calculate_variable_splits()
now treats integer
variables as categorical
. This change is propagated to ceteris_paribus()
, partial_dependence()
, accumulated_dependence()
, conditional_dependence()
, aggregate_profiles()
, DALEX::predict_profile()
, DALEX::model_profile()
ceteris_paribus
/ calculate_variable_splits
when tidymodels
uses integer
variables #145show_observations
#148. This change is propagated to DALEX::plot.predict_profile()
#540.class(x) = "y"
with is(x, "y")
facet_scales
parameter to plot.aggregated_profiles_explainer
('free_x'
by default) #138 and plot.ceteris_paribus_explainer
('free_x'
or 'free_y'
by default, depending on plot type) #136N = NULL
in partial_dependence()
etc. #134plot.ceteris_paribus_explainer
now by default for categorical variables plots profiles (not lines -prev default- nor bars)subtitle
value in plot.fi
changed to NULL
from NA
(unification)ceteris_paribus
function one can specify how grid points shall be calculated, see variable_splits_type
ceteris_paribus
and aggregates are now working with missing data, this solves #120plot(ceteris_paribus)
change default color
to label or ids if more than one profile is detected, this solves #123ceteris_paribus
has now argument variable_splits_with_obs
which included values from new_observations
in the variable_splits
, this solves #124n_sample
argument in feature_importance
(now it's N
) #113plot_profile
now handles multilabel modelsDALEX
is moved to Suggests as in #112plot_categorical_ceteris_paribus
can plot bars (again)bind_plots
functionR v4.0
and depend on R v3.5
to comply with DALEX
title
and subtitle
in several plotsdependency
to dependence
#103ceteris_paribus
profiles are now working for categorical variablesshow_profiles
, show_observations
, show_residuals
are now working for categorical variablesdesc_sorting
in plot.variable_importance_explainer
#94feature_importance
now does 15
permutations on each variable by default. Use the B
argument to change this numberplot.feature_importance
and plotD3.feature_importance
that showcase the permutation dataaggregate_profiles
: preserve _x_
column factor order and sort its values #82aggregate_profiles
use now gaussian kernel smoothing. Use the span
argument for fine control over this parameter (#79)variable_type
and variables
arguments usage in the
aggregate_profiles
, plot.ceteris_paribus
and plotD3.ceteris_paribus
variable_type
argument from plotD3.aggregated_profiles
(now the same as in plot.aggregated_profiles
)DALEXtra
as aspect_importance
is moved to DALEXtra
as well
(See v0.3.12 changelog)aspect_importance
is moved to DALEXtra
(#66)titanic_imputed
from DALEX
(#65)plot.aspect_importance
- it can plot more than single figure triplot
, plot.aspect_importance
and plot_group_variables
to add more clarity in plots and allow some parameterizationtriplot
function that illustrates hierarchical aspect_importance()
groupingsaspect_importance()
functionsaspect_importance()
only_numerical
parameter to variable_type
in functions aggregated_profiles(),
cluster_profiles(), plot() and others, as requested in #15describe()
function for ceteris_paribus()
, feature_importance()
and aggregate_profiles()
explanations. aggregated_profiles_conditional
and aggregated_profiles_accumulated
are rewritten with some code fixeslime
is implemented in the lime()
/aspect_importance()
function.B
that replicates permutations B
times and calculates average from drop loss.plotD3
now supports Ceteris Paribus Profiles.feature_importance
now can take variable_grouping
argument that assess importance of group of featuresshow_profiles
and show_residuals
functions extend Ceteris Paribus Plots.show_aggreagated_profiles
is renamed to show_aggregated_profiles
describe()
and print.ceteris_paribus_descriptions()
for text based descriptions of Ceteris Paribus explainersplot.ceteris_paribus_explainer
works now also for categorical variables. Use the only_numerical = FALSE
to force barspartial_profiles()
, accumulated_profiles()
and conditional_profiles
for variable effectsceteris_paribus_2d
extends classical ceteris paribus profilesceteris_paribus_oscillations
calculates oscilations for ceteris paribus profilescluster_profiles
helps to identify interactionspartial_dependency
calculates partial dependency plotsaggregate_profiles
calculates partial dependency plots and much moremodel_feature_importance
and model_feature_response
from DALEX
to ingredients
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.