pydantic_evals.reporting

ReportCase

Bases: BaseModel

A single case in an evaluation report.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

class ReportCase(BaseModel):
    """A single case in an evaluation report."""

    name: str
    """The name of the [case][pydantic_evals.Case]."""
    inputs: Any
    """The inputs to the task, from [`Case.inputs`][pydantic_evals.Case.inputs]."""
    metadata: Any
    """Any metadata associated with the case, from [`Case.metadata`][pydantic_evals.Case.metadata]."""
    expected_output: Any
    """The expected output of the task, from [`Case.expected_output`][pydantic_evals.Case.expected_output]."""
    output: Any
    """The output of the task execution."""

    metrics: dict[str, float | int]
    attributes: dict[str, Any]

    scores: dict[str, EvaluationResult[int | float]] = field(init=False)
    labels: dict[str, EvaluationResult[str]] = field(init=False)
    assertions: dict[str, EvaluationResult[bool]] = field(init=False)

    task_duration: float
    total_duration: float  # includes evaluator execution time

    # TODO(DavidM): Drop these once we can reference child spans in details panel:
    trace_id: str
    span_id: str

name instance-attribute

name: str

The name of the case.

inputs instance-attribute

inputs: Any

The inputs to the task, from Case.inputs.

metadata instance-attribute

metadata: Any

Any metadata associated with the case, from Case.metadata.

expected_output instance-attribute

expected_output: Any

The expected output of the task, from Case.expected_output.

output instance-attribute

output: Any

The output of the task execution.

ReportCaseAggregate

Bases: BaseModel

A synthetic case that summarizes a set of cases.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

class ReportCaseAggregate(BaseModel):
    """A synthetic case that summarizes a set of cases."""

    name: str

    scores: dict[str, float | int]
    labels: dict[str, dict[str, float]]
    metrics: dict[str, float | int]
    assertions: float | None
    task_duration: float
    total_duration: float

    @staticmethod
    def average(cases: list[ReportCase]) -> ReportCaseAggregate:
        """Produce a synthetic "summary" case by averaging quantitative attributes."""
        num_cases = len(cases)
        if num_cases == 0:
            return ReportCaseAggregate(
                name='Averages',
                scores={},
                labels={},
                metrics={},
                assertions=None,
                task_duration=0.0,
                total_duration=0.0,
            )

        def _scores_averages(scores_by_name: list[dict[str, int | float | bool]]) -> dict[str, float]:
            counts_by_name: dict[str, int] = defaultdict(int)
            sums_by_name: dict[str, float] = defaultdict(float)
            for sbn in scores_by_name:
                for name, score in sbn.items():
                    counts_by_name[name] += 1
                    sums_by_name[name] += score
            return {name: sums_by_name[name] / counts_by_name[name] for name in sums_by_name}

        def _labels_averages(labels_by_name: list[dict[str, str]]) -> dict[str, dict[str, float]]:
            counts_by_name: dict[str, int] = defaultdict(int)
            sums_by_name: dict[str, dict[str, float]] = defaultdict(lambda: defaultdict(float))
            for lbn in labels_by_name:
                for name, label in lbn.items():
                    counts_by_name[name] += 1
                    sums_by_name[name][label] += 1
            return {
                name: {value: count / counts_by_name[name] for value, count in sums_by_name[name].items()}
                for name in sums_by_name
            }

        average_task_duration = sum(case.task_duration for case in cases) / num_cases
        average_total_duration = sum(case.total_duration for case in cases) / num_cases

        # average_assertions: dict[str, float] = _scores_averages([{k: v.value for k, v in case.scores.items()} for case in cases])
        average_scores: dict[str, float] = _scores_averages(
            [{k: v.value for k, v in case.scores.items()} for case in cases]
        )
        average_labels: dict[str, dict[str, float]] = _labels_averages(
            [{k: v.value for k, v in case.labels.items()} for case in cases]
        )
        average_metrics: dict[str, float] = _scores_averages([case.metrics for case in cases])

        average_assertions: float | None = None
        n_assertions = sum(len(case.assertions) for case in cases)
        if n_assertions > 0:
            n_passing = sum(1 for case in cases for assertion in case.assertions.values() if assertion.value)
            average_assertions = n_passing / n_assertions

        return ReportCaseAggregate(
            name='Averages',
            scores=average_scores,
            labels=average_labels,
            metrics=average_metrics,
            assertions=average_assertions,
            task_duration=average_task_duration,
            total_duration=average_total_duration,
        )

average staticmethod

average(cases: list[ReportCase]) -> ReportCaseAggregate

Produce a synthetic "summary" case by averaging quantitative attributes.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

@staticmethod
def average(cases: list[ReportCase]) -> ReportCaseAggregate:
    """Produce a synthetic "summary" case by averaging quantitative attributes."""
    num_cases = len(cases)
    if num_cases == 0:
        return ReportCaseAggregate(
            name='Averages',
            scores={},
            labels={},
            metrics={},
            assertions=None,
            task_duration=0.0,
            total_duration=0.0,
        )

    def _scores_averages(scores_by_name: list[dict[str, int | float | bool]]) -> dict[str, float]:
        counts_by_name: dict[str, int] = defaultdict(int)
        sums_by_name: dict[str, float] = defaultdict(float)
        for sbn in scores_by_name:
            for name, score in sbn.items():
                counts_by_name[name] += 1
                sums_by_name[name] += score
        return {name: sums_by_name[name] / counts_by_name[name] for name in sums_by_name}

    def _labels_averages(labels_by_name: list[dict[str, str]]) -> dict[str, dict[str, float]]:
        counts_by_name: dict[str, int] = defaultdict(int)
        sums_by_name: dict[str, dict[str, float]] = defaultdict(lambda: defaultdict(float))
        for lbn in labels_by_name:
            for name, label in lbn.items():
                counts_by_name[name] += 1
                sums_by_name[name][label] += 1
        return {
            name: {value: count / counts_by_name[name] for value, count in sums_by_name[name].items()}
            for name in sums_by_name
        }

    average_task_duration = sum(case.task_duration for case in cases) / num_cases
    average_total_duration = sum(case.total_duration for case in cases) / num_cases

    # average_assertions: dict[str, float] = _scores_averages([{k: v.value for k, v in case.scores.items()} for case in cases])
    average_scores: dict[str, float] = _scores_averages(
        [{k: v.value for k, v in case.scores.items()} for case in cases]
    )
    average_labels: dict[str, dict[str, float]] = _labels_averages(
        [{k: v.value for k, v in case.labels.items()} for case in cases]
    )
    average_metrics: dict[str, float] = _scores_averages([case.metrics for case in cases])

    average_assertions: float | None = None
    n_assertions = sum(len(case.assertions) for case in cases)
    if n_assertions > 0:
        n_passing = sum(1 for case in cases for assertion in case.assertions.values() if assertion.value)
        average_assertions = n_passing / n_assertions

    return ReportCaseAggregate(
        name='Averages',
        scores=average_scores,
        labels=average_labels,
        metrics=average_metrics,
        assertions=average_assertions,
        task_duration=average_task_duration,
        total_duration=average_total_duration,
    )

EvaluationReport

Bases: BaseModel

A report of the results of evaluating a model on a set of cases.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

class EvaluationReport(BaseModel):
    """A report of the results of evaluating a model on a set of cases."""

    name: str
    """The name of the report."""
    cases: list[ReportCase]
    """The cases in the report."""

    def averages(self) -> ReportCaseAggregate:
        return ReportCaseAggregate.average(self.cases)

    def print(
        self,
        width: int | None = None,
        baseline: EvaluationReport | None = None,
        include_input: bool = False,
        include_output: bool = False,
        include_durations: bool = True,
        include_total_duration: bool = False,
        include_removed_cases: bool = False,
        include_averages: bool = True,
        input_config: RenderValueConfig | None = None,
        output_config: RenderValueConfig | None = None,
        score_configs: dict[str, RenderNumberConfig] | None = None,
        label_configs: dict[str, RenderValueConfig] | None = None,
        metric_configs: dict[str, RenderNumberConfig] | None = None,
        duration_config: RenderNumberConfig | None = None,
    ):  # pragma: no cover
        """Print this report to the console, optionally comparing it to a baseline report.

        If you want more control over the output, use `console_table` instead and pass it to `rich.Console.print`.
        """
        table = self.console_table(
            baseline=baseline,
            include_input=include_input,
            include_output=include_output,
            include_durations=include_durations,
            include_total_duration=include_total_duration,
            include_removed_cases=include_removed_cases,
            include_averages=include_averages,
            input_config=input_config,
            output_config=output_config,
            score_configs=score_configs,
            label_configs=label_configs,
            metric_configs=metric_configs,
            duration_config=duration_config,
        )
        Console(width=width).print(table)

    def console_table(
        self,
        baseline: EvaluationReport | None = None,
        include_input: bool = False,
        include_output: bool = False,
        include_durations: bool = True,
        include_total_duration: bool = False,
        include_removed_cases: bool = False,
        include_averages: bool = True,
        input_config: RenderValueConfig | None = None,
        output_config: RenderValueConfig | None = None,
        score_configs: dict[str, RenderNumberConfig] | None = None,
        label_configs: dict[str, RenderValueConfig] | None = None,
        metric_configs: dict[str, RenderNumberConfig] | None = None,
        duration_config: RenderNumberConfig | None = None,
    ) -> Table:
        """Return a table containing the data from this report, or the diff between this report and a baseline report.

        Optionally include input and output details.
        """
        renderer = EvaluationRenderer(
            include_input=include_input,
            include_output=include_output,
            include_durations=include_durations,
            include_total_duration=include_total_duration,
            include_removed_cases=include_removed_cases,
            include_averages=include_averages,
            input_config={**_DEFAULT_VALUE_CONFIG, **(input_config or {})},
            output_config=output_config or _DEFAULT_VALUE_CONFIG,
            score_configs=score_configs or {},
            label_configs=label_configs or {},
            metric_configs=metric_configs or {},
            duration_config=duration_config or _DEFAULT_DURATION_CONFIG,
        )
        if baseline is None:
            return renderer.build_table(self)
        else:  # pragma: no cover
            return renderer.build_diff_table(self, baseline)

    def __str__(self) -> str:
        """Return a string representation of the report."""
        table = self.console_table()
        io_file = StringIO()
        Console(file=io_file).print(table)
        return io_file.getvalue()

name instance-attribute

name: str

The name of the report.

cases instance-attribute

cases: list[ReportCase]

The cases in the report.

print

print(
    width: int | None = None,
    baseline: EvaluationReport | None = None,
    include_input: bool = False,
    include_output: bool = False,
    include_durations: bool = True,
    include_total_duration: bool = False,
    include_removed_cases: bool = False,
    include_averages: bool = True,
    input_config: RenderValueConfig | None = None,
    output_config: RenderValueConfig | None = None,
    score_configs: (
        dict[str, RenderNumberConfig] | None
    ) = None,
    label_configs: (
        dict[str, RenderValueConfig] | None
    ) = None,
    metric_configs: (
        dict[str, RenderNumberConfig] | None
    ) = None,
    duration_config: RenderNumberConfig | None = None,
)

Print this report to the console, optionally comparing it to a baseline report.

If you want more control over the output, use console_table instead and pass it to rich.Console.print.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

def print(
    self,
    width: int | None = None,
    baseline: EvaluationReport | None = None,
    include_input: bool = False,
    include_output: bool = False,
    include_durations: bool = True,
    include_total_duration: bool = False,
    include_removed_cases: bool = False,
    include_averages: bool = True,
    input_config: RenderValueConfig | None = None,
    output_config: RenderValueConfig | None = None,
    score_configs: dict[str, RenderNumberConfig] | None = None,
    label_configs: dict[str, RenderValueConfig] | None = None,
    metric_configs: dict[str, RenderNumberConfig] | None = None,
    duration_config: RenderNumberConfig | None = None,
):  # pragma: no cover
    """Print this report to the console, optionally comparing it to a baseline report.

    If you want more control over the output, use `console_table` instead and pass it to `rich.Console.print`.
    """
    table = self.console_table(
        baseline=baseline,
        include_input=include_input,
        include_output=include_output,
        include_durations=include_durations,
        include_total_duration=include_total_duration,
        include_removed_cases=include_removed_cases,
        include_averages=include_averages,
        input_config=input_config,
        output_config=output_config,
        score_configs=score_configs,
        label_configs=label_configs,
        metric_configs=metric_configs,
        duration_config=duration_config,
    )
    Console(width=width).print(table)

console_table

console_table(
    baseline: EvaluationReport | None = None,
    include_input: bool = False,
    include_output: bool = False,
    include_durations: bool = True,
    include_total_duration: bool = False,
    include_removed_cases: bool = False,
    include_averages: bool = True,
    input_config: RenderValueConfig | None = None,
    output_config: RenderValueConfig | None = None,
    score_configs: (
        dict[str, RenderNumberConfig] | None
    ) = None,
    label_configs: (
        dict[str, RenderValueConfig] | None
    ) = None,
    metric_configs: (
        dict[str, RenderNumberConfig] | None
    ) = None,
    duration_config: RenderNumberConfig | None = None,
) -> Table

Return a table containing the data from this report, or the diff between this report and a baseline report.

Optionally include input and output details.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

def console_table(
    self,
    baseline: EvaluationReport | None = None,
    include_input: bool = False,
    include_output: bool = False,
    include_durations: bool = True,
    include_total_duration: bool = False,
    include_removed_cases: bool = False,
    include_averages: bool = True,
    input_config: RenderValueConfig | None = None,
    output_config: RenderValueConfig | None = None,
    score_configs: dict[str, RenderNumberConfig] | None = None,
    label_configs: dict[str, RenderValueConfig] | None = None,
    metric_configs: dict[str, RenderNumberConfig] | None = None,
    duration_config: RenderNumberConfig | None = None,
) -> Table:
    """Return a table containing the data from this report, or the diff between this report and a baseline report.

    Optionally include input and output details.
    """
    renderer = EvaluationRenderer(
        include_input=include_input,
        include_output=include_output,
        include_durations=include_durations,
        include_total_duration=include_total_duration,
        include_removed_cases=include_removed_cases,
        include_averages=include_averages,
        input_config={**_DEFAULT_VALUE_CONFIG, **(input_config or {})},
        output_config=output_config or _DEFAULT_VALUE_CONFIG,
        score_configs=score_configs or {},
        label_configs=label_configs or {},
        metric_configs=metric_configs or {},
        duration_config=duration_config or _DEFAULT_DURATION_CONFIG,
    )
    if baseline is None:
        return renderer.build_table(self)
    else:  # pragma: no cover
        return renderer.build_diff_table(self, baseline)

__str__

__str__() -> str

Return a string representation of the report.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

def __str__(self) -> str:
    """Return a string representation of the report."""
    table = self.console_table()
    io_file = StringIO()
    Console(file=io_file).print(table)
    return io_file.getvalue()

RenderValueConfig

Bases: TypedDict

A configuration for rendering a values in an Evaluation report.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

class RenderValueConfig(TypedDict, total=False):
    """A configuration for rendering a values in an Evaluation report."""

    value_formatter: str | Callable[[Any], str]
    diff_checker: Callable[[Any, Any], bool] | None
    diff_formatter: Callable[[Any, Any], str | None] | None
    diff_style: str

RenderNumberConfig

Bases: TypedDict

A configuration for rendering a particular score or metric in an Evaluation report.

See the implementation of _RenderNumber for more clarity on how these parameters affect the rendering.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

class RenderNumberConfig(TypedDict, total=False):
    """A configuration for rendering a particular score or metric in an Evaluation report.

    See the implementation of `_RenderNumber` for more clarity on how these parameters affect the rendering.
    """

    value_formatter: str | Callable[[float | int], str]
    """The logic to use for formatting values.

    * If not provided, format as ints if all values are ints, otherwise at least one decimal place and at least four significant figures.
    * You can also use a custom string format spec, e.g. '{:.3f}'
    * You can also use a custom function, e.g. lambda x: f'{x:.3f}'
    """
    diff_formatter: str | Callable[[float | int, float | int], str | None] | None
    """The logic to use for formatting details about the diff.

    The strings produced by the value_formatter will always be included in the reports, but the diff_formatter is
    used to produce additional text about the difference between the old and new values, such as the absolute or
    relative difference.

    * If not provided, format as ints if all values are ints, otherwise at least one decimal place and at least four
        significant figures, and will include the percentage change.
    * You can also use a custom string format spec, e.g. '{:+.3f}'
    * You can also use a custom function, e.g. lambda x: f'{x:+.3f}'.
        If this function returns None, no extra diff text will be added.
    * You can also use None to never generate extra diff text.
    """
    diff_atol: float
    """The absolute tolerance for considering a difference "significant".

    A difference is "significant" if `abs(new - old) < self.diff_atol + self.diff_rtol * abs(old)`.

    If a difference is not significant, it will not have the diff styles applied. Note that we still show
    both the rendered before and after values in the diff any time they differ, even if the difference is not
    significant. (If the rendered values are exactly the same, we only show the value once.)

    If not provided, use 1e-6.
    """
    diff_rtol: float
    """The relative tolerance for considering a difference "significant".

    See the description of `diff_atol` for more details about what makes a difference "significant".

    If not provided, use 0.001 if all values are ints, otherwise 0.05.
    """
    diff_increase_style: str
    """The style to apply to diffed values that have a significant increase.

    See the description of `diff_atol` for more details about what makes a difference "significant".

    If not provided, use green for scores and red for metrics. You can also use arbitrary `rich` styles, such as "bold red".
    """
    diff_decrease_style: str
    """The style to apply to diffed values that have significant decrease.

    See the description of `diff_atol` for more details about what makes a difference "significant".

    If not provided, use red for scores and green for metrics. You can also use arbitrary `rich` styles, such as "bold red".
    """

value_formatter instance-attribute

value_formatter: str | Callable[[float | int], str]

The logic to use for formatting values.

• If not provided, format as ints if all values are ints, otherwise at least one decimal place and at least four significant figures.
• You can also use a custom string format spec, e.g. '{:.3f}'
• You can also use a custom function, e.g. lambda x: f'{x:.3f}'

diff_formatter instance-attribute

diff_formatter: (
    str
    | Callable[[float | int, float | int], str | None]
    | None
)

The logic to use for formatting details about the diff.

The strings produced by the value_formatter will always be included in the reports, but the diff_formatter is used to produce additional text about the difference between the old and new values, such as the absolute or relative difference.

• If not provided, format as ints if all values are ints, otherwise at least one decimal place and at least four significant figures, and will include the percentage change.
• You can also use a custom string format spec, e.g. '{:+.3f}'
• You can also use a custom function, e.g. lambda x: f'{x:+.3f}'. If this function returns None, no extra diff text will be added.
• You can also use None to never generate extra diff text.

diff_atol instance-attribute

diff_atol: float

The absolute tolerance for considering a difference "significant".

A difference is "significant" if abs(new - old) < self.diff_atol + self.diff_rtol * abs(old).

If a difference is not significant, it will not have the diff styles applied. Note that we still show both the rendered before and after values in the diff any time they differ, even if the difference is not significant. (If the rendered values are exactly the same, we only show the value once.)

If not provided, use 1e-6.

diff_rtol instance-attribute

diff_rtol: float

The relative tolerance for considering a difference "significant".

See the description of diff_atol for more details about what makes a difference "significant".

If not provided, use 0.001 if all values are ints, otherwise 0.05.

diff_increase_style instance-attribute

diff_increase_style: str

The style to apply to diffed values that have a significant increase.

See the description of diff_atol for more details about what makes a difference "significant".

If not provided, use green for scores and red for metrics. You can also use arbitrary rich styles, such as "bold red".

diff_decrease_style instance-attribute

diff_decrease_style: str

The style to apply to diffed values that have significant decrease.

See the description of diff_atol for more details about what makes a difference "significant".

If not provided, use red for scores and green for metrics. You can also use arbitrary rich styles, such as "bold red".

EvaluationRenderer dataclass

A class for rendering an EvalReport or the diff between two EvalReports.

Source code in pydantic_evals/pydantic_evals/reporting/__init__.py

@dataclass
class EvaluationRenderer:
    """A class for rendering an EvalReport or the diff between two EvalReports."""

    # Columns to include
    include_input: bool
    include_output: bool
    include_durations: bool
    include_total_duration: bool

    # Rows to include
    include_removed_cases: bool
    include_averages: bool

    input_config: RenderValueConfig
    output_config: RenderValueConfig
    score_configs: dict[str, RenderNumberConfig]
    label_configs: dict[str, RenderValueConfig]
    metric_configs: dict[str, RenderNumberConfig]
    duration_config: RenderNumberConfig

    def include_scores(self, report: EvaluationReport, baseline: EvaluationReport | None = None):
        return any(case.scores for case in self._all_cases(report, baseline))

    def include_labels(self, report: EvaluationReport, baseline: EvaluationReport | None = None):
        return any(case.labels for case in self._all_cases(report, baseline))

    def include_metrics(self, report: EvaluationReport, baseline: EvaluationReport | None = None):
        return any(case.metrics for case in self._all_cases(report, baseline))

    def include_assertions(self, report: EvaluationReport, baseline: EvaluationReport | None = None):
        return any(case.assertions for case in self._all_cases(report, baseline))

    def _all_cases(self, report: EvaluationReport, baseline: EvaluationReport | None) -> list[ReportCase]:
        if not baseline:
            return report.cases
        else:
            return report.cases + self._baseline_cases_to_include(report, baseline)

    def _baseline_cases_to_include(self, report: EvaluationReport, baseline: EvaluationReport) -> list[ReportCase]:
        if self.include_removed_cases:
            return baseline.cases
        report_case_names = {case.name for case in report.cases}
        return [case for case in baseline.cases if case.name in report_case_names]

    def _get_case_renderer(
        self, report: EvaluationReport, baseline: EvaluationReport | None = None
    ) -> ReportCaseRenderer:
        input_renderer = _ValueRenderer.from_config(self.input_config)
        output_renderer = _ValueRenderer.from_config(self.output_config)
        score_renderers = self._infer_score_renderers(report, baseline)
        label_renderers = self._infer_label_renderers(report, baseline)
        metric_renderers = self._infer_metric_renderers(report, baseline)
        duration_renderer = _NumberRenderer.infer_from_config(
            self.duration_config, 'duration', [x.task_duration for x in self._all_cases(report, baseline)]
        )

        return ReportCaseRenderer(
            include_input=self.include_input,
            include_output=self.include_output,
            include_scores=self.include_scores(report, baseline),
            include_labels=self.include_labels(report, baseline),
            include_metrics=self.include_metrics(report, baseline),
            include_assertions=self.include_assertions(report, baseline),
            include_durations=self.include_durations,
            include_total_duration=self.include_total_duration,
            input_renderer=input_renderer,
            output_renderer=output_renderer,
            score_renderers=score_renderers,
            label_renderers=label_renderers,
            metric_renderers=metric_renderers,
            duration_renderer=duration_renderer,
        )

    def build_table(self, report: EvaluationReport) -> Table:
        case_renderer = self._get_case_renderer(report)
        table = case_renderer.build_base_table(f'Evaluation Summary: {report.name}')
        for case in report.cases:
            table.add_row(*case_renderer.build_row(case))

        if self.include_averages:
            average = report.averages()
            table.add_row(*case_renderer.build_aggregate_row(average))
        return table

    def build_diff_table(self, report: EvaluationReport, baseline: EvaluationReport) -> Table:
        report_cases = report.cases
        baseline_cases = self._baseline_cases_to_include(report, baseline)

        report_cases_by_id = {case.name: case for case in report_cases}
        baseline_cases_by_id = {case.name: case for case in baseline_cases}

        diff_cases: list[tuple[ReportCase, ReportCase]] = []
        removed_cases: list[ReportCase] = []
        added_cases: list[ReportCase] = []

        for case_id in sorted(set(baseline_cases_by_id.keys()) | set(report_cases_by_id.keys())):
            maybe_baseline_case = baseline_cases_by_id.get(case_id)
            maybe_report_case = report_cases_by_id.get(case_id)
            if maybe_baseline_case and maybe_report_case:
                diff_cases.append((maybe_baseline_case, maybe_report_case))
            elif maybe_baseline_case:
                removed_cases.append(maybe_baseline_case)
            elif maybe_report_case:
                added_cases.append(maybe_report_case)
            else:  # pragma: no cover
                assert False, 'This should be unreachable'

        case_renderer = self._get_case_renderer(report, baseline)
        diff_name = baseline.name if baseline.name == report.name else f'{baseline.name} → {report.name}'
        table = case_renderer.build_base_table(f'Evaluation Diff: {diff_name}')
        for baseline_case, new_case in diff_cases:
            table.add_row(*case_renderer.build_diff_row(new_case, baseline_case))
        for case in added_cases:
            row = case_renderer.build_row(case)
            row[0] = f'[green]+ Added Case[/]\n{row[0]}'
            table.add_row(*row)
        for case in removed_cases:
            row = case_renderer.build_row(case)
            row[0] = f'[red]- Removed Case[/]\n{row[0]}'
            table.add_row(*row)

        if self.include_averages:
            report_average = ReportCaseAggregate.average(report_cases)
            baseline_average = ReportCaseAggregate.average(baseline_cases)
            table.add_row(*case_renderer.build_diff_aggregate_row(report_average, baseline_average))

        return table

    def _infer_score_renderers(
        self, report: EvaluationReport, baseline: EvaluationReport | None
    ) -> dict[str, _NumberRenderer]:
        all_cases = self._all_cases(report, baseline)

        values_by_name: dict[str, list[float | int]] = {}
        for case in all_cases:
            for k, score in case.scores.items():
                values_by_name.setdefault(k, []).append(score.value)

        all_renderers: dict[str, _NumberRenderer] = {}
        for name, values in values_by_name.items():
            merged_config = _DEFAULT_NUMBER_CONFIG.copy()
            merged_config.update(self.score_configs.get(name, {}))
            all_renderers[name] = _NumberRenderer.infer_from_config(merged_config, 'score', values)
        return all_renderers

    def _infer_label_renderers(
        self, report: EvaluationReport, baseline: EvaluationReport | None
    ) -> dict[str, _ValueRenderer]:
        all_cases = self._all_cases(report, baseline)
        all_names: set[str] = set()
        for case in all_cases:
            for k in case.labels:
                all_names.add(k)

        all_renderers: dict[str, _ValueRenderer] = {}
        for name in all_names:
            merged_config = _DEFAULT_VALUE_CONFIG.copy()
            merged_config.update(self.label_configs.get(name, {}))
            all_renderers[name] = _ValueRenderer.from_config(merged_config)
        return all_renderers

    def _infer_metric_renderers(
        self, report: EvaluationReport, baseline: EvaluationReport | None
    ) -> dict[str, _NumberRenderer]:
        all_cases = self._all_cases(report, baseline)

        values_by_name: dict[str, list[float | int]] = {}
        for case in all_cases:
            for k, v in case.metrics.items():
                values_by_name.setdefault(k, []).append(v)

        all_renderers: dict[str, _NumberRenderer] = {}
        for name, values in values_by_name.items():
            merged_config = _DEFAULT_NUMBER_CONFIG.copy()
            merged_config.update(self.metric_configs.get(name, {}))
            all_renderers[name] = _NumberRenderer.infer_from_config(merged_config, 'metric', values)
        return all_renderers

    def _infer_duration_renderer(
        self, report: EvaluationReport, baseline: EvaluationReport | None
    ) -> _NumberRenderer:  # pragma: no cover
        all_cases = self._all_cases(report, baseline)
        all_durations = [x.task_duration for x in all_cases]
        if self.include_total_duration:
            all_durations += [x.total_duration for x in all_cases]
        return _NumberRenderer.infer_from_config(self.duration_config, 'duration', all_durations)