python实现决策树分类（2）

在中，我们已经构建了决策树，接下来可以使用它用于实际的数据分类。在执行数据分类时，需要决策时以及标签向量。程序比较测试数据和决策树上的数值，递归执行直到进入叶子节点。

这篇文章主要使用决策树分类器就行分类，数据集采用uci数据库中的红酒，白酒数据，主要特征包括12个，主要有非挥发性酸,挥发性酸度, 柠檬酸, 残糖含量,氯化物, 游离二氧化硫, 总二氧化硫,密度, ph,硫酸盐,酒精, 质量等特征。

下面是具体代码的实现：

#coding :utf-8
'''
2017.6.26 author :erin 
     function: "decesion tree" id3
     
'''
import numpy as np
import pandas as pd
from math import log
import operator 
import random
def load_data():
  
  red = [line.strip().split(';') for line in open('e:/a/winequality-red.csv')]
  white = [line.strip().split(';') for line in open('e:/a/winequality-white.csv')]
  data=red+white
  random.shuffle(data) #打乱data
  x_train=data[:800]
  x_test=data[800:]
  
  features=['fixed','volatile','citric','residual','chlorides','free','total','density','ph','sulphates','alcohol','quality']
  return x_train,x_test,features
 
def cal_entropy(dataset):
 
  
  numentries = len(dataset)
  labelcounts = {}
  for featvec in dataset:
    label = featvec[-1]
    if label not in labelcounts.keys():
      labelcounts[label] = 0
    labelcounts[label] += 1
  entropy = 0.0
  for key in labelcounts.keys():
    p_i = float(labelcounts[key]/numentries)
    entropy -= p_i * log(p_i,2)#log(x,10)表示以10 为底的对数
  return entropy
 
def split_data(data,feature_index,value):
  '''
  划分数据集
  feature_index：用于划分特征的列数，例如“年龄”
  value:划分后的属性值：例如“青少年”
  '''
  data_split=[]#划分后的数据集
  for feature in data:
    if feature[feature_index]==value:
      refeature=feature[:feature_index]
      refeature.extend(feature[feature_index+1:])
      data_split.append(refeature)
  return data_split
def choose_best_to_split(data):
  
  '''
  根据每个特征的信息增益，选择最大的划分数据集的索引特征
  '''
  
  count_feature=len(data[0])-1#特征个数4
  #print(count_feature)#4
  entropy=cal_entropy(data)#原数据总的信息熵
  #print(entropy)#0.9402859586706309
  
  max_info_gain=0.0#信息增益最大
  split_fea_index = -1#信息增益最大，对应的索引号
 
  for i in range(count_feature):
    
    feature_list=[fe_index[i] for fe_index in data]#获取该列所有特征值
    #######################################
 
    # print(feature_list)
    unqval=set(feature_list)#去除重复
    pro_entropy=0.0#特征的熵
    for value in unqval:#遍历改特征下的所有属性
      sub_data=split_data(data,i,value)
      pro=len(sub_data)/float(len(data))
      pro_entropy+=pro*cal_entropy(sub_data)
      #print(pro_entropy)
      
    info_gain=entropy-pro_entropy
    if(info_gain>max_info_gain):
      max_info_gain=info_gain
      split_fea_index=i
  return split_fea_index
    
    
##################################################
def most_occur_label(labels):
  #sorted_label_count[0][0] 次数最多的类标签
  label_count={}
  for label in labels:
    if label not in label_count.keys():
      label_count[label]=0
    else:
      label_count[label]+=1
    sorted_label_count = sorted(label_count.items(),key = operator.itemgetter(1),reverse = true)
  return sorted_label_count[0][0]
def build_decesion_tree(dataset,featnames):
  '''
  字典的键存放节点信息，分支及叶子节点存放值
  '''
  featname = featnames[:]       ################
  classlist = [featvec[-1] for featvec in dataset] #此节点的分类情况
  if classlist.count(classlist[0]) == len(classlist): #全部属于一类
    return classlist[0]
  if len(dataset[0]) == 1:     #分完了,没有属性了
    return vote(classlist)    #少数服从多数
  # 选择一个最优特征进行划分
  bestfeat = choose_best_to_split(dataset)
  bestfeatname = featname[bestfeat]
  del(featname[bestfeat])   #防止下标不准
  decisiontree = {bestfeatname:{}}
  # 创建分支,先找出所有属性值,即分支数
  allvalue = [vec[bestfeat] for vec in dataset]
  specvalue = sorted(list(set(allvalue))) #使有一定顺序
  for v in specvalue:
    copyfeatname = featname[:]
    decisiontree[bestfeatname][v] = build_decesion_tree(split_data(dataset,bestfeat,v),copyfeatname)
  return decisiontree
 
def classify(tree, featnames, x):
  classlabel=''
  root = list(tree.keys())[0]
  firstdict = tree[root]
  featindex = featnames.index(root) #根节点的属性下标
  #classlabel='0'
  for key in firstdict.keys():  #根属性的取值,取哪个就走往哪颗子树
    if x[featindex] == key:
      if type(firstdict[key]) == type({}):
        classlabel = classify(firstdict[key],featnames,x)
      else:
        classlabel = firstdict[key]
  return classlabel
 
  
if __name__ == '__main__':
  x_train,x_test,features=load_data()
  split_fea_index=choose_best_to_split(x_train)
  newtree=build_decesion_tree(x_train,features)
  #print(newtree)
  #classlabel=classify(newtree, features, ['7.4','0.66','0','1.8','0.075','13','40','0.9978','3.51','0.56','9.4','5'] )
  #print(classlabel)
  
  count=0
  for test in x_test:
    label=classify(newtree, features,test)
    
    if(label==test[-1]):
      count=count+1
  acucy=float(count/len(x_test))
  print(acucy)

测试的准确率大概在0.7左右。至此决策树分类算法结束。本文

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。