hex.schemas

Class GLMV3.GLMParametersV3

java.lang.Object

water.Iced

water.api.Schema<P,S>

water.api.ModelParametersSchema<GLMModel.GLMParameters,GLMV3.GLMParametersV3>

hex.schemas.GLMV3.GLMParametersV3

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, water.Freezable

Enclosing class:

GLMV3

public static final class GLMV3.GLMParametersV3
extends water.api.ModelParametersSchema<GLMModel.GLMParameters,GLMV3.GLMParametersV3>

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class water.api.Schema

water.api.Schema.Meta

Field Summary

Fields

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
static java.lang.String[]	fields
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
double	prior
GLMModel.GLMParameters.Solver	solver
boolean	standardize
double	tweedie_link_power
double	tweedie_variance_power

Fields inherited from class water.api.ModelParametersSchema

checkpoint, fold_assignment, fold_column, ignore_const_cols, ignored_columns, keep_cross_validation_predictions, model_id, nfolds, offset_column, response_column, score_each_iteration, training_frame, validation_frame, weights_column

Constructor Summary

Constructors

Constructor and Description
GLMV3.GLMParametersV3()

Method Summary

Methods inherited from class water.api.ModelParametersSchema

append_field_arrays, fields, fillFromImpl, fillImpl, writeParametersJSON

Methods inherited from class water.api.Schema

createAndFillImpl, createImpl, fillFromParms, fillFromParms, get__meta, getExperimentalVersion, getHighestSupportedVersion, getImplClass, getImplClass, getLatestVersion, getSchemaVersion, markdown, markdown, markdown, newInstance, newInstance, registerAllSchemasIfNecessary, schema, schema, schemaClass, schemas, setField

Methods inherited from class water.Iced

clone, frozenType, read_impl, read, readExternal, readJSON_impl, readJSON, toJsonString, write_impl, write, writeExternal, writeJSON_impl, writeJSON

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

fields

public static java.lang.String[] fields

family

@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

tweedie_variance_power

@API(help="Tweedie variance power",
     level=critical,
     gridable=true)
public double tweedie_variance_power

tweedie_link_power

@API(help="Tweedie link power",
     level=critical,
     gridable=true)
public double tweedie_link_power

solver

@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

alpha

@API(help="distribution of regularization between L1 and L2.",
     level=critical,
     gridable=true)
public double[] alpha

lambda

@API(help="regularization strength",
     required=false,
     level=critical,
     gridable=true)
public double[] lambda

lambda_search

@API(help="use lambda search starting at lambda max, given lambda is then interpreted as lambda min",
     level=critical)
public boolean lambda_search

nlambdas

@API(help="number of lambdas to be used in a search",
     level=critical)
public int nlambdas

standardize

@API(help="Standardize numeric columns to have zero mean and unit variance",
     level=critical)
public boolean standardize

non_negative

@API(help="Restrict coefficients (not intercept) to be non-negative")
public boolean non_negative

max_iterations

@API(help="Maximum number of iterations",
     level=secondary)
public int max_iterations

beta_epsilon

@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

objective_epsilon

@API(help="converge if  objective value changes less than this",
     level=expert)
public double objective_epsilon

gradient_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

link

@API(help="",
     level=secondary,
     values={"family_default","identity","logit","log","inverse","tweedie"})
public GLMModel.GLMParameters.Link link

intercept

@API(help="include constant term in the model",
     level=expert)
public boolean intercept

prior

@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

lambda_min_ratio

@API(help="min lambda used in lambda search, specified as a ratio of lambda_max",
     level=expert)
public double lambda_min_ratio

beta_constraints

@API(help="beta constraints",
     direction=INPUT)
public water.api.KeyV3.FrameKeyV3 beta_constraints

max_active_predictors

@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

balance_classes

@API(help="Balance training data class counts via over/under-sampling (for imbalanced data).",
     level=secondary,
     direction=INOUT)
public boolean balance_classes

For imbalanced data, balance training data class counts via over/under-sampling. This can result in improved predictive accuracy.

class_sampling_factors

@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

Desired over/under-sampling ratios per class (lexicographic order). Only when balance_classes is enabled. If not specified, they will be automatically computed to obtain class balance during training.

max_after_balance_size

@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

When classes are balanced, limit the resulting dataset size to the specified multiple of the original dataset size.

max_confusion_matrix_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

For classification models, the maximum size (in terms of classes) of the confusion matrix for it to be printed. This option is meant to avoid printing extremely large confusion matrices.

max_hit_ratio_k

@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

The maximum number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable)

Constructor Detail

GLMV3.GLMParametersV3

public GLMV3.GLMParametersV3()