LinkPredictionMetric

Type Parameters:: U - type of the users.

All Known Implementing Classes:: AbstractClassificationMetric, Accuracy, AUC, F1Score, Precision, Recall

public interface LinkPredictionMetric<U>

Interface for defining metrics for evaluating link prediction algorithms.

Method Summary

Modifier and Type	Method	Description
`double`	`evaluate(Graph<U> graph, Prediction<U> pred)`	Evaluates a link prediction algorithm.
`double`	`evaluate(Graph<U> graph, Prediction<U> pred, java.util.function.Predicate<Pair<U>> filter)`	Evaluates a link prediction algorithm.
`double`	`evaluate(Graph<U> graph, Prediction<U> pred, java.util.stream.Stream<Pair<U>> pairs)`	Evaluates a link prediction algorithm.

Method Details
- evaluate
  
  double evaluate(Graph<U> graph, Prediction<U> pred)
  
  Evaluates a link prediction algorithm. It considers that the prediction is applied over all pairs of users in the network.
  
  Parameters:
  
  graph - a graph containing the set of links to predict.
  
  pred - the prediction.
  
  Returns:
  
  the value of the metric.
- evaluate
  
  double evaluate(Graph<U> graph, Prediction<U> pred, java.util.function.Predicate<Pair<U>> filter)
  
  Evaluates a link prediction algorithm. It considers that the prediction is only applied for a subset of pairs of users in the network: those who pass a given filter.
  
  Parameters:
  
  graph - a graph containing the set of links to predict.
  
  pred - the prediction.
  
  filter - the filter for the different pairs of users.
  
  Returns:
  
  the value of the metric.
- evaluate
  
  double evaluate(Graph<U> graph, Prediction<U> pred, java.util.stream.Stream<Pair<U>> pairs)
  
  Evaluates a link prediction algorithm. It considers that we only apply this over a given set of links.
  
  Parameters:
  
  graph - a graph containing the set of links to predict.
  
  pred - the prediction.
  
  pairs - the set of users to apply the recommendation to.
  
  Returns:
  
  the value of the metric.