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))