How to use _format_groupby_input method in pandera

Best Python code snippet using pandera_python

checks.py

Source:checks.py

...238    def statistics(self, statistics):239        """Set check statistics."""240        self._statistics = statistics241    @staticmethod242    def _format_groupby_input(243        groupby_obj: GroupbyObject,244        groups: Optional[List[str]],245    ) -> Union[Dict[str, Union[pd.Series, pd.DataFrame]]]:246        """Format groupby object into dict of groups to Series or DataFrame.247        :param groupby_obj: a pandas groupby object.248        :param groups: only include these groups in the output.249        :returns: dictionary mapping group names to Series or DataFrame.250        """251        if groups is None:252            return dict(list(groupby_obj))253        group_keys = set(group_key for group_key, _ in groupby_obj)254        invalid_groups = [g for g in groups if g not in group_keys]255        if invalid_groups:256            raise KeyError(257                f"groups {invalid_groups} provided in `groups` argument not a valid group "258                f"key. Valid group keys: {group_keys}"259            )260        return {261            group_key: group262            for group_key, group in groupby_obj263            if group_key in groups264        }265    def _prepare_series_input(266        self,267        df_or_series: Union[pd.Series, pd.DataFrame],268        column: Optional[str] = None,269    ) -> SeriesCheckObj:270        """Prepare input for Column check.271        :param pd.Series series: one-dimensional ndarray with axis labels272            (including time series).273        :param pd.DataFrame dataframe_context: optional dataframe to supply274            when checking a Column in a DataFrameSchema.275        :returns: a Series, or a dictionary mapping groups to Series276            to be used by `_check_fn` and `_vectorized_check`277        """278        if check_utils.is_field(df_or_series):279            return df_or_series280        elif self.groupby is None:281            return df_or_series[column]282        elif isinstance(self.groupby, list):283            return self._format_groupby_input(284                df_or_series.groupby(self.groupby)[column],285                self.groups,286            )287        elif callable(self.groupby):288            return self._format_groupby_input(289                self.groupby(df_or_series)[column],290                self.groups,291            )292        raise TypeError("Type %s not recognized for `groupby` argument.")293    def _prepare_dataframe_input(294        self, dataframe: pd.DataFrame295    ) -> DataFrameCheckObj:296        """Prepare input for DataFrameSchema check.297        :param dataframe: dataframe to validate.298        :returns: a DataFrame, or a dictionary mapping groups to pd.DataFrame299            to be used by `_check_fn` and `_vectorized_check`300        """301        if self.groupby is None:302            return dataframe303        groupby_obj = dataframe.groupby(self.groupby)304        return self._format_groupby_input(groupby_obj, self.groups)305    def __call__(306        self,307        df_or_series: Union[pd.DataFrame, pd.Series],308        column: Optional[str] = None,309    ) -> CheckResult:310        # pylint: disable=too-many-branches311        """Validate pandas DataFrame or Series.312        :param df_or_series: pandas DataFrame of Series to validate.313        :param column: for dataframe checks, apply the check function to this314            column.315        :returns: CheckResult tuple containing:316            ``check_output``: boolean scalar, ``Series`` or ``DataFrame``317            indicating which elements passed the check.318            ``check_passed``: boolean scalar that indicating whether the check...

hypotheses.py

Source:hypotheses.py

...164            )165        if self.is_one_sample_test:166            return dataframe[self.samples[0]]167        check_obj = [(sample, dataframe[sample]) for sample in self.samples]168        return self._format_groupby_input(check_obj, self.samples)169    def _relationships(self, relationship: Union[str, Callable]):170        """Impose a relationship on a supplied Test function.171        :param relationship: represents what relationship conditions are172            imposed on the hypothesis test. A function or lambda function can173            be supplied. If a string is provided, a lambda function will be174            returned from Hypothesis.relationships. Available relationships175            are: "greater_than", "less_than", "not_equal"176        """177        if isinstance(relationship, str):178            if relationship not in self.RELATIONSHIPS:179                raise errors.SchemaInitError(180                    f"The relationship {relationship} isn't a built in method"181                )182            relationship = self.RELATIONSHIPS[relationship]...

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.