water.bindings.pojos

Class Word2VecParametersV3

java.lang.Object

water.bindings.pojos.Schema

water.bindings.pojos.ModelParametersSchema

water.bindings.pojos.Word2VecParametersV3

public class Word2VecParametersV3
extends ModelParametersSchema

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
int	negSampleCnt Number of negative examples, common values are 3 - 10 (0 = not used)
Word2vecWord2VecNormModel	normModel Use Hierarchical Softmax or Negative Sampling
float	sentSampleRate Set threshold for occurrence of words.
int	vecSize Set size of word vectors
int	windowSize Set max skip length between words
Word2vecWord2VecWordModel	wordModel Use the continuous bag of words model or the Skip-Gram model

Fields inherited from class water.bindings.pojos.ModelParametersSchema

checkpoint, fold_assignment, fold_column, ignore_const_cols, ignored_columns, keep_cross_validation_fold_assignment, keep_cross_validation_predictions, max_runtime_secs, model_id, nfolds, offset_column, parallelize_cross_validation, response_column, score_each_iteration, stopping_metric, stopping_rounds, stopping_tolerance, training_frame, validation_frame, weights_column

Constructor Summary

Constructors

Constructor and Description
Word2VecParametersV3()

Method Summary

Methods

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

public int vecSize

Set size of word vectors

windowSize

public int windowSize

Set max skip length between words

sentSampleRate

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

public Word2vecWord2VecNormModel normModel

Use Hierarchical Softmax or Negative Sampling

negSampleCnt

public int negSampleCnt

Number of negative examples, common values are 3 - 10 (0 = not used)

epochs

public int epochs

Number of training iterations to run

minWordFreq

public int minWordFreq

This will discard words that appear less than times

initLearningRate

public float initLearningRate

Set the starting learning rate

wordModel

public Word2vecWord2VecWordModel wordModel

Use the continuous bag of words model or the Skip-Gram model

Constructor Detail

Word2VecParametersV3

public Word2VecParametersV3()

Method Detail

toString

public java.lang.String toString()

Return the contents of this object as a JSON String.

Overrides:

toString in class ModelParametersSchema