water.bindings.pojos.DRFParametersV3 Maven / Gradle / Ivy
package water.bindings.pojos;
import com.google.gson.Gson;
public class DRFParametersV3 extends SharedTreeParametersV3 {
/** Number of variables randomly sampled as candidates at each split. If set to -1, defaults to sqrt{p} for classification and p/3 for regression (where p is the # of predictors */
public int mtries;
/** For binary classification: Build 2x as many trees (one per class) - can lead to higher accuracy. */
public boolean binomial_double_trees;
/* INHERITED: Balance training data class counts via over/under-sampling (for imbalanced data).
* public boolean balance_classes;
*/
/* INHERITED: 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.
* public float[] class_sampling_factors;
*/
/* INHERITED: Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes.
* public float max_after_balance_size;
*/
/* INHERITED: Maximum size (# classes) for confusion matrices to be printed in the Logs
* public int max_confusion_matrix_size;
*/
/* INHERITED: Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable)
* public int max_hit_ratio_k;
*/
/* INHERITED: Number of trees.
* public int ntrees;
*/
/* INHERITED: Maximum tree depth.
* public int max_depth;
*/
/* INHERITED: Fewest allowed (weighted) observations in a leaf (in R called 'nodesize').
* public double min_rows;
*/
/* INHERITED: For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point
* public int nbins;
*/
/* INHERITED: 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
* public int nbins_top_level;
*/
/* INHERITED: For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting.
* public int nbins_cats;
*/
/* INHERITED: Stop making trees when the R^2 metric equals or exceeds this
* public double r2_stopping;
*/
/* INHERITED: Seed for pseudo random number generator (if applicable)
* public long seed;
*/
/* INHERITED: Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets.
* public boolean build_tree_one_node;
*/
/* INHERITED: Row sample rate per tree (from 0.0 to 1.0)
* public float sample_rate;
*/
/* INHERITED: Row sample rate per tree per class (from 0.0 to 1.0)
* public float[] sample_rate_per_class;
*/
/* INHERITED: Column sample rate per tree (from 0.0 to 1.0)
* public float col_sample_rate_per_tree;
*/
/* INHERITED: Score the model after every so many trees. Disabled if set to 0.
* public int score_tree_interval;
*/
/* INHERITED: Minimum relative improvement in squared error reduction for a split to happen.
* public double min_split_improvement;
*/
/* INHERITED: Destination id for this model; auto-generated if not specified
* public ModelKeyV3 model_id;
*/
/* INHERITED: Training frame
* public FrameKeyV3 training_frame;
*/
/* INHERITED: Validation frame
* public FrameKeyV3 validation_frame;
*/
/* INHERITED: Number of folds for N-fold cross-validation
* public int nfolds;
*/
/* INHERITED: Keep cross-validation model predictions
* public boolean keep_cross_validation_predictions;
*/
/* INHERITED: Keep cross-validation fold assignment
* public boolean keep_cross_validation_fold_assignment;
*/
/* INHERITED: Allow parallel training of cross-validation models
* public boolean parallelize_cross_validation;
*/
/* INHERITED: Response column
* public ColSpecifierV3 response_column;
*/
/* INHERITED: Column with observation weights
* public ColSpecifierV3 weights_column;
*/
/* INHERITED: Offset column
* public ColSpecifierV3 offset_column;
*/
/* INHERITED: Column with cross-validation fold index assignment per observation
* public ColSpecifierV3 fold_column;
*/
/* INHERITED: Cross-validation fold assignment scheme, if fold_column is not specified
* public FoldAssignmentScheme fold_assignment;
*/
/* INHERITED: Ignored columns
* public String[] ignored_columns;
*/
/* INHERITED: Ignore constant columns
* public boolean ignore_const_cols;
*/
/* INHERITED: Whether to score during each iteration of model training
* public boolean score_each_iteration;
*/
/* INHERITED: Model checkpoint to resume training with
* public ModelKeyV3 checkpoint;
*/
/* INHERITED: 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)
* public int stopping_rounds;
*/
/* INHERITED: Maximum allowed runtime in seconds for model training. Use 0 to disable.
* public double max_runtime_secs;
*/
/* INHERITED: Metric to use for early stopping (AUTO: logloss for classification, deviance for regression)
* public StoppingMetric stopping_metric;
*/
/* INHERITED: Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much)
* public double stopping_tolerance;
*/
/** Return the contents of this object as a JSON String. */
@Override
public String toString() {
return new Gson().toJson(this);
}
}