Skip to content

Commit 1e8e215

Browse files
qiushiyanqiushiyan
authored
Engine docs for h2o (#748)
* update inst/models.tsv * logistic_reg docs * linear reg docs * boost_tree docs * rand_forest docs * add agua in set_dependency * multinom_reg docs * naive_bayes docs * mlp and rule fit docs * update rmd template and add poisson_reg * threads in h2o.init() * remove template markdown files
1 parent 68a4a49 commit 1e8e215

40 files changed

+2590
-24
lines changed

‎R/boost_tree_h2o.R‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
#' Boosted trees via h2o
2+
#'
3+
#' [h2o::h2o.xgboost()] creates a series of decision trees
4+
#' forming an ensemble. Each tree depends on the results of previous trees.
5+
#' All trees in the ensemble are combined to produce a final prediction.
6+
#'
7+
#' @includeRmd man/rmd/boost_tree_h2o.md details
8+
#'
9+
#' @name details_boost_tree_h2o
10+
#' @keywords internal
11+
NULL
12+
13+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/linear_reg_h2o.R‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
#' Linear regression via h2o
2+
#'
3+
#' This model uses regularized least squares to fit models with numeric outcomes.
4+
#'
5+
#' @includeRmd man/rmd/linear_reg_h2o.md details
6+
#'
7+
#' @name details_linear_reg_h2o
8+
#' @keywords internal
9+
NULL
10+
11+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/logistic_reg_h2o.R‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
#' Logistic regression via h2o
2+
#'
3+
#' [h2o::h2o.glm()] fits a generalized linear model for binary outcomes.
4+
#' A linear combination of the predictors is used to model the log odds of an
5+
#' event.
6+
#'
7+
#' @includeRmd man/rmd/logistic_reg_h2o.md details
8+
#'
9+
#' @name details_logistic_reg_h2o
10+
#' @keywords internal
11+
NULL
12+
13+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/mlp_h2o.R‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
#' Multilayer perceptron via h2o
2+
#'
3+
#' [h2o::h2o.deeplearning()] fits a feed-forward neural network.
4+
#'
5+
#' @includeRmd man/rmd/mlp_h2o.md details
6+
#'
7+
#' @name details_mlp_h2o
8+
#' @keywords internal
9+
NULL
10+
11+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/multinom_reg_h2o.R‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
#' Multinomial regression via h2o
2+
#'
3+
#' [h2o::h2o.glm()] fits a model that uses linear predictors to predict
4+
#' multiclass data for multinomial responses.
5+
#'
6+
#' @includeRmd man/rmd/multinom_reg_h2o.md details
7+
#'
8+
#' @name details_multinom_reg_h2o
9+
#' @keywords internal
10+
NULL
11+
12+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/naive_Bayes_h2o.R‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
#' Naive Bayes models via naivebayes
2+
#'
3+
#' [h2o::h2o.naiveBayes()] fits a model that uses Bayes' theorem to compute
4+
#' the probability of each class, given the predictor values.
5+
#'
6+
#' @includeRmd man/rmd/naive_Bayes_h2o.md details
7+
#'
8+
#' @name details_naive_Bayes_h2o
9+
#' @keywords internal
10+
NULL
11+
12+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/poisson_reg_h2o.R‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
#' Poisson regression via h2o
2+
#'
3+
#' `h2o::h2o.glm()` uses penalized maximum likelihood to fit a model for
4+
#' count data.
5+
#'
6+
#' @includeRmd man/rmd/poisson_reg_h2o.md details
7+
#'
8+
#' @name details_poisson_reg_h2o
9+
#' @keywords internal
10+
NULL
11+
12+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/rand_forest_h2o.R‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
#' Random forests via h2o
2+
#'
3+
#' [h2o::h2o.randomForest()] fits a model that creates a large number of
4+
#' decision trees, each independent of the others. The final prediction uses all
5+
#' predictions from the individual trees and combines them.
6+
#'
7+
#' @includeRmd man/rmd/rand_forest_h2o.md details
8+
#'
9+
#' @name details_rand_forest_h2o
10+
#' @keywords internal
11+
NULL
12+
13+
# See inst/README-DOCS.md for a description of how these files are processed

‎R/rule_fit_h2o.R‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
#' RuleFit models via h2o
2+
#'
3+
#' [h2o::h2o.rulefit()] fits a model that derives simple feature rules from a tree
4+
#' ensemble and uses the rules as features to a regularized (LASSO) model. [agua::h2o_train_rule()]
5+
#' is a wrapper around this function.
6+
#'
7+
#' @includeRmd man/rmd/rule_fit_h2o.md details
8+
#'
9+
#' @name details_rule_fit_h2o
10+
#' @keywords internal
11+
NULL
12+
13+
# See inst/README-DOCS.md for a description of how these files are processed

‎inst/models.tsv‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,9 +9,11 @@
99
"bart" "regression" "dbarts" NA
1010
"boost_tree" "censored regression" "mboost" "censored"
1111
"boost_tree" "classification" "C5.0" NA
12+
"boost_tree" "classification" "h2o" "agua"
1213
"boost_tree" "classification" "lightgbm" "bonsai"
1314
"boost_tree" "classification" "spark" NA
1415
"boost_tree" "classification" "xgboost" NA
16+
"boost_tree" "regression" "h2o" "agua"
1517
"boost_tree" "regression" "lightgbm" "bonsai"
1618
"boost_tree" "regression" "spark" NA
1719
"boost_tree" "regression" "xgboost" NA
@@ -41,6 +43,7 @@
4143
"linear_reg" "regression" "glm" NA
4244
"linear_reg" "regression" "glmnet" NA
4345
"linear_reg" "regression" "gls" "multilevelmod"
46+
"linear_reg" "regression" "h2o" "agua"
4447
"linear_reg" "regression" "keras" NA
4548
"linear_reg" "regression" "lm" NA
4649
"linear_reg" "regression" "lme" "multilevelmod"
@@ -53,6 +56,7 @@
5356
"logistic_reg" "classification" "glm" NA
5457
"logistic_reg" "classification" "glmer" "multilevelmod"
5558
"logistic_reg" "classification" "glmnet" NA
59+
"logistic_reg" "classification" "h2o" "agua"
5660
"logistic_reg" "classification" "keras" NA
5761
"logistic_reg" "classification" "LiblineaR" NA
5862
"logistic_reg" "classification" "spark" NA
@@ -61,16 +65,20 @@
6165
"mars" "classification" "earth" NA
6266
"mars" "regression" "earth" NA
6367
"mlp" "classification" "brulee" NA
68+
"mlp" "classification" "h2o" "agua"
6469
"mlp" "classification" "keras" NA
6570
"mlp" "classification" "nnet" NA
6671
"mlp" "regression" "brulee" NA
72+
"mlp" "regression" "h2o" "agua"
6773
"mlp" "regression" "keras" NA
6874
"mlp" "regression" "nnet" NA
6975
"multinom_reg" "classification" "brulee" NA
7076
"multinom_reg" "classification" "glmnet" NA
77+
"multinom_reg" "classification" "h2o" "agua"
7178
"multinom_reg" "classification" "keras" NA
7279
"multinom_reg" "classification" "nnet" NA
7380
"multinom_reg" "classification" "spark" NA
81+
"naive_Bayes" "classification" "h2o" "agua"
7482
"naive_Bayes" "classification" "klaR" "discrim"
7583
"naive_Bayes" "classification" "naivebayes" "discrim"
7684
"nearest_neighbor" "classification" "kknn" NA
@@ -83,22 +91,27 @@
8391
"poisson_reg" "regression" "glm" "poissonreg"
8492
"poisson_reg" "regression" "glmer" "multilevelmod"
8593
"poisson_reg" "regression" "glmnet" "poissonreg"
94+
"poisson_reg" "regression" "h2o" "agua"
8695
"poisson_reg" "regression" "hurdle" "poissonreg"
8796
"poisson_reg" "regression" "stan" "poissonreg"
8897
"poisson_reg" "regression" "stan_glmer" "multilevelmod"
8998
"poisson_reg" "regression" "zeroinfl" "poissonreg"
9099
"proportional_hazards" "censored regression" "glmnet" "censored"
91100
"proportional_hazards" "censored regression" "survival" "censored"
92101
"rand_forest" "censored regression" "partykit" "censored"
102+
"rand_forest" "classification" "h2o" "agua"
93103
"rand_forest" "classification" "partykit" "bonsai"
94104
"rand_forest" "classification" "randomForest" NA
95105
"rand_forest" "classification" "ranger" NA
96106
"rand_forest" "classification" "spark" NA
107+
"rand_forest" "regression" "h2o" "agua"
97108
"rand_forest" "regression" "partykit" "bonsai"
98109
"rand_forest" "regression" "randomForest" NA
99110
"rand_forest" "regression" "ranger" NA
100111
"rand_forest" "regression" "spark" NA
112+
"rule_fit" "classification" "h2o" "agua"
101113
"rule_fit" "classification" "xrf" "rules"
114+
"rule_fit" "regression" "h2o" "agua"
102115
"rule_fit" "regression" "xrf" "rules"
103116
"surv_reg" "regression" "flexsurv" NA
104117
"surv_reg" "regression" "survival" NA

0 commit comments

Comments
 (0)