This package is considered a duplicate. The official version of this package is found at:https://ctesta01.r-universe.dev/nadir

Package: nadir 1.0.0

Christian Testa

nadir: Super Learning with Flexible Formulas

A functional programming based implementation of the super learner algorithm with an emphasis on supporting the use of formulas to specify learners. This approach offers several improvements compared to past implementations including the ability to easily use random-effects specified in formulas (like y ~ (age | strata) + ...) and construction of new learners is as simple as writing and passing a new function. The super learner algorithm was originally described in van der Laan et al. (2007) <https://biostats.bepress.com/ucbbiostat/paper222/>.

Authors:Christian Testa [aut, cre], Nima Hejazi [ths, aut]

nadir_1.0.0.tar.gz
nadir_1.0.0.zip(r-4.7-any)nadir_1.0.0.zip(r-4.6-any)nadir_1.0.0.zip(r-4.5-any)
nadir_1.0.0.tgz(r-4.6-any)nadir_1.0.0.tgz(r-4.5-any)
nadir_1.0.0.tar.gz(r-4.7-any)nadir_1.0.0.tar.gz(r-4.6-any)
nadir_1.0.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
nadir/json (API)

# Install 'nadir' in R:

install.packages('nadir', repos = c('https://ropensci-staging.r-universe.dev', 'https://cloud.r-project.org'))

Reviews:rOpenSci Software Review #()

Bug tracker:https://github.com/ctesta01/nadir/issues

Pkgdown/docs site:https://ctesta01.github.io

On CRAN:

cross-validation ensemble-learning machine-learning regression

6.20 score 6 stars 44 scripts 286 downloads 62 exports 32 dependencies

Last updated from:d2eef7b6ba. Checks:9 OK, 1 ERROR. Indexed: no.

Target	Result	Time
linux-devel	OK	360
pkgdown docs	ERROR	257
source / vignettes	OK	425
linux-release	OK	442
macos-release	OK	234
macos-oldrel	OK	288
windows-devel	OK	417
windows-release	OK	495
windows-oldrel	OK	414
wasm-release	OK	224

Exports:add_screener add_stratification as_multi_predictor compare_learners crossfit_super_learner cv_character_and_factors_schema cv_origami_schema cv_random_schema cv_super_learner default_determine_weights default_loss_metric determine_super_learner_weights_nnls determine_weights_for_binary_outcomes determine_weights_using_neg_log_loss df_to_survival_stacked list_known_learners lnr_bart lnr_cvglmnet lnr_earth lnr_gam lnr_gausspr lnr_gbm lnr_glm lnr_glm_density lnr_glmer lnr_glmnet lnr_glmnet_grid lnr_hal lnr_hal_grid lnr_heteroskedastic_density lnr_homoskedastic_density lnr_knn lnr_knn_binary lnr_lightgbm lnr_lm lnr_lm_density lnr_lmer lnr_logistic lnr_mean lnr_multinomial_nnet lnr_multinomial_ranger lnr_multinomial_vglm lnr_nnet lnr_ppr lnr_ranger lnr_ranger_binary lnr_rf lnr_rf_binary lnr_rpart lnr_rpart_binary lnr_svm lnr_svm_binary lnr_xgboost make_learner_names_unique nadir_supported_types negative_log_loss negative_log_loss_for_binary screener_cor screener_cor_top_n screener_t_test super_learner truncate_lnr

Dependencies:abind assertthat cli codetools cpp11 data.table digest dplyr future future.apply generics globals glue lifecycle listenv magrittr nnls origami parallelly pillar pkgconfig purrr R6 rlang stringi stringr tibble tidyr tidyselect utf8 vctrs withr

Basic Examples

Getting More Information Out

Rendered fromBasic-Examples.Rmdusingknitr::rmarkdown

Last update: 2026-10-10
Started: 2026-01-05

Help page	Topics
Add a Screener to a Learner	add_screener
Stratify a Learner by One or More Categorical Variables	add_stratification
Construct a Multi-Predictor	as_multi_predictor
Binary Learners in '{nadir}'	binary_learners
Compare Learners	compare_learners
Predicting from a Cross-Fitted Super Learner	coef.nadir_crossfit_sl crossfit_sl_methods fitted.nadir_crossfit_sl formula.nadir_crossfit_sl nobs.nadir_crossfit_sl plot.nadir_crossfit_sl predict.nadir_crossfit_sl print.summary.nadir_crossfit_sl residuals.nadir_crossfit_sl summary.nadir_crossfit_sl
Cross-Fit a Super Learner and Retain Fold-Specific Predictors	crossfit_super_learner
Cross Validation Training/Validation Splits with Characters/Factor Columns	cv_character_and_factors_schema
Cross-Validation with Origami	cv_origami_schema
Assign Data to One of n_folds Randomly and Produce Training/Validation Data Lists	cv_random_schema
Cross-Validating a 'super_learner'	cv_super_learner
Conditional Density Estimation in the '{nadir}' Package	density_learners
Determine SuperLearner Weights with Nonnegative Least Squares	determine_super_learner_weights_nnls
Determine Weights Appropriately for Super Learner given Binary Outcomes	determine_weights_for_binary_outcomes
Determine Weights for Density Estimators for SuperLearner	determine_weights_using_neg_log_loss
Repeat Observations for Survival Stacking	df_to_survival_stacked
Learners in the '{nadir}' Package	learners
List Known Learners	list_known_learners
Bayesian Additive Regression Trees (BART) Learner	lnr_bart
cv.glmnet Learner	lnr_cvglmnet
Earth Learner	lnr_earth
Generalized Additive Model Learner	lnr_gam
Gaussian Process Regression Learner	lnr_gausspr
Gradient Boosting Machines Learner	lnr_gbm
GLM Learner	lnr_glm
Conditional Normal Density Estimation Given Mean Predictors — with GLMs	lnr_glm_density
Generalized Linear Mixed-Effects ('lme4::glmer') Learner	lnr_glmer
glmnet Learner	lnr_glmnet
glmnet Learner over a Grid of Lambda Values	lnr_glmnet_grid
Highly Adaptive Lasso	lnr_hal
Highly Adaptive Lasso over a Grid of Lambda Values	lnr_hal_grid
Conditional Density Estimation with Heteroskedasticity	lnr_heteroskedastic_density
Conditional Density Estimation with Homoskedasticity Assumption	lnr_homoskedastic_density
k-Nearest Neighbors Learner	lnr_knn
k-Nearest Neighbors Learner for Binary Classification	lnr_knn_binary
LightGBM Learner	lnr_lightgbm
Linear Model Learner	lnr_lm
Conditional Normal Density Estimation Given Mean Predictors	lnr_lm_density
Random/Mixed-Effects ('lme4::lmer') Learner	lnr_lmer
Standard Logistic Regression for Binary Classification	lnr_logistic
Mean Learner	lnr_mean
'nnet::multinom' Multinomial Learner	lnr_multinomial_nnet
ranger Multinomial Learner	lnr_multinomial_ranger
'VGAM::vglm' Multinomial Learner	lnr_multinomial_vglm
Use nnet for Binary Classification	lnr_nnet
Projection Pursuit Regression Learner	lnr_ppr
ranger Learner	lnr_ranger
ranger Learner for Binary Outcomes	lnr_ranger_binary
randomForest Learner	lnr_rf
Use Random Forest for Binary Classification	lnr_rf_binary
Recursive Partitioning (CART) Learner	lnr_rpart
Recursive Partitioning (CART) Learner for Binary Classification	lnr_rpart_binary
Support Vector Machine Learner	lnr_svm
Support Vector Machine Learner for Binary Classification	lnr_svm_binary
XGBoost Learner	lnr_xgboost
Make Unique Learner Names	make_learner_names_unique
Multiclass Learners in '{nadir}'	multiclass_learners
Print a 'nadir_sl_model'	coef.nadir_sl_model fitted.nadir_sl_model formula.nadir_sl_model nadir_sl_model_methods nobs.nadir_sl_model predict.nadir_sl_model print.nadir_sl_model residuals.nadir_sl_model summary.nadir_sl_model
Outcome types supported by '{nadir}'	nadir_supported_types
Negative Log Loss	negative_log_loss
Negative Log Loss for Binary	negative_log_loss_for_binary
Plot a Cross-Validated Super Learner	plot.nadir_cv_sl print.nadir_cv_sl
Plot a 'nadir_sl_model'	plot.nadir_sl_model
Correlation Threshold Based Screening	screener_cor
Correlation Threshold Based Screening	screener_cor_top_n
t-test Based Screening: Thresholds on p.values and/or t statistics	screener_t_test
Wrapping Learners with a Screener	screeners
Super Learner: Cross-Validation Based Ensemble Learning	super_learner
Helper to Truncate a Learner's Predictions	truncate_lnr

Package: nadir 1.0.0

nadir: Super Learning with Flexible Formulas

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)