/// <summary>
/// Gathers the required counts for the features and performs feature selection
/// on the above counts. It returns a FeatureStats object that is later used
/// for calculating the probabilities of the model.
/// </summary>
/// <param name="dataset"> </param>
/// <returns> </returns>
private FeatureStats selectFeatures(IList <Document> dataset)
{
FeatureExtraction featureExtractor = new FeatureExtraction();
//the FeatureStats object contains statistics about all the features found in the documents
FeatureStats stats = featureExtractor.extractFeatureStats(dataset); //extract the stats of the dataset
//we pass this information to the feature selection algorithm and we get a list with the selected features
IDictionary <string, double?> selectedFeatures = featureExtractor.chisquare(stats, chisquareCriticalValue);
//clip from the stats all the features that are not selected
IEnumerator <KeyValuePair <string, IDictionary <string, int> > > it = stats.featureCategoryJointCount.GetEnumerator();
while (it.MoveNext())
{
string feature = it.Current.Key;
if (selectedFeatures.ContainsKey(feature) == false)
{
//if the feature is not in the selectedFeatures list remove it
it.Current.Value.Remove(feature);
}
}
return(stats);
}
/// <summary>
/// Generates a FeatureStats Object with metrics about he occurrences of the
/// keywords in categories, the number of category counts and the total number
/// of observations. These stats are used by the feature selection algorithm.
/// </summary>
/// <param name="dataset"> </param>
/// <returns> </returns>
public virtual FeatureStats extractFeatureStats(IList <Document> dataset)
{
FeatureStats stats = new FeatureStats();
int categoryCount = 0;
string category;
int featureCategoryCount = 0;
string feature;
IDictionary <string, int> featureCategoryCounts;
foreach (Document doc in dataset)
{
++stats.n; //increase the number of observations
category = doc.category;
//increase the category counter by one
if (stats.categoryCounts.ContainsKey(category) != true)
{
stats.categoryCounts[category] = 1;
}
else
{
stats.categoryCounts[category] = categoryCount + 1;
}
foreach (KeyValuePair <string, int> entry in doc.tokens)
{
feature = entry.Key;
//get the counts of the feature in the categories
if (stats.featureCategoryJointCount.ContainsKey(feature) != true)
{
stats.featureCategoryJointCount[feature] = new Dictionary <string, int>();
featureCategoryCount = 0;
}
featureCategoryCounts = stats.featureCategoryJointCount[feature];
if (featureCategoryCounts.ContainsKey(category))
{
featureCategoryCount = featureCategoryCounts[category];
}
//increase the number of occurrences of the feature in the category
stats.featureCategoryJointCount[feature][category] = ++featureCategoryCount;
}
}
return(stats);
}
/// <summary>
/// Trains a Naive Bayes classifier by using the Multinomial Model by passing
/// the trainingDataset and the prior probabilities.
/// </summary>
/// <param name="trainingDataset"> </param>
/// <param name="categoryPriors"> </param>
/// <exception cref="IllegalArgumentException"> </exception>
public virtual void train(IDictionary <string, String[]> trainingDataset, IDictionary <string, double> categoryPriors)
{
//preprocess the given dataset
IList <Document> dataset = preprocessDataset(trainingDataset);
//produce the feature stats and select the best features
FeatureStats featureStats = selectFeatures(dataset);
//intiliaze the knowledgeBase of the classifier
knowledgeBase = new NaiveBayesKnowledgeBase();
knowledgeBase.n = featureStats.n; //number of observations
knowledgeBase.d = featureStats.featureCategoryJointCount.Count; //number of features
//check is prior probabilities are given
if (categoryPriors == null)
{
//if not estimate the priors from the sample
knowledgeBase.c = featureStats.categoryCounts.Count; //number of cateogries
knowledgeBase.logPriors = new Dictionary <string, double>();
string category;
int count;
foreach (KeyValuePair <string, int> entry in featureStats.categoryCounts)
{
category = entry.Key;
count = entry.Value;
knowledgeBase.logPriors[category] = Math.Log((double)count / knowledgeBase.n);
}
}
else
{
//if they are provided then use the given priors
knowledgeBase.c = categoryPriors.Count;
//make sure that the given priors are valid
if (knowledgeBase.c != featureStats.categoryCounts.Count)
{
throw new System.ArgumentException("Invalid priors Array: Make sure you pass a prior probability for every supported category.");
}
string category;
double priorProbability;
foreach (KeyValuePair <string, double> entry in categoryPriors)
{
category = entry.Key;
priorProbability = entry.Value;
if (priorProbability == null)
{
throw new System.ArgumentException("Invalid priors Array: Make sure you pass a prior probability for every supported category.");
}
else if (priorProbability < 0 || priorProbability > 1)
{
throw new System.ArgumentException("Invalid priors Array: Prior probabilities should be between 0 and 1.");
}
knowledgeBase.logPriors[category] = Math.Log(priorProbability);
}
}
//We are performing laplace smoothing (also known as add-1). This requires to estimate the total feature occurrences in each category
IDictionary <string, double> featureOccurrencesInCategory = new Dictionary <string, double>();
int occurrences;
double featureOccSum;
foreach (string category in knowledgeBase.logPriors.Keys)
{
featureOccSum = 0.0;
foreach (IDictionary <string, int> categoryListOccurrences in featureStats.featureCategoryJointCount.Values)
{
if (categoryListOccurrences.ContainsKey(category))
{
occurrences = categoryListOccurrences[category];
featureOccSum += occurrences;
}
}
featureOccurrencesInCategory[category] = featureOccSum;
}
//estimate log likelihoods
string feature;
int likelycount;
IDictionary <string, int> featureCategoryCounts;
double logLikelihood;
foreach (string category in knowledgeBase.logPriors.Keys)
{
foreach (KeyValuePair <string, IDictionary <string, int> > entry in featureStats.featureCategoryJointCount)
{
feature = entry.Key;
featureCategoryCounts = entry.Value;
if (featureCategoryCounts.ContainsKey(category) != true)
{
likelycount = 0;
}
else
{
likelycount = featureCategoryCounts[category];
}
logLikelihood = Math.Log((likelycount + 1.0) / (featureOccurrencesInCategory[category] + knowledgeBase.d));
if (knowledgeBase.logLikelihoods.ContainsKey(feature) == false)
{
knowledgeBase.logLikelihoods[feature] = new Dictionary <string, double>();
}
knowledgeBase.logLikelihoods[feature][category] = logLikelihood;
}
}
featureOccurrencesInCategory = null;
}
/// <summary>
/// Perform feature selection by using the chisquare non-parametrical
/// statistical test.
/// </summary>
/// <param name="stats"> </param>
/// <param name="criticalLevel"> </param>
/// <returns> </returns>
public virtual IDictionary <string, double?> chisquare(FeatureStats stats, double criticalLevel)
{
IDictionary <string, double?> selectedFeatures = new Dictionary <string, double?>();
string feature;
string category;
IDictionary <string, int> categoryList;
int N1dot, N0dot, N00, N01, N10, N11;
double chisquareScore;
double?previousScore;
foreach (KeyValuePair <string, IDictionary <string, int> > entry1 in stats.featureCategoryJointCount)
{
feature = entry1.Key;
categoryList = entry1.Value;
//calculate the N1. (number of documents that have the feature)
N1dot = 0;
foreach (int count in categoryList.Values)
{
N1dot += count;
}
//also the N0. (number of documents that DONT have the feature)
N0dot = stats.n - N1dot;
foreach (KeyValuePair <string, int> entry2 in categoryList)
{
category = entry2.Key;
N11 = entry2.Value; //N11 is the number of documents that have the feature and belong on the specific category
N01 = stats.categoryCounts[category] - N11; //N01 is the total number of documents that do not have the particular feature BUT they belong to the specific category
N00 = N0dot - N01; //N00 counts the number of documents that don't have the feature and don't belong to the specific category
N10 = N1dot - N11; //N10 counts the number of documents that have the feature and don't belong to the specific category
//calculate the chisquare score based on the above statistics
chisquareScore = stats.n * Math.Pow(N11 * N00 - N10 * N01, 2) / ((N11 + N01) * (N11 + N10) * (N10 + N00) * (N01 + N00));
//if the score is larger than the critical value then add it in the list
if (chisquareScore >= criticalLevel)
{
//previousScore = selectedFeatures[feature];
previousScore = 0;
if (selectedFeatures.ContainsKey(feature) != true)
{
previousScore = 0;
}
else
{
previousScore = selectedFeatures[feature];
}
if (previousScore == 0 || chisquareScore > previousScore)
{
selectedFeatures[feature] = chisquareScore;
}
}
}
}
return(selectedFeatures);
}