python-机器学习-决策树算法

python-机器学习-决策树算法
这属于用python学习机器学习系列的第二篇
代码如下：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import preprocessing
import re
from collections import defaultdict
from sklearn.model_selection import train_test_split

# 树结构
def tree():
    return defaultdict(tree)
# 决策树
class DecisionTree:

    # 初始化
    def __init__(self, criterion='gini', max_depth=10):
        self.max_depth = max_depth  # 最大树深
        self.tree = tree()  # 树的生成结果
        self.criterion = criterion  # 生成模式 ID3 或 ID4.5 或 gini

    # 拟合函数
    def fit(self, x, y):
        self.tree = self.CreateTree(x, y, 1)
        return self

    # 预测多个样本
    def predict(self, x):
        return np.array([self.hat(i, self.tree) for i in x])

    # 预测某个样本
    def hat(self, x, tree):
        index = tree['index']
        x_hat = x[index]
        key = self.select_close(x_hat, tree["A"])
        if tree["y_hat"].__len__() != 0:
            return float(tree['y_hat'])
        else:
            return self.hat(x, tree['child_' + str(key)])

    # 选取最匹配的key值
    def select_close(self, index, dic):
        result = index
        for key, value in dic.items():
            if key > 0 and index >= key:
                result=key
            elif key <0 and index<(key*-1):
                result=key
        return result

    # 递归生成树
    def CreateTree(self, x, y, depth):
        tree1 = tree()
        data = np.hstack((x, y))
        acount_A = len(x[0])
        d = []  # 熵列表
        l=[]#最佳值列表
        # 遍历获取熵值列表
        for i in range(acount_A):
            x1 = x[:, i]
            bestX=self.calculate_BestNum(x1,y)
            x1 = self.calculate_sortInTwo(x1, bestX)
            d.append(self.calculateEntropy(x1, y))
            l.append(bestX)
        max1 = max(d)  # 最大熵值
        max_index = d.index(max1)  # 获得最大熵的索引值
        x1 = self.calculate_sortInTwo(x[:, max_index],l[max_index])
        A = self.calculate_N(x1)  # 最大熵的特征值分类
        # 节点符值
        tree1['Entropy'] = max1
        tree1['Sample'] = len(data)
        tree1['index'] = max_index
        tree1['A'] = A
        tree1['depth'] = depth
        # 判定熵值和树深是否有效(预剪枝)
        if max1 > 0.001 and self.max_depth > depth:
            Cr = max1*1*len(data)
            tree1['Cr'] = Cr   # 剪枝后的评价数
            x3 = list(x[:, max_index])
            for key, value in A.items():
                indexs = self.calculate_indexInList(x3, key)