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
java.lang.String	checkpoint Model checkpoint to resume training with
int	epochs Number of training iterations to run
FoldAssignmentScheme	fold_assignment Cross-validation fold assignment scheme, if fold_column is not specified
ColSpecifierV3	fold_column Column with cross-validation fold index assignment per observation
boolean	ignore_const_cols Ignore constant columns
java.lang.String[]	ignored_columns Ignored columns
float	initLearningRate Set the starting learning rate
boolean	keep_cross_validation_predictions Keep cross-validation model predictions
int	minWordFreq This will discard words that appear less than times
java.lang.String	model_id Destination id for this model; auto-generated if not specified
int	negSampleCnt Number of negative examples, common values are 3 - 10 (0 = not used)
int	nfolds Number of folds for N-fold cross-validation
NormModel	normModel Use Hierarchical Softmax or Negative Sampling
ColSpecifierV3	offset_column Offset column
ColSpecifierV3	response_column Response column
boolean	score_each_iteration Whether to score during each iteration of model training
float	sentSampleRate Set threshold for occurrence of words.
StoppingMetric	stopping_metric Metric to use for early stopping (AUTO: logloss for classification, deviance for regression)
int	stopping_rounds Early stopping based on convergence of stopping_metric.
double	stopping_tolerance Relative tolerance for metric-based stopping criterion Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much)
java.lang.String	training_frame Training frame
java.lang.String	validation_frame Validation frame
int	vecSize Set size of word vectors
ColSpecifierV3	weights_column Column with observation weights
int	windowSize Set max skip length between words
WordModel	wordModel Use the continuous bag of words model or the Skip-Gram model

Constructor Summary

Constructors

Constructor and Description
Word2VecParametersV3()

Method Summary

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, 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 NormModel 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 WordModel wordModel

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

model_id

public java.lang.String model_id

Destination id for this model; auto-generated if not specified

training_frame

public java.lang.String training_frame

Training frame

validation_frame

public java.lang.String validation_frame

Validation frame

nfolds

public int nfolds

Number of folds for N-fold cross-validation

keep_cross_validation_predictions

public boolean keep_cross_validation_predictions

Keep cross-validation model predictions

response_column

public ColSpecifierV3 response_column

Response column

weights_column

public ColSpecifierV3 weights_column

Column with observation weights

offset_column

public ColSpecifierV3 offset_column

Offset column

fold_column

public ColSpecifierV3 fold_column

Column with cross-validation fold index assignment per observation

fold_assignment

public FoldAssignmentScheme fold_assignment

Cross-validation fold assignment scheme, if fold_column is not specified

ignored_columns

public java.lang.String[] ignored_columns

Ignored columns

ignore_const_cols

public boolean ignore_const_cols

Ignore constant columns

score_each_iteration

public boolean score_each_iteration

Whether to score during each iteration of model training

checkpoint

public java.lang.String checkpoint

Model checkpoint to resume training with

stopping_rounds

public int stopping_rounds

Early stopping based on convergence of stopping_metric. Stop if simple moving average of length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable)

stopping_metric

public StoppingMetric stopping_metric

Metric to use for early stopping (AUTO: logloss for classification, deviance for regression)

stopping_tolerance

public double stopping_tolerance

Relative tolerance for metric-based stopping criterion Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much)

Constructor Detail

Word2VecParametersV3

public Word2VecParametersV3()