Package: DALEXtra 2.3.0

Szymon Maksymiuk

DALEXtra: Extension for 'DALEX' Package

Provides wrapper of various machine learning models. In applied machine learning, there is a strong belief that we need to strike a balance between interpretability and accuracy. However, in field of the interpretable machine learning, there are more and more new ideas for explaining black-box models, that are implemented in 'R'. 'DALEXtra' creates 'DALEX' Biecek (2018) <arxiv:1806.08915> explainer for many type of models including those created using 'python' 'scikit-learn' and 'keras' libraries, and 'java' 'h2o' library. Important part of the package is Champion-Challenger analysis and innovative approach to model performance across subsets of test data presented in Funnel Plot.

Authors:Szymon Maksymiuk [aut, cre], Przemyslaw Biecek [aut], Hubert Baniecki [aut], Anna Kozak [ctb]

DALEXtra_2.3.0.tar.gz
DALEXtra_2.3.0.zip(r-4.5)DALEXtra_2.3.0.zip(r-4.4)DALEXtra_2.3.0.zip(r-4.3)
DALEXtra_2.3.0.tgz(r-4.4-any)DALEXtra_2.3.0.tgz(r-4.3-any)
DALEXtra_2.3.0.tar.gz(r-4.5-noble)DALEXtra_2.3.0.tar.gz(r-4.4-noble)
DALEXtra_2.3.0.tgz(r-4.4-emscripten)DALEXtra_2.3.0.tgz(r-4.3-emscripten)
DALEXtra.pdf |DALEXtra.html
DALEXtra/json (API)
NEWS

# Install 'DALEXtra' in R:
install.packages('DALEXtra', repos = c('https://modeloriented.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/modeloriented/dalextra/issues

On CRAN:

extension-for-dalex-package

7.77 score 66 stars 1 packages 394 scripts 2.5k downloads 19 exports 36 dependencies

Last updated 1 years agofrom:a8baf5791b. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 15 2024
R-4.5-winOKNov 15 2024
R-4.5-linuxOKNov 15 2024
R-4.4-winOKNov 15 2024
R-4.4-macOKNov 15 2024
R-4.3-winOKNov 15 2024
R-4.3-macOKNov 15 2024

Exports:champion_challengercreate_envdalex_load_explainerexplain_h2oexplain_kerasexplain_mlrexplain_mlr3explain_scikitlearnexplain_tidymodelsexplain_xgboostfunnel_measuremodel_type.dalex_explaineroverall_comparisonpredict_model.dalex_explainerpredict_surrogatepredict_surrogate_imlpredict_surrogate_limepredict_surrogate_local_modeltraining_test_comparison

Dependencies:clicodetoolscolorspaceDALEXfansifarverforeachggplot2gluegridExtragtableiBreakDowningredientsisobanditeratorskernelshaplabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigR6RColorBrewerrlangscalestibbleutf8vctrsviridisLitewithr

Readme and manuals

Help Manual

Help pageTopics
Compare machine learning modelschampion_challenger
Create your conda virtual env with DALEXcreate_env
DALEX load explainerdalex_load_explainer
Create explainer from your h2o modelexplain_h2o
Wrapper for Python Keras Modelsexplain_keras
Create explainer from your mlr modelexplain_mlr
Create explainer from your mlr modelexplain_mlr3
Wrapper for Python Scikit-Learn Modelsexplain_scikitlearn
Create explainer from your tidymodels workflow.explain_tidymodels
Create explainer from your xgboost modelexplain_xgboost
Caluculate difference in performance in models across different categoriesfunnel_measure
Exract info from modelmodel_info.GraphLearner model_info.H2OBinomialModel model_info.H2OMultinomialModel model_info.H2ORegressionModel model_info.keras model_info.LearnerClassif model_info.LearnerRegr model_info.model_stack model_info.scikitlearn_model model_info.workflow model_info.WrappedModel model_info.xgb.Booster
Compare champion with challengers globallyoverall_comparison
Funnel plot for difference in measuresplot.funnel_measure
Plot function for overall_comparisonplot.overall_comparison
Plot and compare performance of model between training and test setplot.training_test_comparison
Instance Level Surrogate Modelsmodel_type.dalex_explainer plot.predict_surrogate_lime predict_model.dalex_explainer predict_parts predict_parts_break_down predict_parts_ibreak_down predict_parts_shap predict_surrogate predict_surrogate_iml predict_surrogate_lime predict_surrogate_local_model
Print funnel_measure objectprint.funnel_measure
Print overall_comparison objectprint.overall_comparison
Prints scikitlearn_set classprint.scikitlearn_set
Print funnel_measure objectprint.training_test_comparison
Compare performance of model between training and test settraining_test_comparison
Wrapper over the predict functionyhat.GraphLearner yhat.H2OBinomialModel yhat.H2OMultinomialModel yhat.H2ORegressionModel yhat.keras yhat.LearnerClassif yhat.LearnerRegr yhat.model_stack yhat.scikitlearn_model yhat.workflow yhat.WrappedModel yhat.xgb.Booster