【机器学习】手动实现分类决策树 （不用sk-learn）

【机器学习】手动实现分类决策树 （不用sk-learn）

不用sk-learn库，一步一步实现分类决策树，外加可视化哦~

1. 树结构：二叉树结构+决策节点+叶子节点
2. 度量：entropy或gini
3. 构造树
4. 读入数据：车辆轮廓分类（数据量：846，特征维度：18）
   数据来源：CSDN - 一些用于聚类和分类问题的数据集 分类数据35
5. 训练
6. 测试

下面就开始啦

树结构

二叉树结构

from graphviz import Digraph
import uuid
from random import sample


class BinaryTree:
    def __init__(self, rootObj):
        self.key = rootObj
        self.leftChild = None
        self.rightChild = None
        self.dot = Digraph(comment='Binary Tree')

    def insertLeft(self, newNode):
        if self.leftChild is None:
            self.leftChild = newNode
        else:
            t = newNode
            t.leftChild = self.leftChild
            self.leftChild = t

    def insertRight(self, newNode):
        if self.rightChild is None:
            self.rightChild = newNode
        else:
            t = newNode
            t.rightChild = self.rightChild
            self.rightChild = t

    # 可视化，输出到Binary_Tree.gv
    def print_tree(self, save_path='./Binary_Tree.gv', label=True):

        # colors for labels of nodes
        colors = ['skyblue', 'tomato', 'orange', 'purple', 'green', 'yellow', 'pink', 'red']

        # Draws a binary tree with a node as its root
        def print_node(node, node_tag):
            # The node color
            color = sample(colors, 1)[0]
            if node.leftChild is not None:
                if type(node.leftChild.key).__name__ == 'DecisionNode':  # DecisionNode
                    left_tag = str(uuid.uuid1())  # Data for the left node
                    self.dot.node(left_tag,
                                  str(node.leftChild.key.feature_name + " <= " + str(
                                      node.leftChild.key.feature_value) + " ? "),
                                  style='filled', color=color)  # left
                    label_string = 'Y' if label else ''  # Whether to label the connector indicates a left subtree
                    self.dot.edge(node_tag, left_tag, label=label_string)  # The line between the left child and parent
                    print_node(node.leftChild, left_tag)
                else:  # leaf
                    left_tag = str(uuid.uuid1())
                    self.dot.node(left_tag, str(
                        "samples = " + str(node.leftChild.key.num) + "\n value = " + str(node.leftChild.key.value)),
                                  style='filled', color=color)
                    label_string = 'Y' if label else ''
                    self.dot.edge(node_tag, left_tag, label=label_string)
                    print_node(node.leftChild, left_tag)

            if node.rightChild is not None:
                if type(node.rightChild.key).__name__ == 'DecisionNode'