AnalysisClass-class

Data quality issues such as missing values and outliers are often
interdependent, which makes preprocessing both time-consuming and leads to
suboptimal performance in knowledge discovery tasks. This package supports
preprocessing decision making by visualizing interdependent data quality issues
through means of feature construction. The user can define his own application
domain specific constructed features that express the quality of a data point
such as number of missing values in the point or use nine default features.
The outcome can be explored with plot methods and the feature constructed data
acquired with get methods.

Markus Vattulainen

preproviz

Tools for Visualization of Interdependent Data Quality Issues

AnalysisClass-class function

 <dl>
<dt><code>objectname</code></dt><dd>(character) Name of the object</dd> <dt><code>basedata</code></dt><dd>(data frame) A data frame containing the original data</dd> <dt><code>numericbasedata</code></dt><dd>(data frame) A data frame containing the original data without class labels.</dd> <dt><code>classlabel</code></dt><dd>(factor) A vector of class labels of the original data</dd> <dt><code>constructeddata</code></dt><dd>(data frame) Constructed data. Feature vectors from computevalue combined as a data frame</dd> <dt><code>minmaxconstructeddata</code></dt><dd>(data frame) Min-max normalized constructed data</dd> <dt><code>combineddata</code></dt><dd>(data frame) Basedata and constructed data combined (note: may include missing values)</dd> <dt><code>combinednumericdata</code></dt><dd>(data frame) Basedata and constructed data combined without class labels</dd> <dt><code>longformatmixmaxconstructeddata</code></dt><dd>(data frame) Minmaxconstructeddata in long format</dd> <dt><code>distancematrix</code></dt><dd>(matrix) Distance matrix of minmaxconstructeddata</dd> <dt><code>dendogram</code></dt><dd>(dendrogram) Variable clusters (note: not in use)</dd> <dt><code>lofscores</code></dt><dd>(numeric) A vector of LOF scores</dd> <dt><code>cmds</code></dt><dd>(data frame) Classical multidimensional scaling two-dimensional data point computed from minmaxconstructeddata</dd> <dt><code>variableimportancedata</code></dt><dd>(data frame) Constructed features and their random forest variable importance scores for predicting classlabel</dd> <dt><code>lofsumdata</code></dt><dd>(data frame) mixmax normalized LOF scores of minmaxconstructed data summed with minmax normalized LOF scores of numericbasedata</dd> </dl>

AnalysisClass-class: An S4 class representing analysis data

Description

Arguments

Slots