Universe

A class to help with running the analysis of a single universe contained within a multiverse analysis.

Attributes:

Name	Type	Description
run_no		The run number of the multiverse analysis.
universe_id		The id of the universe.
universe		The universe settings.
output_dir		The directory to which the output should be written.
metrics		A dictionary containing the metrics to be computed.
fairness_metrics		A dictionary containing the fairness metrics to be computed.
ts_start		The timestamp of the start of the analysis.
ts_end		The timestamp of the end of the analysis.

Source code in multiversum/universe.py

class Universe:
    """
    A class to help with running the analysis of a single universe contained
    within a multiverse analysis.

    Attributes:
        run_no: The run number of the multiverse analysis.
        universe_id: The id of the universe.
        universe: The universe settings.
        output_dir: The directory to which the output should be written.
        metrics: A dictionary containing the metrics to be computed.
        fairness_metrics: A dictionary containing the fairness metrics to be
            computed.
        ts_start: The timestamp of the start of the analysis.
        ts_end: The timestamp of the end of the analysis.
    """

    metrics = None
    fairness_metrics = None
    ts_start = None
    ts_end = None

    def __init__(
        self,
        settings: Union[str, Dict[str, Any]],
        metrics: Optional[Dict[str, Callable]] = None,
        fairness_metrics: Optional[Dict[str, Callable]] = None,
        set_seed: bool = True,
    ) -> None:
        """
        Initialize the Universe class.

        The arguments should be passed in from the larger multiverse analysis.

        Args:
            settings: The settings for the universe analysis. This can usually
                just be passed along from the multiverse analysis. You only need
                to specify this yourself when developing / trying out an
                analysis. Possible keys in the dictionary are:
                - dimensions: The specified universe dimensions. This is the
                    only required information.
                - run_no: The run number of the multiverse analysis.
                - seed: The seed to use for analyses.
                - universe_id: The id of the universe.
                output_dir: The directory to which the output should be written.
            metrics: A dictionary containing the metrics to be computed.
                Pass an empty dictionary to not compute any.
            fairness_metrics: A dictionary containing the fairness metrics to be
                computed. (These are cumputed with awareness of groups.)
                Pass an empty dictionary to not compute any.
            set_seed: Whether to use the seed provided in the settings.
                Defaults to True. Please note, that this only sets the seed in
                the Python random module and numpy.
        """
        self.ts_start = time.time()

        # Extract settings
        parsed_settings = (
            json.loads(settings) if isinstance(settings, str) else settings
        )
        self.run_no = parsed_settings["run_no"] if "run_no" in parsed_settings else 0
        self.universe_id = (
            parsed_settings["universe_id"]
            if "universe_id" in parsed_settings
            else "no-universe-id-provided"
        )
        self.dimensions = parsed_settings["dimensions"]
        self.seed = parsed_settings["seed"] if "seed" in parsed_settings else 0
        self.output_dir = (
            Path(parsed_settings["output_dir"])
            if "output_dir" in parsed_settings
            else Path("./output")
        )

        self.metrics = metrics
        self.fairness_metrics = fairness_metrics

        if self.dimensions is None:
            warnings.warn("No dimensions specified for universe analysis.")

        if set_seed:
            random.seed(self.seed)
            np.random.seed(self.seed)

    def get_execution_time(self) -> float:
        """
        Gets the execution time of the universe analysis.

        Returns:
            float: The execution time in seconds.
        """
        if self.ts_end is None:
            print("Stopping execution_time clock.")
            self.ts_end = time.time()
        return self.ts_end - self.ts_start

    def _add_universe_info(
        self, data: pd.DataFrame, overwrite_dimensions: Optional[dict] = None
    ) -> pd.DataFrame:
        """
        Add general universe / run info to the dataframe.

        Args:
            data: The dataframe to which the info should be added.
            overwrite_dimensions: A dictionary containing dimensions to overwrite. (optional)

        Returns:
            The dataframe with the added info.
        """
        return add_universe_info_to_df(
            data=data,
            universe_id=self.universe_id,
            run_no=self.run_no,
            dimensions=self.dimensions
            if overwrite_dimensions is None
            else overwrite_dimensions,
            execution_time=self.get_execution_time(),
        )

    def save_data(self, data: pd.DataFrame, add_info: bool = True) -> None:
        """
        Save the data to the appropriate file for this Universe.

        Args:
            data: The dataframe to be saved.
            add_info: Whether to add universe info to the dataframe. (optional)

        Returns:
            None
        """
        # Add universe data to the dataframe
        if add_info:
            data = self._add_universe_info(data=data)

        # Path management
        target_dir = self.output_dir / "runs" / str(self.run_no) / "data"
        # Make sure the directory exists
        target_dir.mkdir(parents=True, exist_ok=True)
        filename = f"d_{str(self.run_no)}_{self.universe_id}.csv"
        filepath = target_dir / filename
        if filepath.exists():
            warnings.warn(f"File {filepath} already exists. Overwriting it.")
        # Write the file
        data.to_csv(filepath, index=False)

    def compute_sub_universe_metrics(
        self,
        sub_universe: Dict,
        y_pred_prob: pd.Series,
        y_test: pd.Series,
        org_test: pd.DataFrame,
    ) -> Tuple[dict, dict]:
        """
        Computes a set of metrics for a given sub-universe.

        Args:
            sub_universe: A dictionary containing the parameters for the
                sub-universe.
            y_pred_prob: A pandas series containing the predicted
                probabilities.
            y_test: A pandas series containing the true labels.
            org_test: A pandas dataframe containing the test data, including
                variables that were not used as features.

        Returns:
            A tuple containing two dics: explicit fairness metrics and
                performance metrics split by fairness groups.
        """
        # Determine cutoff for predictions
        cutoff_type, cutoff_value = sub_universe["cutoff"].split("_")
        cutoff_value = float(cutoff_value)

        if cutoff_type == "raw":
            threshold = cutoff_value
        elif cutoff_type == "quantile":
            probabilities_true = y_pred_prob[:, 1]
            threshold = np.quantile(probabilities_true, cutoff_value)

        fairness_grouping = sub_universe["eval_fairness_grouping"]
        if fairness_grouping == "majority-minority":
            fairness_group_column = "majmin"
        elif fairness_grouping == "race-all":
            fairness_group_column = "RAC1P"

        y_pred = predict_w_threshold(y_pred_prob, threshold)

        try:
            from fairlearn.metrics import MetricFrame
            from sklearn.metrics import (
                accuracy_score,
                precision_score,
                balanced_accuracy_score,
                f1_score,
            )
            from fairlearn.metrics import (
                false_positive_rate,
                false_negative_rate,
                selection_rate,
                count,
            )
            from fairlearn.metrics import (
                equalized_odds_difference,
                equalized_odds_ratio,
                demographic_parity_difference,
                demographic_parity_ratio,
            )

            metrics = (
                {
                    "accuracy": accuracy_score,
                    "balanced accuracy": balanced_accuracy_score,
                    "f1": f1_score,
                    "precision": precision_score,
                    "false positive rate": false_positive_rate,
                    "false negative rate": false_negative_rate,
                    "selection rate": selection_rate,
                    "count": count,
                }
                if self.metrics is None
                else self.metrics
            )

            fairness_metrics = (
                {
                    "equalized_odds_difference": equalized_odds_difference,
                    "equalized_odds_ratio": equalized_odds_ratio,
                    "demographic_parity_difference": demographic_parity_difference,
                    "demographic_parity_ratio": demographic_parity_ratio,
                }
                if self.fairness_metrics is None
                else self.fairness_metrics
            )

            # Compute fairness metrics
            fairness_dict = {
                name: metric(
                    y_true=y_test,
                    y_pred=y_pred,
                    sensitive_features=org_test[fairness_group_column],
                )
                for name, metric in fairness_metrics.items()
            }

            # Compute "normal" metrics (but split by fairness column)
            metric_frame = MetricFrame(
                metrics=metrics,
                y_true=y_test,
                y_pred=y_pred,
                sensitive_features=org_test[fairness_group_column],
            )

            return (fairness_dict, metric_frame)
        except ImportError:
            raise ImportError(
                "Packages fairlearn and scikit-learn are required for computing metrics."
            )

    def visit_sub_universe(
        self,
        sub_universe: Dict[str, Any],
        y_pred_prob: pd.Series,
        y_test: pd.Series,
        org_test: pd.Series,
        filter_data: Callable,
    ) -> pd.DataFrame:
        """
        Visit a sub-universe and compute the metrics for it.

        Sub-universes correspond to theoretically distinct universes of
        decisions, which can be computed without re-fitting a model. The
        distinction has only been made to improve performance by not having to
        compute these universes from scratch.

        Args:
            sub_universe: A dictionary containing the parameters for the
                sub-universe.
            y_pred_prob: A pandas series containing the predicted
                probabilities.
            y_test: A pandas series containing the true labels.
            org_test: A pandas dataframe containing the test data, including
                variables that were not used as features.
            filter_data: A function that filters data for each sub-universe.
                The function is called for each sub-universe with its
                respective settings and expected to return a pandas Series
                of booleans.

        Returns:
            A pandas dataframe containing the metrics for the sub-universe.
        """
        final_output = self._add_universe_info(
            data=pd.DataFrame(index=[self.universe_id]),
            overwrite_dimensions=sub_universe,
        )

        data_mask = filter_data(sub_universe=sub_universe, org_test=org_test)
        final_output["test_size_n"] = data_mask.sum()
        final_output["test_size_frac"] = data_mask.sum() / len(data_mask)

        # Compute metrics for majority-minority split
        fairness_dict, metric_frame = self.compute_sub_universe_metrics(
            sub_universe,
            y_pred_prob[data_mask],
            y_test[data_mask],
            org_test[data_mask],
        )

        # Add main fairness metrics to final_output
        final_output = add_dict_to_df(final_output, fairness_dict, prefix="fair_main_")
        final_output = add_dict_to_df(
            final_output, dict(metric_frame.overall), prefix="perf_ovrl_"
        )

        # Add group metrics to final output
        final_output = add_dict_to_df(
            final_output, flatten_dict(metric_frame.by_group), prefix="perf_grp_"
        )

        return final_output

    def generate_sub_universes(self) -> List[dict]:
        """
        Generate the sub-universes for the given universe settings.

        Returns:
            A list of dictionaries containing the sub-universes.
        """
        # Wrap all non-lists in the universe to make them work with generate_multiverse_grid
        universe_all_lists = {k: list_wrap(v) for k, v in self.dimensions.items()}

        # Within-Universe variation
        return generate_multiverse_grid(universe_all_lists)

    def compute_final_metrics(
        self,
        y_pred_prob: pd.Series,
        y_test: pd.Series,
        org_test: pd.Series,
        filter_data: Callable,
        save: bool = True,
    ) -> pd.DataFrame:
        """
        Generate the final output for the given universe settings.

        Args:
            y_pred_prob: A pandas series containing the predicted
                probabilities.
            y_test: A pandas series containing the true labels.
            org_test: A pandas dataframe containing the test data, including
                variables that were not used as features.
            filter_data: A function that filters data for each sub-universe.
                The function is called for each sub-universe with its
                respective settings and expected to return a pandas Series
                of booleans.
            save: Whether to save the output to a file. (optional)

        Returns:
            A pandas dataframe containing the final output.
        """
        # Within-Universe variation
        sub_universes = self.generate_sub_universes()

        final_outputs = list()
        for sub_universe in sub_universes:
            final_outputs.append(
                self.visit_sub_universe(
                    sub_universe=sub_universe,
                    y_pred_prob=y_pred_prob,
                    y_test=y_test,
                    org_test=org_test,
                    filter_data=filter_data,
                ).reset_index(drop=True)
            )
        final_output = pd.concat(final_outputs)

        # Write the final output file
        if save:
            self.save_data(final_output, add_info=False)

        return final_output

__init__(settings, metrics=None, fairness_metrics=None, set_seed=True)

Initialize the Universe class.

The arguments should be passed in from the larger multiverse analysis.

Parameters:

Name	Type	Description	Default
settings	Union[str, Dict[str, Any]]	The settings for the universe analysis. This can usually just be passed along from the multiverse analysis. You only need to specify this yourself when developing / trying out an analysis. Possible keys in the dictionary are: - dimensions: The specified universe dimensions. This is the only required information. - run_no: The run number of the multiverse analysis. - seed: The seed to use for analyses. - universe_id: The id of the universe. output_dir: The directory to which the output should be written.	required
metrics	Optional[Dict[str, Callable]]	A dictionary containing the metrics to be computed. Pass an empty dictionary to not compute any.	None
fairness_metrics	Optional[Dict[str, Callable]]	A dictionary containing the fairness metrics to be computed. (These are cumputed with awareness of groups.) Pass an empty dictionary to not compute any.	None
set_seed	bool	Whether to use the seed provided in the settings. Defaults to True. Please note, that this only sets the seed in the Python random module and numpy.	True

Source code in multiversum/universe.py

def __init__(
    self,
    settings: Union[str, Dict[str, Any]],
    metrics: Optional[Dict[str, Callable]] = None,
    fairness_metrics: Optional[Dict[str, Callable]] = None,
    set_seed: bool = True,
) -> None:
    """
    Initialize the Universe class.

    The arguments should be passed in from the larger multiverse analysis.

    Args:
        settings: The settings for the universe analysis. This can usually
            just be passed along from the multiverse analysis. You only need
            to specify this yourself when developing / trying out an
            analysis. Possible keys in the dictionary are:
            - dimensions: The specified universe dimensions. This is the
                only required information.
            - run_no: The run number of the multiverse analysis.
            - seed: The seed to use for analyses.
            - universe_id: The id of the universe.
            output_dir: The directory to which the output should be written.
        metrics: A dictionary containing the metrics to be computed.
            Pass an empty dictionary to not compute any.
        fairness_metrics: A dictionary containing the fairness metrics to be
            computed. (These are cumputed with awareness of groups.)
            Pass an empty dictionary to not compute any.
        set_seed: Whether to use the seed provided in the settings.
            Defaults to True. Please note, that this only sets the seed in
            the Python random module and numpy.
    """
    self.ts_start = time.time()

    # Extract settings
    parsed_settings = (
        json.loads(settings) if isinstance(settings, str) else settings
    )
    self.run_no = parsed_settings["run_no"] if "run_no" in parsed_settings else 0
    self.universe_id = (
        parsed_settings["universe_id"]
        if "universe_id" in parsed_settings
        else "no-universe-id-provided"
    )
    self.dimensions = parsed_settings["dimensions"]
    self.seed = parsed_settings["seed"] if "seed" in parsed_settings else 0
    self.output_dir = (
        Path(parsed_settings["output_dir"])
        if "output_dir" in parsed_settings
        else Path("./output")
    )

    self.metrics = metrics
    self.fairness_metrics = fairness_metrics

    if self.dimensions is None:
        warnings.warn("No dimensions specified for universe analysis.")

    if set_seed:
        random.seed(self.seed)
        np.random.seed(self.seed)

compute_final_metrics(y_pred_prob, y_test, org_test, filter_data, save=True)

Generate the final output for the given universe settings.

Parameters:

Name	Type	Description	Default
y_pred_prob	Series	A pandas series containing the predicted probabilities.	required
y_test	Series	A pandas series containing the true labels.	required
org_test	Series	A pandas dataframe containing the test data, including variables that were not used as features.	required
filter_data	Callable	A function that filters data for each sub-universe. The function is called for each sub-universe with its respective settings and expected to return a pandas Series of booleans.	required
save	bool	Whether to save the output to a file. (optional)	True

Returns:

Type	Description
DataFrame	A pandas dataframe containing the final output.

Source code in multiversum/universe.py

def compute_final_metrics(
    self,
    y_pred_prob: pd.Series,
    y_test: pd.Series,
    org_test: pd.Series,
    filter_data: Callable,
    save: bool = True,
) -> pd.DataFrame:
    """
    Generate the final output for the given universe settings.

    Args:
        y_pred_prob: A pandas series containing the predicted
            probabilities.
        y_test: A pandas series containing the true labels.
        org_test: A pandas dataframe containing the test data, including
            variables that were not used as features.
        filter_data: A function that filters data for each sub-universe.
            The function is called for each sub-universe with its
            respective settings and expected to return a pandas Series
            of booleans.
        save: Whether to save the output to a file. (optional)

    Returns:
        A pandas dataframe containing the final output.
    """
    # Within-Universe variation
    sub_universes = self.generate_sub_universes()

    final_outputs = list()
    for sub_universe in sub_universes:
        final_outputs.append(
            self.visit_sub_universe(
                sub_universe=sub_universe,
                y_pred_prob=y_pred_prob,
                y_test=y_test,
                org_test=org_test,
                filter_data=filter_data,
            ).reset_index(drop=True)
        )
    final_output = pd.concat(final_outputs)

    # Write the final output file
    if save:
        self.save_data(final_output, add_info=False)

    return final_output

compute_sub_universe_metrics(sub_universe, y_pred_prob, y_test, org_test)

Computes a set of metrics for a given sub-universe.

Parameters:

Name	Type	Description	Default
sub_universe	Dict	A dictionary containing the parameters for the sub-universe.	required
y_pred_prob	Series	A pandas series containing the predicted probabilities.	required
y_test	Series	A pandas series containing the true labels.	required
org_test	DataFrame	A pandas dataframe containing the test data, including variables that were not used as features.	required

Returns:

Type	Description
Tuple[dict, dict]	A tuple containing two dics: explicit fairness metrics and performance metrics split by fairness groups.

Source code in multiversum/universe.py

def compute_sub_universe_metrics(
    self,
    sub_universe: Dict,
    y_pred_prob: pd.Series,
    y_test: pd.Series,
    org_test: pd.DataFrame,
) -> Tuple[dict, dict]:
    """
    Computes a set of metrics for a given sub-universe.

    Args:
        sub_universe: A dictionary containing the parameters for the
            sub-universe.
        y_pred_prob: A pandas series containing the predicted
            probabilities.
        y_test: A pandas series containing the true labels.
        org_test: A pandas dataframe containing the test data, including
            variables that were not used as features.

    Returns:
        A tuple containing two dics: explicit fairness metrics and
            performance metrics split by fairness groups.
    """
    # Determine cutoff for predictions
    cutoff_type, cutoff_value = sub_universe["cutoff"].split("_")
    cutoff_value = float(cutoff_value)

    if cutoff_type == "raw":
        threshold = cutoff_value
    elif cutoff_type == "quantile":
        probabilities_true = y_pred_prob[:, 1]
        threshold = np.quantile(probabilities_true, cutoff_value)

    fairness_grouping = sub_universe["eval_fairness_grouping"]
    if fairness_grouping == "majority-minority":
        fairness_group_column = "majmin"
    elif fairness_grouping == "race-all":
        fairness_group_column = "RAC1P"

    y_pred = predict_w_threshold(y_pred_prob, threshold)

    try:
        from fairlearn.metrics import MetricFrame
        from sklearn.metrics import (
            accuracy_score,
            precision_score,
            balanced_accuracy_score,
            f1_score,
        )
        from fairlearn.metrics import (
            false_positive_rate,
            false_negative_rate,
            selection_rate,
            count,
        )
        from fairlearn.metrics import (
            equalized_odds_difference,
            equalized_odds_ratio,
            demographic_parity_difference,
            demographic_parity_ratio,
        )

        metrics = (
            {
                "accuracy": accuracy_score,
                "balanced accuracy": balanced_accuracy_score,
                "f1": f1_score,
                "precision": precision_score,
                "false positive rate": false_positive_rate,
                "false negative rate": false_negative_rate,
                "selection rate": selection_rate,
                "count": count,
            }
            if self.metrics is None
            else self.metrics
        )

        fairness_metrics = (
            {
                "equalized_odds_difference": equalized_odds_difference,
                "equalized_odds_ratio": equalized_odds_ratio,
                "demographic_parity_difference": demographic_parity_difference,
                "demographic_parity_ratio": demographic_parity_ratio,
            }
            if self.fairness_metrics is None
            else self.fairness_metrics
        )

        # Compute fairness metrics
        fairness_dict = {
            name: metric(
                y_true=y_test,
                y_pred=y_pred,
                sensitive_features=org_test[fairness_group_column],
            )
            for name, metric in fairness_metrics.items()
        }

        # Compute "normal" metrics (but split by fairness column)
        metric_frame = MetricFrame(
            metrics=metrics,
            y_true=y_test,
            y_pred=y_pred,
            sensitive_features=org_test[fairness_group_column],
        )

        return (fairness_dict, metric_frame)
    except ImportError:
        raise ImportError(
            "Packages fairlearn and scikit-learn are required for computing metrics."
        )

generate_sub_universes()

Generate the sub-universes for the given universe settings.

Returns:

Type	Description
List[dict]	A list of dictionaries containing the sub-universes.

Source code in multiversum/universe.py

def generate_sub_universes(self) -> List[dict]:
    """
    Generate the sub-universes for the given universe settings.

    Returns:
        A list of dictionaries containing the sub-universes.
    """
    # Wrap all non-lists in the universe to make them work with generate_multiverse_grid
    universe_all_lists = {k: list_wrap(v) for k, v in self.dimensions.items()}

    # Within-Universe variation
    return generate_multiverse_grid(universe_all_lists)

get_execution_time()

Gets the execution time of the universe analysis.

Returns:

Name	Type	Description
float	float	The execution time in seconds.

Source code in multiversum/universe.py

def get_execution_time(self) -> float:
    """
    Gets the execution time of the universe analysis.

    Returns:
        float: The execution time in seconds.
    """
    if self.ts_end is None:
        print("Stopping execution_time clock.")
        self.ts_end = time.time()
    return self.ts_end - self.ts_start

save_data(data, add_info=True)

Save the data to the appropriate file for this Universe.

Parameters:

Name	Type	Description	Default
data	DataFrame	The dataframe to be saved.	required
add_info	bool	Whether to add universe info to the dataframe. (optional)	True

Returns:

Type	Description
None	None

Source code in multiversum/universe.py

def save_data(self, data: pd.DataFrame, add_info: bool = True) -> None:
    """
    Save the data to the appropriate file for this Universe.

    Args:
        data: The dataframe to be saved.
        add_info: Whether to add universe info to the dataframe. (optional)

    Returns:
        None
    """
    # Add universe data to the dataframe
    if add_info:
        data = self._add_universe_info(data=data)

    # Path management
    target_dir = self.output_dir / "runs" / str(self.run_no) / "data"
    # Make sure the directory exists
    target_dir.mkdir(parents=True, exist_ok=True)
    filename = f"d_{str(self.run_no)}_{self.universe_id}.csv"
    filepath = target_dir / filename
    if filepath.exists():
        warnings.warn(f"File {filepath} already exists. Overwriting it.")
    # Write the file
    data.to_csv(filepath, index=False)

visit_sub_universe(sub_universe, y_pred_prob, y_test, org_test, filter_data)

Visit a sub-universe and compute the metrics for it.

Sub-universes correspond to theoretically distinct universes of decisions, which can be computed without re-fitting a model. The distinction has only been made to improve performance by not having to compute these universes from scratch.

Parameters:

Name	Type	Description	Default
sub_universe	Dict[str, Any]	A dictionary containing the parameters for the sub-universe.	required
y_pred_prob	Series	A pandas series containing the predicted probabilities.	required
y_test	Series	A pandas series containing the true labels.	required
org_test	Series	A pandas dataframe containing the test data, including variables that were not used as features.	required
filter_data	Callable	A function that filters data for each sub-universe. The function is called for each sub-universe with its respective settings and expected to return a pandas Series of booleans.	required

Returns:

Type	Description
DataFrame	A pandas dataframe containing the metrics for the sub-universe.

Source code in multiversum/universe.py

def visit_sub_universe(
    self,
    sub_universe: Dict[str, Any],
    y_pred_prob: pd.Series,
    y_test: pd.Series,
    org_test: pd.Series,
    filter_data: Callable,
) -> pd.DataFrame:
    """
    Visit a sub-universe and compute the metrics for it.

    Sub-universes correspond to theoretically distinct universes of
    decisions, which can be computed without re-fitting a model. The
    distinction has only been made to improve performance by not having to
    compute these universes from scratch.

    Args:
        sub_universe: A dictionary containing the parameters for the
            sub-universe.
        y_pred_prob: A pandas series containing the predicted
            probabilities.
        y_test: A pandas series containing the true labels.
        org_test: A pandas dataframe containing the test data, including
            variables that were not used as features.
        filter_data: A function that filters data for each sub-universe.
            The function is called for each sub-universe with its
            respective settings and expected to return a pandas Series
            of booleans.

    Returns:
        A pandas dataframe containing the metrics for the sub-universe.
    """
    final_output = self._add_universe_info(
        data=pd.DataFrame(index=[self.universe_id]),
        overwrite_dimensions=sub_universe,
    )

    data_mask = filter_data(sub_universe=sub_universe, org_test=org_test)
    final_output["test_size_n"] = data_mask.sum()
    final_output["test_size_frac"] = data_mask.sum() / len(data_mask)

    # Compute metrics for majority-minority split
    fairness_dict, metric_frame = self.compute_sub_universe_metrics(
        sub_universe,
        y_pred_prob[data_mask],
        y_test[data_mask],
        org_test[data_mask],
    )

    # Add main fairness metrics to final_output
    final_output = add_dict_to_df(final_output, fairness_dict, prefix="fair_main_")
    final_output = add_dict_to_df(
        final_output, dict(metric_frame.overall), prefix="perf_ovrl_"
    )

    # Add group metrics to final output
    final_output = add_dict_to_df(
        final_output, flatten_dict(metric_frame.by_group), prefix="perf_grp_"
    )

    return final_output