public class StaticWord2Vec extends java.lang.Object implements WordVectors
Modifier and Type | Class and Description |
---|---|
static class |
StaticWord2Vec.Builder |
Modifier and Type | Method and Description |
---|---|
java.util.Map<java.lang.String,java.lang.Double> |
accuracy(java.util.List<java.lang.String> questions)
Accuracy based on questions which are a space separated list of strings
where the first word is the query word, the next 2 words are negative,
and the last word is the predicted word to be nearest
PLEASE NOTE: This method is not available in this implementation.
|
java.lang.String |
getUNK() |
double[] |
getWordVector(java.lang.String word)
Get the word vector for a given matrix
|
org.nd4j.linalg.api.ndarray.INDArray |
getWordVectorMatrix(java.lang.String word)
Get the word vector for a given matrix
|
org.nd4j.linalg.api.ndarray.INDArray |
getWordVectorMatrixNormalized(java.lang.String word)
Returns the word vector divided by the norm2 of the array
|
org.nd4j.linalg.api.ndarray.INDArray |
getWordVectors(java.util.Collection<java.lang.String> labels)
This method returns 2D array, where each row represents corresponding word/label
|
org.nd4j.linalg.api.ndarray.INDArray |
getWordVectorsMean(java.util.Collection<java.lang.String> labels)
This method returns mean vector, built from words/labels passed in
|
boolean |
hasWord(java.lang.String word)
Returns true if the model has this word in the vocab
|
int |
indexOf(java.lang.String word) |
protected void |
init()
Init method validates configuration defined using
|
WeightLookupTable |
lookupTable()
Lookup table for the vectors
PLEASE NOTE: This method is not available in this implementation.
|
void |
setModelUtils(ModelUtils utils)
Specifies ModelUtils to be used to access model
PLEASE NOTE: This method has no effect in this implementation.
|
void |
setUNK(java.lang.String newUNK) |
double |
similarity(java.lang.String label1,
java.lang.String label2)
Returns the similarity of 2 words
|
java.util.List<java.lang.String> |
similarWordsInVocabTo(java.lang.String word,
double accuracy)
Find all words with a similar characters
in the vocab
PLEASE NOTE: This method is not available in this implementation.
|
VocabCache |
vocab()
Vocab for the vectors
|
java.util.Collection<java.lang.String> |
wordsNearest(java.util.Collection<java.lang.String> positive,
java.util.Collection<java.lang.String> negative,
int top)
Words nearest based on positive and negative words
PLEASE NOTE: This method is not available in this implementation.
|
java.util.Collection<java.lang.String> |
wordsNearest(org.nd4j.linalg.api.ndarray.INDArray words,
int top) |
java.util.Collection<java.lang.String> |
wordsNearest(java.lang.String word,
int n)
Get the top n words most similar to the given word
PLEASE NOTE: This method is not available in this implementation.
|
java.util.Collection<java.lang.String> |
wordsNearestSum(java.util.Collection<java.lang.String> positive,
java.util.Collection<java.lang.String> negative,
int top)
Words nearest based on positive and negative words
PLEASE NOTE: This method is not available in this implementation.
|
java.util.Collection<java.lang.String> |
wordsNearestSum(org.nd4j.linalg.api.ndarray.INDArray words,
int top) |
java.util.Collection<java.lang.String> |
wordsNearestSum(java.lang.String word,
int n)
Get the top n words most similar to the given word
PLEASE NOTE: This method is not available in this implementation.
|
public java.lang.String getUNK()
getUNK
in interface WordVectors
public void setUNK(java.lang.String newUNK)
setUNK
in interface WordVectors
protected void init()
public boolean hasWord(java.lang.String word)
hasWord
in interface WordVectors
word
- the word to test forpublic java.util.Collection<java.lang.String> wordsNearest(org.nd4j.linalg.api.ndarray.INDArray words, int top)
wordsNearest
in interface WordVectors
public java.util.Collection<java.lang.String> wordsNearestSum(org.nd4j.linalg.api.ndarray.INDArray words, int top)
wordsNearestSum
in interface WordVectors
public java.util.Collection<java.lang.String> wordsNearestSum(java.lang.String word, int n)
wordsNearestSum
in interface WordVectors
word
- the word to comparen
- the n to getpublic java.util.Collection<java.lang.String> wordsNearestSum(java.util.Collection<java.lang.String> positive, java.util.Collection<java.lang.String> negative, int top)
wordsNearestSum
in interface WordVectors
positive
- the positive wordsnegative
- the negative wordstop
- the top n wordspublic java.util.Map<java.lang.String,java.lang.Double> accuracy(java.util.List<java.lang.String> questions)
accuracy
in interface WordVectors
questions
- the questions to askpublic int indexOf(java.lang.String word)
indexOf
in interface WordVectors
public java.util.List<java.lang.String> similarWordsInVocabTo(java.lang.String word, double accuracy)
similarWordsInVocabTo
in interface WordVectors
word
- the word to compareaccuracy
- the accuracy: 0 to 1public double[] getWordVector(java.lang.String word)
getWordVector
in interface WordVectors
word
- the word to get the matrix forpublic org.nd4j.linalg.api.ndarray.INDArray getWordVectorMatrixNormalized(java.lang.String word)
getWordVectorMatrixNormalized
in interface WordVectors
word
- the word to get the matrix forpublic org.nd4j.linalg.api.ndarray.INDArray getWordVectorMatrix(java.lang.String word)
getWordVectorMatrix
in interface WordVectors
word
- the word to get the matrix forpublic org.nd4j.linalg.api.ndarray.INDArray getWordVectors(java.util.Collection<java.lang.String> labels)
getWordVectors
in interface WordVectors
labels
- public org.nd4j.linalg.api.ndarray.INDArray getWordVectorsMean(java.util.Collection<java.lang.String> labels)
getWordVectorsMean
in interface WordVectors
labels
- public java.util.Collection<java.lang.String> wordsNearest(java.util.Collection<java.lang.String> positive, java.util.Collection<java.lang.String> negative, int top)
wordsNearest
in interface WordVectors
positive
- the positive wordsnegative
- the negative wordstop
- the top n wordspublic java.util.Collection<java.lang.String> wordsNearest(java.lang.String word, int n)
wordsNearest
in interface WordVectors
word
- the word to comparen
- the n to getpublic double similarity(java.lang.String label1, java.lang.String label2)
similarity
in interface WordVectors
label1
- the first wordlabel2
- the second wordpublic VocabCache vocab()
vocab
in interface WordVectors
public WeightLookupTable lookupTable()
lookupTable
in interface WordVectors
public void setModelUtils(ModelUtils utils)
setModelUtils
in interface WordVectors
utils
-