/// <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);
}
