Python Artificial Intelligence Projects for Beginners

Random forests
Random forests are extensions of decision trees and are a kind of ensemble method. 
Ensemble methods can achieve high accuracy by building several classifiers and running a
each one independently. When a classifier makes a decision, you can make use of the most
common and the average decision. If we use the most common method, it is called 
voting
.

---

Prediction with Random Forests
Chapter 2
[ 25 ]
Here's a diagram depicting the ensemble method:
You can think of each classifier as being specialized for a unique perspective on the data.
Each classifier may be a different type. For example, you can combine a decision tree and a
logistic regression and a neural net, or the classifiers may be the same type but trained on
different parts or subsets of the training data.
A random forest is a collection or ensemble of decision trees. Each tree is trained on a
random subset of the attributes, as shown in the following diagram:

---

Prediction with Random Forests
Chapter 2
[ 26 ]
These decision trees are typical decision trees, but there are several of them. The difference,
compared with a single decision tree, particularly in a random forest, is that each tree is
only allowed to look at some of the attributes, typically a small number relative to the total
number of attributes available. Each tree is specialized to just those attributes. These
specialized trees are collected and each offers a vote for its prediction. Whichever outcome
gets the most votes from the ensemble of specialized trees is the winner. That is the final
prediction of the random forest.