water.bindings.pojos

Class Word2VecParametersV3

java.lang.Object

water.bindings.pojos.SchemaV3

water.bindings.pojos.ModelParametersSchemaV3

water.bindings.pojos.Word2VecParametersV3

public class Word2VecParametersV3
extends ModelParametersSchemaV3

Field Summary

Fields

Modifier and Type	Field and Description
int	epochs Number of training iterations to run
float	initLearningRate Set the starting learning rate
int	minWordFreq This will discard words that appear less than times
Word2VecNormModel	normModel Use Hierarchical Softmax
FrameKeyV3	preTrained Id of a data frame that contains a pre-trained (external) word2vec model
float	sentSampleRate Set threshold for occurrence of words.
int	vecSize Set size of word vectors
int	windowSize Set max skip length between words
Word2VecWordModel	wordModel Use the Skip-Gram model

Fields inherited from class water.bindings.pojos.ModelParametersSchemaV3

categoricalEncoding, checkpoint, customMetricFunc, distribution, exportCheckpointsDir, foldAssignment, foldColumn, huberAlpha, ignoreConstCols, ignoredColumns, keepCrossValidationFoldAssignment, keepCrossValidationModels, keepCrossValidationPredictions, maxCategoricalLevels, maxRuntimeSecs, modelId, nfolds, offsetColumn, parallelizeCrossValidation, quantileAlpha, responseColumn, scoreEachIteration, stoppingMetric, stoppingRounds, stoppingTolerance, trainingFrame, tweediePower, validationFrame, weightsColumn

Constructor Summary

Constructors

Constructor and Description
Word2VecParametersV3() Public constructor

Method Summary

Modifier and Type	Method and Description
java.lang.String	toString() Return the contents of this object as a JSON String.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

vecSize

@SerializedName(value="vec_size")
public int vecSize

Set size of word vectors

windowSize

@SerializedName(value="window_size")
public int windowSize

Set max skip length between words

sentSampleRate

@SerializedName(value="sent_sample_rate")
public float sentSampleRate

Set threshold for occurrence of words. Those that appear with higher frequency in the training data will be randomly down-sampled; useful range is (0, 1e-5)

normModel

@SerializedName(value="norm_model")
public Word2VecNormModel normModel

Use Hierarchical Softmax

epochs

public int epochs

Number of training iterations to run

minWordFreq

@SerializedName(value="min_word_freq")
public int minWordFreq

This will discard words that appear less than times

initLearningRate

@SerializedName(value="init_learning_rate")
public float initLearningRate

Set the starting learning rate

wordModel

@SerializedName(value="word_model")
public Word2VecWordModel wordModel

Use the Skip-Gram model

preTrained

@SerializedName(value="pre_trained")
public FrameKeyV3 preTrained

Id of a data frame that contains a pre-trained (external) word2vec model

Constructor Detail

Word2VecParametersV3

public Word2VecParametersV3()

Public constructor

Method Detail

toString

public java.lang.String toString()

Return the contents of this object as a JSON String.

Overrides:

toString in class ModelParametersSchemaV3