Package: hstats 1.2.2

Michael Mayer

hstats: Interaction Statistics

Fast, model-agnostic implementation of different H-statistics introduced by Jerome H. Friedman and Bogdan E. Popescu (2008) <doi:10.1214/07-AOAS148>. These statistics quantify interaction strength per feature, feature pair, and feature triple. The package supports multi-output predictions and can account for case weights. In addition, several variants of the original statistics are provided. The shape of the interactions can be explored through partial dependence plots or individual conditional expectation plots. 'DALEX' explainers, meta learners ('mlr3', 'tidymodels', 'caret') and most other models work out-of-the-box.

Authors:Michael Mayer [aut, cre], Przemyslaw Biecek [ctb]

hstats_1.2.2.tar.gz
hstats_1.2.2.zip(r-4.5)hstats_1.2.2.zip(r-4.4)hstats_1.2.2.zip(r-4.3)
hstats_1.2.2.tgz(r-4.4-any)hstats_1.2.2.tgz(r-4.3-any)
hstats_1.2.2.tar.gz(r-4.5-noble)hstats_1.2.2.tar.gz(r-4.4-noble)
hstats_1.2.2.tgz(r-4.4-emscripten)hstats_1.2.2.tgz(r-4.3-emscripten)
hstats.pdf |hstats.html
hstats/json (API)
NEWS

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

Peer review:

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

On CRAN:

interactioninterpretabilitymachine-learningrstatstatisticsxai

5.76 score 24 stars 34 scripts 329 downloads 12 exports 28 dependencies

Last updated 2 months agofrom:7553d146f9. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 02 2024
R-4.5-winOKNov 02 2024
R-4.5-linuxOKNov 02 2024
R-4.4-winOKNov 02 2024
R-4.4-macOKNov 02 2024
R-4.3-winOKNov 02 2024
R-4.3-macOKNov 02 2024

Exports:average_lossh2h2_overallh2_pairwiseh2_threewayhstatsicemultivariate_gridpartial_deppd_importanceperm_importanceunivariate_grid

Dependencies:clicolorspacefansifarverggplot2gluegtableisobandlabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigR6RColorBrewerrlangscalestibbleutf8vctrsviridisLitewithr

Readme and manuals

Help Manual

Help pageTopics
Subsets "hstats_matrix" Object[.hstats_matrix
Average Lossaverage_loss average_loss.default average_loss.explainer average_loss.ranger
Dimensions of "hstats_matrix" Objectdim.hstats_matrix
Dimnames of "hstats_matrix" Objectdimnames.hstats_matrix
Dimnames (Replacement Method) of "hstats_matrix"dimnames<-.hstats_matrix
Total Interaction Strengthh2 h2.default h2.hstats
Overall Interaction Strengthh2_overall h2_overall.default h2_overall.hstats
Pairwise Interaction Strengthh2_pairwise h2_pairwise.default h2_pairwise.hstats
Three-way Interaction Strengthh2_threeway h2_threeway.default h2_threeway.hstats
Calculate Interaction Statisticshstats hstats.default hstats.explainer hstats.ranger
Individual Conditional Expectationsice ice.default ice.explainer ice.ranger
Multivariate Gridmultivariate_grid
Partial Dependence Plotpartial_dep partial_dep.default partial_dep.explainer partial_dep.ranger
PD Bases Importance (Experimental)pd_importance pd_importance.default pd_importance.hstats
Permutation Importanceperm_importance perm_importance.default perm_importance.explainer perm_importance.ranger
Plot Method for "hstats" Objectplot.hstats
Plots "hstats_matrix" Objectplot.hstats_matrix
Plots "ice" Objectplot.ice
Plots "partial_dep" Objectplot.partial_dep
Print Methodprint.hstats
Prints "hstats_matrix" Objectprint.hstats_matrix
Print Methodprint.hstats_summary
Prints "ice" Objectprint.ice
Prints "partial_dep" Objectprint.partial_dep
Summary Methodsummary.hstats
Univariate Gridunivariate_grid