Module evaluation 

Evaluation module for embeddings and knowledge graphs

This module provides comprehensive evaluation tools and metrics for assessing the quality of embeddings and knowledge graph reasoning systems, including advanced ML techniques for uncertainty quantification, adversarial robustness, fairness assessment, and explanation quality evaluation.

Re-exports

pub use advanced_evaluation::AdvancedEvaluationConfig;

pub use advanced_evaluation::AdvancedEvaluationResults;

pub use advanced_evaluation::AdvancedEvaluator;

pub use advanced_evaluation::AdversarialAttackGenerator;

pub use advanced_evaluation::AdversarialResults;

pub use advanced_evaluation::BasicMetrics;

pub use advanced_evaluation::CrossDomainResults;

pub use advanced_evaluation::ExplanationQualityEvaluator;

pub use advanced_evaluation::ExplanationResults;

pub use advanced_evaluation::FairnessAssessment;

pub use advanced_evaluation::FairnessResults;

pub use advanced_evaluation::TemporalResults;

pub use advanced_evaluation::UncertaintyQuantifier;

pub use advanced_evaluation::UncertaintyResults;

pub use query_evaluation::QueryAnsweringEvaluator;

pub use query_evaluation::QueryEvaluationConfig;

pub use query_evaluation::QueryEvaluationResults;

pub use query_evaluation::QueryMetric;

pub use query_evaluation::QueryResult;

pub use query_evaluation::QueryTemplate;

pub use query_evaluation::QueryType;

pub use query_evaluation::ReasoningStep as QueryReasoningStep;

pub use query_evaluation::TypeSpecificResults;

pub use reasoning_evaluation::ReasoningChain;

pub use reasoning_evaluation::ReasoningEvaluationConfig;

pub use reasoning_evaluation::ReasoningEvaluationResults;

pub use reasoning_evaluation::ReasoningRule;

pub use reasoning_evaluation::ReasoningStep;

pub use reasoning_evaluation::ReasoningTaskEvaluator;

pub use reasoning_evaluation::ReasoningType;

pub use ab_test::evaluate_hits_at_k;

pub use ab_test::evaluate_link_prediction;

pub use ab_test::evaluate_silhouette;

pub use ab_test::AbTestResult;

pub use ab_test::AbTestRunner;

pub use ab_test::EmbedMetric;

pub use ab_test::ModelEvalResult;

pub use ab_test::StatTest;

pub use embedding_metrics::AnalogicalReasoningBenchmark;

pub use embedding_metrics::AnalogyQuad;

pub use embedding_metrics::EmbeddingClusteringMetrics;

pub use embedding_metrics::EmbeddingEvaluator;

pub use kgc_dataset::EvaluationTriple;

pub use kgc_dataset::KgcDataset;

pub use kgc_evaluator::EvalSplit;

pub use kgc_evaluator::KgcEvaluationSuite;

pub use kgc_evaluator::KgcEvaluator;

pub use kgc_evaluator::KgcEvaluatorConfig;

pub use kgc_metrics::compute_filtered_rank;

pub use kgc_metrics::hits_at_k;

pub use kgc_metrics::mean_rank;

pub use kgc_metrics::mean_reciprocal_rank;

pub use kgc_metrics::EvaluationMetrics;

Modules

ab_test

A/B Testing Framework for Embedding Model Comparison

advanced_evaluation

Advanced evaluation system for knowledge graph embeddings

embedding_metrics

Embedding quality metrics: link prediction, analogy reasoning, clustering.

kgc_dataset

KGC dataset with train/valid/test splits and TSV loading. Knowledge Graph Completion dataset abstractions.

kgc_evaluator

KGC evaluator and high-level evaluation suite. Knowledge Graph Completion evaluator.

kgc_metrics

Standard KGC evaluation metrics (MRR, Hits@K, Mean Rank, filtered variants). Standard Knowledge Graph Completion (KGC) evaluation metrics.

query_evaluation

Query answering and reasoning task evaluation

reasoning_evaluation

Reasoning task evaluation for embedding models