cleanRFdata

Removes cases for a Random Forest classification model 
 with missing data and predictors that are constant.

Estimate significance of importance metrics
for a Random Forest model by permuting the response
variable. Produces null distribution of importance
metrics for each predictor variable and p-value of
observed. Provides summary and visualization functions for 'randomForest'
results.

Eric Archer

rfPermute

Estimate Permutation p-Values for Random Forest Importance
Metrics

cleanRFdata function

<dl><dt>x</dt>
<dd>columns used as predictor variables as character or numeric vector.</dd>
<dt>y</dt>
<dd>column used as response variable as character or numeric.</dd>
<dt>data</dt>
<dd>data.frame containing <code>x</code> and <code>y</code> columns.</dd>
<dt>max.levels</dt>
<dd>maximum number of levels in response variable <code>y</code>.</dd></dl>

Arguments

Eric Archer <a href="/link/eric.archer%40noaa.gov?package=rfPermute&version=2.5.2" data-mini-rdoc="rfPermute::eric.archer@noaa.gov">eric.archer@noaa.gov</a>

Author

Clean Random Forest Input Data — cleanRFdata

<dl>

<dt>x</dt>
<dd>columns used as predictor variables as character or numeric vector.</dd>


<dt>y</dt>
<dd>column used as response variable as character or numeric.</dd>


<dt>data</dt>
<dd>data.frame containing <code>x</code> and <code>y</code> columns.</dd>


<dt>max.levels</dt>
<dd>maximum number of levels in response variable <code>y</code>.</dd>

</dl>

Eric Archer <a href='mailto:eric.archer@noaa.gov'>eric.archer@noaa.gov</a>

cleanRFdata: Clean Random Forest Input Data

Description

Usage

Value

Arguments

Author