public class TfidfVectorizer extends AbstractTfidfVectorizer<org.nd4j.linalg.api.ndarray.INDArray>
Vectorizer.RecordCallBack
cache, MIN_WORD_FREQUENCY, minWordFrequency, STOP_WORDS, stopWords, TOKENIZER, tokenizerFactory, VOCAB_CACHE
Constructor and Description |
---|
TfidfVectorizer() |
Modifier and Type | Method and Description |
---|---|
org.nd4j.linalg.api.ndarray.INDArray |
createVector(java.lang.Object[] args)
Create a vector based on the given arguments
|
org.nd4j.linalg.api.ndarray.INDArray |
fitTransform(RecordReader reader)
Fit based on a record reader
|
org.nd4j.linalg.api.ndarray.INDArray |
fitTransform(RecordReader reader,
Vectorizer.RecordCallBack callBack)
Fit based on a record reader
|
org.nd4j.linalg.api.ndarray.INDArray |
transform(Record record)
Transform a record in to a vector
|
createTokenizerFactory, doWithTokens
fit, fit, initialize, toString, wordFrequenciesForRecord
public org.nd4j.linalg.api.ndarray.INDArray createVector(java.lang.Object[] args)
Vectorizer
createVector
in interface Vectorizer<org.nd4j.linalg.api.ndarray.INDArray>
createVector
in class AbstractTfidfVectorizer<org.nd4j.linalg.api.ndarray.INDArray>
args
- the arguments to create a vector withpublic org.nd4j.linalg.api.ndarray.INDArray fitTransform(RecordReader reader)
Vectorizer
fitTransform
in interface Vectorizer<org.nd4j.linalg.api.ndarray.INDArray>
fitTransform
in class AbstractTfidfVectorizer<org.nd4j.linalg.api.ndarray.INDArray>
public org.nd4j.linalg.api.ndarray.INDArray fitTransform(RecordReader reader, Vectorizer.RecordCallBack callBack)
Vectorizer
public org.nd4j.linalg.api.ndarray.INDArray transform(Record record)
Vectorizer
transform
in interface Vectorizer<org.nd4j.linalg.api.ndarray.INDArray>
transform
in class AbstractTfidfVectorizer<org.nd4j.linalg.api.ndarray.INDArray>
record
- the record to write