langcheck.metrics.metric_value

class langcheck.metrics.metric_value.MetricValue(metric_name: str, metric_values: list[NumericType], metric_inputs: MetricInputs, explanations: list[str | None] | None, language: str | None)

Bases: Generic[NumericType]

A rich object that is the output of any langcheck.metrics function.

all() → bool

Equivalent to all(metric_value.metric_values). This is mostly useful for binary metric functions.

any() → bool

Equivalent to any(metric_value.metric_values). This is mostly useful for binary metric functions.

explanations: list[str | None] | None

histogram(jupyter_mode: str = 'inline') → None

Shows an interactive histogram of all data points in MetricValue. Intended to be used in a Jupyter notebook.

This is a convenience function that calls langcheck.plot.histogram().

property is_scatter_compatible: bool

Checks if the metric value is compatible with the scatter plot method. It is only available for metric values with only non-pairwise metric values used from initial release (generated_outputs, prompts, reference_outputs and sources)

language: str | None

metric_inputs: MetricInputs

metric_name: str

metric_values: list[NumericType]

scatter(jupyter_mode: str = 'inline') → None

Shows an interactive scatter plot of all data points in MetricValue. Intended to be used in a Jupyter notebook.

This is a convenience function that calls langcheck.plot.scatter().

to_df() → DataFrame

Returns a DataFrame of metric values for each data point.

class langcheck.metrics.metric_value.MetricValueWithThreshold(metric_name: str, metric_values: list[NumericType], metric_inputs: MetricInputs, explanations: list[str | None] | None, language: str | None, threshold: float | int, threshold_op: str)

Bases: MetricValue

A rich object that is the output of comparing an MetricValue object, e.g. metric_value >= 0.5.

all() → bool

Returns True if all data points pass the threshold.

any() → bool

Returns True if any data points pass the threshold.

property pass_rate: float

Returns the proportion of data points that pass the threshold.

threshold: float | int

threshold_op: str

property threshold_results: list[bool]

Returns a list of booleans indicating whether each data point passes the threshold.

to_df() → DataFrame

Returns a DataFrame of metric values for each data point.