XBART
XBART copied to clipboard
JingyuHe
Update to check and output logloss during training; Change total_points name to avoid rewriting N variable (which changes the yhats_train dimension).
Hey Jingyu, When I run XBART, the console output says that it is running in parallel with some number of cores. However, my actual CPU usage only shows on 1...
While attempting to fit using XBART.multinomial on a test case I encounter the following error: `Error in r_to_json(obj$model_list$tree_pnt) : argument "tree_pnt" is missing, with no default` Code used for testing...
When attempting to use XBART.CLT for binary classification I get the following error: > Error in XBART_CLT_cpp(y, X, Xtest, num_trees, num_sweeps, max_depth, : std::bad_alloc Seems to be a C++ error...
Hi Jingyu: From this program, all posterior samples are zero including sigma. ``` library(XBART) f = function(x) 10*sin(pi*x[ , 1]*x[ , 2]) + 5*x[ , 3]*x[ , 4]^2 + 20*x[...
pip install xbart not working on windows 10... Collecting xbart Using cached xbart-0.1.8.tar.gz (212 kB) Requirement already satisfied: numpy in c:\dev\anaconda3\lib\site-packages (from xbart) (1.18.5) Building wheels for collected packages: xbart...
XGBoost recently added the ability to enforce monotonicity constraints on any features used in a boosted model , so I suppose it will be natural enhancement for XBart. May be...
Move everything in fit_info.h to model.h, move all functions from model.h to model.cpp
