns specified in `unique`,884                # make the column strategy independently unique. This is885                # technically stricter than it should be, since the list of886                # columns in `unique` are required to be jointly unique, but887                # this is a simple solution that produces synthetic data that888                # fulfills the uniqueness constraints of the dataframe.889                column = deepcopy(column)890                column.unique = True891            if not column.regex:892                expanded_columns[col_name] = column893            else:894                regex_columns = draw(895                    st.lists(896                        st.from_regex(column.name, fullmatch=True),897                        min_size=n_regex_columns,898                        max_size=n_regex_columns,899                        unique=True,900                    )901                )902                for regex_col in regex_columns:903                    expanded_columns[regex_col] = deepcopy(column).set_name(904                        regex_col905                    )906        # collect all non-element-wise column checks with undefined strategies907        undefined_strat_column_checks: Dict[str, list] = defaultdict(list)908        for col_name, column in expanded_columns.items():909            undefined_strat_column_checks[col_name].extend(910                check911                for check in column.checks912                if not hasattr(check, "strategy") and not check.element_wise913            )914        # override the column datatype with dataframe-level datatype if915        # specified916        col_dtypes = {917            col_name: str(col.dtype)918            if pandera_dtype is None919            else str(pandera_dtype)920            for col_name, col in expanded_columns.items()921        }922        nullable_columns = {923            col_name: col.nullable924            for col_name, col in expanded_columns.items()925        }926        row_strategy = None927        if row_strategy_checks:928            row_strategy = st.fixed_dictionaries(929                {930                    col_name: make_row_strategy(col, row_strategy_checks)931                    for col_name, col in expanded_columns.items()932                }933            )934        strategy = pdst.data_frames(935            columns=[936                column.strategy_component()937                for column in expanded_columns.values()938            ],939            rows=row_strategy,940            index=pdst.range_indexes(941                min_size=0 if size is None else size, max_size=size942            ),943        )944        # this is a hack to convert np.str_ data values into native python str.945        for col_name, col_dtype in col_dtypes.items():946            if col_dtype in {"object", "str"} or col_dtype.startswith(947                "string"948            ):949                # pylint: disable=cell-var-from-loop,undefined-loop-variable950                strategy = strategy.map(951                    lambda df: df.assign(**{col_name: df[col_name].map(str)})952                )953        strategy = strategy.map(954            lambda df: df if df.empty else df.astype(col_dtypes)955        )956        if size is not None and size > 0 and any(nullable_columns.values()):957            strategy = null_dataframe_masks(strategy, nullable_columns)958        if index is not None:959            strategy = set_pandas_index(strategy, index)960        for check in undefined_strat_df_checks:961            strategy = undefined_check_strategy(strategy, check)962        for col_name, column_checks in undefined_strat_column_checks.items():963            for check in column_checks:  # type: ignore964                strategy = undefined_check_strategy(965                    strategy, check, column=col_name966                )967        return draw(strategy)968    return _dataframe_strategy()969# pylint: disable=unused-argument970def multiindex_strategy(971    pandera_dtype: Optional[DataType] = None,972    strategy: Optional[SearchStrategy] = None,973    *,974    indexes: Optional[List] = None,975    size: Optional[int] = None,976):977    """Strategy to generate a pandas MultiIndex object.978    :param pandera_dtype: :class:`pandera.dtypes.DataType` instance.979    :param strategy: an optional hypothesis strategy. If specified, the980        pandas dtype strategy will be chained onto this strategy.981    :param indexes: a list of :class:`~pandera.schema_components.Index`982        objects....

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.