ingredients v0.3.1

0

Monthly downloads

0th

Percentile

Effects and Importances of Model Ingredients

Collection of tools for assessment of feature importance and feature effects. Key functions are: feature_importance() for assessment of global level feature importance, ceteris_paribus() for calculation of the what-if plots, partial_dependency() for partial dependency plots, conditional_dependency() for conditional dependency plots, accumulated_dependency() for accumulated local effects plots, aggregate_profiles() and cluster_profiles() for aggregation of ceteris paribus profiles, theme_drwhy() with a 'ggplot2' skin for all plots, generic print() and plot() for better usability of selected explainers. The package 'ingredients' is a part of the 'DrWhy.AI' universe (Biecek 2018) <arXiv:1806.08915>.

Functions in ingredients

Name Description
calculate_variable_split Internal Function for Split Points for Selected Variables
plot.ceteris_paribus_oscillations Plot Ceteris Paribus Oscillations
calculate_oscillations Calculate Oscillations for Ceteris Paribus Explainer
calculate_variable_profile Internal Function for Individual Variable Profiles
plot.feature_importance_explainer Plots Variable Importance
plot.ceteris_paribus_2d_explainer Plot Ceteris Paribus 2D Explanations
plot.ceteris_paribus_explainer Plots Ceteris Paribus Profiles
show_observations Adds a Layer with Observations to a Profile Plot
ceteris_paribus_2d Ceteris Paribus 2D Plot
cluster_profiles Cluster Ceteris Paribus Profiles
print.ceteris_paribus_explainer Prints Individual Variable Explainer Summary
select_neighbours Select Subset of Rows Closest to a Specified Observation
show_rugs Adds a Layer with Rugs to a Profile Plot
select_sample Select Subset of Rows
show_aggreagated_profiles Adds a Layer with Aggregated Profiles
conditional_dependency Conditional Dependency Profiles
feature_importance Feature Importance Plots
partial_dependency Partial Dependency Profiles
plot.aggregated_profiles_explainer Adds a Layer with Aggregated Profiles
accumulated_dependency Accumulated Local Effects Profiles aka ALEPlots
aggregate_profiles Aggregate Ceteris Paribus Profiles
plotD3 Plot Feature Importance Objects in D3 with r2d3 Package.
print.aggregated_ceteris_paribus_explainer Prints Aggregated Profiles
theme_drwhy DrWhy Theme for ggplot Objects
ceteris_paribus Ceteris Paribus Profiles aka Individual Variable Profiles
No Results!

Last month downloads

Details

License GPL
Encoding UTF-8
LazyData true
RoxygenNote 6.1.1
URL https://ModelOriented.github.io/ingredients/
BugReports https://github.com/ModelOriented/ingredients/issues
NeedsCompilation no
Packaged 2019-04-06 11:31:56 UTC; pbiecek
Repository CRAN
Date/Publication 2019-04-09 12:10:08 UTC

Include our badge in your README

[![Rdoc](http://www.rdocumentation.org/badges/version/ingredients)](http://www.rdocumentation.org/packages/ingredients)