Nothing
# This file is auto-generated by h2o-3/h2o-bindings/bin/gen_R.py
# Copyright 2016 H2O.ai; Apache License Version 2.0 (see LICENSE for details)
#'
# -------------------------- Model Selection -------------------------- #
#'
#' H2O ModelSelection is used to build the best model with one predictor, two predictors, ... up to max_predictor_number
#' specified in the algorithm parameters when mode=allsubsets. The best model is the one with the highest R2 value. When
#' mode=maxr, the model returned is no longer guaranteed to have the best R2 value.
#'
#' @param x (Optional) A vector containing the names or indices of the predictor variables to use in building the model.
#' If x is missing, then all columns except y are used.
#' @param y The name or column index of the response variable in the data.
#' The response must be either a numeric or a categorical/factor variable.
#' If the response is numeric, then a regression model will be trained, otherwise it will train a classification model.
#' @param training_frame Id of the training data frame.
#' @param model_id Destination id for this model; auto-generated if not specified.
#' @param validation_frame Id of the validation data frame.
#' @param nfolds Number of folds for K-fold cross-validation (0 to disable or >= 2). Defaults to 0.
#' @param seed Seed for random numbers (affects certain parts of the algo that are stochastic and those might or might not be enabled by default).
#' Defaults to -1 (time-based random number).
#' @param fold_assignment Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified' option will
#' stratify the folds based on the response variable, for classification problems. Must be one of: "AUTO",
#' "Random", "Modulo", "Stratified". Defaults to AUTO.
#' @param fold_column Column with cross-validation fold index assignment per observation.
#' @param ignore_const_cols \code{Logical}. Ignore constant columns. Defaults to TRUE.
#' @param score_each_iteration \code{Logical}. Whether to score during each iteration of model training. Defaults to FALSE.
#' @param score_iteration_interval Perform scoring for every score_iteration_interval iterations Defaults to 0.
#' @param offset_column Offset column. This will be added to the combination of columns before applying the link function.
#' @param weights_column Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from
#' the dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative
#' weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the
#' data frame. This is typically the number of times a row is repeated, but non-integer values are supported as
#' well. During training, rows with higher weights matter more, due to the larger loss function pre-factor. If
#' you set weight = 0 for a row, the returned prediction frame at that row is zero and this is incorrect. To get
#' an accurate prediction, remove all rows with weight == 0.
#' @param family Family. For maxr/maxrsweep, only gaussian. For backward, ordinal and multinomial families are not supported
#' Must be one of: "AUTO", "gaussian", "binomial", "fractionalbinomial", "quasibinomial", "poisson", "gamma",
#' "tweedie", "negativebinomial". Defaults to AUTO.
#' @param link Link function. Must be one of: "family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit".
#' Defaults to family_default.
#' @param tweedie_variance_power Tweedie variance power Defaults to 0.
#' @param tweedie_link_power Tweedie link power Defaults to 0.
#' @param theta Theta Defaults to 0.
#' @param solver 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. Must be one of: "AUTO", "IRLSM", "L_BFGS", "COORDINATE_DESCENT_NAIVE", "COORDINATE_DESCENT",
#' "GRADIENT_DESCENT_LH", "GRADIENT_DESCENT_SQERR". Defaults to IRLSM.
#' @param alpha 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.
#' @param lambda Regularization strength Defaults to c(0.0).
#' @param lambda_search \code{Logical}. Use lambda search starting at lambda max, given lambda is then interpreted as lambda min
#' Defaults to FALSE.
#' @param early_stopping \code{Logical}. Stop early when there is no more relative improvement on train or validation (if provided)
#' Defaults to FALSE.
#' @param nlambdas 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.
#' Defaults to 0.
#' @param standardize \code{Logical}. Standardize numeric columns to have zero mean and unit variance Defaults to TRUE.
#' @param missing_values_handling Handling of missing values. Either MeanImputation, Skip or PlugValues. Must be one of: "MeanImputation",
#' "Skip", "PlugValues". Defaults to MeanImputation.
#' @param plug_values 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)
#' @param compute_p_values \code{Logical}. Request p-values computation, p-values work only with IRLSM solver and no regularization
#' Defaults to FALSE.
#' @param remove_collinear_columns \code{Logical}. In case of linearly dependent columns, remove some of the dependent columns Defaults to FALSE.
#' @param intercept \code{Logical}. Include constant term in the model Defaults to TRUE.
#' @param non_negative \code{Logical}. Restrict coefficients (not intercept) to be non-negative Defaults to FALSE.
#' @param max_iterations Maximum number of iterations Defaults to 0.
#' @param objective_epsilon Converge if objective value changes less than this. Default (of -1.0) 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. Defaults to -1.
#' @param beta_epsilon Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to IRLSM solver
#' Defaults to 0.0001.
#' @param gradient_epsilon Converge if objective changes less (using L-infinity norm) than this, ONLY applies to L-BFGS solver. Default
#' (of -1.0) 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. Defaults to -1.
#' @param startval double array to initialize fixed and random coefficients for HGLM, coefficients for GLM.
#' @param prior 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. Defaults to 0.
#' @param cold_start \code{Logical}. 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. Defaults to FALSE.
#' @param lambda_min_ratio 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. Defaults to 0.
#' @param beta_constraints Beta constraints
#' @param max_active_predictors 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. Defaults to -1.
#' @param obj_reg Likelihood divider in objective value computation, default (of -1.0) will set it to 1/nobs Defaults to -1.
#' @param stopping_rounds Early stopping based on convergence of stopping_metric. Stop if simple moving average of length k of the
#' stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable) Defaults to 0.
#' @param stopping_metric Metric to use for early stopping (AUTO: logloss for classification, deviance for regression and anomaly_score
#' for Isolation Forest). Note that custom and custom_increasing can only be used in GBM and DRF with the Python
#' client. Must be one of: "AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "AUCPR",
#' "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing". Defaults to
#' AUTO.
#' @param stopping_tolerance Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this
#' much) Defaults to 0.001.
#' @param balance_classes \code{Logical}. Balance training data class counts via over/under-sampling (for imbalanced data). Defaults to
#' FALSE.
#' @param class_sampling_factors 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.
#' @param max_after_balance_size Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires
#' balance_classes. Defaults to 5.0.
#' @param max_runtime_secs Maximum allowed runtime in seconds for model training. Use 0 to disable. Defaults to 0.
#' @param custom_metric_func Reference to custom evaluation function, format: `language:keyName=funcName`
#' @param nparallelism number of models to build in parallel. Defaults to 0.0 which is adaptive to the system capability Defaults to
#' 0.
#' @param max_predictor_number Maximum number of predictors to be considered when building GLM models. Defaults to 1. Defaults to 1.
#' @param min_predictor_number For mode = 'backward' only. Minimum number of predictors to be considered when building GLM models starting
#' with all predictors to be included. Defaults to 1. Defaults to 1.
#' @param mode Mode: Used to choose model selection algorithms to use. Options include 'allsubsets' for all subsets, 'maxr'
#' that uses sequential replacement and GLM to build all models, slow but works with cross-validation, validation
#' frames for more robust results, 'maxrsweep' that uses sequential replacement and sweeping action, much faster
#' than 'maxr', 'backward' for backward selection. Must be one of: "allsubsets", "maxr", "maxrsweep", "backward".
#' Defaults to maxr.
#' @param build_glm_model \code{Logical}. For maxrsweep mode only. If true, will return full blown GLM models with the desired
#' predictorsubsets. If false, only the predictor subsets, predictor coefficients are returned. This is
#' forspeeding up the model selection process. The users can choose to build the GLM models themselvesby using
#' the predictor subsets themselves. Defaults to false. Defaults to FALSE.
#' @param p_values_threshold For mode='backward' only. If specified, will stop the model building process when all coefficientsp-values
#' drop below this threshold Defaults to 0.
#' @param influence If set to dfbetas will calculate the difference in beta when a datarow is included and excluded in the
#' dataset. Must be one of: "dfbetas".
#' @param multinode_mode \code{Logical}. For maxrsweep only. If enabled, will attempt to perform sweeping action using multiple nodes
#' in the cluster. Defaults to false. Defaults to FALSE.
#' @examples
#' \dontrun{
#' library(h2o)
#' h2o.init()
#' # Run ModelSelection of VOL ~ all predictors
#' prostate_path <- system.file("extdata", "prostate.csv", package = "h2o")
#' prostate <- h2o.uploadFile(path = prostate_path)
#' prostate$CAPSULE <- as.factor(prostate$CAPSULE)
#' model <- h2o.modelSelection(y="VOL", x=c("RACE","AGE","RACE","DPROS"), training_frame=prostate)
#' }
#' @export
h2o.modelSelection <- function(x,
y,
training_frame,
model_id = NULL,
validation_frame = NULL,
nfolds = 0,
seed = -1,
fold_assignment = c("AUTO", "Random", "Modulo", "Stratified"),
fold_column = NULL,
ignore_const_cols = TRUE,
score_each_iteration = FALSE,
score_iteration_interval = 0,
offset_column = NULL,
weights_column = NULL,
family = c("AUTO", "gaussian", "binomial", "fractionalbinomial", "quasibinomial", "poisson", "gamma", "tweedie", "negativebinomial"),
link = c("family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"),
tweedie_variance_power = 0,
tweedie_link_power = 0,
theta = 0,
solver = c("AUTO", "IRLSM", "L_BFGS", "COORDINATE_DESCENT_NAIVE", "COORDINATE_DESCENT", "GRADIENT_DESCENT_LH", "GRADIENT_DESCENT_SQERR"),
alpha = NULL,
lambda = c(0.0),
lambda_search = FALSE,
early_stopping = FALSE,
nlambdas = 0,
standardize = TRUE,
missing_values_handling = c("MeanImputation", "Skip", "PlugValues"),
plug_values = NULL,
compute_p_values = FALSE,
remove_collinear_columns = FALSE,
intercept = TRUE,
non_negative = FALSE,
max_iterations = 0,
objective_epsilon = -1,
beta_epsilon = 0.0001,
gradient_epsilon = -1,
startval = NULL,
prior = 0,
cold_start = FALSE,
lambda_min_ratio = 0,
beta_constraints = NULL,
max_active_predictors = -1,
obj_reg = -1,
stopping_rounds = 0,
stopping_metric = c("AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "AUCPR", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing"),
stopping_tolerance = 0.001,
balance_classes = FALSE,
class_sampling_factors = NULL,
max_after_balance_size = 5.0,
max_runtime_secs = 0,
custom_metric_func = NULL,
nparallelism = 0,
max_predictor_number = 1,
min_predictor_number = 1,
mode = c("allsubsets", "maxr", "maxrsweep", "backward"),
build_glm_model = FALSE,
p_values_threshold = 0,
influence = c("dfbetas"),
multinode_mode = FALSE)
{
# Validate required training_frame first and other frame args: should be a valid key or an H2OFrame object
training_frame <- .validate.H2OFrame(training_frame, required=TRUE)
validation_frame <- .validate.H2OFrame(validation_frame, required=FALSE)
# Validate other required args
# If x is missing, then assume user wants to use all columns as features.
if (missing(x)) {
if (is.numeric(y)) {
x <- setdiff(col(training_frame), y)
} else {
x <- setdiff(colnames(training_frame), y)
}
}
# Build parameter list to send to model builder
parms <- list()
parms$training_frame <- training_frame
args <- .verify_dataxy(training_frame, x, y)
parms$ignored_columns <- args$x_ignore
parms$response_column <- args$y
if (!missing(model_id))
parms$model_id <- model_id
if (!missing(validation_frame))
parms$validation_frame <- validation_frame
if (!missing(nfolds))
parms$nfolds <- nfolds
if (!missing(seed))
parms$seed <- seed
if (!missing(fold_assignment))
parms$fold_assignment <- fold_assignment
if (!missing(fold_column))
parms$fold_column <- fold_column
if (!missing(ignore_const_cols))
parms$ignore_const_cols <- ignore_const_cols
if (!missing(score_each_iteration))
parms$score_each_iteration <- score_each_iteration
if (!missing(score_iteration_interval))
parms$score_iteration_interval <- score_iteration_interval
if (!missing(offset_column))
parms$offset_column <- offset_column
if (!missing(weights_column))
parms$weights_column <- weights_column
if (!missing(family))
parms$family <- family
if (!missing(link))
parms$link <- link
if (!missing(tweedie_variance_power))
parms$tweedie_variance_power <- tweedie_variance_power
if (!missing(tweedie_link_power))
parms$tweedie_link_power <- tweedie_link_power
if (!missing(theta))
parms$theta <- theta
if (!missing(solver))
parms$solver <- solver
if (!missing(alpha))
parms$alpha <- alpha
if (!missing(lambda))
parms$lambda <- lambda
if (!missing(lambda_search))
parms$lambda_search <- lambda_search
if (!missing(early_stopping))
parms$early_stopping <- early_stopping
if (!missing(nlambdas))
parms$nlambdas <- nlambdas
if (!missing(standardize))
parms$standardize <- standardize
if (!missing(missing_values_handling))
parms$missing_values_handling <- missing_values_handling
if (!missing(plug_values))
parms$plug_values <- plug_values
if (!missing(compute_p_values))
parms$compute_p_values <- compute_p_values
if (!missing(remove_collinear_columns))
parms$remove_collinear_columns <- remove_collinear_columns
if (!missing(intercept))
parms$intercept <- intercept
if (!missing(non_negative))
parms$non_negative <- non_negative
if (!missing(max_iterations))
parms$max_iterations <- max_iterations
if (!missing(objective_epsilon))
parms$objective_epsilon <- objective_epsilon
if (!missing(beta_epsilon))
parms$beta_epsilon <- beta_epsilon
if (!missing(gradient_epsilon))
parms$gradient_epsilon <- gradient_epsilon
if (!missing(startval))
parms$startval <- startval
if (!missing(prior))
parms$prior <- prior
if (!missing(cold_start))
parms$cold_start <- cold_start
if (!missing(lambda_min_ratio))
parms$lambda_min_ratio <- lambda_min_ratio
if (!missing(beta_constraints))
parms$beta_constraints <- beta_constraints
if (!missing(max_active_predictors))
parms$max_active_predictors <- max_active_predictors
if (!missing(obj_reg))
parms$obj_reg <- obj_reg
if (!missing(stopping_rounds))
parms$stopping_rounds <- stopping_rounds
if (!missing(stopping_metric))
parms$stopping_metric <- stopping_metric
if (!missing(stopping_tolerance))
parms$stopping_tolerance <- stopping_tolerance
if (!missing(balance_classes))
parms$balance_classes <- balance_classes
if (!missing(class_sampling_factors))
parms$class_sampling_factors <- class_sampling_factors
if (!missing(max_after_balance_size))
parms$max_after_balance_size <- max_after_balance_size
if (!missing(max_runtime_secs))
parms$max_runtime_secs <- max_runtime_secs
if (!missing(custom_metric_func))
parms$custom_metric_func <- custom_metric_func
if (!missing(nparallelism))
parms$nparallelism <- nparallelism
if (!missing(max_predictor_number))
parms$max_predictor_number <- max_predictor_number
if (!missing(min_predictor_number))
parms$min_predictor_number <- min_predictor_number
if (!missing(mode))
parms$mode <- mode
if (!missing(build_glm_model))
parms$build_glm_model <- build_glm_model
if (!missing(p_values_threshold))
parms$p_values_threshold <- p_values_threshold
if (!missing(influence))
parms$influence <- influence
if (!missing(multinode_mode))
parms$multinode_mode <- multinode_mode
# Error check and build model
model <- .h2o.modelJob('modelselection', parms, h2oRestApiVersion=3, verbose=FALSE)
return(model)
}
.h2o.train_segments_modelselection <- function(x,
y,
training_frame,
validation_frame = NULL,
nfolds = 0,
seed = -1,
fold_assignment = c("AUTO", "Random", "Modulo", "Stratified"),
fold_column = NULL,
ignore_const_cols = TRUE,
score_each_iteration = FALSE,
score_iteration_interval = 0,
offset_column = NULL,
weights_column = NULL,
family = c("AUTO", "gaussian", "binomial", "fractionalbinomial", "quasibinomial", "poisson", "gamma", "tweedie", "negativebinomial"),
link = c("family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"),
tweedie_variance_power = 0,
tweedie_link_power = 0,
theta = 0,
solver = c("AUTO", "IRLSM", "L_BFGS", "COORDINATE_DESCENT_NAIVE", "COORDINATE_DESCENT", "GRADIENT_DESCENT_LH", "GRADIENT_DESCENT_SQERR"),
alpha = NULL,
lambda = c(0.0),
lambda_search = FALSE,
early_stopping = FALSE,
nlambdas = 0,
standardize = TRUE,
missing_values_handling = c("MeanImputation", "Skip", "PlugValues"),
plug_values = NULL,
compute_p_values = FALSE,
remove_collinear_columns = FALSE,
intercept = TRUE,
non_negative = FALSE,
max_iterations = 0,
objective_epsilon = -1,
beta_epsilon = 0.0001,
gradient_epsilon = -1,
startval = NULL,
prior = 0,
cold_start = FALSE,
lambda_min_ratio = 0,
beta_constraints = NULL,
max_active_predictors = -1,
obj_reg = -1,
stopping_rounds = 0,
stopping_metric = c("AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "AUCPR", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing"),
stopping_tolerance = 0.001,
balance_classes = FALSE,
class_sampling_factors = NULL,
max_after_balance_size = 5.0,
max_runtime_secs = 0,
custom_metric_func = NULL,
nparallelism = 0,
max_predictor_number = 1,
min_predictor_number = 1,
mode = c("allsubsets", "maxr", "maxrsweep", "backward"),
build_glm_model = FALSE,
p_values_threshold = 0,
influence = c("dfbetas"),
multinode_mode = FALSE,
segment_columns = NULL,
segment_models_id = NULL,
parallelism = 1)
{
# formally define variables that were excluded from function parameters
model_id <- NULL
verbose <- NULL
destination_key <- NULL
# Validate required training_frame first and other frame args: should be a valid key or an H2OFrame object
training_frame <- .validate.H2OFrame(training_frame, required=TRUE)
validation_frame <- .validate.H2OFrame(validation_frame, required=FALSE)
# Validate other required args
# If x is missing, then assume user wants to use all columns as features.
if (missing(x)) {
if (is.numeric(y)) {
x <- setdiff(col(training_frame), y)
} else {
x <- setdiff(colnames(training_frame), y)
}
}
# Build parameter list to send to model builder
parms <- list()
parms$training_frame <- training_frame
args <- .verify_dataxy(training_frame, x, y)
parms$ignored_columns <- args$x_ignore
parms$response_column <- args$y
if (!missing(validation_frame))
parms$validation_frame <- validation_frame
if (!missing(nfolds))
parms$nfolds <- nfolds
if (!missing(seed))
parms$seed <- seed
if (!missing(fold_assignment))
parms$fold_assignment <- fold_assignment
if (!missing(fold_column))
parms$fold_column <- fold_column
if (!missing(ignore_const_cols))
parms$ignore_const_cols <- ignore_const_cols
if (!missing(score_each_iteration))
parms$score_each_iteration <- score_each_iteration
if (!missing(score_iteration_interval))
parms$score_iteration_interval <- score_iteration_interval
if (!missing(offset_column))
parms$offset_column <- offset_column
if (!missing(weights_column))
parms$weights_column <- weights_column
if (!missing(family))
parms$family <- family
if (!missing(link))
parms$link <- link
if (!missing(tweedie_variance_power))
parms$tweedie_variance_power <- tweedie_variance_power
if (!missing(tweedie_link_power))
parms$tweedie_link_power <- tweedie_link_power
if (!missing(theta))
parms$theta <- theta
if (!missing(solver))
parms$solver <- solver
if (!missing(alpha))
parms$alpha <- alpha
if (!missing(lambda))
parms$lambda <- lambda
if (!missing(lambda_search))
parms$lambda_search <- lambda_search
if (!missing(early_stopping))
parms$early_stopping <- early_stopping
if (!missing(nlambdas))
parms$nlambdas <- nlambdas
if (!missing(standardize))
parms$standardize <- standardize
if (!missing(missing_values_handling))
parms$missing_values_handling <- missing_values_handling
if (!missing(plug_values))
parms$plug_values <- plug_values
if (!missing(compute_p_values))
parms$compute_p_values <- compute_p_values
if (!missing(remove_collinear_columns))
parms$remove_collinear_columns <- remove_collinear_columns
if (!missing(intercept))
parms$intercept <- intercept
if (!missing(non_negative))
parms$non_negative <- non_negative
if (!missing(max_iterations))
parms$max_iterations <- max_iterations
if (!missing(objective_epsilon))
parms$objective_epsilon <- objective_epsilon
if (!missing(beta_epsilon))
parms$beta_epsilon <- beta_epsilon
if (!missing(gradient_epsilon))
parms$gradient_epsilon <- gradient_epsilon
if (!missing(startval))
parms$startval <- startval
if (!missing(prior))
parms$prior <- prior
if (!missing(cold_start))
parms$cold_start <- cold_start
if (!missing(lambda_min_ratio))
parms$lambda_min_ratio <- lambda_min_ratio
if (!missing(beta_constraints))
parms$beta_constraints <- beta_constraints
if (!missing(max_active_predictors))
parms$max_active_predictors <- max_active_predictors
if (!missing(obj_reg))
parms$obj_reg <- obj_reg
if (!missing(stopping_rounds))
parms$stopping_rounds <- stopping_rounds
if (!missing(stopping_metric))
parms$stopping_metric <- stopping_metric
if (!missing(stopping_tolerance))
parms$stopping_tolerance <- stopping_tolerance
if (!missing(balance_classes))
parms$balance_classes <- balance_classes
if (!missing(class_sampling_factors))
parms$class_sampling_factors <- class_sampling_factors
if (!missing(max_after_balance_size))
parms$max_after_balance_size <- max_after_balance_size
if (!missing(max_runtime_secs))
parms$max_runtime_secs <- max_runtime_secs
if (!missing(custom_metric_func))
parms$custom_metric_func <- custom_metric_func
if (!missing(nparallelism))
parms$nparallelism <- nparallelism
if (!missing(max_predictor_number))
parms$max_predictor_number <- max_predictor_number
if (!missing(min_predictor_number))
parms$min_predictor_number <- min_predictor_number
if (!missing(mode))
parms$mode <- mode
if (!missing(build_glm_model))
parms$build_glm_model <- build_glm_model
if (!missing(p_values_threshold))
parms$p_values_threshold <- p_values_threshold
if (!missing(influence))
parms$influence <- influence
if (!missing(multinode_mode))
parms$multinode_mode <- multinode_mode
# Build segment-models specific parameters
segment_parms <- list()
if (!missing(segment_columns))
segment_parms$segment_columns <- segment_columns
if (!missing(segment_models_id))
segment_parms$segment_models_id <- segment_models_id
segment_parms$parallelism <- parallelism
# Error check and build segment models
segment_models <- .h2o.segmentModelsJob('modelselection', segment_parms, parms, h2oRestApiVersion=3)
return(segment_models)
}
#' Extracts the best R2 values for all predictor subset size.
#'
#' @param model is a H2OModel with algorithm name of modelselection
#' @export
h2o.get_best_r2_values<- function(model) {
if( is(model, "H2OModel") && (model@algorithm=='modelselection'))
return(model@model$best_r2_values)
}
#' Extracts the predictor added to model at each step.
#'
#' @param model is a H2OModel with algorithm name of modelselection
#' @export
h2o.get_predictors_added_per_step<- function(model) {
if( is(model, "H2OModel") && (model@algorithm=='modelselection')) {
if (model@allparameters$mode != 'backward') {
return(model@model$predictors_added_per_step)
} else {
stop("h2o.get_predictors_added_per_step can not be called with model = backward")
}
}
}
#' Extracts the predictor removed to model at each step.
#'
#' @param model is a H2OModel with algorithm name of modelselection
#' @export
h2o.get_predictors_removed_per_step<- function(model) {
if( is(model, "H2OModel") && (model@algorithm=='modelselection')) {
return(model@model$predictors_removed_per_step)
}
}
#' Extracts the subset of predictor names that yield the best R2 value for each predictor subset size.
#'
#' @param model is a H2OModel with algorithm name of modelselection
#' @export
h2o.get_best_model_predictors<-function(model) {
if ( is(model, "H2OModel") && (model@algorithm=='modelselection'))
return(model@model$best_predictors_subset)
}
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.