impute_cells

by default assumes first column of cell.dat is x1 and second is x2
leave grid1 NULL if feature x1 is a factor
the difference variable has to be named .yhat.diff

internal

Interpretability methods to analyze the behavior and
predictions of any machine learning model. Implemented methods are:
Feature importance described by Fisher et al. (2018)
<arXiv:1801.01489>, accumulated local effects plots described by Apley
(2018) <arXiv:1612.08468>, partial dependence plots described by
Friedman (2001) <www.jstor.org/stable/2699986>, individual conditional
expectation ('ice') plots described by Goldstein et al. (2013)
<doi:10.1080/10618600.2014.907095>, local models (variant of 'lime')
described by Ribeiro et. al (2016) <arXiv:1602.04938>, the Shapley
Value described by Strumbelj et. al (2014)
<doi:10.1007/s10115-013-0679-x>, feature interactions described by
Friedman et. al <doi:10.1214/07-AOAS148> and tree surrogate models.

Christoph Molnar

Interpretable Machine Learning

Patrick Schratz

impute_cells function

<dl><dt>cell.dat</dt>
<dd>data.table with at least 4 columns: .yhat.diff and the two interval indices.
Make sure that empty cells are also included and cell.dat is not the sparse representation.</dd>
<dt>grid1</dt>
<dd>data.frame where each row is the actual value for a given interval index for feature 1.
If empty impute_cells assumes that the feature is categorical (factor).</dd>
<dt>grid2</dt>
<dd>data.frame where each row is the actual value for a given interval index for feature 2</dd>
<dt>x1.ind</dt>
<dd>column number or name of cell.dat for feature 1. If one feature is categorical, has to be x1</dd>
<dt>x2.ind</dt>
<dd>column number or name of cell.dat for feature 2</dd></dl>

Arguments

Impute missing cells of grid — impute_cells

<dl>

<dt>cell.dat</dt>
<dd>data.table with at least 4 columns: .yhat.diff and the two interval indices.
Make sure that empty cells are also included and cell.dat is not the sparse representation.</dd>


<dt>grid1</dt>
<dd>data.frame where each row is the actual value for a given interval index for feature 1.
If empty impute_cells assumes that the feature is categorical (factor).</dd>


<dt>grid2</dt>
<dd>data.frame where each row is the actual value for a given interval index for feature 2</dd>


<dt>x1.ind</dt>
<dd>column number or name of cell.dat for feature 1. If one feature is categorical, has to be x1</dd>


<dt>x2.ind</dt>
<dd>column number or name of cell.dat for feature 2</dd>

</dl>

impute_cells: Impute missing cells of grid

Description

Usage

Arguments