This is a repository for Java code that I developed for various projects but ended up not using. Since it might be of use to someone, I am making it available under a permissive license (MIT license).
In particular, it contains implementations of the following algorithms:
- Enumeration of all cliques of fixed size in a graph (N. Chiba and T. Nishizeki: Arboricity and Subgraph Listing Algorithms. SIAM Journal on Computing 14(1), p. 210-223, 1985)
- Linear regression subject to the constraint of non-negativity of coefficients (NN), summation to one (S1), or both (NNS1), as described in chapter 23 of Lawson and Hanson's book "Solving Least Squares Problems" (1995)
- computation of the Gini coefficient (also: Gini index)
- Gandy's algorithm for computing a sequence of bounds to be used as a stopping criterium in Monte Carlo hypothesis testing (A. Gandy: Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. Journal of the American Statistical Association 104(488), p. 1504-1511, 2009, DOI 10.1198/jasa.2009.tm08368)
- fitting a VAR(1) model to (multivariate) time series data
- basic Latent Semantic Analysis (LSA; also: Latent Semantic Indexing, LSI)