Hannah Frick
Hannah Frick
This tests the error message for trying to use `proportional_hazards()` with the `glmnet` engine _without_ a penalty value because that's the thing the `translate()` method for PH models does in...
The docs for `decision_tree()` say at the start that the > function can fit classification, regression, and censored regression models which is correct. In the documenation for the argument `mode`,...
Currently, predictions for confidence and prediction intervals are their own prediction `type`. This works well for the regression and classification modes with the intervals being based around either the numeric...
``` r library(parsnip) data(Chicago, package = "modeldata") lm_spec % set_engine("glmnet") lm_fit # A tibble: 6 x 1 #> .pred #> #> 1 #> 2 #> 3 #> 4 #> 5...
These two fits via {xgboost} and {parsnip} don't give exactly the same result when they most likely should: ``` r library(parsnip) library(xgboost) data(wa_churn, package = "modeldata") vars [4] training-auc:0.851186 #>...
Currently, the documentation for `fit()` says for `...` > Not currently used; values passed here will be ignored. Other options required to fit the model should be passed using `set_engine()`....
closes #117 ``` r library(mboost) #> Loading required package: parallel #> Loading required package: stabs library(survival) mod
Getting a survival curve via `survFit()` for just one observation in `newdata` fails. I think it's just a matter of not dropping from a 1-column matrix to a vector in...
The `predict()` function has an argument `time` which captures the times at which to predict the survival probability. The functions to do the calculations also have arguments or objects `time`...
the vignette for survival analysis and resampling needs a new home, possibly in censored or tidymodels.org https://github.com/tidymodels/rsample/blob/bafa7ce3f7498896df3b6bfa32632e0858ca9011/vignettes/Applications/Survival_Analysis.Rmd