Making Sense of Data II: A Practical Guide to Data Visualization, Advanced Data Mining Methods, and Applications

APPENDIX B

SOFTWARE

B.1 SOFTWARE OVERVIEW

B.1.1 Software Objectives

The Traceis Data Exploration Studio is a software tool for data analysis and data mining. It was developed to provide a hands-on experience demonstrating many of the techniques described in this book, as well as in the preceding book (Myatt, 2007). It incorporates a number of tools for preparing and summarizing data, as well as tools for grouping, finding patterns, and making predictions. These tools are integrated through a series of coordinating views on to the data. Table B.1 summarizes the methods included in the Traceis software.

The software provides tools for:

• Preparing data: Having identified a data set to mine, the preparation of the data is often one of the most time-consuming aspects of any data mining project. Understanding what types of data are contained in the data set is important; after obtaining a sense of the data, cleaning, transforming, and appropriately reducing the number of variables and observations helps ensure that the set is ready for any subsequent analysis. Preparing the data helps develop a more thorough understanding of the data. The Traceis software contains tools for loading, cleaning, understanding, and reducing the number of observations and variables, as shown in Table B.1.
• Tables and graphs: Visualizing the data can help in preparing the data, to identify patterns and trends, as well as understanding the results of any analysis. Tables and graphs are critical tools for use ...