/// <summary>
/// Calculate P(vj) and P(wk|vj)
///
/// In Total:
/// Variables Num
/// P(vj) c
/// P(wk|vj) n*c
///
/// </summary>
private void CalculateProbabilities(TextClassificationProblem problem)
{
ExampleSet t_Set; // training set
int numCategory;
CategoryCollection categoryCollection;
Vocabulary voc;
//Logging.Info("Retrieving vocabulary");
voc = problem.TrainingSetVocabulary;
//Logging.Info("Retrieving training set");
t_Set = problem.TrainingSet;
numCategory = problem.CategoryCount;
categoryCollection = problem.CategoryCollection;
//Logging.Info("Calculating probabilities");
// Step1: Calculate Probabilities
//
int numVocabulary = voc.Count;
m_prob_vj = new double[numCategory];
m_prob_wk_vj_log = new double[numVocabulary, numCategory];
// Step2: P(vj)
//
for (int i = 0; i < numCategory; i++)
{
m_prob_vj[i] = 1.0 / numCategory;
}
// Step3: P(wk|vj)
//
NaiveBayesCategoryCollection collection = new NaiveBayesCategoryCollection(categoryCollection);
foreach (Example example in t_Set.Examples)
{
collection.AddExample((TextExample)example);
}
// P(wk|vj) = (nc+1)/(n+|Vocabulary|)
//
// nc: the occurence of wk in the n positions.
// n: word position numbers for category vj.
int nc, n;
//
// k: index in vacabulary;
// j: index in categories
int k = 0, j = 0;
foreach (NaiveBayesCategory c in collection.CategorySet)
{
k = 0; // reset
foreach (string word in voc.WordBag.Keys)
{
if (c.WordBag.ContainsKey(word))
nc = c.WordBag[word];
else
nc = 0;
n = c.WordBagOccurence;
//m_prob_wk_vj[k, j] = (nc + 1.0) / (c.Count + numVocabulary);
m_prob_wk_vj_log[k, j] = Math.Log((nc + 1.0) / (n + numVocabulary));
k++; // next word
}
j++; // next category
}
}
/// <summary>
/// Calculate P(vj) and P(wk|vj)
///
/// In Total:
/// Variables Num
/// P(vj) c
/// P(wk|vj) n*c
///
/// </summary>
private void CalculateProbabilities(TextClassificationProblem problem)
{
ExampleSet t_Set; // training set
int numCategory;
CategoryCollection categoryCollection;
Vocabulary voc;
//Logging.Info("Retrieving vocabulary");
voc = problem.TrainingSetVocabulary;
//Logging.Info("Retrieving training set");
t_Set = problem.TrainingSet;
numCategory = problem.CategoryCount;
categoryCollection = problem.CategoryCollection;
//Logging.Info("Calculating probabilities");
// Step1: Calculate Probabilities
//
int numVocabulary = voc.Count;
m_prob_vj = new double[numCategory];
m_prob_wk_vj_log = new double[numVocabulary, numCategory];
// Step2: P(vj)
//
for (int i = 0; i < numCategory; i++)
{
m_prob_vj[i] = 1.0 / numCategory;
}
// Step3: P(wk|vj)
//
NaiveBayesCategoryCollection collection = new NaiveBayesCategoryCollection(categoryCollection);
foreach (Example example in t_Set.Examples)
{
collection.AddExample((TextExample)example);
}
// P(wk|vj) = (nc+1)/(n+|Vocabulary|)
//
// nc: the occurence of wk in the n positions.
// n: word position numbers for category vj.
int nc, n;
//
// k: index in vacabulary;
// j: index in categories
int k = 0, j = 0;
foreach (NaiveBayesCategory c in collection.CategorySet)
{
k = 0; // reset
foreach (string word in voc.WordBag.Keys)
{
if (c.WordBag.ContainsKey(word))
{
nc = c.WordBag[word];
}
else
{
nc = 0;
}
n = c.WordBagOccurence;
//m_prob_wk_vj[k, j] = (nc + 1.0) / (c.Count + numVocabulary);
m_prob_wk_vj_log[k, j] = Math.Log((nc + 1.0) / (n + numVocabulary));
k++; // next word
}
j++; // next category
}
}