基本概念：朴素贝叶斯算法的分类

Question

我想我或多或少地理解朴素贝叶斯，但是我对于其简单的二进制文本分类tast的实现有几个问题。

假设文件D_i就是词汇的某个子集x_1, x_2, ...x_n

有两类c_i任何文件可以落在了，我想计算P(c_i|D)某些输入文档d成比例P(D|c_i)P(c_i)

我有三个问题

1. P(c_i)为#docs in c_i/ #total docs或#words in c_i/ #total words
2. 应该P(x_j|c_i)是#times x_j appears in D/ #times x_j appears in c_i
3. 假设一个x_j不训练集中存在了，我给它的1的概率，这样它不会改变计算？

例如，让我们说，我有一个训练集：

training = [("hello world", "good") 
      ("bye world", "bad")] 

这样的类必须

good_class = {"hello": 1, "world": 1} 
bad_class = {"bye":1, "world:1"} 
all = {"hello": 1, "world": 2, "bye":1} 

所以现在如果我想计算的概率测试字符串不错

test1 = ["hello", "again"] 
p_good = sum(good_class.values())/sum(all.values()) 
p_hello_good = good_class["hello"]/all["hello"] 
p_again_good = 1 # because "again" doesn't exist in our training set 

p_test1_good = p_good * p_hello_good * p_again_good 

Answer 1

由于这个问题太过分了广告，所以我只能回答一个限制方式： -

1： - P（C_I）是C_I /＃合计文档#docs或#words在C_I /＃合计的话

P(c_i) = #c_i/#total docs 

第二个： -如果P（x_j | c_i）是#times x_j出现在D/#times x_j出现在c_i中。
后@larsmans注意到..

It is exactly occurrence of word in a document 
by total number of words in that class in whole dataset. 

3： -假设一个x_j在训练集不存在了，我给它的1的概率，使得其不会改变计算？

For That we have laplace correction or Additive smoothing. It is applied on 
p(x_j|c_i)=(#times x_j appears in D+1)/ (#times x_j +|V|) which will neutralize 
the effect not occurring features.