probably v0.0.3
Monthly downloads
Tools for Post-Processing Class Probability Estimates
Models can be improved by post-processing class probabilities, by: recalibration, conversion to hard probabilities, assessment of equivocal zones, and other activities. 'probably' contains tools for conducting these operations.
Readme
probably
Introduction
probably contains tools to facilitate activities such as:
Conversion of probabilities to discrete class predictions.
Investigating and estimating optimal probability thresholds.
Inclusion of equivocal zones where the probabilities are too uncertain to report a prediction.
Installation
You can install probably from CRAN with:
install.packages("probably")
You can install the development version of probably from GitHub with:
devtools::install_github("topepo/probably")
Examples
Good places to look for examples of using probably are the vignettes.
vignette("equivocal-zones", "probably")discusses the newclass_predclass that probably provides for working with equivocal zones.vignette("where-to-use", "probably")discusses how probably fits in with the rest of the tidymodels ecosystem, and provides an example of optimizing class probability thresholds.
Functions in probably
| Name | Description | |
| append_class_pred | Add a class_pred column | |
| class_pred | Create a class prediction object | |
| levels.class_pred | Extract class_pred levels | |
| probably-package | probably: Tools for Post-Processing Class Probability Estimates | |
| as_class_pred | Coerce to a class_pred object | |
| is_class_pred | Test if an object inherits from class_pred | |
| make_class_pred | Create a class_pred vector from class probabilities | |
| reexports | Objects exported from other packages | |
| threshold_perf | Generate performance metrics across probability thresholds | |
| reportable_rate | Calculate the reportable rate | |
| locate-equivocal | Locate equivocal values | |
| vec_proxy_equal.class_pred | Equality for class_pred | |
| vec_cast.class_pred | Cast a class_pred vector to a specified type | |
| vec_ptype2.class_pred | Find the common type for a class_pred and another object | |
| species_probs | Predictions on animal species | |
| segment_naive_bayes | Image segmentation predictions | |
| No Results! | ||
Vignettes of probably
| Name | ||
| equivocal-zones.Rmd | ||
| where-to-use.Rmd | ||
| No Results! | ||
Last month downloads
Details
| URL | https://github.com/tidymodels/probably/ |
| BugReports | https://github.com/tidymodels/probably/issues |
| License | GPL-2 |
| Encoding | UTF-8 |
| LazyData | true |
| ByteCompile | true |
| RoxygenNote | 6.1.1 |
| VignetteBuilder | knitr |
| NeedsCompilation | no |
| Packaged | 2019-07-07 12:01:32 UTC; davis |
| Repository | CRAN |
| Date/Publication | 2019-07-07 22:40:03 UTC |
| suggests | covr , ggplot2 , knitr , parsnip , rmarkdown , rsample , testthat |
| imports | dplyr , generics , rlang (>= 0.4.0) , tidyselect , vctrs (>= 0.2.0) , yardstick |
| depends | R (>= 2.10) |
| Contributors | RStudio, Max Kuhn |
Include our badge in your README
[](http://www.rdocumentation.org/packages/probably)