Case Study

The Iris dataset was made famous by British statistician/biologist Ronald Fisher in 1936, and has been widely used in the statistical pattern recognition literature ever since. The dataset consists of 150 instances, with 50 belonging to each of three species of Iris – Setosa, Virginica and Versicolor. The objective is to predict the species an instance belongs to based on the values of four continuous features: the length and width of sepals, and the length and width of petals. Generating…