The famous iris dataset is a traditional statistics demonstration dataset for building classification models. It contains data for 3 different classes (species) of iris (Setosa, Versicolour, and Virginica) with 50 observations of each class. Each observation records the flower's petal length and width and the sepal length and width, together with the known class. The goal is to build a classification model to classify new observations of flowers.
A classification (decision) tree model to represent the discovered knowledge is built using a recursive partitioning algorithm. Decision trees are recognised as an easily understandable representation of the discovered knowledge. They are widely popular in situations where insight and explanations are important.
Visit the github repository for more details: https://github.com/gjwgit/iris
To install and run the pre-built model:
$ pip install mlhub
$ ml install iris
$ ml configure iris
$ ml demo iris
$ ml print iris
$ ml display iris