lenskit.metrics.MAE#

class lenskit.metrics.MAE(missing_scores='error', missing_truth='error')#

Bases: PredictMetric, ListMetric, DecomposedMetric

Compute MAE (mean absolute error). This is computed as:

\[\sum_{r_{ui} \in R} \left|r_{ui} - s(i|u)\right|\]

This metric does not do any fallbacks; if you want to compute MAE with fallback predictions (e.g. usign a bias model when a collaborative filter cannot predict), generate predictions with FallbackScorer.

Stability:
Caller (see Stability Levels).
Parameters:

  • missing_scores (Literal['error', 'ignore'])

  • missing_truth (Literal['error', 'ignore'])

__init__(missing_scores='error', missing_truth='error')#
Parameters:

  • missing_scores (Literal['error', 'ignore'])

  • missing_truth (Literal['error', 'ignore'])

Methods

__init__([missing_scores, missing_truth])

align_scores(predictions[, truth])

Align prediction scores and rating values, applying the configured missing dispositions.

compute_list_data(output, test)

Compute measurements for a single list.

extract_list_metric(metric)

Extract a single-list metric from the per-list measurement result (if applicable).

extract_list_metrics(data, /)

Return the given per-list metric result.

global_aggregate(values)

Aggregate list metrics to compute a global value.

measure_list(predictions[, test])

Compute measurements for a single list.

summarize(values, /)

Summarize per-list metric values

Attributes

default

label

The metric's default label in output.

missing_scores

missing_truth

measure_list(predictions, test=None, /)#

Compute measurements for a single list.

Returns:

  • A float for simple metrics

  • Intermediate data for decomposed metrics

  • A dict mapping metric names to values for multi-metric classes

Parameters:
Return type:

float

compute_list_data(output, test)#

Compute measurements for a single list.

Use measure_list in Metric for new implementations.

extract_list_metric(metric)#

Extract a single-list metric from the per-list measurement result (if applicable).

Returns:

The per-list metric, or None if this metric does not compute per-list metrics.

Implement Metric.extract_list_metrics() in new implementations.

global_aggregate(values)#

Aggregate list metrics to compute a global value.

Implement Metric.summarize() in new implementations.