决策树——实践

尚能饭否

于 2016-01-06 15:08:57 发布

阅读量379

点赞数

分类专栏：机器学习文章标签：决策树

本文链接：https://blog.youkuaiyun.com/shangwei1991/article/details/50469028

版权

# -*- coding: utf-8 -*-
"""
Created on Tue Sep 08 10:10:15 2015

@author: Administrator
"""

import operator   #为了能够处理叶子节点的类标签仍然不唯一的情况。
from math import log

#计算训练数据集的香农熵
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0   #这里不能为1,因为后一语句是一定执行的。
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob * log(prob, 2)
    return shannonEnt

#创建训练数据集
def createDataSet():
    dataSet = [[1, 1, 'yes'], 
               [1, 1, 'yes'], 
               [1, 0, 'no'], 
               [0, 1, 'no'], 
               [0, 1, 'no']]
    labels = ['no surfacing',