public class MostSimilarDataset extends Object
Constructor and Description |
---|
MostSimilarDataset(Dataset dataset) |
MostSimilarDataset(List<Dataset> datasets)
Creates a new most similar dataset based on some input datasets.
|
MostSimilarDataset(List<Dataset> datasets,
double threshold)
Creates a new most similar dataset based on some input datasets.
|
Modifier and Type | Method and Description |
---|---|
Language |
getLanguage() |
String |
getName() |
Set<String> |
getPhrases() |
KnownMostSim |
getSimilarities(String phrase) |
MostSimilarDataset |
pruneSmallLists(int n)
Returns a new dataset that only contains phrases with at least n KnownSim entries.
|
List<MostSimilarDataset> |
split(int n)
Returns a list of suitable test cross-validation sets.
|
List<Dataset> |
splitIntoDatasets(int n) |
Dataset |
toDataset()
Converts the most similar dataset back to a "normal" dataset.
|
public MostSimilarDataset(Dataset dataset)
dataset
- MostSimilarDataset(java.util.List)
public MostSimilarDataset(List<Dataset> datasets)
datasets
- public KnownMostSim getSimilarities(String phrase)
public MostSimilarDataset pruneSmallLists(int n)
n
- Minimum number of phrasespublic String getName()
public Language getLanguage()
public Dataset toDataset()
public List<MostSimilarDataset> split(int n)
n
- public List<Dataset> splitIntoDatasets(int n)
n
- split(int)
,
toDataset()
Copyright © 2014. All rights reserved.