Machine learning decision tree

The first 1 Turn off ： What is a decision tree

The first 1 topic

The process of training decision tree is the process of building decision tree
ID3 The algorithm builds a decision tree based on information gain
C4.5 The algorithm builds a decision tree according to the information gain ratio
The decision tree model is highly understandable

The first 2 topic

The decision tree can be a multi branch tree . For example, there are three situations to choose from when buying watermelon ： buy 、 Not buy 、 undetermined . At this time, the decision tree is not a binary tree .

The first 2 Turn off ： Information entropy and information gain

Our mission ： Grasp what is information gain , Complete the program design of calculating information gain .

import numpy as np

def getEnt(array):
    Ent = 0
    for i in range(2):
        Dv = 0