Prediction

makePrediction

Result from <code><a rd-options="" href="/link/predict.WrappedModel?package=mlr&version=2.10" data-mini-rdoc="mlr::predict.WrappedModel">predict.WrappedModel</a></code>.
Use <code>as.data.frame</code> to access all information in a convenient format.
The function <code><a rd-options="" href="/link/getPredictionProbabilities?package=mlr&version=2.10" data-mini-rdoc="mlr::getPredictionProbabilities">getPredictionProbabilities</a></code> is useful to access predicted probabilities. The <code>data</code> member of the object contains always the following columns:
<code>id</code>, index numbers of predicted cases from the task, <code>response</code>
either a numeric or a factor, the predicted response values, <code>truth</code>,
either a numeric or a factor, the true target values.
If probabilities were predicted, as many numeric columns as there were classes named
<code>prob.classname</code>. If standard errors were predicted, a numeric column named <code>se</code>. The constructor <code>makePrediction</code> is mainly for internal use. Object members:
<dl class="dl-horizontal">
<dt>predict.type [<code>character(1)</code>]</dt><dd>Type set in <code><a rd-options="" href="/link/setPredictType?package=mlr&version=2.10" data-mini-rdoc="mlr::setPredictType">setPredictType</a></code>.</dd>
<dt>data [<code>data.frame</code>]</dt><dd>See details.</dd>
<dt>threshold [<code>numeric(1)</code>]</dt><dd>Threshold set in predict function.</dd>
<dt>task.desc [<code><a rd-options="" href="/link/TaskDesc?package=mlr&version=2.10" data-mini-rdoc="mlr::TaskDesc">TaskDesc</a></code>]</dt><dd>Task description object.</dd>
<dt>time [<code>numeric(1)</code>]</dt><dd>Time learner needed to generate predictions.</dd>
<dt>error [<code>character(1)</code>]</dt><dd>Any error messages generated by the learner (default NA_character_).</dd>
</dl> Internal, do not use!

internal

Interface to a large number of classification and regression
techniques, including machine-readable parameter descriptions. There is
also an experimental extension for survival analysis, clustering and
general, example-specific cost-sensitive learning. Generic resampling,
including cross-validation, bootstrapping and subsampling. Hyperparameter
tuning with modern optimization techniques, for single- and multi-objective
problems. Filter and wrapper methods for feature selection. Extension of
basic learners with additional operations common in machine learning, also
allowing for easy nested resampling. Most operations can be parallelized.

Prediction: Prediction object.

Description

Usage

Arguments