机器学习决策树代码实现

最新推荐文章于 2024-07-23 22:06:37 发布

反方向的钟_1

最新推荐文章于 2024-07-23 22:06:37 发布

阅读量172

点赞数

文章标签：算法 python 开发语言机器学习人工智能

本文链接：https://blog.csdn.net/m0_56695478/article/details/127550654

版权


import numpy as np
import pandas as pd
import math
import collections
def import_data():
    data = pd.read_csv('watermelon.txt')
    data.head(10)
    data=np.array(data).tolist()
    
    labels = ['色泽', '根蒂', '敲击', '纹理', '脐部', '触感']

    
    labels_full = {}

    for i in range(len(labels)):
        labelList = [example[i] for example in data]
        uniqueLabel = set(labelList)
        labels_full[labels[i]] = uniqueLabel
    return data,labels,labels_full
data,labels,labels_full=import_data()
def calcShannonEnt(dataSet):
    """
    计算给定数据集的信息熵(香农熵)
    :param dataSet:
    :return:
    """
  
    numEntries = len(dataSet)

    
    labelCounts = collections.defaultdict(int)

    
    for featVec in dataSet:
       
        currentLabel = featVec[-1]

       
        labelCounts[currentLabel] += 1

    
    shannonEnt = 0.0

    for key in labelCounts:
        
        prob = float(labelCounts[key]) / numEntries

        
        shannonEnt -= prob * math.log2(prob)

    return shannonEnt


print(calcShannonEnt(data))  # 输出为：0.9975025463691153
def splitDataSet(dataSet, axis, value):
    """
    按照给定的特征值，将数据集划分
    :param dataSet: 数据集
    :param axis: 给定特征值的坐标
    :param value: 给定特征值满足的条件，只有给定特征值等于这个value的时候才会返回
    :return:
    """
    
    retDataSet = []

    
    for featVec in dataSet:
        
        if featVec[axis] == value:
           
            reducedFeatVec = featVec[:axis]
            
            reducedFeatVec.ex