Publisher Summary

This chapter is about getting familiar with the data. Knowledge about the data is useful for data preprocessing, the first major task of the data mining process. The various attribute types are studied. These include nominal attributes, binary attributes, ordinal attributes, and numeric attributes. Basic statistical descriptions can be used to learn more about each attribute’s values. Given a temperature attribute, one can determine its mean (average value), median (middle value), and mode (most common value). These are measures of central tendency, which give us an idea of the “middle” or center of distribution. Knowing such basic statistics regarding each attribute makes it easier to fill in missing values, smooth noisy values, and spot outliers during data preprocessing. Knowledge of the attributes and attribute values can also help in fixing inconsistencies incurred during data integration. Plotting the measures of central tendency shows us if the data are symmetric or skewed. Quantile plots, histograms, and scatter plots are other graphic displays of basic statistical descriptions. These can all be useful during data preprocessing and can provide insight into areas for mining. The field of data visualization provides many additional techniques for viewing data through graphical means. These can help identify relations, trends, and biases “hidden” in unstructured data sets. The similarity/dissimilarity between objects may also be used to detect outliers in the data, or to perform nearest-neighbor classification. There are many measures for assessing similarity and dissimilarity. In general, such measures are referred to as proximity measures.

It’s tempting to jump straight into mining, but first, we need to get the data ready. This involves having a closer look at attributes and data values. Real-world data are typically noisy, enormous in volume (often several gigabytes or more), and may originate from a hodgepodge of heterogenous sources. This chapter is about getting familiar with your data. Knowledge about your data is useful for data preprocessing (see Chapter 3), the first major task of the data mining process. You will want to know the following: What are the types of attributes or fields that make up your data? What kind of values does each attribute have? Which attributes are discrete, and which are continuous-valued? What do the data look like? How are the values distributed? Are there ways we can visualize the data to get a better sense of it all? Can we spot any outliers? Can we measure the similarity of some data objects with respect to others? Gaining such insight into the data will help with the subsequent analysis.

“So what can we learn about our data that’s helpful in data preprocessing?" We begin in Section 2.1 by studying the various attribute types. These include nominal attributes, binary attributes, ordinal attributes, and numeric attributes. Basic statistical descriptions can be used to learn more about each attribute’s values, as described in Section 2.2. Given a temperature attribute, for example, we can determine its mean (average value), median (middle value), and mode (most common value). These are measures of central tendency, which give us an idea of the “middle” or center of distribution.

Knowing such basic statistics regarding each attribute makes it easier to fill in missing values, smooth noisy values, and spot outliers during data preprocessing. Knowledge of the attributes and attribute values can also help in fixing inconsistencies incurred during data integration. Plotting the measures of central tendency shows us if the data are symmetric or skewed. Quantile plots, histograms, and scatter plots are other graphic displays of basic statistical descriptions. These can all be useful during data preprocessing and can provide insight into areas for mining.

The field of data visualization provides many additional techniques for viewing data through graphical means. These can help identify relations, trends, and biases “hidden” in unstructured data sets. Techniques may be as simple as scatter-plot matrices (where two attributes are mapped onto a 2-D grid) to more sophisticated methods such as tree-maps (where a hierarchical partitioning of the screen is displayed based on the attribute values). Data visualization techniques are described in Section 2.3.

Finally, we may want to examine how similar (or dissimilar) data objects are. For example, suppose we have a database where the data objects are patients, described by their symptoms. We may want to find the similarity or dissimilarity between individual patients. Such information can allow us to find clusters of like patients within the data set. The similarity/dissimilarity between objects may also be used to detect outliers in the data, or to perform nearest-neighbor classification. (Clustering is the topic of Chapters 10 and 11, while nearest-neighbor classification is discussed in Chapter 9.) There are many measures for assessing similarity and dissimilarity. In general, such measures are referred to as proximity measures. Think of the proximity of two objects as a function of the distance between their attribute values, although proximity can also be calculated based on probabilities rather than actual distance. Measures of data proximity are described in Section 2.4.

In summary, by the end of this chapter, you will know the different attribute types and basic statistical measures to describe the central tendency and dispersion (spread) of attribute data. You will also know techniques to visualize attribute distributions and how to compute the similarity or dissimilarity between objects.