public static final class GLMV3.GLMParametersV3 extends water.api.ModelParametersSchema<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.KeyV3.FrameKeyV3 |
beta_constraints |
double |
beta_epsilon |
float[] |
class_sampling_factors
Desired over/under-sampling ratios per class (lexicographic order).
|
GLMModel.GLMParameters.Family |
family |
double |
gradient_epsilon |
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 |
int |
nlambdas |
boolean |
non_negative |
double |
objective_epsilon |
water.api.FrameV3.ColSpecifierV3 |
offset_column |
static java.lang.String[] |
own_fields |
double |
prior |
water.api.FrameV3.ColSpecifierV3 |
response_column |
GLMModel.GLMParameters.Solver |
solver |
boolean |
standardize |
double |
tweedie_link_power |
double |
tweedie_variance_power |
water.api.FrameV3.ColSpecifierV3 |
weights_column |
Constructor and Description |
---|
GLMV3.GLMParametersV3() |
append_field_arrays, fields, fillFromImpl, fillImpl, writeParametersJSON
acceptsFrame, createAndFillImpl, createImpl, extractVersion, fillFromParms, getExperimentalVersion, getHighestSupportedVersion, getImplClass, getImplClass, getLatestVersion, getSchemaVersion, markdown, markdown, markdown, markdown, newInstance, register, registerAllSchemasIfNecessary, schema, schema, schema, schema, schema, schemaClass, schemaClass, schemaClass, schemaClass, schemas
public static java.lang.String[] own_fields
@API(help="Response column", is_member_of_frames={"training_frame","validation_frame"}, is_mutually_exclusive_with="ignored_columns", direction=INOUT) public water.api.FrameV3.ColSpecifierV3 response_column
@API(help="Column with observation weights", is_member_of_frames={"training_frame","validation_frame"}, is_mutually_exclusive_with={"ignored_columns","response_column"}, direction=INOUT) public water.api.FrameV3.ColSpecifierV3 weights_column
@API(help="Offset column", is_member_of_frames={"training_frame","validation_frame"}, is_mutually_exclusive_with={"ignored_columns","response_column","weights_column"}, direction=INOUT) public water.api.FrameV3.ColSpecifierV3 offset_column
@API(help="Family. Use binomial for classification with logistic regression, others are for regression problems.", values={"gaussian","binomial","poisson","gamma","tweedie"}, level=critical) public GLMModel.GLMParameters.Family family
@API(help="Tweedie variance power", level=critical) public double tweedie_variance_power
@API(help="Tweedie link power", level=critical) public double tweedie_link_power
@API(help="Auto will pick solver better suited for the given dataset, in case of lambda search solvers may be changed during computation. 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"}, level=critical) public GLMModel.GLMParameters.Solver solver
@API(help="distribution of regularization between L1 and L2.", level=critical) public double[] alpha
@API(help="regularization strength", required=false, level=critical) 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="number of lambdas to be used in a search", level=critical) public int nlambdas
@API(help="Standardize numeric columns to have zero mean and unit variance", level=critical) public boolean standardize
@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", 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", level=expert) public double gradient_epsilon
@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", level=expert) public double lambda_min_ratio
@API(help="beta constraints", direction=INPUT) public water.api.KeyV3.FrameKeyV3 beta_constraints
@API(help="Maximum number of active predictors during computation. Use as a stopping criterium to prevent expensive model building with many predictors.", 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="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