Performance improvement

[pramitchoudhary]

Based on the benchmarks done here
http://stackoverflow.com/questions/20277982/fastest-pairwise-distance-metric-in-python.
Using scipy.spatial.distance.pdist vs sklearn.metrics.pairwise_distances could help in improving the computation for computing euclidean distance distance. Need to test it out.

[marcotcr]

I don't think it matters one way or the other, sklearn distance is pretty fast already.
The time spent computing distances is always vastly smaller than the time spending with everything else.
Unless you found a case where the above isn't true, it isn't worth the effort.
Thanks : )