Package: DALEX 2.5.1
Przemyslaw Biecek
DALEX: moDel Agnostic Language for Exploration and eXplanation
Any unverified black box model is the path to failure. Opaqueness leads to distrust. Distrust leads to ignoration. Ignoration leads to rejection. DALEX package xrays any model and helps to explore and explain its behaviour. Machine Learning (ML) models are widely used and have various applications in classification or regression. Models created with boosting, bagging, stacking or similar techniques are often used due to their high performance. But such black-box models usually lack direct interpretability. DALEX package contains various methods that help to understand the link between input variables and model output. Implemented methods help to explore the model on the level of a single instance as well as a level of the whole dataset. All model explainers are model agnostic and can be compared across different models. DALEX package is the cornerstone for 'DrWhy.AI' universe of packages for visual model exploration. Find more details in (Biecek 2018) <https://jmlr.org/papers/v19/18-416.html>.
Authors:
DALEX_2.5.1.tar.gz
DALEX_2.5.1.zip(r-4.5)DALEX_2.5.1.zip(r-4.4)DALEX_2.5.1.zip(r-4.3)
DALEX_2.5.1.tgz(r-4.4-any)DALEX_2.5.1.tgz(r-4.3-any)
DALEX_2.5.1.tar.gz(r-4.5-noble)DALEX_2.5.1.tar.gz(r-4.4-noble)
DALEX_2.5.1.tgz(r-4.4-emscripten)DALEX_2.5.1.tgz(r-4.3-emscripten)
DALEX.pdf |DALEX.html✨
DALEX/json (API)
| # Install 'DALEX' in R: |
| install.packages('DALEX', repos = c('https://modeloriented.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/modeloriented/dalex/issues
- HR - Human Resources Data
- HRTest - Human Resources Data
- HR_test - Human Resources Data
- apartments - Apartments Data
- apartmentsTest - Apartments Data
- apartments_test - Apartments Data
- covid_spring - Data for early COVID mortality
- covid_summer - Data for early COVID mortality
- dragons - Dragon Data
- dragons_test - Dragon Data
- fifa - FIFA 20 preprocessed data
- happiness_test - World Happiness Report data
- happiness_train - World Happiness Report data
- titanic - Passengers and Crew on the RMS Titanic Data
- titanic_imputed - Passengers and Crew on the RMS Titanic Data
black-boxdalexdata-scienceexplainable-aiexplainable-artificial-intelligenceexplainable-mlexplanationsexplanatory-model-analysisfairnessimlinterpretabilityinterpretable-machine-learningmachine-learningmodel-visualizationpredictive-modelingresponsible-airesponsible-mlxai
Last updated 3 months agofrom:28a936b067. Checks:OK: 3 NOTE: 4. Indexed: yes.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | OK | Sep 05 2024 |
| R-4.5-win | NOTE | Sep 05 2024 |
| R-4.5-linux | NOTE | Sep 05 2024 |
| R-4.4-win | NOTE | Sep 05 2024 |
| R-4.4-mac | NOTE | Sep 05 2024 |
| R-4.3-win | OK | Sep 05 2024 |
| R-4.3-mac | OK | Sep 05 2024 |
Exports:colors_breakdown_drwhycolors_discrete_drwhycolors_diverging_drwhyexplainexplain.defaultfeature_importanceget_loss_defaultget_loss_one_minus_accuracyget_loss_yardstickindividual_diagnosticsindividual_profileinstall_dependenciesloss_accuracyloss_cross_entropyloss_defaultloss_one_minus_accuracyloss_one_minus_aucloss_root_mean_squareloss_sum_of_squaresloss_yardstickmodel_diagnosticsmodel_infomodel_partsmodel_performancemodel_predictionmodel_profilepredict_diagnosticspredict_partspredict_parts_break_downpredict_parts_break_down_interactionspredict_parts_kernel_shappredict_parts_kernel_shap_aggreagtedpredict_parts_kernel_shap_break_downpredict_parts_oscillationspredict_parts_oscillations_emppredict_parts_oscillations_unipredict_parts_shappredict_parts_shap_aggregatedpredict_profileset_theme_dalexshap_aggregatedsingle_variabletheme_default_dalextheme_drwhytheme_drwhy_verticaltheme_ematheme_ema_verticaltheme_vertical_default_dalexupdate_dataupdate_labelvariable_attributionvariable_effectvariable_effect_accumulated_dependencyvariable_effect_partial_dependencyvariable_importancevariable_profileyhat
Dependencies:clicodetoolscolorspacefansifarverforeachggplot2gluegridExtragtableiBreakDowningredientsisobanditeratorskernelshaplabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigR6RColorBrewerrlangscalestibbleutf8vctrsviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Apartments Data | apartments apartmentsTest apartments_test |
| DrWhy color palettes for ggplot objects | colors_breakdown_drwhy colors_discrete_drwhy colors_diverging_drwhy |
| Data for early COVID mortality | covid covid_spring covid_summer |
| Dragon Data | dragons dragons_test |
| Create Model Explainer | explain explain.default |
| FIFA 20 preprocessed data | fifa |
| Wrapper for Loss Functions from the yardstick Package | get_loss_yardstick loss_yardstick |
| World Happiness Report data | happiness happiness_test happiness_train |
| Human Resources Data | HR HRTest HR_test |
| Install all dependencies for the DALEX package | install_dependencies |
| Calculate Loss Functions | get_loss_default get_loss_one_minus_accuracy loss_accuracy loss_cross_entropy loss_default loss_one_minus_accuracy loss_one_minus_auc loss_root_mean_square loss_sum_of_squares |
| Dataset Level Model Diagnostics | model_diagnostics |
| Exract info from model | model_info model_info.cv.glmnet model_info.default model_info.gbm model_info.glm model_info.glmnet model_info.lm model_info.lrm model_info.model_fit model_info.randomForest model_info.ranger model_info.rpart model_info.svm model_info.train |
| Dataset Level Variable Importance as Change in Loss Function after Variable Permutations | feature_importance model_parts variable_importance |
| Dataset Level Model Performance Measures | model_performance |
| Dataset Level Variable Profile as Partial Dependence or Accumulated Local Dependence Explanations | model_profile single_variable variable_profile |
| Plot List of Explanations | plot.list |
| Plot Dataset Level Model Diagnostics | plot.model_diagnostics |
| Plot Variable Importance Explanations | plot.model_parts |
| Plot Dataset Level Model Performance Explanations | plot.model_performance |
| Plot Dataset Level Model Profile Explanations | plot.model_profile |
| Plot Instance Level Residual Diagnostics | plot.predict_diagnostics |
| Plot Variable Attribution Explanations | plot.predict_parts |
| Plot Variable Profile Explanations | plot.predict_profile |
| Plot Generic for Break Down Objects | plot.shap_aggregated |
| Instance Level Residual Diagnostics | individual_diagnostics predict_diagnostics |
| Instance Level Parts of the Model Predictions | predict_parts predict_parts_break_down predict_parts_break_down_interactions predict_parts_ibreak_down predict_parts_kernel_shap predict_parts_kernel_shap_aggreagted predict_parts_kernel_shap_break_down predict_parts_oscillations predict_parts_oscillations_emp predict_parts_oscillations_uni predict_parts_shap predict_parts_shap_aggregated variable_attribution |
| Instance Level Profile as Ceteris Paribus | individual_profile predict_profile |
| Predictions for the Explainer | model_prediction predict.explainer |
| Print Natural Language Descriptions | print.description |
| Print Explainer Summary | print.explainer |
| Print Dataset Level Model Diagnostics | print.model_diagnostics |
| Print model_info | print.model_info |
| Print Dataset Level Model Performance Summary | print.model_performance |
| Print Dataset Level Model Profile | print.model_profile |
| Print Instance Level Residual Diagnostics | print.predict_diagnostics |
| Default Theme for DALEX plots | set_theme_dalex theme_default_dalex theme_vertical_default_dalex |
| SHAP aggregated values | shap_aggregated |
| DrWhy Theme for ggplot objects | theme_drwhy theme_drwhy_vertical theme_ema theme_ema_vertical |
| Passengers and Crew on the RMS Titanic Data | titanic titanic_imputed |
| Update data of an explainer object | update_data |
| Update label of explainer object | update_label |
| Dataset Level Variable Effect as Partial Dependency Profile or Accumulated Local Effects | variable_effect variable_effect_accumulated_dependency variable_effect_partial_dependency |
| Wrap Various Predict Functions | yhat yhat.cv.glmnet yhat.default yhat.function yhat.gbm yhat.glm yhat.glmnet yhat.lm yhat.lrm yhat.model_fit yhat.party yhat.randomForest yhat.ranger yhat.rpart yhat.svm yhat.train |
