public abstract class SuperLabelUtils extends Object
Constructor and Description |
---|
SuperLabelUtils() |
Modifier and Type | Method and Description |
---|---|
static int[][] |
convertListArrayTo2DArray(ArrayList<Integer>[] listArray) |
static double[] |
convertVotesToDistributionForInstance(HashMap<Integer,Double>[] votes) |
static int[] |
decodeClass(String s)
Decode a string into sparse list of indices
|
static int[] |
decodeValue(String s) |
static String |
encodeClass(int[] c_)
Encode a sparse list of indices to a string
|
static String |
encodeValue(weka.core.Instance x,
int[] indices)
Encode a vector of integer values to a string
|
static int[][] |
extractValues(weka.core.Instances D_)
Returns a map of values for this multi-class Instances.
|
static int[][] |
generatePartition(int L)
generatePartition - return [[0],...,[L-1]].
|
static int[][] |
generatePartition(int[] indices,
int num,
Random r)
Generate a random Partition.
|
static int[][] |
generatePartition(int[] indices,
int num,
Random r,
boolean balanced)
Generate Random Partition
|
static int[][] |
generatePartition(int[] indices,
Random r)
generatePartition - .
|
static int[] |
get_k_subset(int L,
int k,
Random r)
Get k subset - return a set of k label indices (of L possible labels).
|
static HashMap<String,Integer> |
getCounts(weka.core.Instances D,
int[] indices,
int p)
Return a set of all the combinations of attributes at 'indices' in 'D', pruned by 'p'; AND THEIR COUNTS, e.g., {(00:3),(01:8),(11:3))}.
|
static int[][] |
getPartitionFromDatasetHierarchy(weka.core.Instances D)
Get Partition From Dataset Hierarchy - assumes attributes are hierarchically arranged with '.'.
|
static String[] |
getTopNSubsets(String y,
HashMap<String,Integer> masterCombinations,
int N)
GetTopNSubsets - return the top N subsets which differ from y by a single class value, ranked by the frequency storte in masterCombinations.
|
static weka.core.Instances |
makePartitionDataset(weka.core.Instances D,
int[] part)
Make Partition Dataset - out of dataset D, on indices part[].
|
static weka.core.Instances |
makePartitionDataset(weka.core.Instances D,
int[] part,
int P,
int N)
Make Partition Dataset - out of dataset D, on indices part[].
|
static weka.core.Instances |
SLTransformation(weka.core.Instances D,
int[][] indices,
int p,
int n)
Super Label Transformation - transform dataset D into a dataset with
k multi-class target attributes. |
static String |
toString(int[][] partition)
ToString - A string representation for the super-class partition 'partition'.
|
public static int[] get_k_subset(int L, int k, Random r)
public static int[][] generatePartition(int L)
L
- number of labelspublic static int[][] generatePartition(int[] indices, Random r)
indices
- [1,2,..,L]r
- Randompublic static int[][] generatePartition(int[] indices, int num, Random r)
indices
- [0,1,2,...,L-1]num
- number of super-nodes to generate (between 1 and L)r
- Random, if == null, then don't randomizepublic static int[][] generatePartition(int[] indices, int num, Random r, boolean balanced)
indices
- label indicesnum
- the number of partitionsr
- Random, if == null, then don't randomizebalanced
- indicate if balanced (same number of labels in each set) or notpublic static final int[][] getPartitionFromDatasetHierarchy(weka.core.Instances D)
D
- Datasetpublic static final int[][] convertListArrayTo2DArray(ArrayList<Integer>[] listArray)
public static String toString(int[][] partition)
public static weka.core.Instances makePartitionDataset(weka.core.Instances D, int[] part) throws Exception
D
- regular multi-label dataset (of L = classIndex() labels)part
- list of indices we want to make into an LP dataset.Exception
public static weka.core.Instances makePartitionDataset(weka.core.Instances D, int[] part, int P, int N) throws Exception
public static int[][] extractValues(weka.core.Instances D_)
{[2,3,1], [1,0,1, [2,0,1]}
.D_
- multi-class Instancespublic static int[] decodeClass(String s)
public static String encodeClass(int[] c_)
public static int[] decodeValue(String s)
public static String encodeValue(weka.core.Instance x, int[] indices)
public static String[] getTopNSubsets(String y, HashMap<String,Integer> masterCombinations, int N)
public static HashMap<String,Integer> getCounts(weka.core.Instances D, int[] indices, int p)
public static weka.core.Instances SLTransformation(weka.core.Instances D, int[][] indices, int p, int n)
k
multi-class target attributes.
Use the NSR/PS-style pruning and recomposition, according to partition 'indices', and pruning values 'p' and 'n'.indices
- m by k: m super variables, each relating to k original variablesD
- either multi-label or multi-target datasetp
- pruning valuen
- subset relpacement valuePSUtils.PSTransformation
Copyright © 2017. All Rights Reserved.