public static final class GLMV3.GLMParametersV3 extends water.api.schemas3.ModelParametersSchemaV3<GLMModel.GLMParameters,GLMV3.GLMParametersV3>
| 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 |
float[] |
class_sampling_factors
Desired over/under-sampling ratios per class (lexicographic order).
|
boolean |
compute_p_values |
boolean |
early_stopping |
GLMModel.GLMParameters.Family |
family |
static java.lang.String[] |
fields |
double |
gradient_epsilon |
java.lang.String[] |
interactions |
boolean |
intercept |
double[] |
lambda |
double |
lambda_min_ratio |
boolean |
lambda_search |
GLMModel.GLMParameters.Link |
link |
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_hit_ratio_k
The maximum number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable)
|
int |
max_iterations |
DeepLearningModel.DeepLearningParameters.MissingValuesHandling |
missing_values_handling |
int |
nlambdas |
boolean |
non_negative |
double |
obj_reg |
double |
objective_epsilon |
double |
prior |
boolean |
remove_collinear_columns |
long |
seed |
GLMModel.GLMParameters.Solver |
solver |
boolean |
standardize |
double |
tweedie_link_power |
double |
tweedie_variance_power |
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 |
|---|
GLMV3.GLMParametersV3() |
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="Seed for pseudo random number generator (if applicable)",
gridable=true)
public long seed
@API(help="Family. Use binomial for classification with logistic regression, others are for regression problems.",
values={"gaussian","binomial","quasibinomial","multinomial","poisson","gamma","tweedie"},
level=critical)
public GLMModel.GLMParameters.Family family
@API(help="Tweedie variance power",
level=critical,
gridable=true)
public double tweedie_variance_power
@API(help="Tweedie link power",
level=critical,
gridable=true)
public double tweedie_link_power
@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. Coordinate descent is experimental (beta).",
values={"AUTO","IRLSM","L_BFGS","COORDINATE_DESCENT_NAIVE","COORDINATE_DESCENT"},
level=critical)
public GLMModel.GLMParameters.Solver solver
@API(help="distribution of regularization between L1 and L2. 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="Standardize numeric columns to have zero mean and unit variance",
level=critical)
public boolean standardize
@API(help="Handling of missing values. Either MeanImputation or Skip.",
values={"MeanImputation","Skip"},
level=expert,
direction=INOUT,
gridable=true)
public DeepLearningModel.DeepLearningParameters.MissingValuesHandling missing_values_handling
@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="",
level=secondary,
values={"family_default","identity","logit","log","inverse","tweedie"})
public GLMModel.GLMParameters.Link link
@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="Min lambda used in lambda search, specified as a ratio of lambda_max. 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 7000 otherwise it is set to 100000000.",
direction=INPUT,
level=expert)
public int max_active_predictors
@API(help="A list of predictor column indices to interact. All pairwise combinations will be computed for the list.",
direction=INPUT,
level=expert)
public java.lang.String[] interactions
@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="Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable)",
level=secondary,
direction=INOUT)
public int max_hit_ratio_k
@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