Package: distillML 0.1.0.14

Theo Saarinen

distillML: Model Distillation and Interpretability Methods for Machine Learning Models

Provides several methods for model distillation and interpretability for general black box machine learning models and treatment effect estimation methods. For details on the algorithms implemented, see <https://forestry-labs.github.io/distillML/index.html> Brian Cho, Theo F. Saarinen, Jasjeet S. Sekhon, Simon Walter.

Authors:Brian Cho [aut], Theo Saarinen [aut, cre], Jasjeet Sekhon [aut], Simon Walter [aut]

distillML_0.1.0.14.tar.gz
distillML_0.1.0.14.zip(r-4.5)distillML_0.1.0.14.zip(r-4.4)distillML_0.1.0.14.zip(r-4.3)
distillML_0.1.0.14.tgz(r-4.4-any)distillML_0.1.0.14.tgz(r-4.3-any)
distillML_0.1.0.14.tar.gz(r-4.5-noble)distillML_0.1.0.14.tar.gz(r-4.4-noble)
distillML_0.1.0.14.tgz(r-4.4-emscripten)distillML_0.1.0.14.tgz(r-4.3-emscripten)
distillML.pdf |distillML.html✨
distillML/json (API)

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

Peer review:

Bug tracker:https://github.com/forestry-labs/distillml/issues

On CRAN:

bartdistillation-modelexplainable-machine-learningexplainable-mlinterpretabilityinterpretable-machine-learningmachine-learningmodelrandom-forestxgboost

3.86 score 6 stars 12 scripts 280 downloads 14 exports 78 dependencies

Last updated 2 years agofrom:e49a0974e5. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 12 2024
R-4.5-winOKNov 12 2024
R-4.5-linuxOKNov 12 2024
R-4.4-winOKNov 12 2024
R-4.4-macOKNov 12 2024
R-4.3-winOKNov 12 2024
R-4.3-macOKNov 12 2024

Exports:build.gridcenter.predsdistillInterpreterlocalSurrogatepdp.rankpredict_ALEpredict_ICE.Plotterpredict_PDP.1D.Plotterpredict_PDP.2D.PlotterPredictorset.center.atset.grid.pointsSurrogate

Dependencies:backportsbase64encbslibcachemcheckmateclicodetoolscolorspacecpp11data.tabledigestdplyrevaluatefansifarverfastmapfontawesomeforeachfsgenericsggplot2glmnetgluegridExtragtablehighrhtmltoolshtmlwidgetsisobanditeratorsjquerylibjsonliteknitrlabelinglatticelifecyclemagrittrMASSMatrixmemoisemgcvmimemltoolsmunsellnlmeonehotpillarpkgconfigplyrpROCpurrrR6rappdirsRColorBrewerRcppRcppArmadilloRcppEigenRcppThreadRforestryrlangrmarkdownsassscalesshapestringistringrsurvivaltibbletidyrtidyselecttinytexutf8vctrsviridisLitevisNetworkwithrxfunyaml

Readme and manuals

Help Manual

Help pageTopics
Constructs an ALE for a model.ale
Build grid used for weights in distilled surrogate modelbuild.grid
Centers the predicted values for 1-d ICE and PDP plots or 2-d PDP plotscenter.preds
Builds surrogate model from an interpreter object based on the univariate PDP functions of the original model.distill
Interpreter class descriptionInterpreter
Given a interpreter object with at least one pair of features, create a small surrogate model for the two features using the PDP function as the output and the two features as the independent variables.localSurrogate
Given an interpreter object with choice of PDP ranking methodology (default: 'Variance'), produce PDP 'ranking' scores by feature. Optionally, permits a new observation to weight the PDP function and rankings.pdp.rank
Plotting method for Interpretor modelplot-Interpreter plot.Interpreter
Prediction function for the ALE plotspredict_ALE
Prediction Function for ICE Plotspredict_ICE.Plotter
Prediction Function for PDP Plotspredict_PDP.1D.Plotter
Two Dimensional Prediction Curve for PDP Plotspredict_PDP.2D.Plotter
Predict method for Predictor classpredict-Predictor predict.Predictor
Prediction method for the distilled surrogate modelpredict-Surrogate predict.Surrogate
Predictor class descriptionPredictor
The Printing method for Predictor classprint-Predictor print.Predictor
Sets a new center in the PDP and ICE plots made by an Interpreterset.center.at
Sets grid points used for plotting PDP and ICE plotsset.grid.points
Surrogate class descriptionSurrogate