朴素贝叶斯分类器python实现_python: 朴素贝叶斯分类器的简单实现

以下是李航的《统计学习方法》P50 例题的python实现，分为贝叶斯估计和极大似然估计。

import pandas as pd

import numpy as np

from collections import Counter

#分贝叶斯估计与极大似然估计两种计算结果

class MLE():

def Bayesian_estimation(self,np_arr):

#print(np_arr)

#已知类标记为最后一列

list_y_Ck = list(np_arr[-1])

#赋值给y_Ck变量并去重

y_Ck = list(set(np_arr[-1]))

#print(y_Ck)

y_Count = len(list_y_Ck)

#分类数

#print(y_Count)

y_dict = {}

for i in y_Ck:

y_dict[i] = list_y_Ck.count(i)/y_Count

#print(y_dict)

yx_CNT = []

for i in y_dict.keys():

y_Ck_CNT = list_y_Ck.count(i)

#print(y_Ck_CNT)

for j in range(0,np_arr.shape[0]-1):

list_Temp = list(np_arr[j])

list_Temp_new = []

for k in range(len(list_Temp)):

if list(np_arr[-1])[k] == i:

list_Temp_new.append(list_Temp[k])

#print(list_Temp_new)

x_j_count = Counter(list_Temp_new)

yx_CNT.append([i, y_Ck_CNT, j, dict(x_j_count)])

#print(yx_CNT)

for i in yx_CNT:

for j in i[3].keys():

i[3][j] = i[3][j]/i[1]

return y_dict,yx_CNT

def forecast(self,features,path):

data = pd.read_csv(path)

print(data)

np_arr = np.array(data.values)

y_dict,yx_CNT = self.Bayesian_estimation(np_arr.T)

print('1. 极大似然估计法')

print('用于预测的特征值为: {}'.format(features))

yx_p_arr = np.array(yx_CNT)

#print(yx_p_arr)

res1={}

for key in y_dict.keys():

res1[key]=1*y_dict[key]

for i in range(0,len(features)):

res1[key]=res1[key]*yx_p_arr[(yx_p_arr[:,0]==key)&(yx_p_arr[:,2]==i)][:,3][0][features[i]]

print(res1)

return '预测结果为 {}'.format(max(res1,key = res1.get))

class BE():

def Bayesian_estimation(self,np_arr):

#print(np_arr)

#已知类标记为最后一列

list_y_Ck = list(np_arr[-1])

#赋值给y_Ck变量并去重

y_Ck = list(set(np_arr[-1]))

#print(y_Ck)

y_Count = len(list_y_Ck)

#分类数

#print(y_Count)

y_dict = {}

lamda = 1

for i in y_Ck:

y_dict[i] = (list_y_Ck.count(i) + lamda)/(y_Count + len(set(list_y_Ck)))

#print(len(y_dict))

k_ = len(y_dict)

k_lamda = k_ * lamda

yx_CNT = []

for i in y_dict.keys():

y_Ck_CNT = list_y_Ck.count(i)

#print(y_Ck_CNT)

for j in range(0,np_arr.shape[0]-1):

list_Temp = list(np_arr[j])

list_Temp_new = []

for k in range(len(list_Temp)):

if list(np_arr[-1])[k] == i:

list_Temp_new.append(list_Temp[k])

#print(list_Temp_new)

x_j_count = Counter(list_Temp_new)

dit_x_j = dict(x_j_count)

for z in dit_x_j.keys():

dit_x_j[z] = dit_x_j[z] + lamda

yx_CNT.append([i, y_Ck_CNT + lamda, j, dit_x_j])

#print(yx_CNT)

for i in yx_CNT:

for j in i[3].keys():

i[3][j] = i[3][j]/(i[1] + k_lamda)

return y_dict,yx_CNT

def forecast(self,features,path):

data = pd.read_csv(path)

#print(data)

np_arr = np.array(data.values)

y_dict,yx_CNT = self.Bayesian_estimation(np_arr.T)

#print(y_dict)

#print(yx_CNT)

print('2. 贝叶斯估计法')

print('用于预测的特征值为: {}'.format(features))

yx_p_arr = np.array(yx_CNT)

#print(yx_p_arr)

res1={}

for key in y_dict.keys():

res1[key]=1*y_dict[key]

for i in range(0,len(features)):

res1[key]=res1[key]*yx_p_arr[(yx_p_arr[:,0]==key)&(yx_p_arr[:,2]==i)][:,3][0][features[i]]

print(res1)

return '预测结果为 {}'.format(max(res1,key = res1.get))

if __name__ == '__main__':

t = MLE()

path = 'E:\\leetcode\\朴素贝叶斯分类器\\bayes.csv'

features = [2,'S']

print(t.forecast(features,path))

print('\n')

b = BE()

print(b.forecast(features,path))

运算结果为：

x1 x2 Y

0 1 S -1

1 1 M -1

2 1 M 1

3 1 S 1

4 1 S -1

5 2 S -1

6 2 M -1

7 2 M 1

8 2 L 1

9 2 L 1

10 3 L 1

11 3 M 1

12 3 M 1

13 3 L 1

14 3 L -1

1. 极大似然估计法

用于预测的特征值为: [2, 'S']

{1: 0.02222222222222222, -1: 0.06666666666666667}

预测结果为 -1

2. 贝叶斯估计法

用于预测的特征值为: [2, 'S']

{1: 0.0326797385620915, -1: 0.06100217864923746}

预测结果为 -1

蟹蟹