DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home List of Figures List of Tables Data Mining Data Mining Data Mining with Rattle Introduction Data Transform Explore A Model Building Framework Unsupervised Modelling Two Class Models Multi Class Models Regression Models Text Mining Evaluation and Deployment Moving into R Troubleshooting R for the Data Miner R Data Graphics in R Understanding Data Preparing Data Building Models Evaluating Models Algorithms Apriori Bagging Bayes Classifier Boosting Cluster Analysis Conditional Trees Hierarchical Clustering K-Means K-Nearest Neighbours Linear Models Logistic Regression Neural Networks Support Vector Machines Text Mining Open Products AlphaMiner Borgelt Data Mining Suite KNime R Rattle Weka Closed Products C4.5 Clementine Equbits Foresight GhostMiner InductionEngine ODM Enterprise Miner Statistica Data Miner TreeNet Virtual Predict Appendicies Glossary Bibliography Index

Summary Option

While a picture might tell a thousand stories, textual summaries still play an important roll in our understanding of data. We saw a basic summary of our data after first loading the data into Rattle (page ). The data types and the first few values for each of the variables were listed. This is the most basic of summaries and even so, begins to tell a story about the data. It is the beginnings of understanding the data.

Rattle's Summary option of the Explore tab provides a number of more detailed textual summaries of our data.

[width=,trim=0 250 0 0, clip]rattle-audit-explore

With the Use Sample check button we can choose to summarise the whole dataset, or just the training dataset. We might choose to only summarise the sample when the dataset itself is very large and the summaries take a long time to perform. However, this is not very likely and so we would usually not choose the sample option.

The following series of check buttons allows us to fine tune what it is we wish to explore textually. We can choose to display one or many of the summary options. The first three, Summary, Describe, Basic are three alternatives that provide overall statistics for each variables (although the Basics option only summarises numeric variables). The final two, kurtosis and skewness provide specific measures of the characteristics of the data. These are separated out so that we can compare the kurtosis or skewness directly across a number of variables. These two measures both apply only to numeric data.

Support further development through the purchase of the PDF version of the book.
Brought to you by Togaware.