public class ModelParametersSchemaV3 extends SchemaV3
| Modifier and Type | Field and Description |
|---|---|
ModelParametersCategoricalEncodingScheme |
categoricalEncoding
Encoding scheme for categorical features
|
ModelKeyV3 |
checkpoint
Model checkpoint to resume training with.
|
GenmodelutilsDistributionFamily |
distribution
Distribution function
|
ModelParametersFoldAssignmentScheme |
foldAssignment
Cross-validation fold assignment scheme, if fold_column is not specified.
|
ColSpecifierV3 |
foldColumn
Column with cross-validation fold index assignment per observation.
|
double |
huberAlpha
Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1).
|
boolean |
ignoreConstCols
Ignore constant columns.
|
java.lang.String[] |
ignoredColumns
Names of columns to ignore for training.
|
boolean |
keepCrossValidationFoldAssignment
Whether to keep the cross-validation fold assignment.
|
boolean |
keepCrossValidationPredictions
Whether to keep the predictions of the cross-validation models.
|
double |
maxRuntimeSecs
Maximum allowed runtime in seconds for model training.
|
ModelKeyV3 |
modelId
Destination id for this model; auto-generated if not specified.
|
int |
nfolds
Number of folds for N-fold cross-validation (0 to disable or >= 2).
|
ColSpecifierV3 |
offsetColumn
Offset column.
|
boolean |
parallelizeCrossValidation
Allow parallel training of cross-validation models
|
double |
quantileAlpha
Desired quantile for Quantile regression, must be between 0 and 1.
|
ColSpecifierV3 |
responseColumn
Response variable column.
|
boolean |
scoreEachIteration
Whether to score during each iteration of model training.
|
ScoreKeeperStoppingMetric |
stoppingMetric
Metric to use for early stopping (AUTO: logloss for classification, deviance for regression)
|
int |
stoppingRounds
Early stopping based on convergence of stopping_metric.
|
double |
stoppingTolerance
Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much)
|
FrameKeyV3 |
trainingFrame
Id of the training data frame (Not required, to allow initial validation of model parameters).
|
double |
tweediePower
Tweedie power for Tweedie regression, must be between 1 and 2.
|
FrameKeyV3 |
validationFrame
Id of the validation data frame.
|
ColSpecifierV3 |
weightsColumn
Column with observation weights.
|
| Constructor and Description |
|---|
ModelParametersSchemaV3()
Public constructor
|
| Modifier and Type | Method and Description |
|---|---|
java.lang.String |
toString()
Return the contents of this object as a JSON String.
|
public ModelKeyV3 modelId
public FrameKeyV3 trainingFrame
public FrameKeyV3 validationFrame
public int nfolds
public boolean keepCrossValidationPredictions
public boolean keepCrossValidationFoldAssignment
public boolean parallelizeCrossValidation
public GenmodelutilsDistributionFamily distribution
public double tweediePower
public double quantileAlpha
public double huberAlpha
public ColSpecifierV3 responseColumn
public ColSpecifierV3 weightsColumn
public ColSpecifierV3 offsetColumn
public ColSpecifierV3 foldColumn
public ModelParametersFoldAssignmentScheme foldAssignment
public ModelParametersCategoricalEncodingScheme categoricalEncoding
public java.lang.String[] ignoredColumns
public boolean ignoreConstCols
public boolean scoreEachIteration
public ModelKeyV3 checkpoint
public int stoppingRounds
public double maxRuntimeSecs
public ScoreKeeperStoppingMetric stoppingMetric
public double stoppingTolerance