public List <double> GetFeatures(PreprocessedArticle article)
{
List <double> features = new List <double>();
List <string> enabledFeatures = Features.Select(t => t.Name).ToList();
foreach (string tag in enabledFeatures)
{
double feature = 0;
foreach (string keyWord in KeyWords[tag])
{
feature += article.Words.Take((int)(article.Words.Count * PercentOfData)).Distinct().Contains(keyWord) ? 1 : 0;
}
features.Add(feature);
}
double max = features.Max();
if (!max.Equals(0))
{
for (int i = 0; i < features.Count; i++)
{
features[i] /= max;
}
}
return(features);
}
public List <double> GetFeaturesVector(PreprocessedArticle article)
{
List <double> features = new List <double>();
foreach (IFeatureExtractor featureExtractor in FeatureExtractors)
{
features.AddRange(featureExtractor.GetFeatures(article));
}
return(features);
}
public List <double> GetFeatures(PreprocessedArticle article)
{
List <double> features = new List <double>();
List <string> enabledFeatures = Features.Select(t => t.Name).ToList();
foreach (string tag in enabledFeatures)
{
double feature = 0;
foreach (string keyWord in KeyWords[tag])
{
feature += article.Words.Take((int)(article.Words.Count * PercentOfData)).Sum(t => SimilarityFunction.CalculateSimilarity(keyWord, t));
}
if (feature.Equals(0))
{
features.Add(0);
}
else
{
features.Add(feature);
}
}
double max = features.Max();
if (!max.Equals(0.0))
{
for (int i = 0; i < features.Count; i++)
{
features[i] /= max;
}
}
return(features);
}