Factor Analysis on pure python

This MR implements the ISV and the JFA algorithms on pure python using numpy/dask-arrays. In the way I'm implementing it, we can easily run this algorithm in a distributed manner, either locally on an HPC.

Closes #41 (closed)

doc/plot/plot_ISV.py

@@ -57,6 +57,10 @@ ubm = bob.learn.em.GMMMachine(n_gaussians).fit(X)
 gmm_stats = [ubm.acc_statistics(x[np.newaxis]) for x in X]
 isv_machine = bob.learn.em.ISVMachine(ubm, r_U).fit(gmm_stats, y)
 
+# gmm_stats = [ubm.acc_statistics(x) for x in [setosa, versicolor, virginica]]
+# isv_machine = bob.learn.em.ISVMachine(ubm, r_U).fit(gmm_stats, [0, 1, 2])
+
+
 # isvbase = isv_train([setosa, versicolor, virginica], ubm)
 
 # Variability direction