数据挖掘实验——python实现决策树（ID3算法）

实验内容：

使用ID3算法设计实现决策树，使用uci数据集中的Caesarian Section Classification Dataset Data Set数据进行分类

获取数据集：https://archive.ics.uci.edu/ml/datasets/Caesarian+Section+Classification+Dataset

数据集：
@attribute ‘Age’ { 22,26,28,27,32,36,33,23,20,29,25,37,24,18,30,40,31,19,21,35,17,38 }
@attribute ‘Delivery number’ { 1,2,3,4 }
@attribute ‘Delivery time’ { 0,1,2 }
@attribute ‘Blood of Pressure’ { 2,1,0 }

@attribute ‘Heart Problem’ { 1,0 }
@attribute Caesarian { 0,1 }

代码实现：

import pandas as pd

# 加载数据集
# @attribute 'Age' {
    22,26,28,27,32,36,33,23,20,29,25,37,24,18,30,40,31,19,21,35,17,38 } 
# @attribute 'Delivery number' {
    1,2,3,4 }
# @attribute 'Delivery time' {
    0,1,2 }
# @attribute 'Blood of Pressure' {
    2,1,0 }

# @attribute 'Heart Problem' {
    1,0 } 
# @attribute Caesarian {
    0,1 }
data= pd.read_csv('D:/Desktop/caesarian.csv.arff',header=None)
print(data.head())

import math
import operator

def get_data():
    # 数据集
    x = data[[0,1,2,3,4,5]].values.tolist()
    # 分类属性
    labels = ['年龄','数量','时间','血压','心脏病']
    return x,labels

def maxCount(classList):
    Count={
   }
    #统计classList中每个元素出现的次数
    for i in classList:
        if i not in classCount.keys():
            Count[i]=0
        Count[i]+=1
        #根据字典的值降序排列
        sorted_Count=sorted(Count.items(),key=operator.itemgetter(1),reverse=True)
        return sorted_Count[0][0]

def Entropy(x):
    D=len(x)
    #保存每个标签（label）出现次数的字典
    labelCounts={
   }
    #对每组特征向量进行统计
    for m in x:
        Label=m[-1]                     #提取标签
        if Label not in labelCounts.keys():   #标签没有被统计就添加
            labelCounts[Label]=0
        labelCounts[Label