机器学习 周志华 课后习题 7.3
作者:互联网
7.3 试编程拉普拉斯修正的朴素贝叶斯分类器,并以西瓜数据集3.0为训练集,对“测1”样本进行判别。
代码 python
代码实现。
import pandas as pd
import math
import numpy as np
class LaplacianNB():
"""
Laplacian naive bayes for binary classification problem.
"""
def __init__(self):
"""
"""
def train(self, X, y):
"""
Training laplacian naive bayes classifier with traning set (X, y).
Input:
X: list of instances. Each instance is represented by
y: list of labels. 0 represents bad, 1 represents good.
"""
N = len(y)
self.classes = self.count_list(y)
self.class_num = len(self.classes)
self.classes_p = {}
self.classes_p1 = {}
#print self.classes
#进行拉普拉斯修正,求得先验概率
for c, n in self.classes.items():
self.classes_p[c] = float(n+1) / (N+self.class_num)
#未经修正下的先验值
# for c, n in self.classes.items():
# self.classes_p1[c] = float(n ) / (N )
# print(self.classes_p1)
#离散属性
self.discrete_attris_with_good_p = []
self.discrete_attris_with_bad_p = []
for i in range(6):
attr_with_good = []
attr_with_bad = []
for j in range(N):
if y[j] == 1:
attr_with_good.append(X[j][i])
else:
attr_with_bad.append(X[j][i])
unique_with_good = self.count_list(attr_with_good)
unique_with_bad = self.count_list(attr_with_bad)
self.discrete_attris_with_good_p.append(self.discrete_p(unique_with_good, self.classes[1]))
self.discrete_attris_with_bad_p.append(self.discrete_p(unique_with_bad, self.classes[0]))
self.good_mus = []
self.good_vars = []
self.bad_mus = []
self.bad_vars = []
"""
连续属性考虑概率密度
"""
for i in range(2):
attr_with_good = []
attr_with_bad = []
for j in range(N):
if y[j] == 1:
attr_with_good.append(X[j][i+6])
else:
attr_with_bad.append(X[j][i+6])
good_mu, good_var = self.mu_var_of_list(attr_with_good)
bad_mu, bad_var = self.mu_var_of_list(attr_with_bad)
self.good_mus.append(good_mu)
self.good_vars.append(good_var)
self.bad_mus.append(bad_mu)
self.bad_vars.append(bad_var)
def predict(self, x):
"""
"""
p_good = self.classes_p[1]
p_bad = self.classes_p[0]
for i in range(6):
p_good *= self.discrete_attris_with_good_p[i][x[i]]
p_bad *= self.discrete_attris_with_bad_p[i][x[i]]
for i in range(2):
p_good *= self.continuous_p(x[i+6], self.good_mus[i], self.good_vars[i])
p_bad *= self.continuous_p(x[i+6], self.bad_mus[i], self.bad_vars[i])
if p_good >= p_bad:
return p_good, p_bad, "是"
else:
return p_good, p_bad, "否"
def count_list(self, l):
"""
统计元素个数
"""
unique_dict = {}
for e in l:
if e in unique_dict:
unique_dict[e] += 1
else:
unique_dict[e] = 1
return unique_dict
#为每个属性估计条件概率
def discrete_p(self, d, N_class):
"""
Compute discrete attribution probability based on {0:, 1:, 2: }.
"""
new_d = {}
#print d
for a, n in d.items():
new_d[a] = float(n+1) / (N_class + len(d))
return new_d
#求概率密度函数
def continuous_p(self, x, mu, var):
p = 1.0 / (math.sqrt(2*math.pi) * math.sqrt(var)) * math.exp(- (x-mu)**2 /(2*var))
return p
#求均值方差
def mu_var_of_list(self, l):
mu = sum(l) / float(len(l))
var = 0
for i in range(len(l)):
var += (l[i]-mu)**2
var = var / float(len(l))
return mu, var
if __name__=="__main__":
lnb = LaplacianNB()
data = pd.read_csv("data/西瓜数据集3.0.csv")
data=np.array(data)
X=data[:,1:-1]
y=[1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0]
#print X, y
lnb.train(X, y)
#print lnb.discrete_attris_with_good_p
label = lnb.predict(["青绿", "蜷缩", "浊响", "清晰", "凹陷", "硬滑", 0.697, 0.460])
print ("predict ressult: ", label)
标签:周志华,good,attr,self,bad,classes,课后,var,习题 来源: https://blog.csdn.net/JJPOMELO/article/details/121467151