Engine docs for h2o

R/boost_tree_h2o.R

@@ -0,0 +1,13 @@
+#' Boosted trees via h2o
+#'
+#' [h2o::h2o.xgboost()] creates a series of decision trees
+#'  forming an ensemble. Each tree depends on the results of previous trees.
+#'  All trees in the ensemble are combined to produce a final prediction.
+#'
+#' @includeRmd man/rmd/boost_tree_h2o.md details
+#'
+#' @name details_boost_tree_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/linear_reg_h2o.R

@@ -0,0 +1,11 @@
+#' Linear regression via h2o
+#'
+#' This model uses regularized least squares to fit models with numeric outcomes.
+#'
+#' @includeRmd man/rmd/linear_reg_h2o.md details
+#'
+#' @name details_linear_reg_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/logistic_reg_h2o.R

@@ -0,0 +1,13 @@
+#' Logistic regression via h2o
+#'
+#' [h2o::h2o.glm()] fits a generalized linear model for binary outcomes.
+#' A linear combination of the predictors is used to model the log odds of an
+#' event.
+#'
+#' @includeRmd man/rmd/logistic_reg_h2o.md details
+#'
+#' @name details_logistic_reg_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/mlp_h2o.R

@@ -0,0 +1,11 @@
+#' Multilayer perceptron via h2o
+#'
+#' [h2o::h2o.deeplearning()] fits a feed-forward neural network.
+#'
+#' @includeRmd man/rmd/mlp_h2o.md details
+#'
+#' @name details_mlp_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/multinom_reg_h2o.R

@@ -0,0 +1,12 @@
+#' Multinomial regression via h2o
+#'
+#' [h2o::h2o.glm()] fits a model that uses linear predictors to predict
+#' multiclass data for multinomial responses.
+#'
+#' @includeRmd man/rmd/multinom_reg_h2o.md details
+#'
+#' @name details_multinom_reg_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/naive_Bayes_h2o.R

@@ -0,0 +1,12 @@
+#' Naive Bayes models via naivebayes
+#'
+#' [h2o::h2o.naiveBayes()] fits a model that uses Bayes' theorem to compute
+#' the probability of each class, given the predictor values.
+#'
+#' @includeRmd man/rmd/naive_Bayes_h2o.md details
+#'
+#' @name details_naive_Bayes_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/poisson_reg_h2o.R

@@ -0,0 +1,12 @@
+#' Poisson regression via h2o
+#'
+#' `h2o::h2o.glm()` uses penalized maximum likelihood to fit a model for
+#' count data.
+#'
+#' @includeRmd man/rmd/poisson_reg_h2o.md details
+#'
+#' @name details_poisson_reg_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/rand_forest_h2o.R

@@ -0,0 +1,13 @@
+#' Random forests via h2o
+#'
+#' [h2o::h2o.randomForest()] fits a model that creates a large number of
+#' decision trees, each independent of the others. The final prediction uses all
+#' predictions from the individual trees and combines them.
+#'
+#' @includeRmd man/rmd/rand_forest_h2o.md details
+#'
+#' @name details_rand_forest_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/rule_fit_h2o.R

@@ -0,0 +1,13 @@
+#' RuleFit models via h2o
+#'
+#' [h2o::h2o.rulefit()] fits a model that derives simple feature rules from a tree
+#' ensemble and uses the rules as features to a regularized (LASSO) model. [agua::h2o_train_rule()]
+#' is a wrapper around this function.
+#'
+#' @includeRmd man/rmd/rule_fit_h2o.md details
+#'
+#' @name details_rule_fit_h2o
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

inst/models.tsv

@@ -9,9 +9,11 @@
 "bart"	"regression"	"dbarts"	NA
 "boost_tree"	"censored regression"	"mboost"	"censored"
 "boost_tree"	"classification"	"C5.0"	NA
+"boost_tree"	"classification"	"h2o"	"agua"
 "boost_tree"	"classification"	"lightgbm"	"bonsai"
 "boost_tree"	"classification"	"spark"	NA
 "boost_tree"	"classification"	"xgboost"	NA
+"boost_tree"	"regression"	"h2o"	"agua"
 "boost_tree"	"regression"	"lightgbm"	"bonsai"
 "boost_tree"	"regression"	"spark"	NA
 "boost_tree"	"regression"	"xgboost"	NA
@@ -41,6 +43,7 @@
 "linear_reg"	"regression"	"glm"	NA
 "linear_reg"	"regression"	"glmnet"	NA
 "linear_reg"	"regression"	"gls"	"multilevelmod"
+"linear_reg"	"regression"	"h2o"	"agua"
 "linear_reg"	"regression"	"keras"	NA
 "linear_reg"	"regression"	"lm"	NA
 "linear_reg"	"regression"	"lme"	"multilevelmod"
@@ -53,6 +56,7 @@
 "logistic_reg"	"classification"	"glm"	NA
 "logistic_reg"	"classification"	"glmer"	"multilevelmod"
 "logistic_reg"	"classification"	"glmnet"	NA
+"logistic_reg"	"classification"	"h2o"	"agua"
 "logistic_reg"	"classification"	"keras"	NA
 "logistic_reg"	"classification"	"LiblineaR"	NA
 "logistic_reg"	"classification"	"spark"	NA
@@ -61,16 +65,20 @@
 "mars"	"classification"	"earth"	NA
 "mars"	"regression"	"earth"	NA
 "mlp"	"classification"	"brulee"	NA
+"mlp"	"classification"	"h2o"	"agua"
 "mlp"	"classification"	"keras"	NA
 "mlp"	"classification"	"nnet"	NA
 "mlp"	"regression"	"brulee"	NA
+"mlp"	"regression"	"h2o"	"agua"
 "mlp"	"regression"	"keras"	NA
 "mlp"	"regression"	"nnet"	NA
 "multinom_reg"	"classification"	"brulee"	NA
 "multinom_reg"	"classification"	"glmnet"	NA
+"multinom_reg"	"classification"	"h2o"	"agua"
 "multinom_reg"	"classification"	"keras"	NA
 "multinom_reg"	"classification"	"nnet"	NA
 "multinom_reg"	"classification"	"spark"	NA
+"naive_Bayes"	"classification"	"h2o"	"agua"
 "naive_Bayes"	"classification"	"klaR"	"discrim"
 "naive_Bayes"	"classification"	"naivebayes"	"discrim"
 "nearest_neighbor"	"classification"	"kknn"	NA
@@ -83,22 +91,27 @@
 "poisson_reg"	"regression"	"glm"	"poissonreg"
 "poisson_reg"	"regression"	"glmer"	"multilevelmod"
 "poisson_reg"	"regression"	"glmnet"	"poissonreg"
+"poisson_reg"	"regression"	"h2o"	"agua"
 "poisson_reg"	"regression"	"hurdle"	"poissonreg"
 "poisson_reg"	"regression"	"stan"	"poissonreg"
 "poisson_reg"	"regression"	"stan_glmer"	"multilevelmod"
 "poisson_reg"	"regression"	"zeroinfl"	"poissonreg"
 "proportional_hazards"	"censored regression"	"glmnet"	"censored"
 "proportional_hazards"	"censored regression"	"survival"	"censored"
 "rand_forest"	"censored regression"	"partykit"	"censored"
+"rand_forest"	"classification"	"h2o"	"agua"
 "rand_forest"	"classification"	"partykit"	"bonsai"
 "rand_forest"	"classification"	"randomForest"	NA
 "rand_forest"	"classification"	"ranger"	NA
 "rand_forest"	"classification"	"spark"	NA
+"rand_forest"	"regression"	"h2o"	"agua"
 "rand_forest"	"regression"	"partykit"	"bonsai"
 "rand_forest"	"regression"	"randomForest"	NA
 "rand_forest"	"regression"	"ranger"	NA
 "rand_forest"	"regression"	"spark"	NA
+"rule_fit"	"classification"	"h2o"	"agua"
 "rule_fit"	"classification"	"xrf"	"rules"
+"rule_fit"	"regression"	"h2o"	"agua"
 "rule_fit"	"regression"	"xrf"	"rules"
 "surv_reg"	"regression"	"flexsurv"	NA
 "surv_reg"	"regression"	"survival"	NA