Appendix A

VisMiner Reference by Task

Dataset Preparation

Handle Missing Values

VisMiner does not support mining of datasets with any missing values. They are represented in the Control Center by a dataset icon overlaid with a red triangle. Before proceeding with any data exploration or mining tasks all missing values must be handled. To do this:

1. Right click on dataset containing missing values.
2. Select “Handle missing values”.
3. Specify handling option for all attributes with missing values.

Outlier Detection and Isolation

The search for outliers in a dataset takes time, but is facilitated by the data exploration viewers of VisMiner. For a thorough search, complete all of the following:

1. View Summary Statistics for dataset. (Right-click on dataset in Control Center.)
a. Look at minimum and maximum values of each numeric attribute; check that they fall within acceptable range. For example, an attribute GradePointAverage should not have a minimum value less than zero or a maximum value greater than four.
b. For nominal attributes, hover over the cardinality value. When hovered, if there are not too many different values, the unique values will be displayed in a small pop-up box. Check that all values are acceptable.
2. Use either the histogram or parallel coordinate plot to view the distributions of each attribute. Look for outliers at the extremes of numeric attributes.
3. Some outlying observations may not contain extreme values with respect to any single attribute, ...

Get Visual Data Mining: The VisMiner Approach, 2nd Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.