Package | Description |
---|---|
com.google.api.services.bigquery.model |
Modifier and Type | Method and Description |
---|---|
TrainingOptions |
TrainingOptions.clone() |
TrainingOptions |
TrainingRun.getTrainingOptions()
Options that were used for this training run, includes user specified and default options that
were used.
|
TrainingOptions |
TrainingOptions.set(String fieldName,
Object value) |
TrainingOptions |
TrainingOptions.setBatchSize(Long batchSize)
Batch size for dnn models.
|
TrainingOptions |
TrainingOptions.setDataSplitColumn(String dataSplitColumn)
The column to split data with.
|
TrainingOptions |
TrainingOptions.setDataSplitEvalFraction(Double dataSplitEvalFraction)
The fraction of evaluation data over the whole input data.
|
TrainingOptions |
TrainingOptions.setDataSplitMethod(String dataSplitMethod)
The data split type for training and evaluation, e.g.
|
TrainingOptions |
TrainingOptions.setDistanceType(String distanceType)
Distance type for clustering models.
|
TrainingOptions |
TrainingOptions.setDropout(Double dropout)
Dropout probability for dnn models.
|
TrainingOptions |
TrainingOptions.setEarlyStop(Boolean earlyStop)
Whether to stop early when the loss doesn't improve significantly any more (compared to
min_relative_progress).
|
TrainingOptions |
TrainingOptions.setFeedbackType(String feedbackType)
Feedback type that specifies which algorithm to run for matrix factorization.
|
TrainingOptions |
TrainingOptions.setHiddenUnits(List<Long> hiddenUnits)
Hidden units for dnn models.
|
TrainingOptions |
TrainingOptions.setInitialLearnRate(Double initialLearnRate)
Specifies the initial learning rate for the line search learn rate strategy.
|
TrainingOptions |
TrainingOptions.setInputLabelColumns(List<String> inputLabelColumns)
Name of input label columns in training data.
|
TrainingOptions |
TrainingOptions.setItemColumn(String itemColumn)
Item column specified for matrix factorization models.
|
TrainingOptions |
TrainingOptions.setKmeansInitializationColumn(String kmeansInitializationColumn)
The column used to provide the initial centroids for kmeans algorithm when
kmeans_initialization_method is CUSTOM.
|
TrainingOptions |
TrainingOptions.setKmeansInitializationMethod(String kmeansInitializationMethod)
The method used to initialize the centroids for kmeans algorithm.
|
TrainingOptions |
TrainingOptions.setL1Regularization(Double l1Regularization)
L1 regularization coefficient.
|
TrainingOptions |
TrainingOptions.setL2Regularization(Double l2Regularization)
L2 regularization coefficient.
|
TrainingOptions |
TrainingOptions.setLabelClassWeights(Map<String,Double> labelClassWeights)
Weights associated with each label class, for rebalancing the training data.
|
TrainingOptions |
TrainingOptions.setLearnRate(Double learnRate)
Learning rate in training.
|
TrainingOptions |
TrainingOptions.setLearnRateStrategy(String learnRateStrategy)
The strategy to determine learn rate for the current iteration.
|
TrainingOptions |
TrainingOptions.setLossType(String lossType)
Type of loss function used during training run.
|
TrainingOptions |
TrainingOptions.setMaxIterations(Long maxIterations)
The maximum number of iterations in training.
|
TrainingOptions |
TrainingOptions.setMaxTreeDepth(Long maxTreeDepth)
Maximum depth of a tree for boosted tree models.
|
TrainingOptions |
TrainingOptions.setMinRelativeProgress(Double minRelativeProgress)
When early_stop is true, stops training when accuracy improvement is less than
'min_relative_progress'.
|
TrainingOptions |
TrainingOptions.setMinSplitLoss(Double minSplitLoss)
Minimum split loss for boosted tree models.
|
TrainingOptions |
TrainingOptions.setModelUri(String modelUri)
[Beta] Google Cloud Storage URI from which the model was imported.
|
TrainingOptions |
TrainingOptions.setNumClusters(Long numClusters)
Number of clusters for clustering models.
|
TrainingOptions |
TrainingOptions.setNumFactors(Long numFactors)
Num factors specified for matrix factorization models.
|
TrainingOptions |
TrainingOptions.setOptimizationStrategy(String optimizationStrategy)
Optimization strategy for training linear regression models.
|
TrainingOptions |
TrainingOptions.setPreserveInputStructs(Boolean preserveInputStructs)
Whether to preserve the input structs in output feature names.
|
TrainingOptions |
TrainingOptions.setSubsample(Double subsample)
Subsample fraction of the training data to grow tree to prevent overfitting for boosted tree
models.
|
TrainingOptions |
TrainingOptions.setUserColumn(String userColumn)
User column specified for matrix factorization models.
|
TrainingOptions |
TrainingOptions.setWalsAlpha(Double walsAlpha)
Hyperparameter for matrix factoration when implicit feedback type is specified.
|
TrainingOptions |
TrainingOptions.setWarmStart(Boolean warmStart)
Whether to train a model from the last checkpoint.
|
Modifier and Type | Method and Description |
---|---|
TrainingRun |
TrainingRun.setTrainingOptions(TrainingOptions trainingOptions)
Options that were used for this training run, includes user specified and default options that
were used.
|
Copyright © 2011–2020 Google. All rights reserved.