Benchmark data sets are of vital importance in machine learning research, as indicated by the number of repositories that exist to make them publicly available. Although many of these are usable in the stream mining context as well, it is less obvious which data sets can be used to evaluate data stream clustering algorithms. We note that the classic Covertype data set's size makes it attractive for use in stream mining but unfortunately it is specifically designed for classification. Here we detail the process of transforming the Covertype data set into one amenable for unsupervised learning, which we call the Wilderness Area data set. Our quantitative analysis allows us to conclude that the Wilderness Area data set is more appropriate for unsupervised learning than the original Covertype data set.

We present a simple, yet effective, approach to Semi-Supervised Learning. Our approach is based on estimating density-based distances (DBD) using a shortest path calculation on a graph. These Graph-DBD estimates can then be used in any distance-based supervised learning method, such as Nearest Neighbor methods and SVMs with RBF kernels. In order to apply the method to very large data sets, we also present a novel algorithm which integrates nearest neighbor computations into the shortest path search and can find exact shortest paths even in extremely large dense graphs. Significant runtime improvement over the commonly used Laplacian regularization method is then shown on a large scale dataset.