决策树买不买电脑_电脑销售决策树实验数据

from math import log
import operator
import pandas as pd
import numpy as np

def calcShannonEnt(dataSet):  # 计算数据的熵(entropy)
    numEntries=len(dataSet)  # 数据条数
    labelCounts={
   }
    for featVec in dataSet:
        currentLabel=featVec[-1] # 每行数据的最后一个字（类别）
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel]=0
        labelCounts[currentLabel]+=1  # 统计有多少个类以及每个类的数量
    shannonEnt=0
    for key in labelCounts:
        prob=float(labelCounts[key])/numEntries # 计算单个类的熵值
        shannonEnt-=prob*log(prob,2) # 累加每个类的熵值
    return shannonEnt

def createDataSet1():    # 创造数据集
    dataSet = [['<=30', 'high', 'no', 'fair', 'no'],
               ['<=30', 'high', 'no', 'excellent', 'no'],
               ['31…40', 'high', 'no', 'fair'
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23