Python实现计算信息熵的示例代码

from math import log
import pandas as pd

dataSet = pd.read_csv('dataSet.csv', header=None).values.tolist()

numEntries = len(dataSet)  # 数据集大小
    labelCounts = {}
    for featVec in dataSet:  #
        currentLabel = featVec[-1]  # 获取分类标签
        if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0  # 字典值不等于0？？？
        labelCounts[currentLabel] += 1  # 每个类中数据个数统计

    infoEnt = 0.0
    for key in labelCounts:  # 信息熵计算
        prob = float(labelCounts[key]) / numEntries
        infoEnt -= prob * log(prob, 2)
 
    return infoEnt
    # 返回值 infoEnt 为数据集的信息熵，表示为 float 类型

from math import log
import pandas as pd
 
dataSet = pd.read_csv('dataSet.csv', header=None).values.tolist()
 
 
def calcInfoEnt(dataSet):
    numEntries = len(dataSet)  # 数据集大小
    labelCounts = {}
    for featVec in dataSet:  #
        currentLabel = featVec[-1]  # 获取分类标签
        if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0  # 字典值不等于0？？？
        labelCounts[currentLabel] += 1  # 每个类中数据个数统计
    infoEnt = 0.0
    for key in labelCounts:  # 信息熵计算
        prob = float(labelCounts[key]) / numEntries
        infoEnt -= prob * log(prob, 2)
 
    return infoEnt
    # 返回值 infoEnt 为数据集的信息熵，表示为 float 类型
 
 
if __name__ == '__main__':
    # 输出为当前数据集的信息熵
    print(calcInfoEnt(dataSet))

import math
#以整型数据为例，给出其信息熵的计算程序。
###########################################
'''统计已知数据中的不同数据及其出现次数'''
###########################################
def StatDataInf( data ):
    dataArrayLen = len( data )
    diffData = [];
    diffDataNum = [];
    dataCpy = data;
    for i in range( dataArrayLen ):
        count = 0;
        j = i
        if( dataCpy[j] != '/' ):
            temp = dataCpy[i]
            diffData.append( temp )
            while( j < dataArrayLen ):
                if( dataCpy[j] == temp ):
                    count = count + 1
                    dataCpy[j] = '/'
                j = j + 1
            diffDataNum.append( count )
    return diffData, diffDataNum
 
###########################################
'''计算已知数据的熵'''
###########################################
def DataEntropy( data, diffData, diffDataNum ):
    dataArrayLen = len( data )
    diffDataArrayLen = len( diffDataNum )
    entropyVal = 0;
    for i in range( diffDataArrayLen ):
        proptyVal = diffDataNum[i] / dataArrayLen
        entropyVal = entropyVal - proptyVal * math.log2( proptyVal )
    return entropyVal
 
def main():
    data = [1, 2, 1, 2, 1, 2, 1, 2, 1, 2 ]
    [diffData, diffDataNum] = StatDataInf( data )
    entropyVal = DataEntropy( data, diffData, diffDataNum )
    print( entropyVal )
    
    data = [1, 2, 1, 2, 2, 1, 2, 1, 1, 2, 1, 1, 1, 1, 1 ]
    [diffData, diffDataNum] = StatDataInf( data )
    entropyVal = DataEntropy( data, diffData, diffDataNum )
    print( entropyVal )
    
    data = [1, 2, 3, 4, 2, 1, 2, 4, 3, 2, 3, 4, 1, 1, 1 ]
    [diffData, diffDataNum] = StatDataInf( data )
    entropyVal = DataEntropy( data, diffData, diffDataNum )
    print( entropyVal )
    
    data = [1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4 ]
    [diffData, diffDataNum] = StatDataInf( data )
    entropyVal = DataEntropy( data, diffData, diffDataNum )
    print( entropyVal )
    data = [1, 2, 3, 4, 5, 1, 2, 3, 4, 5, 1, 2, 3, 4, 5, 1, 2, 3, 4, 5, 1, 2, 3, 4, 1, 2, 3, 4, 5 ]
    [diffData, diffDataNum] = StatDataInf( data )
    entropyVal = DataEntropy( data, diffData, diffDataNum )
    print( entropyVal )
    
if __name__ == '__main__':
    main()
###########################################
#运行结果
1.0
0.9182958340544896
1.965596230357602
2.0
2.3183692540329317