Package oracle.pgx.api.mllib

Class Pg2vecModelBuilder

  • public class Pg2vecModelBuilder
extends java.lang.Object

    • Constructor Detail

      • Pg2vecModelBuilder

        public Pg2vecModelBuilder​(PgxSession session,
                          oracle.pgx.api.internal.Core core,
                          java.util.function.Supplier<java.lang.String> keystorePathSupplier,
                          java.util.function.Supplier<char[]> keystorePasswordSupplier)
        Please do not use; only meant for being used by PGX itself. Use Analyst.pg2vecModelBuilder() to get a model builder instead.
        Parameters:
        session - PgxSession to which the model is connected
        core - Core to which the model is connected

    • Method Detail

      • setUseGraphletSize

        public Pg2vecModelBuilder setUseGraphletSize​(boolean useGraphletSize)
        Sets whether to use or not the graphlet size (default: true)
        Parameters:
        useGraphletSize - to use or not the graphlet size (default: true)
        Returns:
        builder

      • getUseGraphletSize

        public java.lang.Boolean getUseGraphletSize()
        Gets whether to use or not the graphlet size (default: true)
        Returns:
        to use or not the graphlet size (default: true)

      • setGraphLetIdPropertyName

        public Pg2vecModelBuilder setGraphLetIdPropertyName​(java.lang.String graphLetIdName)
        Sets the property name of the graphlet-id in the input graph (required input)
        Parameters:
        graphLetIdName - property name of the graphlet-id in the input graph
        Returns:
        builder

      • getGraphLetIdPropertyName

        public java.lang.String getGraphLetIdPropertyName()
        Gets the property name of the graphlet-id in the input graph
        Returns:
        property name of the graphlet-id in the input graph

      • setVertexPropertyNames

        public Pg2vecModelBuilder setVertexPropertyNames​(java.util.Collection<java.lang.String> vertexPropertyNames)
        Sets the property names to consider for pg2vec model training (required input)
        Parameters:
        vertexPropertyNames - property names to consider for pg2vec model training
        Returns:
        builder

      • getVertexPropertyNames

        public java.util.Collection<java.lang.String> getVertexPropertyNames()
        Gets the property names to consider for pg2vec model training
        Returns:
        property names to consider for pg2vec model training

      • setMinWordFrequency

        public Pg2vecModelBuilder setMinWordFrequency​(int minWordFrequency)
        Sets the minimum word frequency to consider before pruning (default: 1)
        Parameters:
        minWordFrequency - minimum word frequency to consider before pruning
        Returns:
        builder

      • getMinWordFrequency

        public int getMinWordFrequency()
        Gets the minimum word frequency to consider before pruning (default: 1)
        Returns:
        minimum word frequency to consider before pruning

      • setBatchSize

        public Pg2vecModelBuilder setBatchSize​(int batchSize)
        Sets the batch size for training the model (default: 128)
        Parameters:
        batchSize - batch size for training the model
        Returns:
        builder

      • getBatchSize

        public int getBatchSize()
        Gets the batch size for training the model (default: 128)
        Returns:
        batch size for training the model

      • setNumEpochs

        public Pg2vecModelBuilder setNumEpochs​(int numEpochs)
        Sets the number of epochs to train the model (default: 2)
        Parameters:
        numEpochs - number of epochs to train the model
        Returns:
        builder

      • getNumEpochs

        public int getNumEpochs()
        Gets the number of epochs to train the model (default: 2)
        Returns:
        number of epochs to train the model

      • setLayerSize

        public Pg2vecModelBuilder setLayerSize​(int layerSize)
        Sets the number of dimensions for the output vectors (default: 200)
        Parameters:
        layerSize - number of dimensions for the output vectors
        Returns:
        builder

      • getLayerSize

        public int getLayerSize()
        Gets the number of dimensions for the output vectors (default: 200)
        Returns:
        number of dimensions for the output vectors

      • setLearningRate

        public Pg2vecModelBuilder setLearningRate​(double lr)
        Sets the initial learning rate (default: 0.025)
        Parameters:
        lr - initial learning rate
        Returns:
        builder

      • getLearningRate

        public double getLearningRate()
        Gets the initial learning rate (default: 0.025)
        Returns:
        initial learning rate

      • setMinLearningRate

        public Pg2vecModelBuilder setMinLearningRate​(double minLr)
        Sets the minimum learning rate (default: 0.0001)
        Parameters:
        minLr - minimum learning rate
        Returns:
        builder

      • getMinLearningRate

        public double getMinLearningRate()
        Gets the minimum learning rate (default: 0.0001)
        Returns:
        minimum learning rate

      • setWindowSize

        public Pg2vecModelBuilder setWindowSize​(int windowSize)
        Sets the window size to consider while training the model (default: 5)
        Parameters:
        windowSize - window size to consider while training the model
        Returns:
        builder

      • getWindowSize

        public int getWindowSize()
        Gets the window size to consider while training the model (default: 5)
        Returns:
        window size to consider while training the model

      • setWalkLength

        public Pg2vecModelBuilder setWalkLength​(int walkLength)
        Sets the length of the walks (default: 5)
        Parameters:
        walkLength - length of the walks
        Returns:
        builder

      • getWalkLength

        public int getWalkLength()
        Gets the length of the walks (default: 5)
        Returns:
        length of the walks

      • setWalksPerVertex

        public Pg2vecModelBuilder setWalksPerVertex​(int walksPerVertex)
        Sets the number of walks to consider per vertex (default: 4)
        Parameters:
        walksPerVertex - number of walks to consider per vertex
        Returns:
        builder

      • getWalksPerVertex

        public int getWalksPerVertex()
        Gets the number of walks to consider per vertex (default: 4)
        Returns:
        number of walks to consider per vertex

      • setGraphletSizePropertyName

        public Pg2vecModelBuilder setGraphletSizePropertyName​(java.lang.String graphletSizePropertyName)
        Sets the property name for graphlet size (default: "graphletSize-Pg2vec")
        Returns:
        builder

      • getGraphletSizePropertyName

        public java.lang.String getGraphletSizePropertyName()
        Gets the property name for graphlet size (default: "graphletSize-Pg2vec")
        Returns:
        property name for graphlet size

      • setSeed

        public Pg2vecModelBuilder setSeed​(java.lang.Long seed)
        Sets the random seed for training the model. If set to null, execution will be non-deterministic.

        Note that setting the seed will limit the amount of threads during the learning phase to 1

        Parameters:
        seed - random seed for training the model
        Returns:
        builder

      • getSeed

        public java.lang.Long getSeed()
        Gets the random seed for training the model (default: null)
        Returns:
        seed random seed for training the model

      • setShuffle

        public Pg2vecModelBuilder setShuffle​(boolean shuffle)
        Sets whether to shuffle the random walks before training on them
        Parameters:
        shuffle - whether to shuffle
        Returns:
        builder

      • isShuffle

        public boolean isShuffle()
        Gets whether the model will shuffle the shuffle the random walks before training on them
        Returns:
        whether the model will shuffle the random walks

      • setEnableAccelerator

        public Pg2vecModelBuilder setEnableAccelerator​(boolean enableAccelerator)
        If true, use the accelerator (GPU) if available as the machine learning backend.

        default: {true}

        Parameters:
        enableAccelerator - whether to use the accelerator if available
        Returns:
        this
        Since:
        24.1

      • build

        public Pg2vecModel build()
                  throws java.lang.InterruptedException,
                         java.util.concurrent.ExecutionException
        Builds the Pg2vec Model with the builder configuration
        Returns:
        Pg2vec model
        Throws:
        java.lang.InterruptedException
        java.util.concurrent.ExecutionException