private Dictionary <string, double> makePrediction(String fileContent, SortedDictionary <string, ICategory> sd)
{
ExcludedWords m_ExcludedWords = new ExcludedWords();
m_ExcludedWords.InitDefault();
EnumerableCategory words_in_file = new EnumerableCategory("", m_ExcludedWords);
words_in_file.TeachCategory(fileContent);//理解naive bayes后，我终于理解了，这个就是提取待分类文本的特征(即属性词)
//万事俱备，只欠计算
Dictionary <string, double> score = new Dictionary <string, double>();
foreach (KeyValuePair <string, ICategory> cat in sd)
{
score.Add(cat.Key, 0.0);
}
foreach (KeyValuePair <string, int> kvp1 in words_in_file)
{
// PhraseCount pc_in_file = kvp1.Value;
String words_in_predictionfile = kvp1.Key;//算P(f1=x1|s=si)，其中words_in_predictionfile就是x1
foreach (KeyValuePair <string, ICategory> kvp in sd)
{
ICategory cat = kvp.Value;
int count = cat.GetPhraseCount(words_in_predictionfile);//这里每轮的words_in_predictionfile是待分类文本的特征词
if (0 < count)
{
score[kvp.Key] += System.Math.Log((double)count / (double)cat.TotalWords);//说到底还是按类别(cat1、cat2...)等分类统计概率,就是连乘P(f1=x1|s=si)
}
else//count==0,用0.01代替0防止log无意义
{
score[kvp.Key] += System.Math.Log(0.01 / (double)cat.TotalWords);
}
System.Diagnostics.Trace.WriteLine(words_in_predictionfile + "(" +
kvp.Key + ")" + score[kvp.Key]);
}
}
int total = 0;
foreach (Category cat in sd.Values)
{
total += cat.TotalWords;
}
foreach (KeyValuePair <string, ICategory> kvp in sd) //觉得这里写得很没意思，就是把cat1+cat2+cat3+cat4+cat5作为总和，然后分别用每个类别去除以这个总和，然后取对数
{ //更重要的，这里的含义我真不理解，签名是把每个类别的单词处于该类别的count，然后取对数，相加，然后又加上一个类别除以类别之和取对数
//现在理解了，这就是算先验概率啊
ICategory cat = kvp.Value;
score[kvp.Key] += System.Math.Log((double)cat.TotalWords / (double)total);
}
return(score);
}
/// <summary>
/// Classifies a text<\summary>
/// <returns>
/// returns classification values for the text, the higher, the better is the match.</returns>
public Dictionary <string, double> Classify(System.IO.StreamReader tr)
{
// //所以这个整个过程就是算P(f1=x1,f2=x2...fn=xn|s=si)=P(f1=x1|s=si)*P(f2=x2|s=si)....*P(fn=xn|s=si)*P(s=si)
Dictionary <string, double> score = new Dictionary <string, double>();
foreach (KeyValuePair <string, ICategory> cat in m_Categories)
{
score.Add(cat.Value.Name, 0.0);
}
EnumerableCategory words_in_file = new EnumerableCategory("", m_ExcludedWords);
words_in_file.TeachCategory(tr); //这个的含义是什么？m_Categories里已经算好了所有分类的统计啊。理解naive bayes后，我终于理解了，这个就是提取待分类文本的特征(即属性词)
foreach (KeyValuePair <string, int> kvp1 in words_in_file)
{
String words_in_predictionfile = kvp1.Key;//算P(f1=x1|s=si)，其中words_in_predictionfile就是x1
foreach (KeyValuePair <string, ICategory> kvp in m_Categories)
{
ICategory cat = kvp.Value;
int count = cat.GetPhraseCount(words_in_predictionfile);//这里每轮的words_in_predictionfile是待分类文本的特征词
if (0 < count)
{
score[cat.Name] += System.Math.Log((double)count / (double)cat.TotalWords); //说到底还是按类别(cat1、cat2...)等分类统计概率,就是连乘P(f1=x1|s=si)
}
else //count==0,用0.01代替0防止log无意义
{
score[cat.Name] += System.Math.Log(0.01 / (double)cat.TotalWords);
}
System.Diagnostics.Trace.WriteLine(words_in_predictionfile + "(" +
cat.Name + ")" + score[cat.Name]);
}
}
foreach (KeyValuePair <string, ICategory> kvp in m_Categories) //觉得这里写得很没意思，就是把cat1+cat2+cat3+cat4+cat5作为总和，然后分别用每个类别去除以这个总和，然后取对数
{ //更重要的，这里的含义我真不理解，签名是把每个类别的单词处于该类别的count，然后取对数，相加，然后又加上一个类别除以类别之和取对数
//现在理解了，这就是算先验概率啊
ICategory cat = kvp.Value;
score[cat.Name] += System.Math.Log((double)cat.TotalWords / (double)this.CountTotalWordsInCategories());
}
//所以这个整个过程就是算P(f1=x1,f2=x2...fn=xn|s=si)=P(f1=x1|s=si)*P(f2=x2|s=si)....*P(fn=xn|s=si)*P(s=si)
return(score);
}