public static final class XGBoostV3.XGBoostParametersV3 extends water.api.schemas3.ModelParametersSchemaV3<XGBoostModel.XGBoostParameters,XGBoostV3.XGBoostParametersV3>
categorical_encoding, checkpoint, distribution, fold_assignment, fold_column, huber_alpha, ignore_const_cols, ignored_columns, keep_cross_validation_fold_assignment, keep_cross_validation_predictions, max_categorical_levels, max_runtime_secs, model_id, nfolds, offset_column, parallelize_cross_validation, quantile_alpha, response_column, score_each_iteration, stopping_metric, stopping_rounds, stopping_tolerance, training_frame, tweedie_power, validation_frame, weights_column| Constructor and Description |
|---|
XGBoostV3.XGBoostParametersV3() |
append_field_arrays, fields, fillFromImpl, fillImpl, writeParametersJSONcreateAndFillImpl, createImpl, extractVersionFromSchemaName, fillFromImpl, fillFromImpl, fillFromParms, fillFromParms, fillImpl, getImplClass, getImplClass, getSchemaName, getSchemaType, getSchemaVersion, init_meta, markdown, markdown, newInstance, newInstance, setField, setSchemaType_doNotCallpublic static java.lang.String[] fields
@API(help="(same as n_estimators) Number of trees.",
gridable=true)
public int ntrees
@API(help="(same as ntrees) Number of trees.",
gridable=true)
public int n_estimators
@API(help="Maximum tree depth.",
gridable=true)
public int max_depth
@API(help="(same as min_child_weight) Fewest allowed (weighted) observations in a leaf.",
gridable=true)
public double min_rows
@API(help="(same as min_rows) Fewest allowed (weighted) observations in a leaf.",
gridable=true)
public double min_child_weight
@API(help="(same as eta) Learning rate (from 0.0 to 1.0)",
gridable=true)
public double learn_rate
@API(help="(same as learn_rate) Learning rate (from 0.0 to 1.0)",
gridable=true)
public double eta
@API(help="(same as subsample) Row sample rate per tree (from 0.0 to 1.0)",
gridable=true)
public double sample_rate
@API(help="(same as sample_rate) Row sample rate per tree (from 0.0 to 1.0)",
gridable=true)
public double subsample
@API(help="(same as colsample_bylevel) Column sample rate (from 0.0 to 1.0)",
gridable=true)
public double col_sample_rate
@API(help="(same as col_sample_rate) Column sample rate (from 0.0 to 1.0)",
gridable=true)
public double colsample_bylevel
@API(help="(same as colsample_bytree) Column sample rate per tree (from 0.0 to 1.0)",
level=secondary,
gridable=true)
public double col_sample_rate_per_tree
@API(help="(same as col_sample_rate_per_tree) Column sample rate per tree (from 0.0 to 1.0)",
level=secondary,
gridable=true)
public double colsample_bytree
@API(help="(same as max_delta_step) Maximum absolute value of a leaf node prediction",
level=expert,
gridable=true)
public float max_abs_leafnode_pred
@API(help="(same as max_abs_leafnode_pred) Maximum absolute value of a leaf node prediction",
level=expert,
gridable=true)
public float max_delta_step
@API(help="Score the model after every so many trees. Disabled if set to 0.",
level=secondary,
gridable=false)
public int score_tree_interval
@API(help="Seed for pseudo random number generator (if applicable)",
gridable=true)
public long seed
@API(help="(same as gamma) Minimum relative improvement in squared error reduction for a split to happen",
level=secondary,
gridable=true)
public float min_split_improvement
@API(help="(same as min_split_improvement) Minimum relative improvement in squared error reduction for a split to happen",
level=secondary,
gridable=true)
public float gamma
@API(help="For tree_method=hist only: maximum number of bins",
level=expert,
gridable=true)
public int max_bin
@API(help="For tree_method=hist only: maximum number of leaves",
level=secondary,
gridable=true)
public int num_leaves
@API(help="For tree_method=hist only: the mininum sum of hessian in a leaf to keep splitting",
level=expert,
gridable=true)
public float min_sum_hessian_in_leaf
@API(help="For tree_method=hist only: the mininum data in a leaf to keep splitting",
level=expert,
gridable=true)
public float min_data_in_leaf
@API(help="Tree method",
values={"auto","exact","approx","hist"},
level=secondary,
gridable=true)
public XGBoostModel.XGBoostParameters.TreeMethod tree_method
@API(help="Grow policy - depthwise is standard GBM, lossguide is LightGBM",
values={"depthwise","lossguide"},
level=secondary,
gridable=true)
public XGBoostModel.XGBoostParameters.GrowPolicy grow_policy
@API(help="Booster type",
values={"gbtree","gblinear","dart"},
level=expert,
gridable=true)
public XGBoostModel.XGBoostParameters.Booster booster
@API(help="L2 regularization",
level=expert,
gridable=true)
public float reg_lambda
@API(help="L1 regularization",
level=expert,
gridable=true)
public float reg_alpha
@API(help="Missing Value Handling",
values={"mean_imputation","skip"},
level=expert,
gridable=true)
public XGBoostModel.XGBoostParameters.MissingValuesHandling missing_values_handling
@API(help="Enable quiet mode",
level=expert,
gridable=false)
public boolean quiet_mode
@API(help="For booster=dart only: sample_type",
values={"uniform","weighted"},
level=expert,
gridable=true)
public XGBoostModel.XGBoostParameters.DartSampleType sample_type
@API(help="For booster=dart only: normalize_type",
values={"tree","forest"},
level=expert,
gridable=true)
public XGBoostModel.XGBoostParameters.DartNormalizeType normalize_type
@API(help="For booster=dart only: rate_drop (0..1)",
level=expert,
gridable=true)
public float rate_drop
@API(help="For booster=dart only: one_drop",
level=expert,
gridable=true)
public boolean one_drop
@API(help="For booster=dart only: skip_drop (0..1)",
level=expert,
gridable=true)
public float skip_drop
@API(help="Type of DMatrix. For sparse, NAs and 0 are treated equally.",
values={"auto","dense","sparse"},
level=secondary,
gridable=true)
public XGBoostModel.XGBoostParameters.DMatrixType dmatrix_type
@API(help="Backend. By default (auto), a GPU is used if available.",
values={"auto","gpu","cpu"},
level=expert,
gridable=true)
public XGBoostModel.XGBoostParameters.Backend backend
@API(help="Which GPU to use. ",
level=expert,
gridable=false)
public int gpu_id