embed 1.0.0
CRAN release: 2022-07-02
step_collapse_cart()can pool a predictor’s factor levels using a tree-based method.step_collapse_stringdist()can pool a predictor’s factor levels using string distances.Case weights support have been added to
step_discretize_cart(),step_discretize_xgb(),step_lencode_bayes(),step_lencode_glm(), andstep_lencode_mixed().
embed 0.2.0
CRAN release: 2022-04-13
step_embed()now correctly defaults to have a random id with the word “embed”. (#102)step_feature_hash()is soft deprecated in embed in favor ofstep_dummy_hash()in textrecipes. (#95)Steps now have a dedicated subsection detailing what happens when
tidy()is applied. (#105)Reorganize documentation for all recipe step
tidymethods (#115).Fixed a bug where
woe_table()andstep_woe()didn’t respect the factor levels of the outcome. (109)
embed 0.1.5
CRAN release: 2021-11-24
Re-licensed package from GPL-2 to MIT. See consent from copyright holders here.
The tunable parameter ranges for
step_umap()were changed forneighbors,num_comp, andmin_distto preventuwotsegmentation faults. The step also check to see if the data dimensions are consistent with the argument values.Two new PCA steps were added, each using sparse techniques for estimation:
step_pca_sparse()andstep_pca_sparse_bayes().Updated to use
recipes_eval_select()from recipes 0.1.17 (#85).Added
prefixargument tostep_umap()to harmonize with other recipes steps (#93).All embed recipe steps now officially support empty selections to be more aligned with recipes, dplyr and other packages that use tidyselect.
step_woe()no longer warns about high-cardinality predictors when the recipe is estimated. Instead it warns when categories have fewer than 10 data points in the training set. (#74)
embed 0.1.4
CRAN release: 2021-01-16
Minor release with changes to test for cases when CRAN cannot get
xgboostto work on their Solaris configuration.lme4andrstanarmare now in the Suggests list so they are not automatically installed withembed. A message is written to the console if those packages are missing and their associated steps functions are invoked.
embed 0.1.1
CRAN release: 2020-07-03
Changes to tests to get out of archive jail.
Updated the plumbing behind
step_woe().Due to a bug in
tensorflow, added a “warm start” to instigate a TF session if one does not currently exist.
embed 0.1.0
CRAN release: 2020-05-25
- Changes for
dplyr1.0.0
New Steps
step_discretize_xgb()andstep_discretize_cart()can be used to convert numeric predictors to categorical using supervised binning methods based on tree models. Thanks to Konrad Semsch for the contribution.Added
step_feature_hash()for creating dummy variables using feature hashing.
Breaking Changes
-
tidy.step_woe()now has column names consistent with other recipe steps.
embed 0.0.5
CRAN release: 2020-01-07
The example data are now in the
modeldatapackage.Small TF updates to
step_embed().
embed 0.0.4
CRAN release: 2019-09-15
Methods were added for a future generic called
tunable(). This outlines which parameters in a step can/could be tuned.Small updates to work with different versions of
tidyr.
embed 0.0.3
CRAN release: 2019-07-12
New Steps
-
step_umap()was added for both supervised and unsupervised encodings. -
step_woe()created weight of evidence encodings.
embed 0.0.2
CRAN release: 2018-11-19
A mostly maintainence release to be compatible with version 0.1.3 of recipes.
Other Changes:
The package now depends on the
genericspacakge to get thebroomtidymethods.Karim Lahrichi added the ability to use callbacks when fitting tensorflow models. PR
