C# implementation of a TFIDF and VectorSpaceModel calculation for Information retrieval.
Basically implements different term frequency functions (Logarithmic, Augmented, Boolean etc) together with an IDF function. Might need some performance optimizations/better choice of data structures for larger data sets.
Also a basic Vector Space Model implementation to calculate Cosine similarity between documents or n-dimensional vectors.
For more info: http://en.wikipedia.org/wiki/Tf-idf