The Scalable Highly Adaptive Lasso
Squash HAL objects
Apply copy map
Fast Coercion to Sparse Matrix
List Basis Functions
Compute Degree of Basis Functions
Calculate Proportion of Nonzero Entries
Calculating Centered and Scaled Matrices
Enumerate Basis Functions
Enumerate Basis Functions at Generalized Edges
Generate Basis Functions
HAL: The Highly Adaptive Lasso
HAL Formula: Convert formula or string to formula_HAL object.
Generates rules based on knot points of the fitted HAL basis functions...
HAL Formula term: Generate a single term of the HAL basis
HAL 9000 Quotes
hal9001
Find Copies of Columns
Sort Basis Functions
Build Copy Maps
Build HAL Design Matrix
Mass-based reduction of basis functions
Compute Values of Basis Functions
A default generator for the num_knots argument for each degree of in...
HAL Formula addition: Adding formula term object together into a singl...
Prediction from HAL fits
predict.SL.hal9001
Print formula_hal9001 object
Print Method for Summary Class of HAL fits
Discretize Variables into Number of Bins by Unique Values
Wrapper for Classic SuperLearner
Summary Method for HAL fit objects
A scalable implementation of the highly adaptive lasso algorithm, including routines for constructing sparse matrices of basis functions of the observed data, as well as a custom implementation of Lasso regression tailored to enhance efficiency when the matrix of predictors is composed exclusively of indicator functions. For ease of use and increased flexibility, the Lasso fitting routines invoke code from the 'glmnet' package by default. The highly adaptive lasso was first formulated and described by MJ van der Laan (2017) <doi:10.1515/ijb-2015-0097>, with practical demonstrations of its performance given by Benkeser and van der Laan (2016) <doi:10.1109/DSAA.2016.93>. This implementation of the highly adaptive lasso algorithm was described by Hejazi, Coyle, and van der Laan (2020) <doi:10.21105/joss.02526>.