public static final class MaxRGLMV3.MaxRGLMParametersV3 extends water.api.schemas3.ModelParametersSchemaV3<MaxRGLMModel.MaxRGLMParameters,MaxRGLMV3.MaxRGLMParametersV3>
| Modifier and Type | Field and Description |
|---|---|
double[] |
alpha |
boolean |
balance_classes
For imbalanced data, balance training data class counts via
over/under-sampling.
|
water.api.schemas3.KeyV3.FrameKeyV3 |
beta_constraints |
double |
beta_epsilon |
boolean |
calc_like |
float[] |
class_sampling_factors
Desired over/under-sampling ratios per class (lexicographic order).
|
boolean |
cold_start |
boolean |
compute_p_values |
boolean |
early_stopping |
static java.lang.String[] |
fields |
double |
gradient_epsilon |
boolean |
intercept |
double[] |
lambda |
double |
lambda_min_ratio |
boolean |
lambda_search |
int |
max_active_predictors |
float |
max_after_balance_size
When classes are balanced, limit the resulting dataset size to the
specified multiple of the original dataset size.
|
int |
max_confusion_matrix_size
For classification models, the maximum size (in terms of classes) of
the confusion matrix for it to be printed.
|
int |
max_iterations |
int |
max_predictor_number |
GLMModel.GLMParameters.MissingValuesHandling |
missing_values_handling |
int |
nlambdas |
boolean |
non_negative |
int |
nparallelism |
double |
obj_reg |
double |
objective_epsilon |
water.api.schemas3.KeyV3.FrameKeyV3 |
plug_values |
double |
prior |
boolean |
remove_collinear_columns |
int |
score_iteration_interval |
long |
seed |
GLMModel.GLMParameters.Solver |
solver |
boolean |
standardize |
double[] |
startval |
auc_type, categorical_encoding, checkpoint, custom_distribution_func, custom_metric_func, distribution, export_checkpoints_dir, fold_assignment, fold_column, gainslift_bins, huber_alpha, ignore_const_cols, ignored_columns, keep_cross_validation_fold_assignment, keep_cross_validation_models, 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 |
|---|
MaxRGLMParametersV3() |
append_field_arrays, extractDeclaredApiParameters, fields, fillFromImpl, fillImpl, getAdditionalParameters, writeParametersJSONcreateAndFillImpl, createImpl, extractVersionFromSchemaName, fillFromAny, fillFromBody, fillFromImpl, fillFromImpl, fillFromParms, fillFromParms, fillFromParms, fillImpl, getImplClass, getImplClass, getSchemaName, getSchemaType, getSchemaVersion, init_meta, markdown, markdown, newInstance, newInstance, setField, setSchemaType_doNotCallpublic static final java.lang.String[] fields
@API(help="Seed for pseudo random number generator (if applicable)",
gridable=true)
public long seed
@API(help="AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on problems with small number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for datasets with many columns.",
values={"AUTO","IRLSM","L_BFGS","COORDINATE_DESCENT_NAIVE","COORDINATE_DESCENT","GRADIENT_DESCENT_LH","GRADIENT_DESCENT_SQERR"},
level=critical)
public GLMModel.GLMParameters.Solver solver
@API(help="Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for alpha represents Lasso regression, a value of 0 produces Ridge regression, and anything in between specifies the amount of mixing between the two. Default value of alpha is 0 when SOLVER = \'L-BFGS\'; 0.5 otherwise.",
level=critical,
gridable=true)
public double[] alpha
@API(help="Regularization strength",
required=false,
level=critical,
gridable=true)
public double[] lambda
@API(help="Use lambda search starting at lambda max, given lambda is then interpreted as lambda min",
level=critical)
public boolean lambda_search
@API(help="Stop early when there is no more relative improvement on train or validation (if provided)") public boolean early_stopping
@API(help="Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda search set to True, the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression) otherwise it is set to 100.",
level=critical)
public int nlambdas
@API(help="Perform scoring for every score_iteration_interval iterations",
level=secondary)
public int score_iteration_interval
@API(help="Standardize numeric columns to have zero mean and unit variance",
level=critical)
public boolean standardize
@API(help="Only applicable to multiple alpha/lambda values. If false, build the next model for next set of alpha/lambda values starting from the values provided by current model. If true will start GLM model from scratch.",
level=critical)
public boolean cold_start
@API(help="Handling of missing values. Either MeanImputation, Skip or PlugValues.",
values={"MeanImputation","Skip","PlugValues"},
level=expert,
direction=INOUT,
gridable=true)
public GLMModel.GLMParameters.MissingValuesHandling missing_values_handling
@API(help="Plug Values (a single row frame containing values that will be used to impute missing values of the training/validation frame, use with conjunction missing_values_handling = PlugValues)",
direction=INPUT)
public water.api.schemas3.KeyV3.FrameKeyV3 plug_values
@API(help="Restrict coefficients (not intercept) to be non-negative") public boolean non_negative
@API(help="Maximum number of iterations",
level=secondary)
public int max_iterations
@API(help="Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to IRLSM solver ",
level=expert)
public double beta_epsilon
@API(help="Converge if objective value changes less than this. Default indicates: If lambda_search is set to True the value of objective_epsilon is set to .0001. If the lambda_search is set to False and lambda is equal to zero, the value of objective_epsilon is set to .000001, for any other value of lambda the default value of objective_epsilon is set to .0001.",
level=expert)
public double objective_epsilon
@API(help="Converge if objective changes less (using L-infinity norm) than this, ONLY applies to L-BFGS solver. Default indicates: If lambda_search is set to False and lambda is equal to zero, the default value of gradient_epsilon is equal to .000001, otherwise the default value is .0001. If lambda_search is set to True, the conditional values above are 1E-8 and 1E-6 respectively.",
level=expert)
public double gradient_epsilon
@API(help="Likelihood divider in objective value computation, default is 1/nobs") public double obj_reg
@API(help="double array to initialize fixed and random coefficients for HGLM, coefficients for GLM.",
gridable=true)
public double[] startval
@API(help="if true, will return likelihood function value for HGLM.") public boolean calc_like
@API(help="Include constant term in the model",
level=expert)
public boolean intercept
@API(help="Prior probability for y==1. To be used only for logistic regression iff the data has been sampled and the mean of response does not reflect reality.",
level=expert)
public double prior
@API(help="Minimum lambda used in lambda search, specified as a ratio of lambda_max (the smallest lambda that drives all coefficients to zero). Default indicates: if the number of observations is greater than the number of variables, then lambda_min_ratio is set to 0.0001; if the number of observations is less than the number of variables, then lambda_min_ratio is set to 0.01.",
level=expert)
public double lambda_min_ratio
@API(help="Beta constraints",
direction=INPUT)
public water.api.schemas3.KeyV3.FrameKeyV3 beta_constraints
@API(help="Maximum number of active predictors during computation. Use as a stopping criterion to prevent expensive model building with many predictors. Default indicates: If the IRLSM solver is used, the value of max_active_predictors is set to 5000 otherwise it is set to 100000000.",
direction=INPUT,
level=expert)
public int max_active_predictors
@API(help="Balance training data class counts via over/under-sampling (for imbalanced data).",
level=secondary,
direction=INOUT)
public boolean balance_classes
@API(help="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.",
level=expert,
direction=INOUT)
public float[] class_sampling_factors
@API(help="Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes.",
level=expert,
direction=INOUT)
public float max_after_balance_size
@API(help="[Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs",
level=secondary,
direction=INOUT)
public int max_confusion_matrix_size
@API(help="Request p-values computation, p-values work only with IRLSM solver and no regularization",
level=secondary,
direction=INPUT)
public boolean compute_p_values
@API(help="In case of linearly dependent columns, remove some of the dependent columns",
level=secondary,
direction=INPUT)
public boolean remove_collinear_columns
@API(help="Maximum number of predictors to be considered when building GLM models. Defaiult to 1.",
level=secondary,
direction=INPUT)
public int max_predictor_number
@API(help="number of models to build in parallel. Default to 0.0 which is adaptive to the system capability",
level=secondary,
gridable=true)
public int nparallelism