Understanding the multivariate dataset

A multivariate dataset is defined as a set of multiple observations (attributes) associated with different aspects of a phenomenon. In this chapter, we will use a multivariate dataset result of a chemical analysis of wines that grew in three different cultivars from the same area in Italy. The Wine dataset is available in the UC Irvine Machine Learning Repository and can be freely downloaded from the following link:

http://archive.ics.uci.edu/ml/datasets/Wine

The dataset includes 13 features with no missing data and all the features are numerical or real values.

The complete list of features is listed as follows:

• Alcohol

• Malic acid

• Ash

• Alkalinity of ash

• Magnesium

• Total phenols

• Flavonoids

• Nonflavonoid phenols

• Proanthocyanins

• Color intensity

• Hue

• OD280/OD315 of diluted wines

• Proline

The dataset has 178 records from three different classes. The distribution is seen in the following figure corresponding to 59 for class 1, 71 for class 2, and 48 for class 3:

The first five...