August 2018
Intermediate to advanced
344 pages
9h 20m
English
There is another type of process for creating decision trees and subdividing data into categories. That is called the Entropy model, or information gain. Entropy is a measurement of the amount of disorder in the sample of data provided. We can also call this process information gain, since we are measuring how much each criteria contributed to our knowledge of which class it belongs to.
The formula for entropy is a negative log base 2 function, that is still primarily looking at the probability of a class belonging to a population, which is just the number of individuals belonging to each class divided by the total number in the sample:
Entropy = ∑_(i=1)^c▒[-p_i*log2(p_i)]
To substitute entropy as our group criteria in our program, ...
Read now
Unlock full access