Package org.deeplearning4j.models.word2vec.iterator

Class Word2VecDataSetIterator

  • All Implemented Interfaces:
    Serializable, Iterator<org.nd4j.linalg.dataset.DataSet>, org.nd4j.linalg.dataset.api.iterator.DataSetIterator
    public class Word2VecDataSetIterator
extends Object
implements org.nd4j.linalg.dataset.api.iterator.DataSetIterator
    See Also:
    Serialized Form

    • Constructor Detail

      • Word2VecDataSetIterator

        public Word2VecDataSetIterator​(Word2Vec vec,
                               LabelAwareSentenceIterator iter,
                               List<String> labels,
                               int batch,
                               boolean homogenization,
                               boolean addLabels)
        Allows for customization of all of the params of the iterator
        Parameters:
        vec - the word2vec model to use
        iter - the sentence iterator to use
        labels - the possible labels
        batch - the batch size
        homogenization - whether to homogenize the sentences or not
        addLabels - whether to add labels for windows

      • Word2VecDataSetIterator

        public Word2VecDataSetIterator​(Word2Vec vec,
                               LabelAwareSentenceIterator iter,
                               List<String> labels)
        Initializes this iterator with homogenization and adding labels and a batch size of 10
        Parameters:
        vec - the vector model to use
        iter - the sentence iterator to use
        labels - the possible labels

      • Word2VecDataSetIterator

        public Word2VecDataSetIterator​(Word2Vec vec,
                               LabelAwareSentenceIterator iter,
                               List<String> labels,
                               int batch)
        Initializes this iterator with homogenization and adding labels
        Parameters:
        vec - the vector model to use
        iter - the sentence iterator to use
        labels - the possible labels
        batch - the batch size

    • Method Detail

      • next

        public org.nd4j.linalg.dataset.DataSet next​(int num)
        Like the standard next method but allows a customizable number of examples returned
        Specified by:
        next in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator
        Parameters:
        num - the number of examples
        Returns:
        the next data applyTransformToDestination

      • inputColumns

        public int inputColumns()
        Specified by:
        inputColumns in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • totalOutcomes

        public int totalOutcomes()
        Specified by:
        totalOutcomes in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • resetSupported

        public boolean resetSupported()
        Specified by:
        resetSupported in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • asyncSupported

        public boolean asyncSupported()
        Specified by:
        asyncSupported in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • reset

        public void reset()
        Specified by:
        reset in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • batch

        public int batch()
        Specified by:
        batch in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • setPreProcessor

        public void setPreProcessor​(org.nd4j.linalg.dataset.api.DataSetPreProcessor preProcessor)
        Specified by:
        setPreProcessor in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • getLabels

        public List<String> getLabels()
        Specified by:
        getLabels in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

      • hasNext

        public boolean hasNext()
        Returns true if the iteration has more elements. (In other words, returns true if next(int) would return an element rather than throwing an exception.)
        Specified by:
        hasNext in interface Iterator<org.nd4j.linalg.dataset.DataSet>
        Returns:
        true if the iteration has more elements

      • next

        public org.nd4j.linalg.dataset.DataSet next()
        Returns the next element in the iteration.
        Specified by:
        next in interface Iterator<org.nd4j.linalg.dataset.DataSet>
        Returns:
        the next element in the iteration

      • remove

        public void remove()
        Removes from the underlying collection the last element returned by this iterator (optional operation). This method can be called only once per call to next(int). The behavior of an iterator is unspecified if the underlying collection is modified while the iteration is in progress in any way other than by calling this method.
        Specified by:
        remove in interface Iterator<org.nd4j.linalg.dataset.DataSet>
        Throws:
        UnsupportedOperationException - if the remove operation is not supported by this iterator
        IllegalStateException - if the next method has not yet been called, or the remove method has already been called after the last call to the next method