SharedTreeParametersV3 (h2o-bindings 3.46.0 API)

java.lang.Object
- water.bindings.pojos.SchemaV3
- - water.bindings.pojos.ModelParametersSchemaV3
  - - water.bindings.pojos.SharedTreeParametersV3

Direct Known Subclasses:

DRFParametersV3, GBMParametersV3, IsolationForestParametersV3, UpliftDRFParametersV3
```
public class SharedTreeParametersV3
extends ModelParametersSchemaV3
```

Field Summary

Fields
Modifier and Type	Field and Description
`boolean`	`balanceClasses` Balance training data class counts via over/under-sampling (for imbalanced data).
`boolean`	`buildTreeOneNode` Run on one node only; no network overhead but fewer cpus used.
`boolean`	`calibrateModel` Use Platt Scaling (default) or Isotonic Regression to calculate calibrated class probabilities.
`FrameKeyV3`	`calibrationFrame` Data for model calibration
`TreeCalibrationHelperCalibrationMethod`	`calibrationMethod` Calibration method to use
`boolean`	`checkConstantResponse` Check if response column is constant.
`float[]`	`classSamplingFactors` Desired over/under-sampling ratios per class (in lexicographic order).
`double`	`colSampleRateChangePerLevel` Relative change of the column sampling rate for every level (must be > 0.0 and <= 2.0)
`double`	`colSampleRatePerTree` Column sample rate per tree (from 0.0 to 1.0)
`TreeSharedTreeModelSharedTreeParametersHistogramType`	`histogramType` What type of histogram to use for finding optimal split points
`java.lang.String`	`inTrainingCheckpointsDir` Create checkpoints into defined directory while training process is still running.
`int`	`inTrainingCheckpointsTreeInterval` Checkpoint the model after every so many trees.
`float`	`maxAfterBalanceSize` Maximum relative size of the training data after balancing class counts (can be less than 1.0).
`int`	`maxConfusionMatrixSize` [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs
`int`	`maxDepth` Maximum tree depth (0 for unlimited).
`double`	`minRows` Fewest allowed (weighted) observations in a leaf.
`double`	`minSplitImprovement` Minimum relative improvement in squared error reduction for a split to happen
`int`	`nbins` For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point
`int`	`nbinsCats` For categorical columns (factors), build a histogram of this many bins, then split at the best point.
`int`	`nbinsTopLevel` For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level
`int`	`ntrees` Number of trees.
`double`	`r2Stopping` r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead.
`double[]`	`sampleRatePerClass` A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree
`int`	`scoreTreeInterval` Score the model after every so many trees.
`long`	`seed` Seed for pseudo random number generator (if applicable)

Constructor Summary

Constructors
Constructor and Description

SharedTreeParametersV3()
Public constructor

Constructors
Constructor and Description
`SharedTreeParametersV3()` Public constructor

Method Summary

All Methods Instance Methods Concrete 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

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

- Field Detail
  - balanceClasses
```
@SerializedName(value="balance_classes")
public boolean balanceClasses
```
    Balance training data class counts via over/under-sampling (for imbalanced data).
  - classSamplingFactors
```
@SerializedName(value="class_sampling_factors")
public float[] classSamplingFactors
```
    Desired over/under-sampling ratios per class (in lexicographic order). If not specified, sampling factors will be automatically computed to obtain class balance during training. Requires balance_classes.
  - maxAfterBalanceSize
```
@SerializedName(value="max_after_balance_size")
public float maxAfterBalanceSize
```
    Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes.
  - maxConfusionMatrixSize
```
@SerializedName(value="max_confusion_matrix_size")
public int maxConfusionMatrixSize
```
    [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs
  - ntrees
```
public int ntrees
```
    Number of trees.
  - maxDepth
```
@SerializedName(value="max_depth")
public int maxDepth
```
    Maximum tree depth (0 for unlimited).
  - minRows
```
@SerializedName(value="min_rows")
public double minRows
```
    Fewest allowed (weighted) observations in a leaf.
  - nbins
```
public int nbins
```
    For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point
  - nbinsTopLevel
```
@SerializedName(value="nbins_top_level")
public int nbinsTopLevel
```
    For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level
  - nbinsCats
```
@SerializedName(value="nbins_cats")
public int nbinsCats
```
    For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting.
  - r2Stopping
```
@SerializedName(value="r2_stopping")
public double r2Stopping
```
    r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making trees when the R^2 metric equals or exceeds this
  - seed
```
public long seed
```
    Seed for pseudo random number generator (if applicable)
  - buildTreeOneNode
```
@SerializedName(value="build_tree_one_node")
public boolean buildTreeOneNode
```
    Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets.
  - sampleRatePerClass
```
@SerializedName(value="sample_rate_per_class")
public double[] sampleRatePerClass
```
    A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree
  - colSampleRatePerTree
```
@SerializedName(value="col_sample_rate_per_tree")
public double colSampleRatePerTree
```
    Column sample rate per tree (from 0.0 to 1.0)
  - colSampleRateChangePerLevel
```
@SerializedName(value="col_sample_rate_change_per_level")
public double colSampleRateChangePerLevel
```
    Relative change of the column sampling rate for every level (must be > 0.0 and <= 2.0)
  - scoreTreeInterval
```
@SerializedName(value="score_tree_interval")
public int scoreTreeInterval
```
    Score the model after every so many trees. Disabled if set to 0.
  - minSplitImprovement
```
@SerializedName(value="min_split_improvement")
public double minSplitImprovement
```
    Minimum relative improvement in squared error reduction for a split to happen
  - histogramType
```
@SerializedName(value="histogram_type")
public TreeSharedTreeModelSharedTreeParametersHistogramType histogramType
```
    What type of histogram to use for finding optimal split points
  - calibrateModel
```
@SerializedName(value="calibrate_model")
public boolean calibrateModel
```
    Use Platt Scaling (default) or Isotonic Regression to calculate calibrated class probabilities. Calibration can provide more accurate estimates of class probabilities.
  - calibrationFrame
```
@SerializedName(value="calibration_frame")
public FrameKeyV3 calibrationFrame
```
    Data for model calibration
  - calibrationMethod
```
@SerializedName(value="calibration_method")
public TreeCalibrationHelperCalibrationMethod calibrationMethod
```
    Calibration method to use
  - checkConstantResponse
```
@SerializedName(value="check_constant_response")
public boolean checkConstantResponse
```
    Check if response column is constant. If enabled, then an exception is thrown if the response column is a constant value.If disabled, then model will train regardless of the response column being a constant value or not.
  - inTrainingCheckpointsDir
```
@SerializedName(value="in_training_checkpoints_dir")
public java.lang.String inTrainingCheckpointsDir
```
    Create checkpoints into defined directory while training process is still running. In case of cluster shutdown, this checkpoint can be used to restart training.
  - inTrainingCheckpointsTreeInterval
```
@SerializedName(value="in_training_checkpoints_tree_interval")
public int inTrainingCheckpointsTreeInterval
```
    Checkpoint the model after every so many trees. Parameter is used only when in_training_checkpoints_dir is defined
- Constructor Detail
  - SharedTreeParametersV3
```
public SharedTreeParametersV3()
```
    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

Class SharedTreeParametersV3

Field Summary

Fields inherited from class water.bindings.pojos.ModelParametersSchemaV3

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

balanceClasses

classSamplingFactors

maxAfterBalanceSize

maxConfusionMatrixSize

ntrees

maxDepth

minRows

nbins

nbinsTopLevel

nbinsCats

r2Stopping

seed

buildTreeOneNode

sampleRatePerClass

colSampleRatePerTree

colSampleRateChangePerLevel

scoreTreeInterval

minSplitImprovement

histogramType

calibrateModel

calibrationFrame

calibrationMethod

checkConstantResponse

inTrainingCheckpointsDir

inTrainingCheckpointsTreeInterval

Constructor Detail

SharedTreeParametersV3

Method Detail

toString